Update to bsnes v016 release.

- Added Direct3D renderer with options for disabling hardware filtering and scanlines
    - Screenshots can now be captured in BMP, JPEG, or PNG format
    - Added config file option to specify default ROM and SRAM paths
    - Config file is always loaded from path to bsnes executable
    - Added support for analog mode joypad input
    - Up to 32 joypads can be used at once now
    - Fixed bug regarding enabling interlace mid-frame
    - Moved PPU rendering to V=240, from V=0
    - Started on new debugger. So far only debug messages and memory editor added
    - Added joypad axis resistance option for analog input mode
    - Added config file option to set window style attributes
    - Added color adjustment settings for brightness, contrast, gamma, and scanline intensity
    - Added grayscale, sepia, and invert color settings
    - Added NTSC filter by blargg, HQ2x filter by MaxSt, and Scale2x filter
    - PPU now renders scanline 224
    - Revampled about box
    - Added Game Genie / PAR cheat code support + editor, saves codes to .cht files
    - HDMA channels are no longer disabled when starting DMA, fixes Dracula X [DMV27]
    - Fixes to OAM priority mode (not perfect), fixes Final Fantasy: Mystic Quest [DMV27]
    - Fixed ENDX sound bug, fixes voices in Earthworm Jim 2 [DMV27]
    - bsnes should now compile with MinGW [DMV27]
    - Added DSP-2 support
    - Added OBC-1 support
    - Major rewrite of SNES address bus mirroring and MMIO handlers
    - Many address mirroring corrections, fixes Dezaemon, etc
    - Blocked invalid (H)DMA transfers, fixes Kirby's Super Funhouse
    - Wrote Win32 API wrapper and ported all GUI code to use it, should help to create Linux GUI later on
    - Revampled input system, should lead to customizable GUI shortcut keys later on
    - Fixed numerous bugs with input registers. Fixes many games that previous had their intro cut off (Super Conflict, etc), and many that never accepted input (Super Double Dragon, etc)
    - Moved auto joypad strobing from V=225 to V=227
    - Killed OAM table caching and window range caching, as they were actually hindering speed
    - Rewrote input configuration screen to show currently mapped keys
    - Greatly enhanced configuration options for each video profile
    - Modified fullscreen mode to exit to windowed mode when menu is activated, use F11 to toggle fullscreen mode
    - Fixed bugs in txs, wai, brk, cop, and rti opcodes [DMV27]
    - Fixed bug with emulation-mode IRQs [DMV27]
    - Initializing DMA registers to $ff [DMV27]
    - Memory writes now update CPU MDR register (open bus) [DMV27]
    - Improved ROM header detection, fixes Chou Jikuu Yousai Macross [DMV27]
    - Reading OAM no longer updates OAM latch
    - Writing to OAM high table no longer updates OAM latch
    - Writing CGRAM now updates CGRAM latch
    - Improved pseudo-hires rendering [blargg]
    - Much, much more

bsnes.cfg

@@ -1,87 +0,0 @@
-# Applies contrast adjust filter to video output when enabled
-# Works by lowering the brightness of darker colors,
-# while leaving brighter colors alone; thus reducing saturation
-# (default = true)
-snes.video_color_curve = true
-
-# Selects color adjustment filter for video output
-#   0 = Normal (no filter, rgb555)
-#   1 = Grayscale mode (l5)
-#   2 = VGA mode (rgb332)
-#   3 = Genesis mode (rgb333)
-# (default = 0)
-snes.video_color_adjust_mode = 0
-
-# Mutes SNES audio output when enabled
-# (default = true)
-snes.mute = true
-
-# Video mode
-#   0 = 256x224w
-#   1 = 512x448w
-#   2 = 960x720w
-#   3 = 640x480f
-#   4 = 1024x768f
-# (default = 1)
-video.mode = 1
-
-# Use Video RAM instead of System RAM
-# (default = true)
-video.use_vram = true
-
-# Wait for vertical retrace when updating screen
-# (default = false)
-video.vblank = false
-
-# Show framerate in window title
-# (default = true)
-gui.show_fps = false
-
-# Joypad1 up
-# (default = 0x26)
-input.joypad1.up = 0x26
-
-# Joypad1 down
-# (default = 0x28)
-input.joypad1.down = 0x28
-
-# Joypad1 left
-# (default = 0x25)
-input.joypad1.left = 0x25
-
-# Joypad1 right
-# (default = 0x27)
-input.joypad1.right = 0x27
-
-# Joypad1 A
-# (default = 0x58)
-input.joypad1.a = 0x58
-
-# Joypad1 B
-# (default = 0x5a)
-input.joypad1.b = 0x5a
-
-# Joypad1 X
-# (default = 0x53)
-input.joypad1.x = 0x53
-
-# Joypad1 Y
-# (default = 0x41)
-input.joypad1.y = 0x41
-
-# Joypad1 L
-# (default = 0x44)
-input.joypad1.l = 0x44
-
-# Joypad1 R
-# (default = 0x43)
-input.joypad1.r = 0x43
-
-# Joypad1 select
-# (default = 0x10)
-input.joypad1.select = 0x10
-
-# Joypad1 start
-# (default = 0xd)
-input.joypad1.start = 0xd
-

license.txt

@@ -19,3 +19,8 @@ http://www.libsdl.org/
 
 This library is distributed under the terms of the GNU LGPL:
 http://www.gnu.org/copyleft/lesser.html
+
+Licensing Exemptions:
+---------------------
+Richard Bannister has asked for and received my permission to distribute
+a binary-only port of bsnes on the Mac OS X platform.

src/apu/apu.h

@@ -27,4 +27,7 @@ static const uint8 iplrom[64];
   virtual bool in_opcode();
   void disassemble_opcode(char *output);
   inline uint16 __relb(int8 offset, int op_len);
+
+  APU() {}
+  virtual ~APU() {}
 };

src/apu/apuregs.h

@@ -13,7 +13,7 @@ private:
     inline bool operator ^= (bool i) { if(i)_b ^= B; return (_b & B); }
   };
 public:
-  union {
+union {
   uint8 _b;
   bit<0x80> n;
   bit<0x40> v;
@@ -23,7 +23,7 @@ public:
   bit<0x04> i;
   bit<0x02> z;
   bit<0x01> c;
-  };
+};
 
   APURegFlags() { _b = 0; }
   inline operator uint8() { return _b; }
@@ -38,10 +38,11 @@ public:
 uint16 pc;
 union {
   uint16 ya;
-//not endian-safe
-  struct {
-    uint8 a, y;
-  };
+#ifdef ARCH_LSB
+  struct { uint8 a, y; };
+#else
+  struct { uint8 y, a; };
+#endif
 };
 uint8 x, sp;
 APURegFlags p;

src/apu/bapu/bapu.cpp

@@ -1,224 +1,11 @@
 #include "../../base.h"
 
-#include "bapu_op_fn.cpp"
-#include "bapu_op_mov.cpp"
-#include "bapu_op_pc.cpp"
-#include "bapu_op_read.cpp"
-#include "bapu_op_rmw.cpp"
-#include "bapu_op_misc.cpp"
-
-#include "bapu_exec.cpp"
-
-uint8 bAPU::spcram_read(uint16 addr) {
-uint8 r;
-  if(addr >= 0x00f0 && addr <= 0x00ff) {
-    switch(addr) {
-    case 0xf0: //TEST -- operation unknown, supposedly returns 0x00
-      r = 0x00;
-      break;
-    case 0xf1: //CONTROL -- write-only register, always returns 0x00
-      r = 0x00;
-      break;
-    case 0xf2: //DSPADDR
-      r = status.dsp_addr;
-      break;
-    case 0xf3: //DSPDATA
-    //0x80-0xff is a read-only mirror of 0x00-0x7f
-      r = dsp->read(status.dsp_addr & 0x7f);
-      break;
-    case 0xf4: //CPUIO0
-    case 0xf5: //CPUIO1
-    case 0xf6: //CPUIO2
-    case 0xf7: //CPUIO3
-      r = cpu->port_read(addr & 3);
-      break;
-    case 0xf8: //???
-    case 0xf9: //??? -- Mapped to SPCRAM
-      r = spcram[addr];
-      break;
-    case 0xfa: //T0TARGET
-    case 0xfb: //T1TARGET
-    case 0xfc: //T2TARGET -- write-only registers, always return 0x00
-      r = 0x00;
-      break;
-    case 0xfd: //T0OUT -- 4-bit counter value
-      r = t0.stage3_ticks & 15;
-      t0.stage3_ticks = 0;
-      break;
-    case 0xfe: //T1OUT -- 4-bit counter value
-      r = t1.stage3_ticks & 15;
-      t1.stage3_ticks = 0;
-      break;
-    case 0xff: //T2OUT -- 4-bit counter value
-      r = t2.stage3_ticks & 15;
-      t2.stage3_ticks = 0;
-      break;
-    }
-  } else if(addr < 0xffc0) {
-    r = spcram[addr];
-  } else {
-    if(status.iplrom_enabled == true) {
-      r = iplrom[addr & 0x3f];
-    } else {
-      r = spcram[addr];
-    }
-  }
-  snes->notify(SNES::SPCRAM_READ, addr, r);
-  return r;
-}
-
-void bAPU::spcram_write(uint16 addr, uint8 value) {
-  if(addr >= 0x00f0 && addr <= 0x00ff) {
-    switch(addr) {
-    case 0xf0: //TEST -- operation unknown
-      break;
-    case 0xf1: //CONTROL
-      status.iplrom_enabled = !!(value & 0x80);
-
-    //one-time clearing of APU port read registers,
-    //emulated by simulating CPU writes of 0x00
-      if(value & 0x20) {
-        cpu->port_write(2, 0x00);
-        cpu->port_write(3, 0x00);
-      }
-      if(value & 0x10) {
-        cpu->port_write(0, 0x00);
-        cpu->port_write(1, 0x00);
-      }
-
-    //0->1 transistion resets timers
-      if(t2.enabled == false && (value & 0x04)) {
-        t2.stage2_ticks = 0;
-        t2.stage3_ticks = 0;
-      }
-      t2.enabled = !!(value & 0x04);
-
-      if(t1.enabled == false && (value & 0x02)) {
-        t1.stage2_ticks = 0;
-        t1.stage3_ticks = 0;
-      }
-      t1.enabled = !!(value & 0x02);
-
-      if(t0.enabled == false && (value & 0x01)) {
-        t0.stage2_ticks = 0;
-        t0.stage3_ticks = 0;
-      }
-      t0.enabled = !!(value & 0x01);
-      break;
-    case 0xf2: //DSPADDR
-      status.dsp_addr = value;
-      break;
-    case 0xf3: //DSPDATA
-    //0x80-0xff is a read-only mirror of 0x00-0x7f
-      if(status.dsp_addr < 0x80) {
-        dsp->write(status.dsp_addr & 0x7f, value);
-      }
-      break;
-    case 0xf4: //CPUIO0
-    case 0xf5: //CPUIO1
-    case 0xf6: //CPUIO2
-    case 0xf7: //CPUIO3
-      port_write(addr & 3, value);
-      break;
-    case 0xf8: //???
-    case 0xf9: //??? - Mapped to SPCRAM
-      spcram[addr] = value;
-      break;
-    case 0xfa: //T0TARGET
-      t0.target = value;
-      break;
-    case 0xfb: //T1TARGET
-      t1.target = value;
-      break;
-    case 0xfc: //T2TARGET
-      t2.target = value;
-      break;
-    case 0xfd: //T0OUT
-    case 0xfe: //T1OUT
-    case 0xff: //T2OUT -- read-only registers
-      break;
-    }
-  } else {
-  //writes to $ffc0-$ffff always go to spcram,
-  //even if the iplrom is enabled.
-    spcram[addr] = value;
-  }
-  snes->notify(SNES::SPCRAM_WRITE, addr, value);
-}
-
-uint8 bAPU::port_read(uint8 port) {
-  return spcram[0xf4 + (port & 3)];
-}
-
-void bAPU::port_write(uint8 port, uint8 value) {
-  spcram[0xf4 + (port & 0x03)] = value;
-}
-
-void bAPU::add_cycles(int cycles) {
-  status.cycles_executed += cycles;
-
-  t0.add_cycles(cycles);
-  t1.add_cycles(cycles);
-  t2.add_cycles(cycles);
-}
-
-uint32 bAPU::cycles_executed() {
-uint32 r = status.cycles_executed;
-  status.cycles_executed = 0;
-  return (r << 4) + (r << 3);
-}
-
-uint8 bAPU::op_read() {
-uint8 r;
-  r = spcram_read(regs.pc);
-  regs.pc++;
-  return r;
-}
-
-uint8 bAPU::op_read(uint8 mode, uint16 addr) {
-uint8 r;
-  switch(mode) {
-  case OPMODE_ADDR:
-    r = spcram_read(addr);
-    break;
-  case OPMODE_DP:
-    r = spcram_read(((regs.p.p)?0x100:0x000) + (addr & 0xff));
-    break;
-  }
-  return r;
-}
-
-void bAPU::op_write(uint8 mode, uint16 addr, uint8 value) {
-  switch(mode) {
-  case OPMODE_ADDR:
-    spcram_write(addr, value);
-    break;
-  case OPMODE_DP:
-    spcram_write(((regs.p.p)?0x100:0x000) + (addr & 0xff), value);
-    break;
-  }
-}
-
-uint8 bAPU::stack_read() {
-  regs.sp++;
-  return spcram_read(0x0100 | regs.sp);
-}
-
-void bAPU::stack_write(uint8 value) {
-  spcram_write(0x0100 | regs.sp, value);
-  regs.sp--;
-}
-
-uint8 *bAPU::get_spcram_handle() {
-  if(!spcram) {
-    alert("bAPU::get_spcram_handle() -- spcram uninitialized");
-  }
-
-  return spcram;
-}
+#include "core/core.cpp"
+#include "memory/memory.cpp"
+#include "timing/timing.cpp"
 
 void bAPU::run() {
-  exec_cycle();
+  exec();
 }
 
 void bAPU::power() {
@@ -275,25 +62,3 @@ bAPU::bAPU() {
 bAPU::~bAPU() {
   if(spcram)free(spcram);
 }
-
-//cycles should never be greater than 12. since the minimum
-//cycle_frequency value is 16, we don't have to worry about
-//two ticks occuring in one call to this function.
-void bAPUTimer::add_cycles(int cycles) {
-//stage 1 increment
-  stage1_ticks += cycles;
-  if(stage1_ticks < cycle_frequency)return;
-
-  stage1_ticks -= cycle_frequency;
-  if(enabled == false)return;
-
-//stage 2 increment
-  stage2_ticks++;
-
-  if(stage2_ticks != target)return;
-
-//stage 3 increment
-  stage2_ticks = 0;
-  stage3_ticks++;
-  stage3_ticks &= 15;
-}

src/apu/bapu/bapu.h

@@ -1,20 +1,8 @@
-class bAPU;
-
-class bAPUTimer {
-public:
-uint8 cycle_frequency, target;
-uint8 stage1_ticks, stage2_ticks, stage3_ticks;
-bool  enabled;
-  inline void add_cycles(int cycles);
-};
-
 class bAPU : public APU {
-private:
-typedef void (bAPU::*op)();
-op optbl[256];
-
 public:
-uint16 dp, sp, rd, wr, bit, ya;
+#include "core/core.h"
+#include "memory/memory.h"
+#include "timing/timing.h"
 
 struct {
   uint8  cycle_pos, opcode;
@@ -25,57 +13,12 @@ struct {
 
 //$f2
   uint8  dsp_addr;
-}status;
+} status;
 
-bAPUTimer t0, t1, t2;
-
-uint8 *spcram;
-  inline uint8  spcram_read (uint16 addr);
-  inline void   spcram_write(uint16 addr, uint8 value);
-  inline uint8  port_read (uint8 port);
-  inline void   port_write(uint8 port,  uint8 value);
-
-  inline uint8 *get_spcram_handle();
   inline void run();
-  inline uint32 cycles_executed();
   inline void power();
   inline void reset();
 
-  inline void   add_cycles(int cycles);
-
-enum {
-  OPMODE_ADDR = 0,
-  OPMODE_DP = 1
-};
-  inline uint8 op_read();
-  inline uint8 op_read (uint8 mode, uint16 addr);
-  inline void  op_write(uint8 mode, uint16 addr, uint8 value);
-  inline uint8 stack_read();
-  inline void  stack_write(uint8 value);
-
-  inline void exec_cycle();
-  inline bool in_opcode();
-  inline void init_op_table();
-
-  inline uint8  op_adc (uint8  x, uint8  y);
-  inline uint16 op_addw(uint16 x, uint16 y);
-  inline uint8  op_and (uint8  x, uint8  y);
-  inline uint8  op_cmp (uint8  x, uint8  y);
-  inline uint16 op_cmpw(uint16 x, uint16 y);
-  inline uint8  op_eor (uint8  x, uint8  y);
-  inline uint8  op_inc (uint8  x);
-  inline uint16 op_incw(uint16 x);
-  inline uint8  op_dec (uint8  x);
-  inline uint16 op_decw(uint16 x);
-  inline uint8  op_or  (uint8  x, uint8  y);
-  inline uint8  op_sbc (uint8  x, uint8  y);
-  inline uint16 op_subw(uint16 x, uint16 y);
-  inline uint8  op_asl (uint8  x);
-  inline uint8  op_lsr (uint8  x);
-  inline uint8  op_rol (uint8  x);
-  inline uint8  op_ror (uint8  x);
-#include "bapu_op.h"
-
   bAPU();
   ~bAPU();
 };

src/apu/bapu/bapu_exec.cpp

@@ -1,25 +0,0 @@
-void bAPU::exec_cycle() {
-uint8 op;
-  if(status.cycle_pos == 0) {
-    op = spcram_read(regs.pc);
-    snes->notify(SNES::APU_EXEC_OPCODE_BEGIN);
-    status.opcode = op_read();
-    status.cycle_pos = 1;
-    add_cycles(1);
-  } else {
-    (this->*optbl[status.opcode])();
-    add_cycles(1);
-    if(status.cycle_pos == 0) {
-      snes->notify(SNES::APU_EXEC_OPCODE_END);
-    }
-  }
-}
-
-//only return true when we are on an opcode edge
-bool bAPU::in_opcode() {
-  return (status.cycle_pos != 0);
-}
-
-void bAPU::init_op_table() {
-#include "bapu_optable.cpp"
-}

src/apu/bapu/bapugen.cpp

@@ -1,168 +0,0 @@
-#include "../../lib/libbase.h"
-#include "../../lib/libstring.h"
-#include "../../lib/libstring.cpp"
-
-FILE *fp, *fph, *fpt;
-
-string data, line, part, subpart;
-string output_table, output_header, output_op;
-
-int op_count;
-struct _op_list {
-string name;
-string arg;
-}op_list[64];
-
-int line_num;
-
-void clear_op_list() {
-  op_count = 0;
-  for(int i=0;i<64;i++) {
-    strcpy(op_list[i].name, "");
-    for(int l=0;l<8;l++) {
-      strcpy(op_list[i].arg[l], "");
-    }
-  }
-}
-
-void gen_header() {
-int i = line_num, l, n, z;
-char t[4096];
-  clear_op_list();
-  while(1) {
-    z = op_count++;
-    strcpy(part, line[i]);
-    strrtrim(part, "),");
-    strrtrim(part, ") {");
-    split(subpart, "(", part);
-    strcpy(op_list[z].name, subpart[0]);
-    split(part, ", ", subpart[1]);
-    for(l=0;l<count(part);l++) {
-      strcpy(op_list[z].arg[l], part[l]);
-    }
-    if(!strend(line[i], " {"))break;
-    i++;
-  }
-
-  sprintf(output_op,     "void bAPU::op_$$() {\r\n  switch(status.cycle_pos++) {\r\n");
-  sprintf(output_header, "void op_$$();\r\n");
-  sprintf(output_table,  "optbl[$0] = &bAPU::op_$$;\r\n");
-
-  line_num = i + 1;
-}
-
-void update_line(int i, int n) {
-  replace(line[i], "end;", "status.cycle_pos = 0;");
-}
-
-void gen_op() {
-int i = line_num, n;
-char t[4096];
-  while(1) {
-    if(!strcmp(line[i], "}"))break;
-
-    n = strdec(line[i]);
-    sprintf(t, "%d:", n);
-    strltrim(line[i], t);
-    sprintf(t, "  case %d:\r\n", n);
-    strcat(output_op, t);
-
-    update_line(i, n);
-    if(strcmp(line[i], "")) {
-      strcat(output_op, "    ");
-      strcat(output_op, line[i]);
-      strcat(output_op, "\r\n");
-    }
-
-    i++;
-    while(1) {
-      if((strptr(line[i])[1]) == ':' || (strptr(line[i])[2]) == ':' || !strcmp(line[i], "}"))break;
-
-      update_line(i, n);
-      strcat(output_op, "  ");
-      strcat(output_op, line[i]);
-      strcat(output_op, "\r\n");
-
-      i++;
-    }
-    if(!strcmp(line[i], "}"))strcat(output_op, "    status.cycle_pos = 0;\r\n");
-    strcat(output_op, "    break;\r\n");
-  }
-  strcat(output_op, "  }\r\n}");
-
-  line_num = i + 1;
-}
-
-void gen_final() {
-string t;
-int i, l;
-  for(i=0;i<op_count;i++) {
-    strcpy(t, output_op);
-    replace(t, "$$", op_list[i].name);
-    replace(t, "$0", op_list[i].arg[0]);
-    replace(t, "$1", op_list[i].arg[1]);
-    replace(t, "$2", op_list[i].arg[2]);
-    replace(t, "$3", op_list[i].arg[3]);
-    replace(t, "$4", op_list[i].arg[4]);
-    replace(t, "$5", op_list[i].arg[5]);
-    replace(t, "$6", op_list[i].arg[6]);
-    replace(t, "$7", op_list[i].arg[7]);
-    fprintf(fp, "%s\r\n\r\n", strptr(t));
-
-    strcpy(t, output_header);
-    replace(t, "$$", op_list[i].name);
-    fprintf(fph, "%s", strptr(t));
-
-    strcpy(t, output_table);
-    replace(t, "$$", op_list[i].name);
-    replace(t, "$0", op_list[i].arg[0]);
-    fprintf(fpt, "%s", strptr(t));
-  }
-}
-
-void generate(char *dest, char *src) {
-  fp = fopen(src, "rb");
-
-  fseek(fp, 0, SEEK_END);
-int fsize = ftell(fp);
-  fseek(fp, 0, SEEK_SET);
-char *buf = (char*)malloc(fsize + 1);
-  fread(buf, 1, fsize, fp);
-  fclose(fp);
-  buf[fsize] = 0;
-
-  strcpy(data, buf);
-  free(buf);
-  replace(data, "\r\n", "\n");
-  split(line, "\n", data);
-
-  fp = fopen(dest, "wb");
-
-  line_num = 0;
-  while(line_num < count(line)) {
-    while(!strcmp(line[line_num], "") && line_num < count(line))line_num++;
-    if(line_num >= count(line))break;
-
-    gen_header();
-    gen_op();
-    gen_final();
-  }
-
-  fclose(fp);
-}
-
-int main() {
-  fph = fopen("bapu_op.h", "wb");
-  fpt = fopen("bapu_optable.cpp", "wb");
-
-  generate("bapu_op_mov.cpp",  "op_mov.b");
-  generate("bapu_op_pc.cpp",   "op_pc.b");
-  generate("bapu_op_read.cpp", "op_read.b");
-  generate("bapu_op_rmw.cpp",  "op_rmw.b");
-  generate("bapu_op_misc.cpp", "op_misc.b");
-
-  fclose(fph);
-  fclose(fpt);
-
-  return 0;
-}

src/apu/bapu/cc.bat

@@ -1,3 +0,0 @@
-cl /ML /O2 bapugen.cpp
-@pause
-@del *.obj

src/apu/bapu/clean.bat

@@ -1 +0,0 @@
-@del *.exe

src/apu/bapu/core/bapugen.cpp

@@ -0,0 +1,18 @@
+#define CLASS_NAME "bAPU"
+#include "../../../lib/opgen.cpp"
+
+int main() {
+  fph = fopen("op.h", "wb");
+  fpt = fopen("optable.cpp", "wb");
+
+  generate("op_mov.cpp",  "op_mov.b");
+  generate("op_pc.cpp",   "op_pc.b");
+  generate("op_read.cpp", "op_read.b");
+  generate("op_rmw.cpp",  "op_rmw.b");
+  generate("op_misc.cpp", "op_misc.b");
+
+  fclose(fph);
+  fclose(fpt);
+
+  return 0;
+}

src/apu/bapu/core/cc.bat

@@ -0,0 +1,3 @@
+cl /O2 /wd4996 bapugen.cpp
+@pause
+@del *.obj

src/apu/bapu/core/clean.bat

@@ -0,0 +1,8 @@
+@del *.exe
+@del op.h
+@del optable.cpp
+@del op_mov.cpp
+@del op_pc.cpp
+@del op_read.cpp
+@del op_rmw.cpp
+@del op_misc.cpp

src/apu/bapu/core/core.cpp

@@ -0,0 +1,36 @@
+#include "opfn.cpp"
+#include "op_mov.cpp"
+#include "op_pc.cpp"
+#include "op_read.cpp"
+#include "op_rmw.cpp"
+#include "op_misc.cpp"
+
+void bAPU::exec() {
+  if(status.cycle_pos) {
+    (this->*optbl[status.opcode])();
+    add_cycles(1);
+    if(status.cycle_pos == 0) {
+    #ifdef DEBUGGER
+      snes->notify(SNES::APU_EXEC_OPCODE_END);
+    #endif
+    }
+    return;
+  }
+
+//on first cycle?
+#ifdef DEBUGGER
+  snes->notify(SNES::APU_EXEC_OPCODE_BEGIN);
+#endif
+  status.opcode = op_read();
+  status.cycle_pos = 1;
+  add_cycles(1);
+}
+
+//only return true when we are on an opcode edge
+bool bAPU::in_opcode() {
+  return (status.cycle_pos != 0);
+}
+
+void bAPU::init_op_table() {
+  #include "optable.cpp"
+}

src/apu/bapu/core/core.h

@@ -0,0 +1,25 @@
+void (bAPU::*optbl[256])();
+uint16 dp, sp, rd, wr, bit, ya;
+  inline uint8  op_adc (uint8  x, uint8  y);
+  inline uint16 op_addw(uint16 x, uint16 y);
+  inline uint8  op_and (uint8  x, uint8  y);
+  inline uint8  op_cmp (uint8  x, uint8  y);
+  inline uint16 op_cmpw(uint16 x, uint16 y);
+  inline uint8  op_eor (uint8  x, uint8  y);
+  inline uint8  op_inc (uint8  x);
+  inline uint16 op_incw(uint16 x);
+  inline uint8  op_dec (uint8  x);
+  inline uint16 op_decw(uint16 x);
+  inline uint8  op_or  (uint8  x, uint8  y);
+  inline uint8  op_sbc (uint8  x, uint8  y);
+  inline uint16 op_subw(uint16 x, uint16 y);
+  inline uint8  op_asl (uint8  x);
+  inline uint8  op_lsr (uint8  x);
+  inline uint8  op_rol (uint8  x);
+  inline uint8  op_ror (uint8  x);
+
+  inline void   exec();
+  inline bool   in_opcode();
+  inline void   init_op_table();
+
+#include "op.h"

src/apu/bapu/core/op_misc.cpp

@@ -1,55 +1,55 @@
 void bAPU::op_nop() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_sleep() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
+  case 1: {
+    } break;
+  case 2: {
     regs.pc--;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_stop() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
+  case 1: {
+    } break;
+  case 2: {
     regs.pc--;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_xcn() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
-    break;
-  case 4:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     regs.a = (regs.a >> 4) | (regs.a << 4);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_daa() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
+  case 1: {
+    } break;
+  case 2: {
     if(regs.p.c || (regs.a) > 0x99) {
       regs.a += 0x60;
       regs.p.c = 1;
@@ -60,15 +60,15 @@ void bAPU::op_daa() {
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_das() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
+  case 1: {
+    } break;
+  case 2: {
     if(!regs.p.c || (regs.a) > 0x99) {
       regs.a -= 0x60;
       regs.p.c = 0;
@@ -79,512 +79,512 @@ void bAPU::op_das() {
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clrc() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.p.c = 0;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clrp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.p.p = 0;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_setc() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.p.c = 1;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_setp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.p.p = 1;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clrv() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.p.v = 0;
     regs.p.h = 0;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_notc() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
+  case 1: {
+    } break;
+  case 2: {
     regs.p.c ^= 1;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_ei() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
+  case 1: {
+    } break;
+  case 2: {
     regs.p.i = 1;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_di() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
+  case 1: {
+    } break;
+  case 2: {
     regs.p.i = 0;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_set0_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |=  0x01;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clr0_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd &= ~0x01;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_set1_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |=  0x02;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clr1_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd &= ~0x02;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_set2_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |=  0x04;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clr2_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd &= ~0x04;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_set3_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |=  0x08;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clr3_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd &= ~0x08;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_set4_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |=  0x10;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clr4_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd &= ~0x10;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_set5_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |=  0x20;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clr5_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd &= ~0x20;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_set6_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |=  0x40;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clr6_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd &= ~0x40;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_set7_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |=  0x80;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_clr7_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd &= ~0x80;
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_tset_addr_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_ADDR, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     regs.p.n = !!((rd & regs.a) & 0x80);
     regs.p.z = ((rd & regs.a) == 0);
     rd |= regs.a;
-    break;
-  case 5:
+    } break;
+  case 5: {
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_tclr_addr_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_ADDR, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     regs.p.n = !!((rd & regs.a) & 0x80);
     regs.p.z = ((rd & regs.a) == 0);
     rd &=~ regs.a;
-    break;
-  case 5:
+    } break;
+  case 5: {
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_push_a() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     stack_write(regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_push_x() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     stack_write(regs.x);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_push_y() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     stack_write(regs.y);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_push_p() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     stack_write(regs.p);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_pop_a() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.a = stack_read();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_pop_x() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.x = stack_read();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_pop_y() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.y = stack_read();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_pop_p() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.p = stack_read();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mul_ya() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
-    break;
-  case 4:
-    break;
-  case 5:
-    break;
-  case 6:
-    break;
-  case 7:
-    break;
-  case 8:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
+    } break;
+  case 4: {
+    } break;
+  case 5: {
+    } break;
+  case 6: {
+    } break;
+  case 7: {
+    } break;
+  case 8: {
     ya = regs.y * regs.a;
     regs.a = ya;
     regs.y = ya >> 8;
@@ -592,33 +592,33 @@ void bAPU::op_mul_ya() {
     regs.p.n = !!(regs.y & 0x80);
     regs.p.z = (regs.y == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_div_ya_x() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
-    break;
-  case 4:
-    break;
-  case 5:
-    break;
-  case 6:
-    break;
-  case 7:
-    break;
-  case 8:
-    break;
-  case 9:
-    break;
-  case 10:
-    break;
-  case 11:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
+    } break;
+  case 4: {
+    } break;
+  case 5: {
+    } break;
+  case 6: {
+    } break;
+  case 7: {
+    } break;
+  case 8: {
+    } break;
+  case 9: {
+    } break;
+  case 10: {
+    } break;
+  case 11: {
     ya = regs.ya;
   //overflow set if quotient >= 256
     regs.p.v = !!(regs.y >= regs.x);
@@ -637,7 +637,7 @@ void bAPU::op_div_ya_x() {
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 

src/apu/bapu/core/op_mov.cpp

@@ -1,710 +1,710 @@
 void bAPU::op_mov_a_x() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = regs.x;
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_y() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = regs.y;
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_x_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.x = regs.a;
     regs.p.n = !!(regs.x & 0x80);
     regs.p.z = (regs.x == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_y_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.y = regs.a;
     regs.p.n = !!(regs.y & 0x80);
     regs.p.z = (regs.y == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_x_sp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.x = regs.sp;
     regs.p.n = !!(regs.x & 0x80);
     regs.p.z = (regs.x == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_sp_x() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.sp = regs.x;
     regs.p.n = !!(regs.sp & 0x80);
     regs.p.z = (regs.sp == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_const() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = op_read();
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_x_const() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.x = op_read();
     regs.p.n = !!(regs.x & 0x80);
     regs.p.z = (regs.x == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_y_const() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.y = op_read();
     regs.p.n = !!(regs.y & 0x80);
     regs.p.z = (regs.y == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_ix() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
+  case 1: {
+    } break;
+  case 2: {
     regs.a = op_read(OPMODE_DP, regs.x);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_ixinc() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.a = op_read(OPMODE_DP, regs.x++);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     regs.a = op_read(OPMODE_DP, sp);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_x_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     regs.x = op_read(OPMODE_DP, sp);
     regs.p.n = !!(regs.x & 0x80);
     regs.p.z = (regs.x == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_y_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     regs.y = op_read(OPMODE_DP, sp);
     regs.p.n = !!(regs.y & 0x80);
     regs.p.z = (regs.y == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.a = op_read(OPMODE_DP, sp + regs.x);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_x_dpy() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.x = op_read(OPMODE_DP, sp + regs.y);
     regs.p.n = !!(regs.x & 0x80);
     regs.p.z = (regs.x == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_y_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.y = op_read(OPMODE_DP, sp + regs.x);
     regs.p.n = !!(regs.y & 0x80);
     regs.p.z = (regs.y == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     sp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     regs.a = op_read(OPMODE_ADDR, sp);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_x_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     sp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     regs.x = op_read(OPMODE_ADDR, sp);
     regs.p.n = !!(regs.x & 0x80);
     regs.p.z = (regs.x == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_y_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     sp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     regs.y = op_read(OPMODE_ADDR, sp);
     regs.p.n = !!(regs.y & 0x80);
     regs.p.z = (regs.y == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_addrx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     sp |= op_read() << 8;
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     regs.a = op_read(OPMODE_ADDR, sp + regs.x);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_addry() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     sp |= op_read() << 8;
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     regs.a = op_read(OPMODE_ADDR, sp + regs.y);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_idpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read() + regs.x;
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     sp  = op_read(OPMODE_DP, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     sp |= op_read(OPMODE_DP, dp + 1) << 8;
-    break;
-  case 5:
+    } break;
+  case 5: {
     regs.a = op_read(OPMODE_ADDR, sp);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_a_idpy() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     sp  = op_read(OPMODE_DP, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     sp |= op_read(OPMODE_DP, dp + 1) << 8;
-    break;
-  case 5:
+    } break;
+  case 5: {
     regs.a = op_read(OPMODE_ADDR, sp + regs.y);
     regs.p.n = !!(regs.a & 0x80);
     regs.p.z = (regs.a == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_dp_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_DP, sp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_dp_const() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     rd = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp = op_read();
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_ix_a() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     op_write(OPMODE_DP, regs.x, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_ixinc_a() {
   switch(status.cycle_pos++) {
-  case 1:
-    break;
-  case 2:
-    break;
-  case 3:
+  case 1: {
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     op_write(OPMODE_DP, regs.x++, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_dp_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     op_write(OPMODE_DP, dp, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_dp_x() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     op_write(OPMODE_DP, dp, regs.x);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_dp_y() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     op_write(OPMODE_DP, dp, regs.y);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_dpx_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     op_write(OPMODE_DP, dp + regs.x, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_dpy_x() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     op_write(OPMODE_DP, dp + regs.y, regs.x);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_dpx_y() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     op_write(OPMODE_DP, dp + regs.x, regs.y);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_addr_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     op_write(OPMODE_ADDR, dp, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_addr_x() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     op_write(OPMODE_ADDR, dp, regs.x);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_addr_y() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
-    break;
-  case 4:
+    } break;
+  case 3: {
+    } break;
+  case 4: {
     op_write(OPMODE_ADDR, dp, regs.y);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_addrx_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
-    break;
-  case 4:
-    break;
-  case 5:
+    } break;
+  case 3: {
+    } break;
+  case 4: {
+    } break;
+  case 5: {
     op_write(OPMODE_ADDR, dp + regs.x, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_addry_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
-    break;
-  case 4:
-    break;
-  case 5:
+    } break;
+  case 3: {
+    } break;
+  case 4: {
+    } break;
+  case 5: {
     op_write(OPMODE_ADDR, dp + regs.y, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_idpx_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read() + regs.x;
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     dp  = op_read(OPMODE_DP, sp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     dp |= op_read(OPMODE_DP, sp + 1) << 8;
-    break;
-  case 5:
-    break;
-  case 6:
+    } break;
+  case 5: {
+    } break;
+  case 6: {
     op_write(OPMODE_ADDR, dp, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov_idpy_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     dp  = op_read(OPMODE_DP, sp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     dp |= op_read(OPMODE_DP, sp + 1) << 8;
-    break;
-  case 5:
-    break;
-  case 6:
+    } break;
+  case 5: {
+    } break;
+  case 6: {
     op_write(OPMODE_ADDR, dp + regs.y, regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_movw_ya_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     regs.a = op_read(OPMODE_DP, sp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     regs.y = op_read(OPMODE_DP, sp + 1);
     regs.p.n = !!(regs.ya & 0x8000);
     regs.p.z = (regs.ya == 0);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_movw_dp_ya() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     op_write(OPMODE_DP, dp,     regs.a);
-    break;
-  case 4:
+    } break;
+  case 4: {
     op_write(OPMODE_DP, dp + 1, regs.y);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov1_c_bit() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     sp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     bit = sp >> 13;
     sp &= 0x1fff;
     rd = op_read(OPMODE_ADDR, sp);
     regs.p.c = !!(rd & (1 << bit));
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_mov1_bit_c() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     bit = dp >> 13;
     dp &= 0x1fff;
     rd = op_read(OPMODE_ADDR, dp);
     if(regs.p.c)rd |=  (1 << bit);
     else        rd &= ~(1 << bit);
-    break;
-  case 4:
+    } break;
+  case 4: {
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 

src/apu/bapu/core/op_pc.b

@@ -37,16 +37,25 @@ bbc7(0xf3, 0x80, ==) {
 6:regs.pc += (int8)rd;
 }
 
-cbne_dp(0x2e, 0),
-cbne_dpx(0xde, regs.x) {
+cbne_dp(0x2e) {
 1:dp = op_read();
 2:rd = op_read();
-3:sp = op_read(OPMODE_DP, dp + $1);
+3:sp = op_read(OPMODE_DP, dp);
 4:if(regs.a == sp)end;
 5:
 6:regs.pc += (int8)rd;
 }
 
+cbne_dpx(0xde) {
+1:dp = op_read();
+2:rd = op_read();
+3:
+4:sp = op_read(OPMODE_DP, dp + regs.x);
+5:if(regs.a == sp)end;
+6:
+7:regs.pc += (int8)rd;
+}
+
 dbnz_dp(0x6e) {
 1:dp = op_read();
 2:rd = op_read();

src/apu/bapu/core/op_rmw.cpp

@@ -1,452 +1,452 @@
 void bAPU::op_inc_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = op_inc(regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_inc_x() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.x = op_inc(regs.x);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_inc_y() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.y = op_inc(regs.y);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_dec_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = op_dec(regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_dec_x() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.x = op_dec(regs.x);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_dec_y() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.y = op_dec(regs.y);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_asl_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = op_asl(regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_lsr_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = op_lsr(regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_rol_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = op_rol(regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_ror_a() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     regs.a = op_ror(regs.a);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_inc_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_inc(rd);
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_dec_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_dec(rd);
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_asl_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_asl(rd);
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_lsr_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_lsr(rd);
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_rol_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_rol(rd);
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_ror_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_ror(rd);
     op_write(OPMODE_DP, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_inc_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     rd = op_read(OPMODE_DP, dp + regs.x);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_inc(rd);
     op_write(OPMODE_DP, dp + regs.x, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_dec_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     rd = op_read(OPMODE_DP, dp + regs.x);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_dec(rd);
     op_write(OPMODE_DP, dp + regs.x, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_asl_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     rd = op_read(OPMODE_DP, dp + regs.x);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_asl(rd);
     op_write(OPMODE_DP, dp + regs.x, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_lsr_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     rd = op_read(OPMODE_DP, dp + regs.x);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_lsr(rd);
     op_write(OPMODE_DP, dp + regs.x, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_rol_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     rd = op_read(OPMODE_DP, dp + regs.x);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_rol(rd);
     op_write(OPMODE_DP, dp + regs.x, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_ror_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
-    break;
-  case 3:
+    } break;
+  case 2: {
+    } break;
+  case 3: {
     rd = op_read(OPMODE_DP, dp + regs.x);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_ror(rd);
     op_write(OPMODE_DP, dp + regs.x, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_inc_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_ADDR, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_inc(rd);
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_dec_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_ADDR, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_dec(rd);
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_asl_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_ADDR, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_asl(rd);
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_lsr_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_ADDR, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_lsr(rd);
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_rol_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_ADDR, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_rol(rd);
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_ror_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp  = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     dp |= op_read() << 8;
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd = op_read(OPMODE_ADDR, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_ror(rd);
     op_write(OPMODE_ADDR, dp, rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_incw_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd  = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |= op_read(OPMODE_DP, dp + 1) << 8;
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_incw(rd);
     op_write(OPMODE_DP, dp + 1, rd >> 8);
-    break;
-  case 5:
+    } break;
+  case 5: {
     op_write(OPMODE_DP, dp,     rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bAPU::op_decw_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd  = op_read(OPMODE_DP, dp);
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd |= op_read(OPMODE_DP, dp + 1) << 8;
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd = op_decw(rd);
     op_write(OPMODE_DP, dp + 1, rd >> 8);
-    break;
-  case 5:
+    } break;
+  case 5: {
     op_write(OPMODE_DP, dp,     rd);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 

src/apu/bapu/core/opfn.cpp

@@ -9,12 +9,11 @@ int16 r = x + y + regs.p.c;
 }
 
 uint16 bAPU::op_addw(uint16 x, uint16 y) {
-int32 r = x + y;
-  regs.p.n = !!(r & 0x8000);
-  regs.p.v = !!(~(x ^ y) & (y ^ (uint16)r) & 0x8000);
-  regs.p.h = !!((x ^ y ^ (uint16)r) & 0x10);
+int16 r;
+  regs.p.c = 0;
+  r  = op_adc(x, y);
+  r |= op_adc(x >> 8, y >> 8) << 8;
   regs.p.z = ((uint16)r == 0);
-  regs.p.c = (r > 0xffff);
   return r;
 }
 
@@ -66,12 +65,11 @@ int16 r = x - y - !regs.p.c;
 }
 
 uint16 bAPU::op_subw(uint16 x, uint16 y) {
-int32 r = x - y;
-  regs.p.n = !!(r & 0x8000);
-  regs.p.v = !!((x ^ y) & (x ^ (uint16)r) & 0x8000);
-  regs.p.h = !((x ^ y ^ (uint16)r) & 0x10);
+int16 r;
+  regs.p.c = 1;
+  r  = op_sbc(x, y);
+  r |= op_sbc(x >> 8, y >> 8) << 8;
   regs.p.z = ((uint16)r == 0);
-  regs.p.c = (r >= 0);
   return r;
 }
 

src/apu/bapu/memory/memory.cpp

@@ -0,0 +1,199 @@
+uint8 bAPU::spcram_read(uint16 addr) {
+uint8 r;
+  if(addr >= 0x00f0 && addr <= 0x00ff) {
+    switch(addr) {
+    case 0xf0: //TEST -- operation unknown, supposedly returns 0x00
+      r = 0x00;
+      break;
+    case 0xf1: //CONTROL -- write-only register, always returns 0x00
+      r = 0x00;
+      break;
+    case 0xf2: //DSPADDR
+      r = status.dsp_addr;
+      break;
+    case 0xf3: //DSPDATA
+    //0x80-0xff is a read-only mirror of 0x00-0x7f
+      r = r_dsp->read(status.dsp_addr & 0x7f);
+      break;
+    case 0xf4: //CPUIO0
+    case 0xf5: //CPUIO1
+    case 0xf6: //CPUIO2
+    case 0xf7: //CPUIO3
+      r = r_cpu->port_read(addr & 3);
+      break;
+    case 0xf8: //???
+    case 0xf9: //??? -- Mapped to SPCRAM
+      r = spcram[addr];
+      break;
+    case 0xfa: //T0TARGET
+    case 0xfb: //T1TARGET
+    case 0xfc: //T2TARGET -- write-only registers, always return 0x00
+      r = 0x00;
+      break;
+    case 0xfd: //T0OUT -- 4-bit counter value
+      r = t0.stage3_ticks & 15;
+      t0.stage3_ticks = 0;
+      break;
+    case 0xfe: //T1OUT -- 4-bit counter value
+      r = t1.stage3_ticks & 15;
+      t1.stage3_ticks = 0;
+      break;
+    case 0xff: //T2OUT -- 4-bit counter value
+      r = t2.stage3_ticks & 15;
+      t2.stage3_ticks = 0;
+      break;
+    }
+  } else if(addr < 0xffc0) {
+    r = spcram[addr];
+  } else {
+    if(status.iplrom_enabled == true) {
+      r = iplrom[addr & 0x3f];
+    } else {
+      r = spcram[addr];
+    }
+  }
+
+#ifdef DEBUGGER
+  snes->notify(SNES::SPCRAM_READ, addr, r);
+#endif
+  return r;
+}
+
+void bAPU::spcram_write(uint16 addr, uint8 value) {
+  if(addr >= 0x00f0 && addr <= 0x00ff) {
+    switch(addr) {
+    case 0xf0: //TEST -- operation unknown
+      break;
+    case 0xf1: //CONTROL
+      status.iplrom_enabled = !!(value & 0x80);
+
+    //one-time clearing of APU port read registers,
+    //emulated by simulating CPU writes of 0x00
+      if(value & 0x20) {
+        r_cpu->port_write(2, 0x00);
+        r_cpu->port_write(3, 0x00);
+      }
+      if(value & 0x10) {
+        r_cpu->port_write(0, 0x00);
+        r_cpu->port_write(1, 0x00);
+      }
+
+    //0->1 transistion resets timers
+      if(t2.enabled == false && (value & 0x04)) {
+        t2.stage2_ticks = 0;
+        t2.stage3_ticks = 0;
+      }
+      t2.enabled = !!(value & 0x04);
+
+      if(t1.enabled == false && (value & 0x02)) {
+        t1.stage2_ticks = 0;
+        t1.stage3_ticks = 0;
+      }
+      t1.enabled = !!(value & 0x02);
+
+      if(t0.enabled == false && (value & 0x01)) {
+        t0.stage2_ticks = 0;
+        t0.stage3_ticks = 0;
+      }
+      t0.enabled = !!(value & 0x01);
+      break;
+    case 0xf2: //DSPADDR
+      status.dsp_addr = value;
+      break;
+    case 0xf3: //DSPDATA
+    //0x80-0xff is a read-only mirror of 0x00-0x7f
+      if(status.dsp_addr < 0x80) {
+        r_dsp->write(status.dsp_addr & 0x7f, value);
+      }
+      break;
+    case 0xf4: //CPUIO0
+    case 0xf5: //CPUIO1
+    case 0xf6: //CPUIO2
+    case 0xf7: //CPUIO3
+      port_write(addr & 3, value);
+      break;
+    case 0xf8: //???
+    case 0xf9: //??? - Mapped to SPCRAM
+      spcram[addr] = value;
+      break;
+    case 0xfa: //T0TARGET
+      t0.target = value;
+      break;
+    case 0xfb: //T1TARGET
+      t1.target = value;
+      break;
+    case 0xfc: //T2TARGET
+      t2.target = value;
+      break;
+    case 0xfd: //T0OUT
+    case 0xfe: //T1OUT
+    case 0xff: //T2OUT -- read-only registers
+      break;
+    }
+  } else {
+  //writes to $ffc0-$ffff always go to spcram,
+  //even if the iplrom is enabled.
+    spcram[addr] = value;
+  }
+
+#ifdef DEBUGGER
+  snes->notify(SNES::SPCRAM_WRITE, addr, value);
+#endif
+}
+
+uint8 bAPU::port_read(uint8 port) {
+  return spcram[0xf4 + (port & 3)];
+}
+
+void bAPU::port_write(uint8 port, uint8 value) {
+  spcram[0xf4 + (port & 0x03)] = value;
+}
+
+uint8 bAPU::op_read() {
+uint8 r;
+  r = spcram_read(regs.pc);
+  regs.pc++;
+  return r;
+}
+
+uint8 bAPU::op_read(uint8 mode, uint16 addr) {
+uint8 r;
+  switch(mode) {
+  case OPMODE_ADDR:
+    r = spcram_read(addr);
+    break;
+  case OPMODE_DP:
+    r = spcram_read(((regs.p.p)?0x100:0x000) + (addr & 0xff));
+    break;
+  }
+  return r;
+}
+
+void bAPU::op_write(uint8 mode, uint16 addr, uint8 value) {
+  switch(mode) {
+  case OPMODE_ADDR:
+    spcram_write(addr, value);
+    break;
+  case OPMODE_DP:
+    spcram_write(((regs.p.p)?0x100:0x000) + (addr & 0xff), value);
+    break;
+  }
+}
+
+uint8 bAPU::stack_read() {
+  regs.sp++;
+  return spcram_read(0x0100 | regs.sp);
+}
+
+void bAPU::stack_write(uint8 value) {
+  spcram_write(0x0100 | regs.sp, value);
+  regs.sp--;
+}
+
+uint8 *bAPU::get_spcram_handle() {
+  if(!spcram) {
+    alert("bAPU::get_spcram_handle() -- spcram uninitialized");
+  }
+
+  return spcram;
+}

src/apu/bapu/memory/memory.h

@@ -0,0 +1,14 @@
+enum { OPMODE_ADDR, OPMODE_DP };
+uint8 *spcram;
+  inline uint8  spcram_read (uint16 addr);
+  inline void   spcram_write(uint16 addr, uint8 value);
+  inline uint8  port_read (uint8 port);
+  inline void   port_write(uint8 port,  uint8 value);
+
+  inline uint8 *get_spcram_handle();
+
+  inline uint8  op_read();
+  inline uint8  op_read (uint8 mode, uint16 addr);
+  inline void   op_write(uint8 mode, uint16 addr, uint8 value);
+  inline uint8  stack_read();
+  inline void   stack_write(uint8 value);

src/apu/bapu/timing/timing.cpp

@@ -0,0 +1,35 @@
+void bAPU::add_cycles(int cycles) {
+  status.cycles_executed += cycles;
+
+  t0.add_cycles(cycles);
+  t1.add_cycles(cycles);
+  t2.add_cycles(cycles);
+}
+
+uint32 bAPU::cycles_executed() {
+uint32 r = status.cycles_executed;
+  status.cycles_executed = 0;
+  return (r << 4) + (r << 3);
+}
+
+//cycles should never be greater than 12. since the minimum
+//cycle_frequency value is 16, we don't have to worry about
+//two ticks occuring in one call to this function.
+void bAPU::bAPUTimer::add_cycles(int cycles) {
+//stage 1 increment
+  stage1_ticks += cycles;
+  if(stage1_ticks < cycle_frequency)return;
+
+  stage1_ticks -= cycle_frequency;
+  if(enabled == false)return;
+
+//stage 2 increment
+  stage2_ticks++;
+
+  if(stage2_ticks != target)return;
+
+//stage 3 increment
+  stage2_ticks = 0;
+  stage3_ticks++;
+  stage3_ticks &= 15;
+}

src/apu/bapu/timing/timing.h

@@ -0,0 +1,9 @@
+class bAPUTimer {
+public:
+uint8 cycle_frequency, target;
+uint8 stage1_ticks, stage2_ticks, stage3_ticks;
+bool  enabled;
+  inline void add_cycles(int cycles);
+} t0, t1, t2;
+  inline void   add_cycles(int cycles);
+  inline uint32 cycles_executed();

src/apu/bapuskip/bapuskip.cpp

@@ -1,171 +0,0 @@
-#include "../../base.h"
-
-uint8 bAPUSkip::spcram_read (uint16 addr) { return 0xff; }
-void  bAPUSkip::spcram_write(uint16 addr, uint8 value) {}
-
-/*
-  This routine is very serious. It will eat holes through
-  the ROM to skip APU test conditions. Or in other words,
-  it will disable and/or force branches when neccesary.
-
-  It can very easily break or corrupt a game and prevent it
-  from being playable until the ROM is reloaded (ROM writes
-  are only performed in memory, of course).
-
-  However, this kind of brute force approach is required to
-  get many games playable without proper SPC700 emulation.
-*/
-uint8 bAPUSkip::port_read(uint8 port) {
-  port &= 3;
-_apu_port *p = &apu_port[port];
-int i, x, y, z, t;
-uint32 addr;
-
-  addr = cpu->regs.pc.d;
-  p->read_addr[p->read_pos & 31] = addr;
-
-//- lda $214x
-//  cmp $214x
-//  bne -
-//  cmp ???
-//  beq/bne -
-__test1:
-//look for an lda/cmp read pattern
-  if(addr == p->read_addr[(p->read_pos - 1) & 31])goto __test2;
-  if(addr != p->read_addr[(p->read_pos - 2) & 31])goto __test2;
-  if(addr == p->read_addr[(p->read_pos - 3) & 31])goto __test2;
-  if(addr != p->read_addr[(p->read_pos - 4) & 31])goto __test2;
-  if(p->read_addr[(p->read_pos - 1) & 31] != p->read_addr[(p->read_pos - 3) & 31])goto __test2;
-//try and find compare opcode
-  for(i=0;i<24;i++) {
-    x = mem_bus->read(addr + i);
-    if(x == OP_CMP_CONST || x == OP_CPX_CONST || x == OP_CPY_CONST)break;
-    if(x == OP_CMP_ADDR  || x == OP_CPX_ADDR  || x == OP_CPY_ADDR) break;
-    if(x == OP_CMP_LONG)break;
-  }
-  if(i == 24)goto __test2;
-//seek to next opcode
-  if(x == OP_CMP_CONST) {
-    i += (cpu->regs.p.m)?2:3;
-  } else if(x == OP_CPX_CONST || x == OP_CPY_CONST) {
-    i += (cpu->regs.p.x)?2:3;
-  } else if(x == OP_CMP_ADDR || x == OP_CPX_ADDR || x == OP_CPY_ADDR) {
-    i += 3;
-  } else { //(x == OP_CMP_LONG) {
-    i += 4;
-  }
-  x = mem_bus->read(addr + i);
-  if(x == OP_BNE) {
-    mem_bus->cart->write_protect(false);
-    mem_bus->write(addr + i,     OP_NOP);
-    mem_bus->write(addr + i + 1, OP_NOP);
-    mem_bus->cart->write_protect(true);
-  } else if(x == OP_BEQ) {
-    mem_bus->cart->write_protect(false);
-    mem_bus->write(addr + i, OP_BRA);
-    mem_bus->cart->write_protect(true);
-  } else goto __test2;
-  goto __pass;
-
-//- lda $214x
-//  cmp ???
-//  beq/bne -
-__test2:
-//look for a repeated read pattern
-  if(addr != p->read_addr[(p->read_pos - 1) & 31])goto __test3;
-  if(addr != p->read_addr[(p->read_pos - 2) & 31])goto __test3;
-  if(addr != p->read_addr[(p->read_pos - 3) & 31])goto __test3;
-  if(addr != p->read_addr[(p->read_pos - 4) & 31])goto __test3;
-  if(addr != p->read_addr[(p->read_pos - 5) & 31])goto __test3;
-  if(addr != p->read_addr[(p->read_pos - 6) & 31])goto __test3;
-  if(addr != p->read_addr[(p->read_pos - 7) & 31])goto __test3;
-  if(addr != p->read_addr[(p->read_pos - 8) & 31])goto __test3;
-//try and find compare opcode
-  for(i=0;i<24;i++) {
-    x = mem_bus->read(addr + i);
-    if(x == OP_CMP_CONST || x == OP_CPX_CONST || x == OP_CPY_CONST)break;
-    if(x == OP_CMP_ADDR  || x == OP_CPX_ADDR  || x == OP_CPY_ADDR) break;
-    if(x == OP_CMP_LONG)break;
-  }
-  if(i == 24)goto __test3;
-//seek to next opcode
-  if(x == OP_CMP_CONST) {
-    i += (cpu->regs.p.m)?2:3;
-  } else if(x == OP_CPX_CONST || x == OP_CPY_CONST) {
-    i += (cpu->regs.p.x)?2:3;
-  } else if(x == OP_CMP_ADDR || x == OP_CPX_ADDR || x == OP_CPY_ADDR) {
-    i += 3;
-  } else if(x == OP_CMP_LONG) {
-    i += 4;
-  }
-  x = mem_bus->read(addr + i);
-  if(x == OP_BNE) {
-    mem_bus->cart->write_protect(false);
-    mem_bus->write(addr + i,     OP_NOP);
-    mem_bus->write(addr + i + 1, OP_NOP);
-    mem_bus->cart->write_protect(true);
-  } else if(x == OP_BEQ) {
-    mem_bus->cart->write_protect(false);
-    mem_bus->write(addr + i, OP_BRA);
-    mem_bus->cart->write_protect(true);
-  } else goto __test3;
-  goto __pass;
-
-//fallback
-__test3:
-  if(p->pos < 4) {
-    if(!(port & 1)) {
-      p->value = cpu->regs.a.l;
-    } else {
-      p->value = cpu->regs.a.h;
-    }
-  } else if(p->pos < 8) {
-    if(!(port & 1)) {
-      p->value = cpu->regs.x.l;
-    } else {
-      p->value = cpu->regs.x.h;
-    }
-  } else if(p->pos < 12) {
-    if(!(port & 1)) {
-      p->value = cpu->regs.y.l;
-    } else {
-      p->value = cpu->regs.y.h;
-    }
-  } else if(p->pos < 16) {
-    p->value = rand();
-  }
-  if(++p->pos == 16)p->pos = 0;
-
-__pass:
-  p->read_pos++;
-  p->read_pos &= 31;
-  return p->value;
-}
-
-void bAPUSkip::port_write(uint8 port, uint8 value) {
-  port &= 3;
-  apu_port[port].value = value;
-}
-
-void bAPUSkip::run() {
-  snes->notify(SNES::APU_EXEC_OPCODE_BEGIN);
-  snes->notify(SNES::APU_EXEC_OPCODE_END);
-}
-
-void bAPUSkip::power() {
-  reset();
-}
-
-void bAPUSkip::reset() {
-  regs.a  = 0x00;
-  regs.x  = 0x00;
-  regs.y  = 0x00;
-  regs.sp = 0x00;
-  regs.p  = 0x02;
-  regs.pc = 0xffc0;
-
-  memset(&apu_port[0], 0, sizeof(_apu_port));
-  memset(&apu_port[1], 0, sizeof(_apu_port));
-  memset(&apu_port[2], 0, sizeof(_apu_port));
-  memset(&apu_port[3], 0, sizeof(_apu_port));
-}

src/apu/bapuskip/bapuskip.h

@@ -1,37 +0,0 @@
-class bAPUSkip : public APU {
-private:
-uint8 spcram[65536];
-
-public:
-
-struct _apu_port {
-  uint8  value;
-  uint8  step, pos;
-  uint32 read_addr[32], read_pos;
-}apu_port[4];
-
-enum {
-  OP_CMP_CONST = 0xc9,
-  OP_CPX_CONST = 0xe0,
-  OP_CPY_CONST = 0xc0,
-  OP_CMP_ADDR  = 0xcd,
-  OP_CPX_ADDR  = 0xec,
-  OP_CPY_ADDR  = 0xcc,
-  OP_CMP_LONG  = 0xcf,
-  OP_BNE       = 0xd0,
-  OP_BEQ       = 0xf0,
-  OP_BRA       = 0x80,
-  OP_NOP       = 0xea
-};
-
-  uint8  spcram_read (uint16 addr);
-  void   spcram_write(uint16 addr, uint8 value);
-  uint8  port_read   (uint8 port);
-  void   port_write  (uint8 port, uint8 value);
-
-  uint8 *get_spcram_handle() { return spcram; }
-  void   run();
-  uint32 cycles_executed() { return 12 * 24; }
-  void   power();
-  void   reset();
-};

src/base.h

@@ -1,8 +1,37 @@
-#include <time.h>
-#include "lib/libbase.h"
-#include "lib/libvector.h"
-#include "lib/libstring.h"
-#include "lib/libconfig.h"
+#define BSNES_VERSION "0.016"
+#define BSNES_TITLE "bsnes v" BSNES_VERSION
+
+#define MEMCORE bMemBus
+#define CPUCORE bCPU
+#define APUCORE bAPU
+#define DSPCORE bDSP
+#define PPUCORE bPPU
+
+//game genie + pro action replay code support (~1-3% speed hit)
+#define CHEAT_SYSTEM
+
+//enable GZ, ZIP format support
+//#define GZIP_SUPPORT
+
+//enable JMA support
+//#define JMA_SUPPORT
+
+//debugging extensions (~10% speed hit)
+#define DEBUGGER
+
+//snes core polymorphism
+//(allow mem/cpu/apu/ppu overriding, ~10% speed hit)
+//#define POLYMORPHISM
+
+//this should be declared in the port-specific makefiles
+//#define ARCH_LSB
+//#define ARCH_MSB
+
+#ifndef ARCH_LSB
+  #ifndef ARCH_MSB
+    #define ARCH_LSB
+  #endif
+#endif
 
 #if defined(_WIN32)
   #define _WIN32_
@@ -14,9 +43,21 @@
   #error "unknown architecture"
 #endif
 
+#include "lib/libbase.h"
+#include "lib/libvector.h"
+#include "lib/libstring.h"
+#include "lib/libconfig.h"
+#include "lib/libbpf.h"
+
+inline uint16 read16(uint8 *addr, uint pos) {
+#ifdef ARCH_LSB
+  return *((uint16*)(addr + pos));
+#else
+  return (addr[pos]) | (addr[pos + 1] << 8);
+#endif
+}
+
 //platform-specific global functions
-void *memalloc(uint32 size, char *name = 0, ...);
-void memfree(void *mem, char *name = 0, ...);
 void alert(char *s, ...);
 void dprintf(char *s, ...);
 

src/cart/cart.cpp

@@ -0,0 +1,369 @@
+#include "../base.h"
+
+void Cartridge::read_header() {
+  cart.srtc = false;
+  cart.sdd1 = false;
+  cart.c4   = false;
+  cart.dsp2 = false;
+  cart.obc1 = false;
+
+  if(cart.header_index == 0x7fc0 && cart.rom_size >= 0x401000) {
+    cart.mapper = EXLOROM;
+  } else if(cart.header_index == 0x7fc0 && rom[cart.header_index + MAPPER] == 0x32) {
+    cart.mapper = EXLOROM;
+  } else if(cart.header_index == 0x7fc0) {
+    cart.mapper = LOROM;
+  } else if(cart.header_index == 0xffc0) {
+    cart.mapper = HIROM;
+  } else { //cart.header_index == 0x40ffc0
+    cart.mapper = EXHIROM;
+  }
+
+uint8 mapper   = rom[cart.header_index + MAPPER];
+uint8 rom_type = rom[cart.header_index + ROM_TYPE];
+  if(mapper == 0x35 && rom_type == 0x55) {
+    cart.srtc = true;
+  }
+
+  if(mapper == 0x32 && (rom_type == 0x43 || rom_type == 0x45)) {
+    cart.sdd1 = true;
+  }
+
+  if(mapper == 0x20 && rom_type == 0xf3) {
+    cart.c4 = true;
+  }
+
+  if(mapper == 0x20 && rom_type == 0x05) {
+    cart.dsp2 = true;
+  }
+
+  if(mapper == 0x30 && rom_type == 0x25) {
+    cart.obc1 = true;
+  }
+
+  cart.cart_mmio = cart.c4 | cart.dsp2 | cart.obc1;
+
+  if(rom[cart.header_index + SRAM_SIZE] & 7) {
+    cart.sram_size = 1024 << (rom[cart.header_index + SRAM_SIZE] & 7);
+  } else {
+    cart.sram_size = 0;
+  }
+
+  cart.region = ((rom[cart.header_index + REGION] & 0x7f) < 2) ? NTSC : PAL;
+
+  memcpy(&cart.name, &rom[cart.header_index + CART_NAME], 21);
+  cart.name[21] = 0;
+
+  for(int i = 0; i < 22; i++) {
+    if(cart.name[i] & 0x80) {
+      cart.name[i] = '?';
+    }
+  }
+}
+
+void Cartridge::find_header() {
+int32 score_lo = 0,
+      score_hi = 0,
+      score_ex = 0;
+
+  if(rom_size < 0x010000) {
+  //cart too small to be anything else
+    cart.header_index = 0x007fc0;
+    return;
+  }
+
+  if((rom[0x7fc0 + MAPPER] & ~0x10) == 0x20)score_lo++;
+  if((rom[0xffc0 + MAPPER] & ~0x10) == 0x21)score_hi++;
+
+  if(rom[0x7fc0 + ROM_TYPE] < 0x08)score_lo++;
+  if(rom[0xffc0 + ROM_TYPE] < 0x08)score_hi++;
+
+  if(rom[0x7fc0 + ROM_SIZE] < 0x10)score_lo++;
+  if(rom[0xffc0 + ROM_SIZE] < 0x10)score_hi++;
+
+  if(rom[0x7fc0 + SRAM_SIZE] < 0x08)score_lo++;
+  if(rom[0xffc0 + SRAM_SIZE] < 0x08)score_hi++;
+
+  if(rom[0x7fc0 + REGION] < 14)score_lo++;
+  if(rom[0xffc0 + REGION] < 14)score_hi++;
+
+  if(rom[0x7fc0 + LICENSE] < 3)score_lo++;
+  if(rom[0xffc0 + LICENSE] < 3)score_hi++;
+
+uint16 cksum, icksum;
+  cksum  = rom[0x7fc0 +  CKSUM] | (rom[0x7fc0 +  CKSUM + 1] << 8);
+  icksum = rom[0x7fc0 + ICKSUM] | (rom[0x7fc0 + ICKSUM + 1] << 8);
+  if((cksum + icksum) == 0xffff && (cksum != 0) && (icksum != 0)) {
+    score_lo += 8;
+  }
+
+  cksum  = rom[0xffc0 +  CKSUM] | (rom[0xffc0 +  CKSUM + 1] << 8);
+  icksum = rom[0xffc0 + ICKSUM] | (rom[0xffc0 + ICKSUM + 1] << 8);
+  if((cksum + icksum) == 0xffff && (cksum != 0) && (icksum != 0)) {
+    score_hi += 8;
+  }
+
+  if(rom_size < 0x401000) {
+    score_ex = 0;
+  } else {
+    if(rom[0x7fc0 + MAPPER] == 0x32)score_lo++;
+    else score_ex += 16;
+  }
+
+  if(score_lo >= score_hi && score_lo >= score_ex) {
+    cart.header_index = 0x007fc0;
+  } else if(score_hi >= score_ex) {
+    cart.header_index = 0x00ffc0;
+  } else {
+    cart.header_index = 0x40ffc0;
+  }
+}
+
+void Cartridge::load_sram() {
+  if(cart.sram_size == 0) {
+    sram = 0;
+    return;
+  }
+
+FileReader ff(sram_fn);
+  if(!ff.ready()) {
+    sram = (uint8*)malloc(cart.sram_size);
+    memset(sram, 0, cart.sram_size);
+    return;
+  }
+
+  sram = ff.read(cart.sram_size);
+}
+
+void Cartridge::save_sram() {
+  if(cart.sram_size == 0)return;
+
+FileWriter ff(sram_fn);
+  if(!ff.ready())return;
+
+  ff.write(sram, cart.sram_size);
+}
+
+void Cartridge::load_rom(Reader *rf) {
+  base_rom = rf->read();
+  rom_size = rf->size();
+
+  if((rom_size & 0x7fff) == 0x0200) {
+    rom = base_rom + 512;
+    rom_size -= 512;
+  } else {
+    rom = base_rom;
+  }
+
+  cart.rom_size = rom_size;
+
+  cart.crc32 = 0xffffffff;
+  for(int32 i = 0; i < cart.rom_size; i++) {
+    cart.crc32 = crc32_adjust(cart.crc32, rom[i]);
+  }
+  cart.crc32 = ~cart.crc32;
+}
+
+void Cartridge::patch_rom(Reader *rf) {
+uint8 *patch_data = rf->read();
+uint32 patch_size = rf->size();
+BPF bpf;
+  if(patch_size < 34)return;
+
+uint32 target;
+  target  = patch_data[BPF::INDEX_FORMAT + 0] <<  0;
+  target |= patch_data[BPF::INDEX_FORMAT + 1] <<  8;
+  target |= patch_data[BPF::INDEX_FORMAT + 2] << 16;
+  target |= patch_data[BPF::INDEX_FORMAT + 3] << 24;
+  if(target != BPF::FORMAT_SNES) {
+    alert("Warning: BPF patch file is not in SNES format!\n\n"
+      "The patch will still be applied, but it will not be "
+      "possible to determine whether the patch was created "
+      "against an image with a header or without a header.\n\n"
+      "bsnes is now forced to assume the patch was created "
+      "against a headerless source image. If this is not the "
+      "case, then patching will fail!\n\n"
+      "If you are the author of this patch, please recreate "
+      "the patch in SNES format.\n\n"
+      "If you are not the patch author, please contact the "
+      "author and ask them to create an SNES format BPF patch.");
+  }
+
+  if(bpf.apply_patch(patch_size, patch_data, rom_size, rom) == true) {
+    SafeFree(base_rom);
+  uint8 *temp = bpf.get_output_handle(rom_size);
+    base_rom = (uint8*)malloc(rom_size);
+    memcpy(base_rom, temp, rom_size);
+    rom = base_rom;
+    cart.rom_size = rom_size;
+  } else {
+    alert("Failed to apply patch.\n\nThis could be because the patch itself "
+      "does not match its internal checksum, because the ROM loaded does not "
+      "match the patch information for either the original or modified file, "
+      "or because the patched file does not match the checksum of either the "
+      "original or modified file that is stored inside the patch.\n\n"
+      "The original ROM image will be used instead.");
+  }
+  SafeFree(patch_data);
+}
+
+bool Cartridge::load(const char *fn) {
+  if(cart_loaded == true)return false;
+  if(strlen(fn) < 3)return false;
+
+  dprintf("* Loading \"%s\"...", fn);
+
+  strcpy(rom_fn, fn);
+
+  switch(Reader::detect(rom_fn)) {
+  case Reader::RF_NORMAL: {
+  FileReader ff(rom_fn);
+    if(!ff.ready()) {
+      alert("Error loading image file (%s)!", rom_fn);
+      return false;
+    }
+    load_rom(static_cast<Reader*>(&ff));
+    break;
+  }
+#ifdef GZIP_SUPPORT
+  case Reader::RF_GZ: {
+  GZReader gf(rom_fn);
+    if(!gf.ready()) {
+      alert("Error loading image file (%s)!", rom_fn);
+      return false;
+    }
+    load_rom(static_cast<Reader*>(&gf));
+    break;
+  }
+  case Reader::RF_ZIP: {
+  ZipReader zf(rom_fn);
+    load_rom(static_cast<Reader*>(&zf));
+    break;
+  }
+#endif
+#ifdef JMA_SUPPORT
+  case Reader::RF_JMA: {
+    try {
+    JMAReader jf(rom_fn);
+      load_rom(static_cast<Reader*>(&jf));
+    } catch(JMA::jma_errors jma_error) {
+      alert("Error loading image file (%s)!", rom_fn);
+      return false;
+    }
+    break;
+  }
+#endif
+  }
+
+//remove ROM extension
+  strcpy(sram_fn, fn);
+  for(int i = strlen(fn) - 1; i >= 0; i--) {
+    if(sram_fn[i] == '.') {
+      sram_fn[i] = 0;
+      break;
+    }
+  }
+
+//check for bpf patch
+#ifdef GZIP_SUPPORT
+  strcpy(patch_fn, sram_fn);
+  strcat(patch_fn, ".bpz");
+  if(fexists(patch_fn)) {
+  ZipReader zf(patch_fn);
+    patch_rom(static_cast<Reader*>(&zf));
+  } else {
+#endif
+    strcpy(patch_fn, sram_fn);
+    strcat(patch_fn, ".bpf");
+    if(fexists(patch_fn)) {
+    FileReader ff(patch_fn);
+      patch_rom(static_cast<Reader*>(&ff));
+    }
+#ifdef GZIP_SUPPORT
+  }
+#endif
+
+//add SRAM extension
+  strcat(sram_fn, ".");
+  strcat(sram_fn, config::fs.save_ext.sget());
+
+//override default path (current directory)?
+  if(strmatch(config::fs.save_path.sget(), "") == false) {
+  //remove path if fs.sram_path was specified
+  string new_fn, parts;
+    strcpy(new_fn, sram_fn);
+    replace(new_fn, "\\", "/");
+    split(parts, "/", new_fn);
+
+  //add new SRAM path
+    strcpy(new_fn, config::fs.save_path.sget());
+
+  //append fs.base_path if fs.sram_path is not fully-qualified path
+    if(strbegin(new_fn, "./") == true) {
+      strltrim(new_fn, "./");
+      strcpy(new_fn[1], new_fn[0]);
+      strcpy(new_fn[0], config::fs.base_path.sget());
+      strcat(new_fn[0], new_fn[1]);
+    }
+
+  //finally, append SRAM file name
+    strcat(new_fn, parts[count(parts) - 1]);
+    strcpy(sram_fn, strptr(new_fn));
+  }
+
+//load cheat file if it exists
+  strcpy(cheat_fn, sram_fn);
+  strrtrim(cheat_fn, config::fs.save_ext.sget());
+  strrtrim(cheat_fn, ".");
+  strcat(cheat_fn, ".cht");
+  if(fexists(cheat_fn) == true) {
+  FileReader ff(cheat_fn);
+    cheat.load(static_cast<Reader*>(&ff));
+  }
+
+  find_header();
+  read_header();
+  load_sram();
+  cart_loaded = true;
+  r_mem->load_cart();
+  return true;
+}
+
+bool Cartridge::unload() {
+  if(cart_loaded == false)return false;
+
+  r_mem->unload_cart();
+
+  if(base_rom) {
+    SafeFree(base_rom);
+  }
+
+  if(sram) {
+    save_sram();
+    SafeFree(sram);
+  }
+
+  if(cheat.count() > 0 || fexists(cheat_fn)) {
+  FileWriter ff(cheat_fn);
+    cheat.save(static_cast<Writer*>(&ff));
+    cheat.clear();
+  }
+
+  cart_loaded = false;
+  return true;
+}
+
+Cartridge::Cartridge() {
+  cart_loaded = false;
+
+  base_rom = 0;
+  rom      = 0;
+  sram     = 0;
+  rom_size = 0;
+}
+
+Cartridge::~Cartridge() {
+  if(cart_loaded == true) {
+    unload();
+  }
+}

src/cart/cart.h

@@ -0,0 +1,68 @@
+class Cartridge {
+public:
+bool cart_loaded;
+char rom_fn[4096], sram_fn[4096], cheat_fn[4096], patch_fn[4096];
+
+uint8 *base_rom, *rom, *sram;
+uint32 rom_size;
+
+enum {
+//header fields
+  CART_NAME = 0x00,
+  MAPPER    = 0x15,
+  ROM_TYPE  = 0x16,
+  ROM_SIZE  = 0x17,
+  SRAM_SIZE = 0x18,
+  REGION    = 0x19,
+  LICENSE   = 0x1a,
+  VERSION   = 0x1b,
+  ICKSUM    = 0x1c,
+  CKSUM     = 0x1e,
+
+//regions
+  NTSC = 0,
+  PAL  = 1,
+
+//memory mappers
+  LOROM   = 0x20,
+  HIROM   = 0x21,
+  EXLOROM = 0x22,
+  EXHIROM = 0x25,
+};
+
+struct {
+  uint32 crc32;
+  uint32 header_index;
+
+  char   name[32];
+  uint32 rom_size;
+  uint32 sram_size;
+  bool   region;
+
+  uint32 mapper;
+
+//set to true for games that need cart MMIO mapping (c4, dsp-n, ...),
+//for games that map outside the standard MMIO range of $2000-$5fff
+  bool   cart_mmio;
+  bool   srtc;
+  bool   sdd1;
+  bool   c4;
+  bool   dsp2;
+  bool   obc1;
+} cart;
+
+  void load_rom(Reader *rf);
+  void patch_rom(Reader *rf);
+  void load_sram();
+  void save_sram();
+  void find_header();
+  void read_header();
+  bool loaded() { return cart_loaded; }
+  bool load(const char *fn);
+  bool unload();
+
+  Cartridge();
+  ~Cartridge();
+};
+
+extern Cartridge cartridge;

src/cheat/cheat.cpp

@@ -0,0 +1,334 @@
+#include "../base.h"
+
+/*****
+ * string <> binary code translation routines
+ * decode() "7e1234:56" ->  0x7e123456
+ * encode()  0x7e123456 -> "7e1234:56"
+ *****/
+
+bool Cheat::decode(char *str, uint32 &addr, uint8 &data, uint8 &type) {
+string t, part;
+  strcpy(t, str);
+  strlower(t);
+  if(strlen(t) == 8 || (strlen(t) == 9 && strptr(t)[6] == ':')) {
+    type = CT_PRO_ACTION_REPLAY;
+    replace(t, ":", "");
+  uint32 r = strhex(t);
+    addr = r >> 8;
+    data = r & 0xff;
+    return true;
+  } else if(strlen(t) == 9 && strptr(t)[4] == '-') {
+    type = CT_GAME_GENIE;
+    replace(t, "-", "");
+    strtr(t, "df4709156bc8a23e", "0123456789abcdef");
+  uint32 r = strhex(t);
+  //8421 8421 8421 8421 8421 8421
+  //abcd efgh ijkl mnop qrst uvwx
+  //ijkl qrst opab cduv wxef ghmn
+    addr = (!!(r & 0x002000) << 23) | (!!(r & 0x001000) << 22) |
+           (!!(r & 0x000800) << 21) | (!!(r & 0x000400) << 20) |
+           (!!(r & 0x000020) << 19) | (!!(r & 0x000010) << 18) |
+           (!!(r & 0x000008) << 17) | (!!(r & 0x000004) << 16) |
+           (!!(r & 0x800000) << 15) | (!!(r & 0x400000) << 14) |
+           (!!(r & 0x200000) << 13) | (!!(r & 0x100000) << 12) |
+           (!!(r & 0x000002) << 11) | (!!(r & 0x000001) << 10) |
+           (!!(r & 0x008000) <<  9) | (!!(r & 0x004000) <<  8) |
+           (!!(r & 0x080000) <<  7) | (!!(r & 0x040000) <<  6) |
+           (!!(r & 0x020000) <<  5) | (!!(r & 0x010000) <<  4) |
+           (!!(r & 0x000200) <<  3) | (!!(r & 0x000100) <<  2) |
+           (!!(r & 0x000080) <<  1) | (!!(r & 0x000040) <<  0);
+    data = r >> 24;
+    return true;
+  }
+  return false;
+}
+
+bool Cheat::encode(char *str, uint32 addr, uint8 data, uint8 type) {
+  if(type == CT_PRO_ACTION_REPLAY) {
+    sprintf(str, "%0.6x:%0.2x", addr, data);
+    return true;
+  } else if(type == CT_GAME_GENIE) {
+  uint32 r = addr;
+    addr = (!!(r & 0x008000) << 23) | (!!(r & 0x004000) << 22) |
+           (!!(r & 0x002000) << 21) | (!!(r & 0x001000) << 20) |
+           (!!(r & 0x000080) << 19) | (!!(r & 0x000040) << 18) |
+           (!!(r & 0x000020) << 17) | (!!(r & 0x000010) << 16) |
+           (!!(r & 0x000200) << 15) | (!!(r & 0x000100) << 14) |
+           (!!(r & 0x800000) << 13) | (!!(r & 0x400000) << 12) |
+           (!!(r & 0x200000) << 11) | (!!(r & 0x100000) << 10) |
+           (!!(r & 0x000008) <<  9) | (!!(r & 0x000004) <<  8) |
+           (!!(r & 0x000002) <<  7) | (!!(r & 0x000001) <<  6) |
+           (!!(r & 0x080000) <<  5) | (!!(r & 0x040000) <<  4) |
+           (!!(r & 0x020000) <<  3) | (!!(r & 0x010000) <<  2) |
+           (!!(r & 0x000800) <<  1) | (!!(r & 0x000400) <<  0);
+    sprintf(str, "%0.2x%0.2x-%0.4x", data, addr >> 16, addr & 0xffff);
+    strtr(str, "0123456789abcdef", "df4709156bc8a23e");
+    return true;
+  }
+  return false;
+}
+
+/*****
+ * address lookup table manipulation and mirroring
+ * mirror_address() 0x000000 -> 0x7e0000
+ * set() enable specified address, mirror accordingly
+ * clear() disable specified address, mirror accordingly
+ *****/
+
+uint Cheat::mirror_address(uint addr) {
+  if((addr & 0x40e000) != 0x0000)return addr;
+//8k WRAM mirror
+//$[00-3f|80-bf]:[0000-1fff] -> $7e:[0000-1fff]
+  return (0x7e0000 + (addr & 0x1fff));
+}
+
+void Cheat::set(uint32 addr) {
+  addr = mirror_address(addr);
+
+  mask[addr >> 3] |= 1 << (addr & 7);
+  if((addr & 0xffe000) == 0x7e0000) {
+  //mirror $7e:[0000-1fff] to $[00-3f|80-bf]:[0000-1fff]
+  uint mirror;
+    for(int x = 0; x <= 0x3f; x++) {
+      mirror = ((0x00 + x) << 16) + (addr & 0x1fff);
+      mask[mirror >> 3] |= 1 << (mirror & 7);
+      mirror = ((0x80 + x) << 16) + (addr & 0x1fff);
+      mask[mirror >> 3] |= 1 << (mirror & 7);
+    }
+  }
+}
+
+void Cheat::clear(uint32 addr) {
+  addr = mirror_address(addr);
+
+//is there more than one cheat code using the same address
+//(and likely a different override value) that is enabled?
+//if so, do not clear code lookup table entry for this address.
+uint8 r;
+  if(read(addr, r) == true)return;
+
+  mask[addr >> 3] &= ~(1 << (addr & 7));
+  if((addr & 0xffe000) == 0x7e0000) {
+  //mirror $7e:[0000-1fff] to $[00-3f|80-bf]:[0000-1fff]
+  uint mirror;
+    for(int x = 0; x <= 0x3f; x++) {
+      mirror = ((0x00 + x) << 16) + (addr & 0x1fff);
+      mask[mirror >> 3] &= ~(1 << (mirror & 7));
+      mirror = ((0x80 + x) << 16) + (addr & 0x1fff);
+      mask[mirror >> 3] &= ~(1 << (mirror & 7));
+    }
+  }
+}
+
+/*****
+ * read() is used by MemBus::read() if Cheat::enabled(addr)
+ * returns true to look up cheat code.
+ * returns true if cheat code was found, false if it was not.
+ * when true, cheat code substitution value is stored in data.
+ *****/
+
+bool Cheat::read(uint32 addr, uint8 &data) {
+  addr = mirror_address(addr);
+  for(int i = 0; i < cheat_count; i++) {
+    if(enabled(i) == false)continue;
+    if(addr == mirror_address(index[i].addr)) {
+      data = index[i].data;
+      return true;
+    }
+  }
+//code not found, or code is disabled
+  return false;
+}
+
+/*****
+ * update_cheat_status() will scan to see if any codes are
+ * enabled. if any are, make sure the cheat system is on.
+ * otherwise, turn cheat system off to speed up emulation.
+ *****/
+void Cheat::update_cheat_status() {
+  for(int i = 0; i < cheat_count; i++) {
+    if(index[i].enabled) {
+      cheat_enabled = true;
+      return;
+    }
+  }
+  cheat_enabled = false;
+}
+
+/*****
+ * cheat list manipulation routines
+ *****/
+
+bool Cheat::add(bool enable, char *code, char *desc) {
+  if(cheat_count >= CHEAT_LIMIT)return false;
+
+uint32 addr, len;
+uint8  data, type;
+  if(decode(code, addr, data, type) == false)return false;
+
+  index[cheat_count].enabled = enable;
+  index[cheat_count].addr = addr;
+  index[cheat_count].data = data;
+  len = strlen(code);
+  len = len > 16 ? 16 : len;
+  memcpy(index[cheat_count].code, code, len);
+  index[cheat_count].code[len] = 0;
+  len = strlen(desc);
+  len = len > 128 ? 128 : len;
+  memcpy(index[cheat_count].desc, desc, len);
+  index[cheat_count].desc[len] = 0;
+  cheat_count++;
+  (enable) ? set(addr) : clear(addr);
+
+  update_cheat_status();
+  return true;
+}
+
+bool Cheat::edit(uint32 n, bool enable, char *code, char *desc) {
+  if(n >= cheat_count)return false;
+
+uint32 addr, len;
+uint8  data, type;
+  if(decode(code, addr, data, type) == false)return false;
+
+//disable current code and clear from code lookup table
+  index[n].enabled = false;
+  clear(index[n].addr);
+
+//update code and enable in code lookup table
+  index[n].enabled = enable;
+  index[n].addr = addr;
+  index[n].data = data;
+  len = strlen(code);
+  len = len > 16 ? 16 : len;
+  memcpy(index[n].code, code, len);
+  index[n].code[len] = 0;
+  len = strlen(desc);
+  len = len > 128 ? 128 : len;
+  memcpy(index[n].desc, desc, len);
+  index[n].desc[len] = 0;
+  set(addr);
+
+  update_cheat_status();
+  return true;
+}
+
+bool Cheat::remove(uint32 n) {
+  if(n >= cheat_count)return false;
+
+  for(int i = n; i < cheat_count; i++) {
+    index[i].enabled = index[i + 1].enabled;
+    index[i].addr    = index[i + 1].addr;
+    index[i].data    = index[i + 1].data;
+    strcpy(index[i].desc, index[i + 1].desc);
+  }
+
+  cheat_count--;
+
+  update_cheat_status();
+  return true;
+}
+
+bool Cheat::get(uint32 n, bool &enable, uint32 &addr, uint8 &data, char *code, char *desc) {
+  if(n >= cheat_count)return false;
+  enable = index[n].enabled;
+  addr   = index[n].addr;
+  data   = index[n].data;
+  strcpy(code, index[n].code);
+  strcpy(desc, index[n].desc);
+  return true;
+}
+
+/*****
+ * code status modifier routines
+ *****/
+
+bool Cheat::enabled(uint32 n) {
+  if(n >= cheat_count)return false;
+  return index[n].enabled;
+}
+
+void Cheat::enable(uint32 n) {
+  if(n >= cheat_count)return;
+  index[n].enabled = true;
+  set(index[n].addr);
+  update_cheat_status();
+}
+
+void Cheat::disable(uint32 n) {
+  if(n >= cheat_count)return;
+  index[n].enabled = false;
+  clear(index[n].addr);
+  update_cheat_status();
+}
+
+/*****
+ * cheat file manipulation routines
+ *****/
+
+bool Cheat::load(Reader *rf) {
+  if(!rf->ready())return false;
+
+uint8 *raw_data = rf->read();
+string data;
+  raw_data[rf->size()] = 0;
+  strcpy(data, (char*)raw_data);
+  SafeFree(raw_data);
+  replace(data, "\r\n", "\n");
+string line;
+  split(line, "\n", data);
+  for(int i = 0; i < ::count(line); i++) {
+  string part;
+  uint8  en = *(strptr(line[i]));
+    if(en == '+') {
+      strltrim(line[i], "+");
+    } else if(en == '-') {
+      strltrim(line[i], "-");
+    } else {
+      continue;
+    }
+    qreplace(line[i], " ", "");
+    qsplit(part, ",", line[i]);
+    if(::count(part) != 2)continue;
+    strunquote(part[1]);
+    add(en == '+', strptr(part[0]), strptr(part[1]));
+  }
+
+  return true;
+}
+
+bool Cheat::save(Writer *wf) {
+  if(!wf->ready())return false;
+
+string data;
+char   t[4096];
+  strcpy(data, "");
+  for(int i = 0; i < cheat_count; i++) {
+    sprintf(t, "%c%s, \"%s\"\r\n", index[i].enabled ? '+' : '-', index[i].code, index[i].desc);
+    strcat(data, t);
+  }
+
+  wf->write((uint8*)strptr(data), strlen(data));
+  return true;
+}
+
+/*****
+ * initialization routines
+ *****/
+
+void Cheat::clear() {
+  cheat_enabled = false;
+  cheat_count   = 0;
+  memset(mask, 0, 0x200000);
+  for(int i = 0; i < CHEAT_LIMIT + 1; i++) {
+    index[i].enabled = false;
+    index[i].addr    = 0x000000;
+    index[i].data    = 0x00;
+    strcpy(index[i].code, "");
+    strcpy(index[i].desc, "");
+  }
+}
+
+Cheat::Cheat() {
+  clear();
+}

src/cheat/cheat.h

@@ -0,0 +1,48 @@
+#define CHEAT_LIMIT 1024
+
+class Cheat {
+public:
+enum { CT_PRO_ACTION_REPLAY, CT_GAME_GENIE };
+
+struct CheatIndex {
+  bool   enabled;
+  uint32 addr;
+  uint8  data;
+  char   code[ 16 + 1];
+  char   desc[128 + 1];
+} index[CHEAT_LIMIT + 1];
+bool   cheat_enabled;
+uint32 cheat_count;
+uint8  mask[0x200000];
+
+  inline bool enabled() { return cheat_enabled; }
+  inline uint count() { return cheat_count; }
+  inline bool exists(uint32 addr) { return bool(mask[addr >> 3] & 1 << (addr & 7)); }
+
+  bool  decode(char *str, uint32 &addr, uint8 &data, uint8 &type);
+  bool  encode(char *str, uint32  addr, uint8  data, uint8  type);
+
+private:
+  uint  mirror_address(uint addr);
+  void  set(uint32 addr);
+  void  clear(uint32 addr);
+public:
+
+  bool  read(uint32 addr, uint8 &data);
+
+  void  update_cheat_status();
+  bool  add(bool enable, char *code, char *desc);
+  bool  edit(uint32 n, bool enable, char *code, char *desc);
+  bool  get(uint32 n, bool &enable, uint32 &addr, uint8 &data, char *code, char *desc);
+  bool  remove (uint32 n);
+  bool  enabled(uint32 n);
+  void  enable (uint32 n);
+  void  disable(uint32 n);
+  bool  load(Reader *rf);
+  bool  save(Writer *wf);
+  void  clear();
+
+  Cheat();
+};
+
+extern Cheat cheat;

src/chip/c4/c4.cpp

@@ -0,0 +1,197 @@
+/*
+  C4 emulation
+
+  Used in Rockman X2/X3 (Megaman X2/X3)
+  Portions (c) anomie, Overload, zsKnight, Nach, byuu
+*/
+
+#include "../../base.h"
+
+#include "c4data.cpp"
+#include "c4fn.cpp"
+#include "c4oam.cpp"
+#include "c4ops.cpp"
+
+void C4::init() {}
+void C4::enable() {}
+
+uint32 C4::ldr(uint8 r) {
+uint16 addr = 0x0080 + (r * 3);
+  return (reg[addr]) | (reg[addr + 1] << 8) | (reg[addr + 2] << 16);
+}
+
+void C4::str(uint8 r, uint32 data) {
+uint16 addr = 0x0080 + (r * 3);
+  reg[addr    ] = (data);
+  reg[addr + 1] = (data >> 8);
+  reg[addr + 2] = (data >> 16);
+}
+
+void C4::mul(uint32 x, uint32 y, uint32 &rl, uint32 &rh) {
+int64 rx = x & 0xffffff;
+int64 ry = y & 0xffffff;
+  if(rx & 0x800000)rx |= ~0x7fffff;
+  if(ry & 0x800000)ry |= ~0x7fffff;
+
+  rx *= ry;
+
+  rl = (rx)       & 0xffffff;
+  rh = (rx >> 24) & 0xffffff;
+}
+
+uint32 C4::sin(uint32 rx) {
+  r0 = rx & 0x1ff;
+  if(r0 & 0x100)r0 ^= 0x1ff;
+  if(r0 & 0x080)r0 ^= 0x0ff;
+  if(rx & 0x100) {
+    return sin_table[r0 + 0x80];
+  } else {
+    return sin_table[r0];
+  }
+}
+
+uint32 C4::cos(uint32 rx) {
+  return sin(rx + 0x080);
+}
+
+void C4::immediate_reg(uint32 start) {
+  r0 = ldr(0);
+  for(uint32 i=start;i<48;i++) {
+    if((r0 & 0x0fff) < 0x0c00) {
+      ram[r0 & 0x0fff] = immediate_data[i];
+    }
+    r0++;
+  }
+  str(0, r0);
+}
+
+void C4::transfer_data() {
+uint32 src;
+uint16 dest, count;
+  src   = (reg[0x40]) | (reg[0x41] << 8) | (reg[0x42] << 16);
+  count = (reg[0x43]) | (reg[0x44] << 8);
+  dest  = (reg[0x45]) | (reg[0x46] << 8);
+
+  for(uint32 i=0;i<count;i++) {
+    write(dest++, r_mem->read(src++));
+  }
+}
+
+void C4::write(uint16 addr, uint8 data) {
+  addr &= 0x1fff;
+
+  if(addr < 0x0c00) {
+  //ram
+    ram[addr] = data;
+    return;
+  }
+
+  if(addr < 0x1f00) {
+  //unmapped
+    return;
+  }
+
+//command register
+  reg[addr & 0xff] = data;
+
+  if(addr == 0x1f47) {
+  //memory transfer
+    transfer_data();
+    return;
+  }
+
+  if(addr == 0x1f4f) {
+  //c4 command
+    if(reg[0x4d] == 0x0e && !(data & 0xc3)) {
+    //c4 test command
+      reg[0x80] = data >> 2;
+      return;
+    }
+
+    switch(data) {
+    case 0x00:op00();break;
+    case 0x01:op01();break;
+    case 0x05:op05();break;
+    case 0x0d:op0d();break;
+    case 0x10:op10();break;
+    case 0x13:op13();break;
+    case 0x15:op15();break;
+    case 0x1f:op1f();break;
+    case 0x22:op22();break;
+    case 0x25:op25();break;
+    case 0x2d:op2d();break;
+    case 0x40:op40();break;
+    case 0x54:op54();break;
+    case 0x5c:op5c();break;
+    case 0x5e:op5e();break;
+    case 0x60:op60();break;
+    case 0x62:op62();break;
+    case 0x64:op64();break;
+    case 0x66:op66();break;
+    case 0x68:op68();break;
+    case 0x6a:op6a();break;
+    case 0x6c:op6c();break;
+    case 0x6e:op6e();break;
+    case 0x70:op70();break;
+    case 0x72:op72();break;
+    case 0x74:op74();break;
+    case 0x76:op76();break;
+    case 0x78:op78();break;
+    case 0x7a:op7a();break;
+    case 0x7c:op7c();break;
+    case 0x89:op89();break;
+    }
+  }
+}
+
+void C4::writeb(uint16 addr, uint8 data) {
+  write(addr,     data);
+}
+
+void C4::writew(uint16 addr, uint16 data) {
+  write(addr,     data);
+  write(addr + 1, data >> 8);
+}
+
+void C4::writel(uint16 addr, uint32 data) {
+  write(addr,     data);
+  write(addr + 1, data >>  8);
+  write(addr + 2, data >> 16);
+}
+
+uint8 C4::read(uint16 addr) {
+  addr &= 0x1fff;
+
+  if(addr < 0x0c00) {
+    return ram[addr];
+  }
+
+  if(addr >= 0x1f00) {
+    return reg[addr & 0xff];
+  }
+
+  return r_cpu->regs.mdr;
+}
+
+uint8 C4::readb(uint16 addr) {
+  return read(addr);
+}
+
+uint16 C4::readw(uint16 addr) {
+  return read(addr) | (read(addr + 1) << 8);
+}
+
+uint32 C4::readl(uint16 addr) {
+  return read(addr) | (read(addr + 1) << 8) + (read(addr + 2) << 16);
+}
+
+void C4::power() {
+  reset();
+}
+
+void C4::reset() {
+  memset(ram, 0, 0x0c00);
+  memset(reg, 0, 0x0100);
+}
+
+C4::C4() {}

src/chip/c4/c4.h

@@ -0,0 +1,94 @@
+class C4 {
+private:
+uint8  ram[0x0c00];
+uint8  reg[0x0100];
+uint32 r0, r1, r2,  r3,  r4,  r5,  r6,  r7,
+       r8, r9, r10, r11, r12, r13, r14, r15;
+
+static const uint8  immediate_data[48];
+static const uint16 wave_data[40];
+static const uint32 sin_table[256];
+
+static const int16 SinTable[512];
+static const int16 CosTable[512];
+
+int16 C4WFXVal, C4WFYVal, C4WFZVal, C4WFX2Val, C4WFY2Val, C4WFDist, C4WFScale;
+int16 C41FXVal, C41FYVal, C41FAngleRes, C41FDist, C41FDistVal;
+
+double tanval;
+double c4x,c4y,c4z, c4x2,c4y2,c4z2;
+
+void C4TransfWireFrame();
+void C4TransfWireFrame2();
+void C4CalcWireFrame();
+void C4DrawLine(int32 X1, int32 Y1, int16 Z1, int32 X2, int32 Y2, int16 Z2, uint8 Color);
+void C4DrawWireFrame();
+void C4DoScaleRotate(int row_padding);
+
+public:
+  uint32 ldr(uint8 r);
+  void   str(uint8 r, uint32 data);
+  void   mul(uint32 x, uint32 y, uint32 &rl, uint32 &rh);
+  uint32 sin(uint32 rx);
+  uint32 cos(uint32 rx);
+
+  void   transfer_data();
+  void   immediate_reg(uint32 num);
+
+  void   op00_00();
+  void   op00_03();
+  void   op00_05();
+  void   op00_07();
+  void   op00_08();
+  void   op00_0b();
+  void   op00_0c();
+
+  void   op00();
+  void   op01();
+  void   op05();
+  void   op0d();
+  void   op10();
+  void   op13();
+  void   op15();
+  void   op1f();
+  void   op22();
+  void   op25();
+  void   op2d();
+  void   op40();
+  void   op54();
+  void   op5c();
+  void   op5e();
+  void   op60();
+  void   op62();
+  void   op64();
+  void   op66();
+  void   op68();
+  void   op6a();
+  void   op6c();
+  void   op6e();
+  void   op70();
+  void   op72();
+  void   op74();
+  void   op76();
+  void   op78();
+  void   op7a();
+  void   op7c();
+  void   op89();
+
+  void   init();
+  void   enable();
+  void   power();
+  void   reset();
+
+  void   write (uint16 addr, uint8 data);
+  void   writeb(uint16 addr, uint8 data);
+  void   writew(uint16 addr, uint16 data);
+  void   writel(uint16 addr, uint32 data);
+
+  uint8  read (uint16 addr);
+  uint8  readb(uint16 addr);
+  uint16 readw(uint16 addr);
+  uint32 readl(uint16 addr);
+
+  C4();
+};

src/chip/c4/c4data.cpp

@@ -0,0 +1,183 @@
+const uint8 C4::immediate_data[48] = {
+  0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0x00, 0xff, 0x00, 0x00, 0x00, 0xff,
+  0xff, 0xff, 0x00, 0x00, 0xff, 0xff, 0x00, 0x00, 0x80, 0xff, 0xff, 0x7f,
+  0x00, 0x80, 0x00, 0xff, 0x7f, 0x00, 0xff, 0x7f, 0xff, 0x7f, 0xff, 0xff,
+  0x00, 0x00, 0x01, 0xff, 0xff, 0xfe, 0x00, 0x01, 0x00, 0xff, 0xfe, 0x00
+};
+
+const uint16 C4::wave_data[40] = {
+  0x0000, 0x0002, 0x0004, 0x0006, 0x0008, 0x000a, 0x000c, 0x000e,
+  0x0200, 0x0202, 0x0204, 0x0206, 0x0208, 0x020a, 0x020c, 0x020e,
+  0x0400, 0x0402, 0x0404, 0x0406, 0x0408, 0x040a, 0x040c, 0x040e,
+  0x0600, 0x0602, 0x0604, 0x0606, 0x0608, 0x060a, 0x060c, 0x060e,
+  0x0800, 0x0802, 0x0804, 0x0806, 0x0808, 0x080a, 0x080c, 0x080e
+};
+
+const uint32 C4::sin_table[256] = {
+  0x000000, 0x000324, 0x000648, 0x00096c, 0x000c8f, 0x000fb2, 0x0012d5, 0x0015f6,
+  0x001917, 0x001c37, 0x001f56, 0x002273, 0x002590, 0x0028aa, 0x002bc4, 0x002edb,
+  0x0031f1, 0x003505, 0x003817, 0x003b26, 0x003e33, 0x00413e, 0x004447, 0x00474d,
+  0x004a50, 0x004d50, 0x00504d, 0x005347, 0x00563e, 0x005931, 0x005c22, 0x005f0e,
+  0x0061f7, 0x0064dc, 0x0067bd, 0x006a9b, 0x006d74, 0x007049, 0x007319, 0x0075e5,
+  0x0078ad, 0x007b70, 0x007e2e, 0x0080e7, 0x00839c, 0x00864b, 0x0088f5, 0x008b9a,
+  0x008e39, 0x0090d3, 0x009368, 0x0095f6, 0x00987f, 0x009b02, 0x009d7f, 0x009ff6,
+  0x00a267, 0x00a4d2, 0x00a736, 0x00a994, 0x00abeb, 0x00ae3b, 0x00b085, 0x00b2c8,
+  0x00b504, 0x00b73a, 0x00b968, 0x00bb8f, 0x00bdae, 0x00bfc7, 0x00c1d8, 0x00c3e2,
+  0x00c5e4, 0x00c7de, 0x00c9d1, 0x00cbbb, 0x00cd9f, 0x00cf7a, 0x00d14d, 0x00d318,
+  0x00d4db, 0x00d695, 0x00d848, 0x00d9f2, 0x00db94, 0x00dd2d, 0x00debe, 0x00e046,
+  0x00e1c5, 0x00e33c, 0x00e4aa, 0x00e60f, 0x00e76b, 0x00e8bf, 0x00ea09, 0x00eb4b,
+  0x00ec83, 0x00edb2, 0x00eed8, 0x00eff5, 0x00f109, 0x00f213, 0x00f314, 0x00f40b,
+  0x00f4fa, 0x00f5de, 0x00f6ba, 0x00f78b, 0x00f853, 0x00f912, 0x00f9c7, 0x00fa73,
+  0x00fb14, 0x00fbac, 0x00fc3b, 0x00fcbf, 0x00fd3a, 0x00fdab, 0x00fe13, 0x00fe70,
+  0x00fec4, 0x00ff0e, 0x00ff4e, 0x00ff84, 0x00ffb1, 0x00ffd3, 0x00ffec, 0x00fffb,
+  0x000000, 0xfffcdb, 0xfff9b7, 0xfff693, 0xfff370, 0xfff04d, 0xffed2a, 0xffea09,
+  0xffe6e8, 0xffe3c8, 0xffe0a9, 0xffdd8c, 0xffda6f, 0xffd755, 0xffd43b, 0xffd124,
+  0xffce0e, 0xffcafa, 0xffc7e8, 0xffc4d9, 0xffc1cc, 0xffbec1, 0xffbbb8, 0xffb8b2,
+  0xffb5af, 0xffb2af, 0xffafb2, 0xffacb8, 0xffa9c1, 0xffa6ce, 0xffa3dd, 0xffa0f1,
+  0xff9e08, 0xff9b23, 0xff9842, 0xff9564, 0xff928b, 0xff8fb6, 0xff8ce6, 0xff8a1a,
+  0xff8752, 0xff848f, 0xff81d1, 0xff7f18, 0xff7c63, 0xff79b4, 0xff770a, 0xff7465,
+  0xff71c6, 0xff6f2c, 0xff6c97, 0xff6a09, 0xff6780, 0xff64fd, 0xff6280, 0xff6009,
+  0xff5d98, 0xff5b2d, 0xff58c9, 0xff566b, 0xff5414, 0xff51c4, 0xff4f7a, 0xff4d37,
+  0xff4afb, 0xff48c5, 0xff4697, 0xff4470, 0xff4251, 0xff4038, 0xff3e27, 0xff3c1e,
+  0xff3a1b, 0xff3821, 0xff362e, 0xff3444, 0xff3260, 0xff3085, 0xff2eb2, 0xff2ce7,
+  0xff2b24, 0xff296a, 0xff27b7, 0xff260d, 0xff246b, 0xff22d2, 0xff2141, 0xff1fb9,
+  0xff1e3a, 0xff1cc3, 0xff1b55, 0xff19f0, 0xff1894, 0xff1740, 0xff15f6, 0xff14b4,
+  0xff137c, 0xff124d, 0xff1127, 0xff100a, 0xff0ef6, 0xff0dec, 0xff0ceb, 0xff0bf4,
+  0xff0b05, 0xff0a21, 0xff0945, 0xff0874, 0xff07ac, 0xff06ed, 0xff0638, 0xff058d,
+  0xff04eb, 0xff0453, 0xff03c4, 0xff0340, 0xff02c5, 0xff0254, 0xff01ec, 0xff018f,
+  0xff013b, 0xff00f1, 0xff00b1, 0xff007b, 0xff004e, 0xff002c, 0xff0013, 0xff0004
+};
+
+const int16 C4::SinTable[512] = {
+       0,    402,    804,   1206,   1607,   2009,   2410,   2811,
+    3211,   3611,   4011,   4409,   4808,   5205,   5602,   5997,
+    6392,   6786,   7179,   7571,   7961,   8351,   8739,   9126,
+    9512,   9896,  10278,  10659,  11039,  11416,  11793,  12167,
+   12539,  12910,  13278,  13645,  14010,  14372,  14732,  15090,
+   15446,  15800,  16151,  16499,  16846,  17189,  17530,  17869,
+   18204,  18537,  18868,  19195,  19519,  19841,  20159,  20475,
+   20787,  21097,  21403,  21706,  22005,  22301,  22594,  22884,
+   23170,  23453,  23732,  24007,  24279,  24547,  24812,  25073,
+   25330,  25583,  25832,  26077,  26319,  26557,  26790,  27020,
+   27245,  27466,  27684,  27897,  28106,  28310,  28511,  28707,
+   28898,  29086,  29269,  29447,  29621,  29791,  29956,  30117,
+   30273,  30425,  30572,  30714,  30852,  30985,  31114,  31237,
+   31357,  31471,  31581,  31685,  31785,  31881,  31971,  32057,
+   32138,  32214,  32285,  32351,  32413,  32469,  32521,  32568,
+   32610,  32647,  32679,  32706,  32728,  32745,  32758,  32765,
+   32767,  32765,  32758,  32745,  32728,  32706,  32679,  32647,
+   32610,  32568,  32521,  32469,  32413,  32351,  32285,  32214,
+   32138,  32057,  31971,  31881,  31785,  31685,  31581,  31471,
+   31357,  31237,  31114,  30985,  30852,  30714,  30572,  30425,
+   30273,  30117,  29956,  29791,  29621,  29447,  29269,  29086,
+   28898,  28707,  28511,  28310,  28106,  27897,  27684,  27466,
+   27245,  27020,  26790,  26557,  26319,  26077,  25832,  25583,
+   25330,  25073,  24812,  24547,  24279,  24007,  23732,  23453,
+   23170,  22884,  22594,  22301,  22005,  21706,  21403,  21097,
+   20787,  20475,  20159,  19841,  19519,  19195,  18868,  18537,
+   18204,  17869,  17530,  17189,  16846,  16499,  16151,  15800,
+   15446,  15090,  14732,  14372,  14010,  13645,  13278,  12910,
+   12539,  12167,  11793,  11416,  11039,  10659,  10278,   9896,
+    9512,   9126,   8739,   8351,   7961,   7571,   7179,   6786,
+    6392,   5997,   5602,   5205,   4808,   4409,   4011,   3611,
+    3211,   2811,   2410,   2009,   1607,   1206,    804,    402,
+       0,   -402,   -804,  -1206,  -1607,  -2009,  -2410,  -2811,
+   -3211,  -3611,  -4011,  -4409,  -4808,  -5205,  -5602,  -5997,
+   -6392,  -6786,  -7179,  -7571,  -7961,  -8351,  -8739,  -9126,
+   -9512,  -9896, -10278, -10659, -11039, -11416, -11793, -12167,
+  -12539, -12910, -13278, -13645, -14010, -14372, -14732, -15090,
+  -15446, -15800, -16151, -16499, -16846, -17189, -17530, -17869,
+  -18204, -18537, -18868, -19195, -19519, -19841, -20159, -20475,
+  -20787, -21097, -21403, -21706, -22005, -22301, -22594, -22884,
+  -23170, -23453, -23732, -24007, -24279, -24547, -24812, -25073,
+  -25330, -25583, -25832, -26077, -26319, -26557, -26790, -27020,
+  -27245, -27466, -27684, -27897, -28106, -28310, -28511, -28707,
+  -28898, -29086, -29269, -29447, -29621, -29791, -29956, -30117,
+  -30273, -30425, -30572, -30714, -30852, -30985, -31114, -31237,
+  -31357, -31471, -31581, -31685, -31785, -31881, -31971, -32057,
+  -32138, -32214, -32285, -32351, -32413, -32469, -32521, -32568,
+  -32610, -32647, -32679, -32706, -32728, -32745, -32758, -32765,
+  -32767, -32765, -32758, -32745, -32728, -32706, -32679, -32647,
+  -32610, -32568, -32521, -32469, -32413, -32351, -32285, -32214,
+  -32138, -32057, -31971, -31881, -31785, -31685, -31581, -31471,
+  -31357, -31237, -31114, -30985, -30852, -30714, -30572, -30425,
+  -30273, -30117, -29956, -29791, -29621, -29447, -29269, -29086,
+  -28898, -28707, -28511, -28310, -28106, -27897, -27684, -27466,
+  -27245, -27020, -26790, -26557, -26319, -26077, -25832, -25583,
+  -25330, -25073, -24812, -24547, -24279, -24007, -23732, -23453,
+  -23170, -22884, -22594, -22301, -22005, -21706, -21403, -21097,
+  -20787, -20475, -20159, -19841, -19519, -19195, -18868, -18537,
+  -18204, -17869, -17530, -17189, -16846, -16499, -16151, -15800,
+  -15446, -15090, -14732, -14372, -14010, -13645, -13278, -12910,
+  -12539, -12167, -11793, -11416, -11039, -10659, -10278,  -9896,
+   -9512,  -9126,  -8739,  -8351,  -7961,  -7571,  -7179,  -6786,
+   -6392,  -5997,  -5602,  -5205,  -4808,  -4409,  -4011,  -3611,
+   -3211,  -2811,  -2410,  -2009,  -1607,  -1206,   -804,   -402
+};
+
+const int16 C4::CosTable[512] = {
+   32767,  32765,  32758,  32745,  32728,  32706,  32679,  32647,
+   32610,  32568,  32521,  32469,  32413,  32351,  32285,  32214,
+   32138,  32057,  31971,  31881,  31785,  31685,  31581,  31471,
+   31357,  31237,  31114,  30985,  30852,  30714,  30572,  30425,
+   30273,  30117,  29956,  29791,  29621,  29447,  29269,  29086,
+   28898,  28707,  28511,  28310,  28106,  27897,  27684,  27466,
+   27245,  27020,  26790,  26557,  26319,  26077,  25832,  25583,
+   25330,  25073,  24812,  24547,  24279,  24007,  23732,  23453,
+   23170,  22884,  22594,  22301,  22005,  21706,  21403,  21097,
+   20787,  20475,  20159,  19841,  19519,  19195,  18868,  18537,
+   18204,  17869,  17530,  17189,  16846,  16499,  16151,  15800,
+   15446,  15090,  14732,  14372,  14010,  13645,  13278,  12910,
+   12539,  12167,  11793,  11416,  11039,  10659,  10278,   9896,
+    9512,   9126,   8739,   8351,   7961,   7571,   7179,   6786,
+    6392,   5997,   5602,   5205,   4808,   4409,   4011,   3611,
+    3211,   2811,   2410,   2009,   1607,   1206,    804,    402,
+       0,   -402,   -804,  -1206,  -1607,  -2009,  -2410,  -2811,
+   -3211,  -3611,  -4011,  -4409,  -4808,  -5205,  -5602,  -5997,
+   -6392,  -6786,  -7179,  -7571,  -7961,  -8351,  -8739,  -9126,
+   -9512,  -9896, -10278, -10659, -11039, -11416, -11793, -12167,
+  -12539, -12910, -13278, -13645, -14010, -14372, -14732, -15090,
+  -15446, -15800, -16151, -16499, -16846, -17189, -17530, -17869,
+  -18204, -18537, -18868, -19195, -19519, -19841, -20159, -20475,
+  -20787, -21097, -21403, -21706, -22005, -22301, -22594, -22884,
+  -23170, -23453, -23732, -24007, -24279, -24547, -24812, -25073,
+  -25330, -25583, -25832, -26077, -26319, -26557, -26790, -27020,
+  -27245, -27466, -27684, -27897, -28106, -28310, -28511, -28707,
+  -28898, -29086, -29269, -29447, -29621, -29791, -29956, -30117,
+  -30273, -30425, -30572, -30714, -30852, -30985, -31114, -31237,
+  -31357, -31471, -31581, -31685, -31785, -31881, -31971, -32057,
+  -32138, -32214, -32285, -32351, -32413, -32469, -32521, -32568,
+  -32610, -32647, -32679, -32706, -32728, -32745, -32758, -32765,
+  -32767, -32765, -32758, -32745, -32728, -32706, -32679, -32647,
+  -32610, -32568, -32521, -32469, -32413, -32351, -32285, -32214,
+  -32138, -32057, -31971, -31881, -31785, -31685, -31581, -31471,
+  -31357, -31237, -31114, -30985, -30852, -30714, -30572, -30425,
+  -30273, -30117, -29956, -29791, -29621, -29447, -29269, -29086,
+  -28898, -28707, -28511, -28310, -28106, -27897, -27684, -27466,
+  -27245, -27020, -26790, -26557, -26319, -26077, -25832, -25583,
+  -25330, -25073, -24812, -24547, -24279, -24007, -23732, -23453,
+  -23170, -22884, -22594, -22301, -22005, -21706, -21403, -21097,
+  -20787, -20475, -20159, -19841, -19519, -19195, -18868, -18537,
+  -18204, -17869, -17530, -17189, -16846, -16499, -16151, -15800,
+  -15446, -15090, -14732, -14372, -14010, -13645, -13278, -12910,
+  -12539, -12167, -11793, -11416, -11039, -10659, -10278,  -9896,
+   -9512,  -9126,  -8739,  -8351,  -7961,  -7571,  -7179,  -6786,
+   -6392,  -5997,  -5602,  -5205,  -4808,  -4409,  -4011,  -3611,
+   -3211,  -2811,  -2410,  -2009,  -1607,  -1206,   -804,   -402,
+       0,    402,    804,   1206,   1607,   2009,   2410,   2811,
+    3211,   3611,   4011,   4409,   4808,   5205,   5602,   5997,
+    6392,   6786,   7179,   7571,   7961,   8351,   8739,   9126,
+    9512,   9896,  10278,  10659,  11039,  11416,  11793,  12167,
+   12539,  12910,  13278,  13645,  14010,  14372,  14732,  15090,
+   15446,  15800,  16151,  16499,  16846,  17189,  17530,  17869,
+   18204,  18537,  18868,  19195,  19519,  19841,  20159,  20475,
+   20787,  21097,  21403,  21706,  22005,  22301,  22594,  22884,
+   23170,  23453,  23732,  24007,  24279,  24547,  24812,  25073,
+   25330,  25583,  25832,  26077,  26319,  26557,  26790,  27020,
+   27245,  27466,  27684,  27897,  28106,  28310,  28511,  28707,
+   28898,  29086,  29269,  29447,  29621,  29791,  29956,  30117,
+   30273,  30425,  30572,  30714,  30852,  30985,  31114,  31237,
+   31357,  31471,  31581,  31685,  31785,  31881,  31971,  32057,
+   32138,  32214,  32285,  32351,  32413,  32469,  32521,  32568,
+   32610,  32647,  32679,  32706,  32728,  32745,  32758,  32765
+};

src/chip/c4/c4fn.cpp

@@ -0,0 +1,242 @@
+#include <math.h>
+#define Tan(a) (CosTable[a] ? ((((int32)SinTable[a]) << 16) / CosTable[a]) : 0x80000000)
+#define sar(b, n) ((b) >> (n))
+#ifdef PI
+#undef PI
+#endif
+#define PI 3.1415926535897932384626433832795
+
+//Wireframe Helpers
+void C4::C4TransfWireFrame() {
+  c4x = (double)C4WFXVal;
+  c4y = (double)C4WFYVal;
+  c4z = (double)C4WFZVal - 0x95;
+
+//Rotate X
+  tanval = -(double)C4WFX2Val * PI * 2 / 128;
+  c4y2   = c4y * ::cos(tanval) - c4z * ::sin(tanval);
+  c4z2   = c4y * ::sin(tanval) + c4z * ::cos(tanval);
+
+//Rotate Y
+  tanval = -(double)C4WFY2Val * PI * 2 / 128;
+  c4x2   = c4x * ::cos(tanval)  + c4z2 * ::sin(tanval);
+  c4z    = c4x * -::sin(tanval) + c4z2 * ::cos(tanval);
+
+//Rotate Z
+  tanval = -(double)C4WFDist * PI * 2 / 128;
+  c4x    = c4x2 * ::cos(tanval) - c4y2 * ::sin(tanval);
+  c4y    = c4x2 * ::sin(tanval) + c4y2 * ::cos(tanval);
+
+//Scale
+  C4WFXVal = (int16)(c4x * C4WFScale / (0x90 * (c4z + 0x95)) * 0x95);
+  C4WFYVal = (int16)(c4y * C4WFScale / (0x90 * (c4z + 0x95)) * 0x95);
+}
+
+void C4::C4CalcWireFrame() {
+  C4WFXVal = C4WFX2Val - C4WFXVal;
+  C4WFYVal = C4WFY2Val - C4WFYVal;
+
+  if(abs(C4WFXVal) > abs(C4WFYVal)) {
+    C4WFDist = abs(C4WFXVal) + 1;
+    C4WFYVal = (256 * (long)C4WFYVal) / abs(C4WFXVal);
+    C4WFXVal = (C4WFXVal < 0) ? -256 : 256;
+  } else if(C4WFYVal != 0) {
+    C4WFDist = abs(C4WFYVal) + 1;
+    C4WFXVal = (256 * (long)C4WFXVal) / abs(C4WFYVal);
+    C4WFYVal = (C4WFYVal < 0) ? -256 : 256;
+  } else {
+    C4WFDist = 0;
+  }
+}
+
+void C4::C4TransfWireFrame2() {
+  c4x = (double)C4WFXVal;
+  c4y = (double)C4WFYVal;
+  c4z = (double)C4WFZVal;
+
+//Rotate X
+  tanval = -(double)C4WFX2Val * PI * 2 / 128;
+  c4y2   = c4y * ::cos(tanval) - c4z * ::sin(tanval);
+  c4z2   = c4y * ::sin(tanval) + c4z * ::cos(tanval);
+
+//Rotate Y
+  tanval = -(double)C4WFY2Val * PI * 2 / 128;
+  c4x2   = c4x * ::cos(tanval)  + c4z2 * ::sin(tanval);
+  c4z    = c4x * -::sin(tanval) + c4z2 * ::cos(tanval);
+
+//Rotate Z
+  tanval = -(double)C4WFDist * PI * 2 / 128;
+  c4x    = c4x2 * ::cos(tanval) - c4y2 * ::sin(tanval);
+  c4y    = c4x2 * ::sin(tanval) + c4y2 * ::cos(tanval);
+
+//Scale
+  C4WFXVal = (int16)(c4x * C4WFScale / 0x100);
+  C4WFYVal = (int16)(c4y * C4WFScale / 0x100);
+}
+
+void C4::C4DrawWireFrame() {
+uint32 line = readl(0x1f80);
+uint32 point1, point2;
+int16 X1, Y1, Z1;
+int16 X2, Y2, Z2;
+uint8 Color;
+  for(int32 i = ram[0x0295]; i > 0; i--, line += 5) {
+    if(r_mem->read(line) == 0xff && r_mem->read(line + 1) == 0xff) {
+    int32 tmp = line - 5;
+      while(r_mem->read(tmp + 2) == 0xff && r_mem->read(tmp + 3) == 0xff && (tmp + 2) >= 0) { tmp -= 5; }
+      point1 = (read(0x1f82) << 16) | (r_mem->read(tmp + 2) << 8) | r_mem->read(tmp + 3);
+    } else {
+      point1 = (read(0x1f82) << 16) | (r_mem->read(line) << 8) | r_mem->read(line + 1);
+    }
+    point2 = (read(0x1f82) << 16) | (r_mem->read(line + 2) << 8) | r_mem->read(line + 3);
+
+    X1=(r_mem->read(point1 + 0) << 8) | r_mem->read(point1 + 1);
+    Y1=(r_mem->read(point1 + 2) << 8) | r_mem->read(point1 + 3);
+    Z1=(r_mem->read(point1 + 4) << 8) | r_mem->read(point1 + 5);
+    X2=(r_mem->read(point2 + 0) << 8) | r_mem->read(point2 + 1);
+    Y2=(r_mem->read(point2 + 2) << 8) | r_mem->read(point2 + 3);
+    Z2=(r_mem->read(point2 + 4) << 8) | r_mem->read(point2 + 5);
+    Color = r_mem->read(line + 4);
+    C4DrawLine(X1, Y1, Z1, X2, Y2, Z2, Color);
+  }
+}
+
+void C4::C4DrawLine(int32 X1, int32 Y1, int16 Z1, int32 X2, int32 Y2, int16 Z2, uint8 Color) {
+//Transform coordinates
+  C4WFXVal  = (int16)X1;
+  C4WFYVal  = (int16)Y1;
+  C4WFZVal  = Z1;
+  C4WFScale = read(0x1f90);
+  C4WFX2Val = read(0x1f86);
+  C4WFY2Val = read(0x1f87);
+  C4WFDist  = read(0x1f88);
+  C4TransfWireFrame2();
+  X1 = (C4WFXVal + 48) << 8;
+  Y1 = (C4WFYVal + 48) << 8;
+
+  C4WFXVal = (int16)X2;
+  C4WFYVal = (int16)Y2;
+  C4WFZVal = Z2;
+  C4TransfWireFrame2();
+  X2 = (C4WFXVal + 48) << 8;
+  Y2 = (C4WFYVal + 48) << 8;
+
+//Get line info
+  C4WFXVal  = (int16)(X1 >> 8);
+  C4WFYVal  = (int16)(Y1 >> 8);
+  C4WFX2Val = (int16)(X2 >> 8);
+  C4WFY2Val = (int16)(Y2 >> 8);
+  C4CalcWireFrame();
+  X2 = (int16)C4WFXVal;
+  Y2 = (int16)C4WFYVal;
+
+//Render line
+  for(int32 i = C4WFDist ? C4WFDist : 1; i > 0; i--) {
+    if(X1 > 0xff && Y1 > 0xff && X1 < 0x6000 && Y1 < 0x6000) {
+    uint16 addr = (((Y1 >> 8) >> 3) << 8) - (((Y1 >> 8) >> 3) << 6) + (((X1 >> 8) >> 3) << 4) + ((Y1 >> 8) & 7) * 2;
+    uint8 bit = 0x80 >> ((X1 >> 8) & 7);
+      ram[addr + 0x300] &= ~bit;
+      ram[addr + 0x301] &= ~bit;
+      if(Color & 1) { ram[addr + 0x300] |= bit; }
+      if(Color & 2) { ram[addr + 0x301] |= bit; }
+    }
+    X1 += X2;
+    Y1 += Y2;
+  }
+}
+
+void C4::C4DoScaleRotate(int row_padding) {
+int16 A, B, C, D;
+
+//Calculate matrix
+int32 XScale = readw(0x1f8f);
+int32 YScale = readw(0x1f92);
+  if(XScale & 0x8000)XScale = 0x7fff;
+  if(YScale & 0x8000)YScale = 0x7fff;
+
+  if(readw(0x1f80) == 0) { //no rotation
+    A = (int16)XScale;
+    B = 0;
+    C = 0;
+    D = (int16)YScale;
+  } else if(readw(0x1f80) == 128) { //90 degree rotation
+    A = 0;
+    B = (int16)(-YScale);
+    C = (int16)XScale;
+    D = 0;
+  } else if(readw(0x1f80) == 256) { //180 degree rotation
+    A = (int16)(-XScale);
+    B = 0;
+    C = 0;
+    D = (int16)(-YScale);
+  } else if(readw(0x1f80) == 384) { //270 degree rotation
+    A = 0;
+    B = (int16)YScale;
+    C = (int16)(-XScale);
+    D = 0;
+  } else {
+    A = (int16)  sar(CosTable[readw(0x1f80) & 0x1ff] * XScale, 15);
+    B = (int16)(-sar(SinTable[readw(0x1f80) & 0x1ff] * YScale, 15));
+    C = (int16)  sar(SinTable[readw(0x1f80) & 0x1ff] * XScale, 15);
+    D = (int16)  sar(CosTable[readw(0x1f80) & 0x1ff] * YScale, 15);
+  }
+
+//Calculate Pixel Resolution
+uint8 w = read(0x1f89) & ~7;
+uint8 h = read(0x1f8c) & ~7;
+
+//Clear the output RAM
+  memset(ram, 0, (w + row_padding / 4) * h / 2);
+
+int32 Cx = (int16)readw(0x1f83);
+int32 Cy = (int16)readw(0x1f86);
+
+//Calculate start position (i.e. (Ox, Oy) = (0, 0))
+//The low 12 bits are fractional, so (Cx<<12) gives us the Cx we want in
+//the function. We do Cx*A etc normally because the matrix parameters
+//already have the fractional parts.
+int32 LineX = (Cx << 12) - Cx * A - Cx * B;
+int32 LineY = (Cy << 12) - Cy * C - Cy * D;
+
+//Start loop
+uint32 X, Y;
+uint8 byte;
+int32 outidx = 0;
+uint8 bit    = 0x80;
+  for(int32 y = 0; y < h; y++) {
+    X = LineX;
+    Y = LineY;
+    for(int32 x = 0; x < w; x++) {
+      if((X >> 12) >= w || (Y >> 12) >= h) {
+        byte = 0;
+      } else {
+      uint32 addr = (Y >> 12) * w + (X >> 12);
+        byte = read(0x600 + (addr >> 1));
+        if(addr & 1) { byte >>= 4; }
+      }
+
+    //De-bitplanify
+      if(byte & 1) { ram[outidx     ] |= bit; }
+      if(byte & 2) { ram[outidx +  1] |= bit; }
+      if(byte & 4) { ram[outidx + 16] |= bit; }
+      if(byte & 8) { ram[outidx + 17] |= bit; }
+
+      bit >>= 1;
+      if(!bit) {
+        bit     = 0x80;
+        outidx += 32;
+      }
+
+      X += A; //Add 1 to output x => add an A and a C
+      Y += C;
+    }
+    outidx += 2 + row_padding;
+    if(outidx & 0x10) {
+      outidx &= ~0x10;
+    } else {
+      outidx -= w * 4 + row_padding;
+    }
+    LineX += B; //Add 1 to output y => add a B and a D
+    LineY += D;
+  }
+}

src/chip/c4/c4oam.cpp

@@ -0,0 +1,224 @@
+//Build OAM
+void C4::op00_00() {
+uint32 oamptr = ram[0x626] << 2;
+  for(int32 i=0x1fd;i>oamptr && i>=0;i-=4) {
+  //clear oam-to-be
+    if(i >= 0)ram[i] = 0xe0;
+  }
+
+uint16 globalx, globaly;
+uint32 oamptr2;
+int16  sprx, spry;
+uint8  sprname, sprattr;
+uint8  sprcount;
+  globalx = readw(0x621);
+  globaly = readw(0x623);
+  oamptr2 = 0x200 + (ram[0x626] >> 2);
+
+  if(!ram[0x620])return;
+
+  sprcount = 128 - ram[0x626];
+uint8 offset = (ram[0x626] & 3) * 2;
+  for(int pri=0x30;pri>=0;pri-=0x10) {
+  uint32 srcptr = 0x220;
+    for(int i=ram[0x620];i>0 && sprcount>0;i--, srcptr+=16) {
+      if((ram[srcptr + 4] & 0x30) != pri)continue;
+      sprx = readw(srcptr)     - globalx;
+      spry = readw(srcptr + 2) - globaly;
+      sprname = ram[srcptr + 5];
+      sprattr = ram[srcptr + 4] | ram[srcptr + 6];
+
+    uint32 spraddr = readl(srcptr + 7);
+      if(r_mem->read(spraddr)) {
+      int16 x, y;
+        for(int sprcnt=r_mem->read(spraddr++);sprcnt>0 && sprcount>0;sprcnt--, spraddr+=4) {
+          x = (int8)r_mem->read(spraddr + 1);
+          if(sprattr & 0x40) {
+            x = -x - ((r_mem->read(spraddr) & 0x20) ? 16 : 8);
+          }
+          x += sprx;
+          if(x >= -16 && x <= 272) {
+            y = (int8)r_mem->read(spraddr + 2);
+            if(sprattr & 0x80) {
+              y = -y - ((r_mem->read(spraddr) & 0x20) ? 16 : 8);
+            }
+            y += spry;
+            if(y >= -16 && y <= 224) {
+              ram[oamptr    ] = (uint8)x;
+              ram[oamptr + 1] = (uint8)y;
+              ram[oamptr + 2] = sprname + r_mem->read(spraddr + 3);
+              ram[oamptr + 3] = sprattr ^ (r_mem->read(spraddr) & 0xc0);
+              ram[oamptr2] &= ~(3 << offset);
+              if(x & 0x100)ram[oamptr2] |= 1 << offset;
+              if(r_mem->read(spraddr) & 0x20)ram[oamptr2] |= 2 << offset;
+              oamptr += 4;
+              sprcount--;
+              offset = (offset + 2) & 6;
+              if(!offset)oamptr2++;
+            }
+          }
+        }
+      } else if(sprcount > 0) {
+        ram[oamptr    ] = (uint8)sprx;
+        ram[oamptr + 1] = (uint8)spry;
+        ram[oamptr + 2] = sprname;
+        ram[oamptr + 3] = sprattr;
+        ram[oamptr2] &= ~(3 << offset);
+        if(sprx & 0x100)ram[oamptr2] |= 3 << offset;
+        else ram[oamptr2] |= 2 << offset;
+        oamptr += 4;
+        sprcount--;
+        offset = (offset + 2) & 6;
+        if(!offset)oamptr2++;
+      }
+    }
+  }
+}
+
+//Scale and Rotate
+void C4::op00_03() {
+  C4DoScaleRotate(0);
+}
+
+//Transform Lines
+void C4::op00_05() {
+  C4WFX2Val = read(0x1f83);
+  C4WFY2Val = read(0x1f86);
+  C4WFDist  = read(0x1f89);
+  C4WFScale = read(0x1f8c);
+
+//Transform Vertices
+uint32 ptr = 0;
+  for(int32 i = readw(0x1f80); i > 0; i--, ptr += 0x10) {
+    C4WFXVal = readw(ptr + 1);
+    C4WFYVal = readw(ptr + 5);
+    C4WFZVal = readw(ptr + 9);
+    C4TransfWireFrame();
+
+  //Displace
+    writew(ptr + 1, C4WFXVal + 0x80);
+    writew(ptr + 5, C4WFYVal + 0x50);
+  }
+
+  writew(0x600,     23);
+  writew(0x602,     0x60);
+  writew(0x605,     0x40);
+  writew(0x600 + 8, 23);
+  writew(0x602 + 8, 0x60);
+  writew(0x605 + 8, 0x40);
+
+  ptr = 0xb02;
+uint32 ptr2 = 0;
+  for(int32 i = readw(0xb00); i > 0; i--, ptr += 2, ptr2 += 8) {
+    C4WFXVal  = readw((read(ptr + 0) << 4) + 1);
+    C4WFYVal  = readw((read(ptr + 0) << 4) + 5);
+    C4WFX2Val = readw((read(ptr + 1) << 4) + 1);
+    C4WFY2Val = readw((read(ptr + 1) << 4) + 5);
+    C4CalcWireFrame();
+    writew(ptr2 + 0x600, C4WFDist ? C4WFDist : 1);
+    writew(ptr2 + 0x602, C4WFXVal);
+    writew(ptr2 + 0x605, C4WFYVal);
+  }
+}
+
+//Scale and Rotate
+void C4::op00_07() {
+  C4DoScaleRotate(64);
+}
+
+//Draw Wireframe
+void C4::op00_08() {
+  C4DrawWireFrame();
+}
+
+//Disintegrate
+void C4::op00_0b() {
+uint8  width, height;
+uint32 startx, starty;
+uint32 srcptr;
+uint32 x, y;
+int32  scalex, scaley;
+int32  cx, cy;
+int32  i, j;
+  width  = read(0x1f89);
+  height = read(0x1f8c);
+  cx     = readw(0x1f80);
+  cy     = readw(0x1f83);
+
+  scalex = (int16)readw(0x1f86);
+  scaley = (int16)readw(0x1f8f);
+  startx = -cx * scalex + (cx << 8);
+  starty = -cy * scaley + (cy << 8);
+  srcptr = 0x600;
+
+  for(i = 0; i < (width * height) >> 1; i++) {
+    write(i, 0);
+  }
+
+  for(y = starty, i = 0;i < height; i++, y += scaley) {
+    for(x = startx, j = 0;j < width; j++, x += scalex) {
+      if((x >> 8) < width && (y >> 8) < height && (y >> 8) * width + (x >> 8) < 0x2000) {
+      uint8 pixel = (j & 1) ? (ram[srcptr] >> 4) : (ram[srcptr]);
+      int32 index = (y >> 11) * width * 4 + (x >> 11) * 32 + ((y >> 8) & 7) * 2;
+      uint8 mask = 0x80 >> ((x >> 8) & 7);
+        if(pixel & 1)ram[index     ] |= mask;
+        if(pixel & 2)ram[index +  1] |= mask;
+        if(pixel & 4)ram[index + 16] |= mask;
+        if(pixel & 8)ram[index + 17] |= mask;
+      }
+      if(j & 1)srcptr++;
+    }
+  }
+}
+
+//Bitplane Wave
+void C4::op00_0c() {
+uint32 destptr = 0;
+uint32 waveptr = read(0x1f83);
+uint16 mask1   = 0xc0c0;
+uint16 mask2   = 0x3f3f;
+
+int32 i, j;
+int16 height, temp;
+  for(j = 0; j < 0x10; j++) {
+    do {
+      height = -((int8)ram[waveptr + 0xb00]) - 16;
+      for(i = 0; i < 40; i++) {
+        temp = readw(destptr + wave_data[i]) & mask2;
+        if(height >= 0) {
+          if(height < 8) {
+            temp |= mask1 & readw(0xa00 + height * 2);
+          } else {
+            temp |= mask1 & 0xff00;
+          }
+        }
+        writew(destptr + wave_data[i], temp);
+        height++;
+      }
+      waveptr = (waveptr + 1) & 0x7f;
+      mask1   = (mask1 >> 2) | (mask1 << 6);
+      mask2   = (mask2 >> 2) | (mask2 << 6);
+    } while(mask1 != 0xc0c0);
+    destptr += 16;
+
+    do {
+      height = -((int8)ram[waveptr + 0xb00]) - 16;
+      for(i = 0; i < 40; i++) {
+        temp = readw(destptr + wave_data[i]) & mask2;
+        if(height >= 0) {
+          if(height < 8) {
+            temp |= mask1 & readw(0xa10 + height * 2);
+          } else {
+            temp |= mask1 & 0xff00;
+          }
+          writew(destptr + wave_data[i], temp);
+          height++;
+        }
+        waveptr = (waveptr + 1) & 0x7f;
+        mask1   = (mask1 >> 2) | (mask1 << 6);
+        mask2   = (mask2 >> 2) | (mask2 << 6);
+      }
+    } while(mask1 != 0xc0c0);
+    destptr += 16;
+  }
+}

src/chip/c4/c4ops.cpp

@@ -0,0 +1,222 @@
+//Sprite Functions
+void C4::op00() {
+  switch(reg[0x4d]) {
+  case 0x00:op00_00();break;
+  case 0x03:op00_03();break;
+  case 0x05:op00_05();break;
+  case 0x07:op00_07();break;
+  case 0x08:op00_08();break;
+  case 0x0b:op00_0b();break;
+  case 0x0c:op00_0c();break;
+  }
+}
+
+//Draw Wireframe
+void C4::op01() {
+  memset(ram + 0x300, 0, 2304);
+  C4DrawWireFrame();
+}
+
+//Propulsion
+void C4::op05() {
+int32 temp = 0x10000;
+  if(readw(0x1f83)) {
+    temp = sar((temp / readw(0x1f83)) * readw(0x1f81), 8);
+  }
+  writew(0x1f80, temp);
+}
+
+//Set Vector length
+void C4::op0d() {
+  C41FXVal    = readw(0x1f80);
+  C41FYVal    = readw(0x1f83);
+  C41FDistVal = readw(0x1f86);
+  tanval = sqrt(((double)C41FYVal) * ((double)C41FYVal) + ((double)C41FXVal) * ((double)C41FXVal));
+  tanval = (double)C41FDistVal / tanval;
+  C41FYVal = (int16)(((double)C41FYVal * tanval) * 0.99);
+  C41FXVal = (int16)(((double)C41FXVal * tanval) * 0.98);
+  writew(0x1f89, C41FXVal);
+  writew(0x1f8c, C41FYVal);
+}
+
+//Triangle
+void C4::op10() {
+  r0 = ldr(0);
+  r1 = ldr(1);
+
+  r4 = r0 & 0x1ff;
+  if(r1 & 0x8000)r1 |= ~0x7fff;
+
+  mul(cos(r4), r1, r5, r2);
+  r5 = (r5 >> 16) & 0xff;
+  r2 = (r2 << 8) + r5;
+
+  mul(sin(r4), r1, r5, r3);
+  r5 = (r5 >> 16) & 0xff;
+  r3 = (r3 << 8) + r5;
+
+  str(0, r0);
+  str(1, r1);
+  str(2, r2);
+  str(3, r3);
+  str(4, r4);
+  str(5, r5);
+}
+
+//Triangle
+void C4::op13() {
+  r0 = ldr(0);
+  r1 = ldr(1);
+
+  r4 = r0 & 0x1ff;
+
+  mul(cos(r4), r1, r5, r2);
+  r5 = (r5 >> 8) & 0xffff;
+  r2 = (r2 << 16) + r5;
+
+  mul(sin(r4), r1, r5, r3);
+  r5 = (r5 >> 8) & 0xffff;
+  r3 = (r3 << 16) + r5;
+
+  str(0, r0);
+  str(1, r1);
+  str(2, r2);
+  str(3, r3);
+  str(4, r4);
+  str(5, r5);
+}
+
+//Pythagorean
+void C4::op15() {
+  C41FXVal = readw(0x1f80);
+  C41FYVal = readw(0x1f83);
+  C41FDist = (int16)sqrt((double)C41FXVal * (double)C41FXVal + (double)C41FYVal * (double)C41FYVal);
+  writew(0x1f80, C41FDist);
+}
+
+//Calculate distance
+void C4::op1f() {
+  C41FXVal = readw(0x1f80);
+  C41FYVal = readw(0x1f83);
+  if(!C41FXVal) {
+    C41FAngleRes = (C41FYVal > 0) ? 0x080 : 0x180;
+  } else {
+    tanval = ((double)C41FYVal) / ((double)C41FXVal);
+    C41FAngleRes = (short)(atan(tanval) / (PI * 2) * 512);
+    C41FAngleRes = C41FAngleRes;
+    if(C41FXVal < 0) {
+      C41FAngleRes += 0x100;
+    }
+    C41FAngleRes &= 0x1ff;
+  }
+  writew(0x1f86, C41FAngleRes);
+}
+
+//Trapezoid
+void C4::op22() {
+int16 angle1 = readw(0x1f8c) & 0x1ff;
+int16 angle2 = readw(0x1f8f) & 0x1ff;
+int32 tan1 = Tan(angle1);
+int32 tan2 = Tan(angle2);
+int16 y = readw(0x1f83) - readw(0x1f89);
+int16 left, right;
+  for(int32 j = 0; j < 225; j++, y++) {
+    if(y >= 0) {
+      left  = sar((int32)tan1 * y, 16) - readw(0x1f80) + readw(0x1f86);
+      right = sar((int32)tan2 * y, 16) - readw(0x1f80) + readw(0x1f86) + readw(0x1f93);
+
+      if(left < 0 && right < 0) {
+        left  = 1;
+        right = 0;
+      } else if(left < 0) {
+        left  = 0;
+      } else if(right < 0) {
+        right = 0;
+      }
+
+      if(left > 255 && right > 255) {
+        left  = 255;
+        right = 254;
+      } else if(left > 255) {
+        left  = 255;
+      } else if(right > 255) {
+        right = 255;
+      }
+    } else {
+      left  = 1;
+      right = 0;
+    }
+    ram[j + 0x800] = (uint8)left;
+    ram[j + 0x900] = (uint8)right;
+  }
+}
+
+//Multiply
+void C4::op25() {
+  r0 = ldr(0);
+  r1 = ldr(1);
+  mul(r0, r1, r0, r1);
+  str(0, r0);
+  str(1, r1);
+}
+
+//Transform Coords
+void C4::op2d() {
+  C4WFXVal  = readw(0x1f81);
+  C4WFYVal  = readw(0x1f84);
+  C4WFZVal  = readw(0x1f87);
+  C4WFX2Val = read (0x1f89);
+  C4WFY2Val = read (0x1f8a);
+  C4WFDist  = read (0x1f8b);
+  C4WFScale = readw(0x1f90);
+  C4TransfWireFrame2();
+  writew(0x1f80, C4WFXVal);
+  writew(0x1f83, C4WFYVal);
+}
+
+//Sum
+void C4::op40() {
+  r0 = 0;
+  for(uint32 i=0;i<0x800;i++) {
+    r0 += ram[i];
+  }
+  str(0, r0);
+}
+
+//Square
+void C4::op54() {
+  r0 = ldr(0);
+  mul(r0, r0, r1, r2);
+  str(1, r1);
+  str(2, r2);
+}
+
+//Immediate Register
+void C4::op5c() {
+  str(0, 0x000000);
+  immediate_reg(0);
+}
+
+//Immediate Register (Multiple)
+void C4::op5e() { immediate_reg( 0); }
+void C4::op60() { immediate_reg( 3); }
+void C4::op62() { immediate_reg( 6); }
+void C4::op64() { immediate_reg( 9); }
+void C4::op66() { immediate_reg(12); }
+void C4::op68() { immediate_reg(15); }
+void C4::op6a() { immediate_reg(18); }
+void C4::op6c() { immediate_reg(21); }
+void C4::op6e() { immediate_reg(24); }
+void C4::op70() { immediate_reg(27); }
+void C4::op72() { immediate_reg(30); }
+void C4::op74() { immediate_reg(33); }
+void C4::op76() { immediate_reg(36); }
+void C4::op78() { immediate_reg(39); }
+void C4::op7a() { immediate_reg(42); }
+void C4::op7c() { immediate_reg(45); }
+
+//Immediate ROM
+void C4::op89() {
+  str(0, 0x054336);
+  str(1, 0xffffff);
+}

src/chip/dsp2/dsp2.cpp

@@ -0,0 +1,133 @@
+#include "../../base.h"
+#include "dsp2_op.cpp"
+
+void DSP2::init() {}
+void DSP2::enable() {}
+
+void DSP2::power() {
+  reset();
+}
+
+void DSP2::reset() {
+  status.waiting_for_command = true;
+  status.in_count  = 0;
+  status.in_index  = 0;
+  status.out_count = 0;
+  status.out_index = 0;
+
+  status.op05transparent = 0;
+  status.op05haslen      = false;
+  status.op05len         = 0;
+  status.op06haslen      = false;
+  status.op06len         = 0;
+  status.op09word1       = 0;
+  status.op09word2       = 0;
+  status.op0dhaslen      = false;
+  status.op0doutlen      = 0;
+  status.op0dinlen       = 0;
+}
+
+uint8 DSP2::read(uint16 addr) {
+uint8 r = 0xff;
+  if(status.out_count) {
+    r = status.output[status.out_index++];
+    status.out_index &= 511;
+    if(status.out_count == status.out_index) {
+      status.out_count = 0;
+    }
+  }
+  return r;
+}
+
+void DSP2::write(uint16 addr, uint8 data) {
+  if(status.waiting_for_command) {
+    status.command  = data;
+    status.in_index = 0;
+    status.waiting_for_command = false;
+
+    switch(data) {
+    case 0x01: status.in_count = 32; break;
+    case 0x03: status.in_count =  1; break;
+    case 0x05: status.in_count =  1; break;
+    case 0x06: status.in_count =  1; break;
+    case 0x07: break;
+    case 0x08: break;
+    case 0x09: status.in_count =  4; break;
+    case 0x0d: status.in_count =  2; break;
+    case 0x0f: status.in_count =  0; break;
+    }
+  } else {
+    status.parameters[status.in_index++] = data;
+    status.in_index &= 511;
+  }
+
+  if(status.in_count == status.in_index) {
+    status.waiting_for_command = true;
+    status.out_index = 0;
+    switch(status.command) {
+    case 0x01: {
+      status.out_count = 32;
+      op01();
+    } break;
+
+    case 0x03: {
+      op03();
+    } break;
+
+    case 0x05: {
+      if(status.op05haslen) {
+        status.op05haslen = false;
+        status.out_count  = status.op05len;
+        op05();
+      } else {
+        status.op05len    = status.parameters[0];
+        status.in_index   = 0;
+        status.in_count   = status.op05len * 2;
+        status.op05haslen = true;
+        if(data)status.waiting_for_command = false;
+      }
+    } break;
+
+    case 0x06: {
+      if(status.op06haslen) {
+        status.op06haslen = false;
+        status.out_count  = status.op06len;
+        op06();
+      } else {
+        status.op06len    = status.parameters[0];
+        status.in_index   = 0;
+        status.in_count   = status.op06len;
+        status.op06haslen = true;
+        if(data)status.waiting_for_command = false;
+      }
+    } break;
+
+    case 0x07: break;
+    case 0x08: break;
+
+    case 0x09: {
+      op09();
+    } break;
+
+    case 0x0d: {
+      if(status.op0dhaslen) {
+        status.op0dhaslen = false;
+        status.out_count  = status.op0doutlen;
+        op0d();
+      } else {
+        status.op0dinlen  = status.parameters[0];
+        status.op0doutlen = status.parameters[1];
+        status.in_index   = 0;
+        status.in_count   = (status.op0dinlen + 1) >> 1;
+        status.op0dhaslen = true;
+        if(data)status.waiting_for_command = false;
+      }
+    } break;
+
+    case 0x0f: break;
+    }
+  }
+}
+
+DSP2::DSP2() {}
+DSP2::~DSP2() {}

src/chip/dsp2/dsp2.h

@@ -0,0 +1,40 @@
+class DSP2 {
+public:
+struct {
+  bool waiting_for_command;
+  uint command;
+  uint in_count,  in_index;
+  uint out_count, out_index;
+
+  uint8 parameters[512];
+  uint8 output[512];
+
+  uint8  op05transparent;
+  bool   op05haslen;
+  int    op05len;
+  bool   op06haslen;
+  int    op06len;
+  uint16 op09word1;
+  uint16 op09word2;
+  bool   op0dhaslen;
+  int    op0doutlen;
+  int    op0dinlen;
+} status;
+  void   init();
+  void   enable();
+  void   power();
+  void   reset();
+
+  void   op01();
+  void   op03();
+  void   op05();
+  void   op06();
+  void   op09();
+  void   op0d();
+
+  uint8  read (uint16 addr);
+  void   write(uint16 addr, uint8 data);
+
+  DSP2();
+  ~DSP2();
+};

src/chip/dsp2/dsp2_op.cpp

@@ -0,0 +1,173 @@
+//convert bitmap to bitplane tile
+void DSP2::op01() {
+//op01 size is always 32 bytes input and output
+//the hardware does strange things if you vary the size
+
+unsigned char c0, c1, c2, c3;
+unsigned char *p1  = status.parameters;
+unsigned char *p2a = status.output;
+unsigned char *p2b = status.output + 16; //halfway
+
+//process 8 blocks of 4 bytes each
+  for(int j = 0; j < 8; j++) {
+    c0 = *p1++;
+    c1 = *p1++;
+    c2 = *p1++;
+    c3 = *p1++;
+
+    *p2a++ = (c0 & 0x10) << 3 |
+             (c0 & 0x01) << 6 |
+             (c1 & 0x10) << 1 |
+             (c1 & 0x01) << 4 |
+             (c2 & 0x10) >> 1 |
+             (c2 & 0x01) << 2 |
+             (c3 & 0x10) >> 3 |
+             (c3 & 0x01);
+
+    *p2a++ = (c0 & 0x20) << 2 |
+             (c0 & 0x02) << 5 |
+             (c1 & 0x20)      |
+             (c1 & 0x02) << 3 |
+             (c2 & 0x20) >> 2 |
+             (c2 & 0x02) << 1 |
+             (c3 & 0x20) >> 4 |
+             (c3 & 0x02) >> 1;
+
+    *p2b++ = (c0 & 0x40) << 1 |
+             (c0 & 0x04) << 4 |
+             (c1 & 0x40) >> 1 |
+             (c1 & 0x04) << 2 |
+             (c2 & 0x40) >> 3 |
+             (c2 & 0x04)      |
+             (c3 & 0x40) >> 5 |
+             (c3 & 0x04) >> 2;
+
+    *p2b++ = (c0 & 0x80)      |
+             (c0 & 0x08) << 3 |
+             (c1 & 0x80) >> 2 |
+             (c1 & 0x08) << 1 |
+             (c2 & 0x80) >> 4 |
+             (c2 & 0x08) >> 1 |
+             (c3 & 0x80) >> 6 |
+             (c3 & 0x08) >> 3;
+  }
+}
+
+//set transparent color
+void DSP2::op03() {
+  status.op05transparent = status.parameters[0];
+}
+
+//replace bitmap using transparent color
+void DSP2::op05() {
+uint8 color;
+// Overlay bitmap with transparency.
+// Input:
+//
+//   Bitmap 1:  i[0] <=> i[size-1]
+//   Bitmap 2:  i[size] <=> i[2*size-1]
+//
+// Output:
+//
+//   Bitmap 3:  o[0] <=> o[size-1]
+//
+// Processing:
+//
+//   Process all 4-bit pixels (nibbles) in the bitmap
+//
+//   if ( BM2_pixel == transparent_color )
+//      pixelout = BM1_pixel
+//   else
+//      pixelout = BM2_pixel
+
+// The max size bitmap is limited to 255 because the size parameter is a byte
+// I think size=0 is an error.  The behavior of the chip on size=0 is to
+// return the last value written to DR if you read DR on Op05 with
+// size = 0.  I don't think it's worth implementing this quirk unless it's
+// proven necessary.
+
+unsigned char c1, c2;
+unsigned char *p1 = status.parameters;
+unsigned char *p2 = status.parameters + status.op05len;
+unsigned char *p3 = status.output;
+
+  color = status.op05transparent & 0x0f;
+
+  for(int n = 0; n < status.op05len; n++) {
+    c1 = *p1++;
+    c2 = *p2++;
+    *p3++ = ( ((c2 >> 4)   == color ) ? c1 & 0xf0 : c2 & 0xf0 ) |
+            ( ((c2 & 0x0f) == color ) ? c1 & 0x0f : c2 & 0x0f );
+  }
+}
+
+//reverse bitmap
+void DSP2::op06() {
+// Input:
+//    size
+//    bitmap
+
+int i, j;
+  for(i = 0, j = status.op06len - 1; i < status.op06len; i++, j--) {
+    status.output[j] = (status.parameters[i] << 4) | (status.parameters[i] >> 4);
+  }
+}
+
+//multiply
+void DSP2::op09() {
+  status.out_count = 4;
+
+  status.op09word1 = status.parameters[0] | (status.parameters[1] << 8);
+  status.op09word2 = status.parameters[2] | (status.parameters[3] << 8);
+
+uint32 r;
+  r = status.op09word1 * status.op09word2;
+  status.output[0] = r;
+  status.output[1] = r >> 8;
+  status.output[2] = r >> 16;
+  status.output[3] = r >> 24;
+}
+
+//scale bitmap
+void DSP2::op0d() {
+// Bit accurate hardware algorithm - uses fixed point math
+// This should match the DSP2 Op0D output exactly
+// I wouldn't recommend using this unless you're doing hardware debug.
+// In some situations it has small visual artifacts that
+// are not readily apparent on a TV screen but show up clearly
+// on a monitor.  Use Overload's scaling instead.
+// This is for hardware verification testing.
+//
+// One note:  the HW can do odd byte scaling but since we divide
+// by two to get the count of bytes this won't work well for
+// odd byte scaling (in any of the current algorithm implementations).
+// So far I haven't seen Dungeon Master use it.
+// If it does we can adjust the parameters and code to work with it
+
+uint32 multiplier; // Any size int >= 32-bits
+uint32 pixloc;     // match size of multiplier
+int    i, j;
+uint8  pixelarray[512];
+  if(status.op0dinlen <= status.op0doutlen) {
+    multiplier = 0x10000; // In our self defined fixed point 0x10000 == 1
+  } else {
+    multiplier = (status.op0dinlen << 17) / ((status.op0doutlen << 1) + 1);
+  }
+
+  pixloc = 0;
+  for(i = 0; i < status.op0doutlen * 2; i++) {
+    j = pixloc >> 16;
+
+    if(j & 1) {
+      pixelarray[i] = (status.parameters[j >> 1] & 0x0f);
+    } else {
+      pixelarray[i] = (status.parameters[j >> 1] & 0xf0) >> 4;
+    }
+
+    pixloc += multiplier;
+  }
+
+  for(i = 0; i < status.op0doutlen; i++) {
+    status.output[i] = (pixelarray[i << 1] << 4) | pixelarray[(i << 1) + 1];
+  }
+}

src/chip/obc1/obc1.cpp

@@ -0,0 +1,88 @@
+#include "../../base.h"
+
+void OBC1::init() {}
+void OBC1::enable() {}
+
+void OBC1::power() {
+  reset();
+}
+
+void OBC1::reset() {
+  memset(cartridge.sram, 0xff, 0x2000);
+  status.baseptr = (cartridge.sram[0x1ff5] & 1) ? 0x1800 : 0x1c00;
+  status.address = (cartridge.sram[0x1ff6] & 0x7f);
+  status.shift   = (cartridge.sram[0x1ff6] & 3) << 1;
+}
+
+uint8 OBC1::read(uint16 addr) {
+  addr &= 0x1fff;
+
+  if((addr & 0x1ff8) != 0x1ff0) {
+    return cartridge.sram[addr];
+  }
+
+  switch(addr) {
+  case 0x1ff0:
+    return cartridge.sram[status.baseptr + (status.address << 2) + 0];
+  case 0x1ff1:
+    return cartridge.sram[status.baseptr + (status.address << 2) + 1];
+  case 0x1ff2:
+    return cartridge.sram[status.baseptr + (status.address << 2) + 2];
+  case 0x1ff3:
+    return cartridge.sram[status.baseptr + (status.address << 2) + 3];
+  case 0x1ff4:
+    return cartridge.sram[status.baseptr + (status.address >> 2) + 0x200];
+  case 0x1ff5:
+  case 0x1ff6:
+  case 0x1ff7:
+    return cartridge.sram[addr];
+  }
+
+//never used, blocks compiler warning
+  return 0x00;
+}
+
+void OBC1::write(uint16 addr, uint8 data) {
+  addr &= 0x1fff;
+
+  if((addr & 0x1ff8) != 0x1ff0) {
+    cartridge.sram[addr] = data;
+    return;
+  }
+
+  switch(addr) {
+  case 0x1ff0:
+    cartridge.sram[status.baseptr + (status.address << 2) + 0] = data;
+    break;
+  case 0x1ff1:
+    cartridge.sram[status.baseptr + (status.address << 2) + 1] = data;
+    break;
+  case 0x1ff2:
+    cartridge.sram[status.baseptr + (status.address << 2) + 2] = data;
+    break;
+  case 0x1ff3:
+    cartridge.sram[status.baseptr + (status.address << 2) + 3] = data;
+    break;
+  case 0x1ff4: {
+  uint8 temp;
+    temp = cartridge.sram[status.baseptr + (status.address >> 2) + 0x200];
+    temp = (temp & ~(3 << status.shift)) | ((data & 3) << status.shift);
+    cartridge.sram[status.baseptr + (status.address >> 2) + 0x200] = temp;
+  } break;
+  case 0x1ff5:
+    status.baseptr = (data & 1) ? 0x1800 : 0x1c00;
+    cartridge.sram[addr] = data;
+    break;
+  case 0x1ff6:
+    status.address = (data & 0x7f);
+    status.shift   = (data & 3) << 1;
+    cartridge.sram[addr] = data;
+    break;
+  case 0x1ff7:
+    cartridge.sram[addr] = data;
+    break;
+  }
+}
+
+OBC1::OBC1() {}
+OBC1::~OBC1() {}

src/chip/obc1/obc1.h

@@ -0,0 +1,18 @@
+class OBC1 {
+public:
+struct {
+  uint16 address;
+  uint16 baseptr;
+  uint16 shift;
+} status;
+  void   init();
+  void   enable();
+  void   power();
+  void   reset();
+
+  uint8  read (uint16 addr);
+  void   write(uint16 addr, uint8 data);
+
+  OBC1();
+  ~OBC1();
+};

src/chip/sdd1/sdd1.cpp

@@ -1,12 +1,11 @@
 #include "../../base.h"
 #include "sdd1emu.cpp"
 
-void SDD1::init() {
-}
+void SDD1::init() {}
 
 void SDD1::enable() {
-  for(int i=0x4800;i<=0x4807;i++) {
-    mem_bus->set_mmio_mapper(i, mmio);
+  for(int i = 0x4800; i <= 0x4807; i++) {
+    r_mem->set_mmio_mapper(i, this);
   }
 }
 
@@ -47,14 +46,13 @@ uint8 SDD1::mmio_read(uint16 addr) {
   case 0x4807:return (sdd1.index[3] >> 20) & 7;
   }
 
-  return cpu->regs.mdr;
+  return r_cpu->regs.mdr;
 }
 
 void SDD1::mmio_write(uint16 addr, uint8 data) {
-int i;
   switch(addr) {
   case 0x4801:
-    for(i=0;i<8;i++) {
+    for(int i = 0; i < 8; i++) {
       sdd1.active[i] = !!(data & (1 << i));
     }
     break;
@@ -90,14 +88,4 @@ uint8 SDD1::dma_read() {
   return sdd1.buffer[sdd1.buffer_index++];
 }
 
-SDD1::SDD1() {
-  mmio = new SDD1MMIO();
-}
-
-uint8 SDD1MMIO::read(uint32 addr) {
-  return sdd1->mmio_read(addr);
-}
-
-void SDD1MMIO::write(uint32 addr, uint8 value) {
-  sdd1->mmio_write(addr, value);
-}
+SDD1::SDD1() {}

src/chip/sdd1/sdd1.h

@@ -1,15 +1,8 @@
 #include "sdd1emu.h"
 
-class SDD1MMIO : public MMIO {
-public:
-  inline uint8 read (uint32 addr);
-  inline void  write(uint32 addr, uint8 value);
-};
-
-class SDD1 {
+class SDD1 : public MMIO {
 public:
 SDD1emu sdd1emu;
-SDD1MMIO *mmio;
 
 struct {
   uint32 index[4];      //memory mapping registers
@@ -19,7 +12,7 @@ struct {
   uint16 buffer_size;
   bool   active[8];     //true when DMA channel should pass through S-DD1
   bool   dma_active;
-}sdd1;
+} sdd1;
   void   init();
   void   enable();
   void   power();
@@ -30,7 +23,7 @@ struct {
   bool   dma_active();
   uint8  dma_read();
 
-  uint8  mmio_read(uint16 addr);
+  uint8  mmio_read (uint16 addr);
   void   mmio_write(uint16 addr, uint8 data);
 
   SDD1();

src/chip/sdd1/sdd1emu.cpp

@@ -28,7 +28,7 @@ understood.
 
 ************************************************************************/
 
-#define SDD1_read(__addr) (mem_bus->read(__addr))
+#define SDD1_read(__addr) (r_mem->read(__addr))
 
 ////////////////////////////////////////////////////
 

src/chip/srtc/srtc.cpp

@@ -74,12 +74,11 @@ tm *t;
   srtc.data[12] = t->tm_wday;
 }
 
-void SRTC::init() {
-}
+void SRTC::init() {}
 
 void SRTC::enable() {
-  mem_bus->set_mmio_mapper(0x2800, mmio);
-  mem_bus->set_mmio_mapper(0x2801, mmio);
+  r_mem->set_mmio_mapper(0x2800, this);
+  r_mem->set_mmio_mapper(0x2801, this);
 }
 
 void SRTC::power() {
@@ -92,12 +91,46 @@ void SRTC::reset() {
   srtc.mode  = SRTC_READ;
 }
 
+uint8 SRTC::mmio_read(uint16 addr) {
+  switch(addr) {
+
+  case 0x2800: {
+    if(srtc.mode == SRTC_READ) {
+      if(srtc.index < 0) {
+        set_time();
+        srtc.index++;
+        return 0x0f; //send start message
+      } else if(srtc.index > MAX_SRTC_INDEX) {
+        srtc.index = -1;
+        return 0x0f; //send finished message
+      } else {
+        return srtc.data[srtc.index++];
+      }
+    } else {
+      return 0x00;
+    }
+  } break;
+
+  case 0x2801: {
+  } break;
+
+  }
+
+  return r_cpu->regs.mdr;
+}
+
 //Please see notes above about the implementation of the S-RTC
 //Writes are stored the srtc.data[] array, but they are ignored
 //as reads will refresh the data array with the current system
 //time. The write method is only here for the sake of faux
 //emulation of the real hardware.
-void SRTC::write(uint8 data) {
+void SRTC::mmio_write(uint16 addr, uint8 data) {
+  switch(addr) {
+
+  case 0x2800: {
+  } break;
+
+  case 0x2801: {
     data &= 0x0f; //only the low four bits are used
 
     if(data >= 0x0d) {
@@ -148,39 +181,9 @@ void SRTC::write(uint8 data) {
       //unknown behaviour
       }
     }
-}
+  } break;
 
-uint8 SRTC::read() {
-  if(srtc.mode == SRTC_READ) {
-    if(srtc.index < 0) {
-      set_time();
-      srtc.index++;
-      return 0x0f; //send start message
-    } else if(srtc.index > MAX_SRTC_INDEX) {
-      srtc.index = -1;
-      return 0x0f; //send finished message
-    } else {
-      return srtc.data[srtc.index++];
-    }
-  } else {
-    return 0x00;
   }
 }
 
-SRTC::SRTC() {
-  mmio = new SRTCMMIO();
-}
-
-uint8 SRTCMMIO::read(uint32 addr) {
-  switch(addr) {
-  case 0x2800:return srtc->read();
-  }
-
-  return cpu->regs.mdr;
-}
-
-void SRTCMMIO::write(uint32 addr, uint8 value) {
-  switch(addr) {
-  case 0x2801:srtc->write(value);break;
-  }
-}
+SRTC::SRTC() {}

src/chip/srtc/srtc.h

@@ -1,10 +1,4 @@
-class SRTCMMIO : public MMIO {
-public:
-  inline uint8 read (uint32 addr);
-  inline void  write(uint32 addr, uint8 value);
-};
-
-class SRTC {
+class SRTC : public MMIO {
 public:
 enum { MAX_SRTC_INDEX = 0x0c };
 
@@ -20,8 +14,6 @@ enum {
   SRTC_COMMAND_CLEAR = 4
 };
 
-SRTCMMIO *mmio;
-
 /******************************
 [srtc.data structure]
 Index  Description   Range
@@ -50,8 +42,9 @@ struct {
   void  enable();
   void  power();
   void  reset();
-  void  write(uint8 data);
-  uint8 read();
+
+  uint8 mmio_read (uint16 addr);
+  void  mmio_write(uint16 addr, uint8 data);
 
   SRTC();
 };

src/config/config.cpp

@@ -2,27 +2,79 @@ Config config_file;
 
 namespace config {
 
-SNES::VideoColorAdjust SNES::video_color_curve(&config_file, "snes.video_color_curve",
-  "Applies contrast adjust filter to video output when enabled\n"
-  "Works by lowering the brightness of darker colors,\n"
-  "while leaving brighter colors alone; thus reducing saturation",
-  true, Setting::TRUE_FALSE);
+FS::Path FS::base_path(0, "fs.base_path", "Directory that bsnes resides in", "");
 
-SNES::VideoColorAdjust SNES::video_color_adjust_mode(&config_file, "snes.video_color_adjust_mode",
-  "Selects color adjustment filter for video output\n"
-  "  0 = Normal (no filter, rgb555)\n"
-  "  1 = Grayscale mode (l5)\n"
-  "  2 = VGA mode (rgb332)\n"
-  "  3 = Genesis mode (rgb333)",
-  0, Setting::DEC);
+FS::Path FS::rom_path(&config_file, "fs.rom_path",
+  "Default path to look for ROM files in (\"\" = use default directory)", "");
+FS::Path FS::save_path(&config_file, "fs.save_path",
+  "Default path for all save RAM and cheat files (\"\" = use current directory)", "");
+
+void FS::Path::sset(const char *_data) {
+string path;
+  strcpy(path, _data);
+  strunquote(path);
+  replace(path, "\\", "/");
+
+//blank path?
+  if(strlen(path) == 0) {
+    Setting::sset(strptr(path));
+    return;
+  }
+
+//missing final directory marker?
+  if(strptr(path)[strlen(path) - 1] != '/') {
+    strcat(path, "/");
+  }
+
+  Setting::sset(strptr(path));
+}
+
+Setting FS::save_ext(&config_file, "fs.save_ext",
+  "Extension to be used for all save RAM files", "srm");
+
+SNES::VideoColorAdjust SNES::gamma_ramp(&config_file, "snes.colorfilter.gamma_ramp",
+  "Use precalculated TV-style gamma ramp", true, Setting::TRUE_FALSE);
+SNES::VideoColorAdjust SNES::sepia(&config_file, "snes.colorfilter.sepia",
+  "Convert color to sepia tone", false, Setting::TRUE_FALSE);
+SNES::VideoColorAdjust SNES::grayscale(&config_file, "snes.colorfilter.grayscale",
+  "Convert color to grayscale tone", false, Setting::TRUE_FALSE);
+SNES::VideoColorAdjust SNES::invert(&config_file, "snes.colorfilter.invert",
+  "Invert output image colors", false, Setting::TRUE_FALSE);
+SNES::VideoColorAdjust SNES::contrast(&config_file, "snes.colorfilter.contrast",
+  "", 0,  Setting::DEC);
+SNES::VideoColorAdjust SNES::brightness(&config_file, "snes.colorfilter.brightness",
+  "", 0, Setting::DEC);
+SNES::VideoColorAdjust SNES::gamma(&config_file, "snes.colorfilter.gamma",
+  "", 100, Setting::DEC);
 
 void SNES::VideoColorAdjust::set(uint32 _data) {
-  data = _data;
+  Setting::set(_data);
   ::snes->update_color_lookup_table();
 }
 
-Setting SNES::mute(&config_file, "snes.mute",
-  "Mutes SNES audio output when enabled",
-  true, Setting::TRUE_FALSE);
+Setting SNES::ntsc_merge_fields(&config_file, "snes.ntsc_merge_fields",
+"Merge fields in NTSC video filter\n"
+"Set to true if using filter at any refresh rate other than 60hz\n"
+"", false, Setting::TRUE_FALSE);
+
+Setting SNES::mute(&config_file, "snes.mute", "Mutes SNES audio output when enabled",
+  false, Setting::TRUE_FALSE);
+
+//do not save these settings to config_file
+Setting CPU::hdma_enable(0, "cpu.hdma_enable", "Enable HDMA effects", true, Setting::TRUE_FALSE);
+Setting PPU::opt_enable(0, "ppu.opt_enable", "Enable offset-per-tile effects", true, Setting::TRUE_FALSE);
+
+Setting PPU::bg1_pri0_enable(0, "ppu.bg1_pri0_enable", "Enable BG1 Priority 0", true, Setting::TRUE_FALSE);
+Setting PPU::bg1_pri1_enable(0, "ppu.bg1_pri1_enable", "Enable BG1 Priority 1", true, Setting::TRUE_FALSE);
+Setting PPU::bg2_pri0_enable(0, "ppu.bg2_pri0_enable", "Enable BG2 Priority 0", true, Setting::TRUE_FALSE);
+Setting PPU::bg2_pri1_enable(0, "ppu.bg2_pri1_enable", "Enable BG2 Priority 1", true, Setting::TRUE_FALSE);
+Setting PPU::bg3_pri0_enable(0, "ppu.bg3_pri0_enable", "Enable BG3 Priority 0", true, Setting::TRUE_FALSE);
+Setting PPU::bg3_pri1_enable(0, "ppu.bg3_pri1_enable", "Enable BG3 Priority 1", true, Setting::TRUE_FALSE);
+Setting PPU::bg4_pri0_enable(0, "ppu.bg4_pri0_enable", "Enable BG4 Priority 0", true, Setting::TRUE_FALSE);
+Setting PPU::bg4_pri1_enable(0, "ppu.bg4_pri1_enable", "Enable BG4 Priority 1", true, Setting::TRUE_FALSE);
+Setting PPU::oam_pri0_enable(0, "ppu.oam_pri0_enable", "Enable OAM Priority 0", true, Setting::TRUE_FALSE);
+Setting PPU::oam_pri1_enable(0, "ppu.oam_pri1_enable", "Enable OAM Priority 1", true, Setting::TRUE_FALSE);
+Setting PPU::oam_pri2_enable(0, "ppu.oam_pri2_enable", "Enable OAM Priority 2", true, Setting::TRUE_FALSE);
+Setting PPU::oam_pri3_enable(0, "ppu.oam_pri3_enable", "Enable OAM Priority 3", true, Setting::TRUE_FALSE);
 
 };

src/config/config.h

@@ -2,14 +2,39 @@ extern Config config_file;
 
 namespace config {
 
+extern struct FS {
+  static class Path : public Setting {
+  public:
+    void sset(const char *_data);
+    SettingOperators(Path);
+  } base_path, rom_path, save_path;
+  static Setting save_ext;
+} fs;
+
 extern struct SNES {
   static class VideoColorAdjust : public Setting {
   public:
     void set(uint32 _data);
     SettingOperators(VideoColorAdjust);
-  } video_color_curve, video_color_adjust_mode;
+  } gamma_ramp, sepia, grayscale, invert, contrast, brightness, gamma;
 
+  static Setting ntsc_merge_fields;
   static Setting mute;
 } snes;
 
+extern struct CPU {
+  static Setting hdma_enable;
+} cpu;
+
+extern struct PPU {
+  static Setting opt_enable;
+
+  static Setting bg1_pri0_enable, bg1_pri1_enable;
+  static Setting bg2_pri0_enable, bg2_pri1_enable;
+  static Setting bg3_pri0_enable, bg3_pri1_enable;
+  static Setting bg4_pri0_enable, bg4_pri1_enable;
+  static Setting oam_pri0_enable, oam_pri1_enable;
+  static Setting oam_pri2_enable, oam_pri3_enable;
+} ppu;
+
 };

src/cpu/bcpu/bcpu.cpp

@@ -1,71 +1,72 @@
 #include "../../base.h"
 
-#include "bcpu_opfn.cpp"
-#include "bcpu_op_read.cpp"
-#include "bcpu_op_rmw.cpp"
-#include "bcpu_op_write.cpp"
-#include "bcpu_op_pc.cpp"
-#include "bcpu_op_misc.cpp"
+#include "core/core.cpp"
+#include "memory/memory.cpp"
+#include "dma/dma.cpp"
+#include "timing/timing.cpp"
 
 #include "bcpu_exec.cpp"
 #include "bcpu_mmio.cpp"
-#include "bcpu_dma.cpp"
-
-#include "bcpu_timing.cpp"
-
 #include "bcpu_int.cpp"
 
 uint8 bCPU::pio_status() { return status.pio; }
 
 void bCPU::run() {
-  switch(status.cpu_state) {
-  case CPUSTATE_DMA:
-    dma_run();
-    break;
-  case CPUSTATE_WAI:
-  case CPUSTATE_RUN:
-    if(status.cycle_pos == 0) {
-    //interrupts only trigger on opcode edges
-      if(time.nmi_pending == true) {
-        time.nmi_pending = false;
-        irq(0xffea);
-        break;
-      }
-      if(time.irq_pending == true) {
-        time.irq_pending = false;
-        irq(0xffee);
-        break;
-      }
-    }
-  //fallthrough
-  case CPUSTATE_STP:
-    exec_cycle();
-    break;
+  if(run_state.hdma) {
+    exec_hdma();
+    return;
   }
 
-  cycle_edge();
+  if(run_state.dma) {
+    exec_dma();
+    return;
+  }
+
+  if(status.cycle_pos == 0) {
+  //interrupts only trigger on opcode edges
+    if(!run_state.irq && !run_state.stp) {
+      if(time.nmi_pending == true) {
+        time.nmi_pending = false;
+        aa.w = 0xffea;
+        run_state.irq = true;
+      } else if(time.irq_pending == true) {
+        time.irq_pending = false;
+        aa.w = 0xffee;
+        run_state.irq = true;
+      }
+    }
+  }
+
+  exec_cycle();
 }
 
 void bCPU::scanline() {
-  status.hdma_triggered = false;
+  time.hdma_triggered = false;
 
-  if(vcounter() == 225 && status.auto_joypad_poll == true) {
-    snes->poll_input();
+  if(vcounter() == (overscan() == false ? 227 : 242) && status.auto_joypad_poll == true) {
+    snes->poll_input(SNES::DEV_JOYPAD1);
+    snes->poll_input(SNES::DEV_JOYPAD2);
   //When the SNES auto-polls the joypads, it writes 1, then 0 to
   //$4016, then reads from each 16 times to get the joypad state
   //information. As a result, the joypad read positions are set
   //to 16 after such a poll. Position 16 is the controller
   //connected status bit.
     status.joypad1_read_pos = 16;
+    status.joypad2_read_pos = 16;
   }
 }
 
 void bCPU::frame() {
-  hdma_initialize();
-
   time.nmi_read = 1;
   time.nmi_line = 1;
   time.nmi_transition = 0;
+
+  if(cpu_version == 2) {
+    time.hdmainit_trigger_pos = 12 + dma_counter();
+  } else {
+    time.hdmainit_trigger_pos = 12 + 8 - dma_counter();
+  }
+  time.hdmainit_triggered = false;
 }
 
 void bCPU::power() {
@@ -78,7 +79,9 @@ void bCPU::power() {
 
 void bCPU::reset() {
 //reset vector location
-  regs.pc  = mem_bus->read(0xfffc) | (mem_bus->read(0xfffd) << 8);
+  regs.pc.d = 0;
+  regs.pc.l = r_mem->read(0xfffc);
+  regs.pc.h = r_mem->read(0xfffd);
 
 //registers are not fully reset by SNES
   regs.x.h = 0x00;
@@ -90,152 +93,38 @@ void bCPU::reset() {
   regs.e   = 1;
   regs.mdr = 0x00;
 
+//simulate pbr:pc push during reset irq vector
+  regs.s.l -= 3;
+
   time_reset();
   mmio_reset();
   dma_reset();
 
-  status.cpu_state = CPUSTATE_RUN;
-  status.dma_state = DMASTATE_STOP;
+  run_state.hdma = false;
+  run_state.dma  = false;
+  run_state.irq  = false;
+  run_state.wai  = false;
+  run_state.stp  = false;
 
   status.cycle_pos       = 0;
   status.cycle_count     = 0;
   status.cycles_executed = 0;
 
-  status.hdma_triggered = false;
-
   apu_port[0] = 0x00;
   apu_port[1] = 0x00;
   apu_port[2] = 0x00;
   apu_port[3] = 0x00;
 
   frame();
-}
 
-uint8 bCPU::port_read(uint8 port) {
-  return apu_port[port & 3];
-}
-
-void bCPU::port_write(uint8 port, uint8 value) {
-  apu_port[port & 3] = value;
-}
-
-void bCPU::cpu_c2() {
-  if(regs.d.l != 0x00) {
-    cpu_io();
-  }
-}
-
-void bCPU::cpu_c4(uint16 x, uint16 y) {
-  if(!regs.p.x && (x & 0xff00) != (y & 0xff00)) {
-    cpu_io();
-  }
-}
-
-void bCPU::cpu_c6(uint16 addr) {
-  if(regs.e && (regs.pc.w & 0xff00) != (addr & 0xff00)) {
-    cpu_io();
-  }
-}
-
-/* The next 3 functions control bus timing for the CPU.
- * cpu_io is an I/O cycle, and always 6 clock cycles long.
- * mem_read / mem_write indicate memory access bus cycle,
- * they are either 6, 8, or 12 bus cycles long, depending
- * both on location and the $420d.1 FastROM enable bit.
- */
-
-void bCPU::cpu_io() {
-  if(status.is_last_cycle)last_cycle_exec();
-
-  status.cycle_count = 6;
-  add_cycles(6);
-}
-
-uint8 bCPU::mem_read(uint32 addr) {
-  if(status.is_last_cycle)last_cycle_exec();
-
-  status.cycle_count = mem_bus->speed(addr);
-  add_cycles(status.cycle_count - 4);
-  regs.mdr = mem_bus->read(addr);
-  add_cycles(4);
-  return regs.mdr;
-}
-
-void bCPU::mem_write(uint32 addr, uint8 value) {
-  if(status.is_last_cycle)last_cycle_exec();
-
-  status.cycle_count = mem_bus->speed(addr);
-  add_cycles(status.cycle_count);
-  mem_bus->write(addr, value);
-}
-
-uint32 bCPU::op_addr(uint8 mode, uint32 addr) {
-  switch(mode) {
-  case OPMODE_ADDR:
-    addr &= 0xffff;
-    break;
-  case OPMODE_LONG:
-    addr &= 0xffffff;
-    break;
-  case OPMODE_DBR:
-    addr = ((regs.db << 16) + addr) & 0xffffff;
-    break;
-  case OPMODE_PBR:
-    addr &= 0xffff;
-    addr = (regs.pc.b << 16) + addr;
-    break;
-  case OPMODE_DP:
-    addr &= 0xffff;
-    addr = (regs.d + addr) & 0xffff;
-    break;
-  case OPMODE_SP:
-    addr &= 0xffff;
-    addr = (regs.s + addr) & 0xffff;
-    break;
-  }
-  return addr;
-}
-
-uint8 bCPU::op_read() {
-uint8 r;
-  r = mem_read(regs.pc.d);
-  regs.pc.w++;
-  return r;
-}
-
-uint8 bCPU::op_read(uint8 mode, uint32 addr) {
-  addr = op_addr(mode, addr);
-  return mem_read(addr);
-}
-
-void bCPU::op_write(uint8 mode, uint32 addr, uint8 value) {
-  addr = op_addr(mode, addr);
-  mem_write(addr, value);
-}
-
-uint8 bCPU::stack_read() {
-  if(regs.e) {
-    regs.s.l++;
-  } else {
-    regs.s.w++;
-  }
-  return mem_read(regs.s);
-}
-
-void bCPU::stack_write(uint8 value) {
-  mem_write(regs.s, value);
-  if(regs.e) {
-    regs.s.l--;
-  } else {
-    regs.s.w--;
-  }
+//initial latch values for $213c/$213d
+//[x]0035 : [y]0000 (53.0 -> 212) [lda $2137]
+//[x]0038 : [y]0000 (56.5 -> 226) [nop : lda $2137]
+  add_cycles(186);
 }
 
 bCPU::bCPU() {
-  mmio = new bCPUMMIO(this);
   init_op_tables();
 }
 
-bCPU::~bCPU() {
-  delete(mmio);
-}
+bCPU::~bCPU() {}

src/cpu/bcpu/bcpu.h

@@ -1,63 +1,47 @@
-class bCPU;
-
-class bCPUMMIO : public MMIO {
-public:
-bCPU *cpu;
-  inline uint8 read (uint32 addr);
-  inline void  write(uint32 addr, uint8 value);
-  bCPUMMIO(bCPU *_cpu);
-};
-
 class bCPU : public CPU {
-private:
-void (bCPU::*optbl[256])();
+public:
+#include "core/core.h"
+#include "memory/memory.h"
+#include "dma/dma.h"
+#include "timing/timing.h"
 
 enum { NTSC = 0, PAL = 1 };
 uint8 region;
 
-public:
-#include "bcpu_timing.h"
-
-uint8 apu_port[4];
-  inline uint8 port_read (uint8 port);
-  inline void  port_write(uint8 port, uint8 value);
-
 enum {
-  OPMODE_ADDR = 1, OPMODE_LONG = 2,
-  OPMODE_DBR  = 3, OPMODE_PBR  = 4,
-  OPMODE_DP   = 5, OPMODE_SP   = 6
-};
-
-CPUReg24 aa, rd;
-uint8    dp, sp;
-
-enum {
-  CPUSTATE_RUN = 0,
-  CPUSTATE_WAI,
-  CPUSTATE_STP,
-  CPUSTATE_DMA
-};
-
-enum {
-  DMASTATE_STOP = 0,
   DMASTATE_DMASYNC,
   DMASTATE_DMASYNC2,
+  DMASTATE_DMASYNC3,
   DMASTATE_RUN,
   DMASTATE_CPUSYNC,
-  DMASTATE_CPUSYNC2
+
+  HDMASTATE_IDMASYNC,
+  HDMASTATE_IDMASYNC2,
+  HDMASTATE_IDMASYNC3,
+  HDMASTATE_ICPUSYNC,
+
+  HDMASTATE_DMASYNC,
+  HDMASTATE_DMASYNC2,
+  HDMASTATE_DMASYNC3,
+  HDMASTATE_RUN,
+  HDMASTATE_CPUSYNC
 };
 
 struct {
-  uint8  cpu_state, cycle_pos, cycle_count;
+  bool hdma;
+  bool dma;
+  bool irq;
+  bool stp;
+  bool wai;
+} run_state;
+
+struct {
+  uint8  cycle_pos, cycle_count;
   uint8  opcode;
   uint32 cycles_executed;
 
-//set by last_cycle(), cleared by last_cycle_exec()
-  bool   is_last_cycle;
-
-  uint8  dma_state;
-  uint32 dma_cycle_count;
-  bool   hdma_triggered;
+  uint8  dma_state, hdma_state;
+  uint32 dma_cycle_count, hdma_cycle_count;
 
 //$4207-$420a
   uint16 virq_trigger, hirq_trigger;
@@ -65,9 +49,9 @@ struct {
 //$2181-$2183
   uint32 wram_addr;
 
-//$4016
-  uint8  joypad1_strobe_value;
-  uint8  joypad1_read_pos;
+//$4016-$4017
+  bool   joypad_strobe_latch;
+  uint8  joypad1_read_pos, joypad2_read_pos;
 
 //$4200
   bool   nmi_enabled;
@@ -92,47 +76,7 @@ struct {
   uint16 r4216;
 } status;
 
-struct {
-  uint32 read_index; //set to 0 at beginning of DMA/HDMA
-
-//$420b
-  bool   active;
-//$420c
-  bool   hdma_enabled;
-//$43x0
-  uint8  dmap;
-  bool   direction;
-  bool   hdma_indirect;
-  int8   incmode;
-  bool   fixedxfer;
-  uint8  xfermode;
-//$43x1
-  uint8  destaddr;
-//$43x2-$43x3
-  uint16 srcaddr;
-//$43x4
-  uint8  srcbank;
-//$43x5-$43x6
-  uint16 xfersize;
-//$43x7
-  uint8  hdma_ibank;
-//$43x8-$43x9
-  uint16 hdma_addr;
-//$43xa
-  uint8  hdma_line_counter;
-//$43xb/$43xf
-  uint8  hdma_unknown;
-
-//hdma-specific
-  bool   hdma_first_line;
-  bool   hdma_repeat;
-  uint16 hdma_iaddr;
-  bool   hdma_active;
-} channel[8];
-
   inline bool   hdma_test();
-
-  inline void   irq(uint16 addr);
   inline bool   nmi_test();
   inline bool   irq_test();
 
@@ -144,18 +88,7 @@ struct {
   inline void   power();
   inline void   reset();
 
-//dma commands
-  inline void   dma_run();
-  inline void   hdma_run();
-  inline void   hdma_initialize();
-  inline void   dma_cputommio(uint8 i, uint8 index);
-  inline void   dma_mmiotocpu(uint8 i, uint8 index);
-  inline void   dma_write(uint8 i, uint8 index);
-  inline uint32 dma_addr(uint8 i);
-  inline uint32 hdma_addr(uint8 i);
-  inline uint32 hdma_iaddr(uint8 i);
-  inline void   hdma_write(uint8 i, uint8 l, uint8 x);
-  inline void   dma_reset();
+  inline void   irq_run();
 
 //mmio commands
   void  mmio_reset();
@@ -172,6 +105,8 @@ struct {
   uint8 mmio_r4217();
   uint8 mmio_r4218();
   uint8 mmio_r4219();
+  uint8 mmio_r421a();
+  uint8 mmio_r421b();
   uint8 mmio_r43x0(uint8 i);
   uint8 mmio_r43x1(uint8 i);
   uint8 mmio_r43x2(uint8 i);
@@ -216,75 +151,17 @@ struct {
   void  mmio_w43xa(uint8 value, uint8 i);
   void  mmio_w43xb(uint8 value, uint8 i);
 
-enum { CYCLE_OPREAD = 0, CYCLE_READ, CYCLE_WRITE, CYCLE_IO };
+  uint8 mmio_read (uint16 addr);
+  void  mmio_write(uint16 addr, uint8 data);
+
+enum { CYCLE_OPREAD, CYCLE_READ, CYCLE_WRITE, CYCLE_IO };
+  inline void pre_exec_cycle();
+  inline void exec_hdma();
+  inline void exec_dma();
   inline void exec_cycle();
   inline void last_cycle();
-  inline void last_cycle_exec();
-  inline void cycle_edge();
   inline bool in_opcode();
 
-//cpu extra-cycle conditions
-  inline void cpu_c2();
-  inline void cpu_c4(uint16 x, uint16 y);
-  inline void cpu_c6(uint16 addr);
-  inline void cpu_io();
-
-  inline uint8  mem_read (uint32 addr);
-  inline void   mem_write(uint32 addr, uint8 value);
-  inline uint32 op_addr(uint8 mode, uint32 addr);
-  inline uint8  op_read();
-  inline uint8  op_read(uint8 mode, uint32 addr);
-  inline void   op_write(uint8 mode, uint32 addr, uint8 value);
-  inline uint8  stack_read();
-  inline void   stack_write(uint8 value);
-
-//opcode functions
-  inline void init_op_tables();
-
-//op_read
-  inline void op_adc_b();
-  inline void op_adc_w();
-  inline void op_and_b();
-  inline void op_and_w();
-  inline void op_bit_b();
-  inline void op_bit_w();
-  inline void op_cmp_b();
-  inline void op_cmp_w();
-  inline void op_cpx_b();
-  inline void op_cpx_w();
-  inline void op_cpy_b();
-  inline void op_cpy_w();
-  inline void op_eor_b();
-  inline void op_eor_w();
-  inline void op_lda_b();
-  inline void op_lda_w();
-  inline void op_ldx_b();
-  inline void op_ldx_w();
-  inline void op_ldy_b();
-  inline void op_ldy_w();
-  inline void op_ora_b();
-  inline void op_ora_w();
-  inline void op_sbc_b();
-  inline void op_sbc_w();
-//op_rmw
-  inline void op_inc_b();
-  inline void op_inc_w();
-  inline void op_dec_b();
-  inline void op_dec_w();
-  inline void op_asl_b();
-  inline void op_asl_w();
-  inline void op_lsr_b();
-  inline void op_lsr_w();
-  inline void op_rol_b();
-  inline void op_rol_w();
-  inline void op_ror_b();
-  inline void op_ror_w();
-  inline void op_trb_b();
-  inline void op_trb_w();
-  inline void op_tsb_b();
-  inline void op_tsb_w();
-#include "bcpu_op.h"
-
   bCPU();
   ~bCPU();
 };

src/cpu/bcpu/bcpu_dma.cpp

@@ -1,220 +0,0 @@
-uint32 bCPU::dma_addr(uint8 i) {
-uint32 r;
-  r  = channel[i].srcaddr;
-  r |= (channel[i].srcbank << 16);
-  return r;
-}
-
-void bCPU::dma_cputommio(uint8 i, uint8 index) {
-uint8 x;
-  if(sdd1->dma_active() == true) {
-    x = sdd1->dma_read();
-  } else {
-    x = mem_bus->read(dma_addr(i));
-  }
-
-  mem_bus->write(0x2100 | ((channel[i].destaddr + index) & 0xff), x);
-
-  if(channel[i].fixedxfer == false) {
-    channel[i].srcaddr += channel[i].incmode;
-  }
-
-  add_cycles(8);
-  channel[i].xfersize--;
-}
-
-void bCPU::dma_mmiotocpu(uint8 i, uint8 index) {
-uint8 x;
-  x = mem_bus->read(0x2100 | ((channel[i].destaddr + index) & 0xff));
-  mem_bus->write(dma_addr(i), x);
-
-  if(channel[i].fixedxfer == false) {
-    channel[i].srcaddr += channel[i].incmode;
-  }
-
-  add_cycles(8);
-  channel[i].xfersize--;
-}
-
-void bCPU::dma_write(uint8 i, uint8 index) {
-  if(channel[i].direction == 0) {
-    dma_cputommio(i, index);
-  } else {
-    dma_mmiotocpu(i, index);
-  }
-}
-
-void bCPU::dma_run() {
-int i;
-  for(i=0;i<8;i++) {
-    if(channel[i].active == false)continue;
-
-  //first byte transferred?
-    if(channel[i].read_index == 0) {
-      sdd1->dma_begin(i, dma_addr(i), channel[i].xfersize);
-    }
-
-    switch(channel[i].xfermode) {
-    case 0:dma_write(i, 0);                               break; //0
-    case 1:dma_write(i, channel[i].read_index & 1);       break; //0,1
-    case 2:dma_write(i, 0);                               break; //0,0
-    case 3:dma_write(i, (channel[i].read_index >> 1) & 1);break; //0,0,1,1
-    case 4:dma_write(i, channel[i].read_index & 3);       break; //0,1,2,3
-    case 5:dma_write(i, channel[i].read_index & 1);       break; //0,1,0,1
-    case 6:dma_write(i, 0);                               break; //0,0     [2]
-    case 7:dma_write(i, (channel[i].read_index >> 1) & 1);break; //0,0,1,1 [3]
-    }
-
-    channel[i].read_index++;
-
-    if(channel[i].xfersize == 0) {
-      channel[i].active = false;
-    }
-
-    return;
-  }
-
-  status.dma_state = DMASTATE_CPUSYNC;
-}
-
-uint32 bCPU::hdma_addr(uint8 i) {
-uint32 r;
-  r  = channel[i].hdma_addr;
-  r |= (channel[i].srcbank << 16);
-  channel[i].hdma_addr++;
-  return r;
-}
-
-uint32 bCPU::hdma_iaddr(uint8 i) {
-uint32 r;
-  r  = channel[i].hdma_iaddr;
-  r |= (channel[i].hdma_ibank << 16);
-  channel[i].hdma_iaddr++;
-  return r;
-}
-
-void bCPU::hdma_write(uint8 i, uint8 l, uint8 x) {
-uint16 index;
-  switch(channel[i].xfermode) {
-  case 0:index = 0;           break; //0
-  case 1:index = l & 1;       break; //0,1
-  case 2:index = 0;           break; //0,0
-  case 3:index = (l >> 1) & 1;break; //0,0,1,1
-  case 4:index = l & 3;       break; //0,1,2,3
-  case 5:index = l & 1;       break; //0,1,0,1
-  case 6:index = 0;           break; //0,0     [2]
-  case 7:index = (l >> 1) & 1;break; //0,0,1,1 [3]
-  }
-
-  index = 0x2100 | ((channel[i].destaddr + index) & 0xff);
-  mem_bus->write(index, x);
-}
-
-void bCPU::hdma_run() {
-int l, xferlen;
-uint8 x, active_channels = 0;
-static uint8 hdma_xferlen[8] = { 1, 2, 2, 4, 4, 4, 2, 4 };
-  for(int i=0;i<8;i++) {
-    if(channel[i].hdma_active == false)continue;
-
-    add_cycles(8);
-    active_channels++;
-
-    if(channel[i].hdma_line_counter == 0) {
-      channel[i].hdma_line_counter = mem_bus->read(hdma_addr(i));
-
-      if(channel[i].hdma_line_counter == 0) {
-        channel[i].hdma_active = false;
-        continue;
-      }
-
-      if(channel[i].hdma_line_counter > 0x80) {
-        channel[i].hdma_repeat = true;
-        channel[i].hdma_line_counter -= 0x80;
-      } else {
-        channel[i].hdma_repeat = false;
-      }
-
-      channel[i].hdma_first_line = true;
-
-      if(channel[i].hdma_indirect == true) {
-        channel[i].hdma_iaddr  = mem_bus->read(hdma_addr(i));
-        channel[i].hdma_iaddr |= mem_bus->read(hdma_addr(i)) << 8;
-        add_cycles(16);
-      }
-    }
-
-    channel[i].hdma_line_counter--;
-    if(channel[i].hdma_first_line == false && channel[i].hdma_repeat == false)continue;
-    channel[i].hdma_first_line = false;
-
-    xferlen = hdma_xferlen[channel[i].xfermode];
-    for(l=0;l<xferlen;l++) {
-      if(channel[i].hdma_indirect == false) {
-        x = mem_bus->read(hdma_addr(i));
-      } else {
-        x = mem_bus->read(hdma_iaddr(i));
-      }
-
-      hdma_write(i, l, x);
-      add_cycles(8);
-    }
-  }
-
-  if(active_channels != 0) {
-    add_cycles(18);
-  }
-}
-
-void bCPU::hdma_initialize() {
-uint8 active_channels = 0;
-  for(int i=0;i<8;i++) {
-  //does this happen when $420c channel bit is clear?
-    channel[i].hdma_addr         = channel[i].srcaddr;
-    channel[i].hdma_line_counter = 0x00;
-
-    if(channel[i].hdma_enabled == false) {
-      channel[i].hdma_active = false;
-      continue;
-    }
-
-    channel[i].hdma_active = true;
-    active_channels++;
-
-    if(channel[i].hdma_indirect == false) {
-      add_cycles(8);
-    } else {
-      add_cycles(24);
-    }
-  }
-
-  if(active_channels != 0) {
-    add_cycles(18);
-  }
-}
-
-void bCPU::dma_reset() {
-  for(int i=0;i<8;i++) {
-    channel[i].read_index        = 0;
-    channel[i].active            = false;
-    channel[i].hdma_enabled      = false;
-    channel[i].dmap              = 0x00;
-    channel[i].direction         = 0;
-    channel[i].hdma_indirect     = false;
-    channel[i].incmode           = 1;
-    channel[i].fixedxfer         = false;
-    channel[i].xfermode          = 0;
-    channel[i].destaddr          = 0;
-    channel[i].srcaddr           = 0;
-    channel[i].xfersize          = 0;
-    channel[i].hdma_ibank        = 0;
-    channel[i].hdma_addr         = 0x0000;
-    channel[i].hdma_line_counter = 0x00;
-    channel[i].hdma_unknown      = 0x00;
-
-    channel[i].hdma_active       = false;
-    channel[i].hdma_first_line   = false;
-    channel[i].hdma_repeat       = false;
-    channel[i].hdma_iaddr        = 0x0000;
-  }
-}

src/cpu/bcpu/bcpu_exec.cpp

@@ -1,71 +1,174 @@
 void bCPU::last_cycle() {
-  status.is_last_cycle = true;
-}
-
-void bCPU::last_cycle_exec() {
-  status.is_last_cycle = false;
-
-  time.nmi_pending = nmi_test();
+//DMV27: keep previous nmi value,
+//to allow wai and irq to work properly
+  time.nmi_pending = nmi_test() || time.nmi_pending;
   time.irq_pending = irq_test();
 }
 
-void bCPU::cycle_edge() {
-int c, n, z;
-  if(status.dma_state != DMASTATE_STOP) {
+void bCPU::pre_exec_cycle() {
+  if(!run_state.dma && !run_state.hdma)return;
+
+int c, z;
+  if(run_state.hdma) {
+    switch(status.hdma_state) {
+    case HDMASTATE_ICPUSYNC:
+    case HDMASTATE_CPUSYNC:
+      c = status.cycle_count;
+      z = c - (status.hdma_cycle_count % c);
+      if(!z)z = c;
+      add_cycles(z);
+      run_state.hdma = false;
+      break;
+    }
+  }
+
+  if(run_state.dma) {
+    switch(status.dma_state) {
+    case DMASTATE_CPUSYNC:
+      c = status.cycle_count;
+      z = c - (status.dma_cycle_count % c);
+      if(!z)z = c;
+      add_cycles(z);
+      run_state.dma = false;
+      break;
+    }
+  }
+}
+
+void bCPU::exec_hdma() {
+int n;
+static int z;
+  switch(status.hdma_state) {
+  case HDMASTATE_IDMASYNC:
+    status.hdma_cycle_count = 0;
+    z = 0;
+    if(!run_state.dma) {
+      exec_cycle();
+      status.hdma_state = HDMASTATE_IDMASYNC2;
+    } else {
+      status.hdma_state = HDMASTATE_IDMASYNC3;
+    }
+    break;
+  case HDMASTATE_IDMASYNC2:
+    n = 8 - dma_counter() + 8;
+    add_cycles(n);
+    status.hdma_cycle_count += n;
+    status.hdma_state = HDMASTATE_IDMASYNC3;
+    break;
+  case HDMASTATE_IDMASYNC3:
+    channel[z].hdma_active = channel[z].hdma_enabled;
+    if(channel[z].hdma_enabled) {
+      channel[z].hdma_addr = channel[z].srcaddr;
+      hdma_update(z); //updates status.hdma_cycle_count
+    }
+    if(++z < 8)break;
+    if(!run_state.dma) {
+      status.hdma_state = HDMASTATE_ICPUSYNC;
+    } else {
+      run_state.hdma = false;
+    }
+    break;
+  case HDMASTATE_ICPUSYNC:
+    exec_cycle();
+    break;
+
+  case HDMASTATE_DMASYNC:
+    status.hdma_cycle_count = 0;
+    z = 0;
+    if(!run_state.dma) {
+      exec_cycle();
+      status.hdma_state = HDMASTATE_DMASYNC2;
+    } else {
+      status.hdma_state = HDMASTATE_DMASYNC3;
+    }
+    break;
+  case HDMASTATE_DMASYNC2:
+    n = 8 - dma_counter() + 8;
+    add_cycles(n);
+    status.hdma_cycle_count += n;
+    status.hdma_state = HDMASTATE_DMASYNC3;
+    break;
+  case HDMASTATE_DMASYNC3:
+    if(channel[z].hdma_active) {
+      add_cycles(8);
+      status.hdma_cycle_count += 8;
+    }
+    if(++z < 8)break;
+    status.hdma_state = HDMASTATE_RUN;
+    break;
+  case HDMASTATE_RUN:
+    hdma_run(); //updates status.hdma_cycle_count
+    if(!run_state.dma) {
+      status.hdma_state = HDMASTATE_CPUSYNC;
+    } else {
+      run_state.hdma = false;
+    }
+    break;
+  case HDMASTATE_CPUSYNC:
+    exec_cycle();
+    break;
+  }
+}
+
+void bCPU::exec_dma() {
+int n;
+static int z;
   switch(status.dma_state) {
   case DMASTATE_DMASYNC:
+    exec_cycle();
     status.dma_state = DMASTATE_DMASYNC2;
     break;
   case DMASTATE_DMASYNC2:
     n = 8 - dma_counter() + 8;
     add_cycles(n);
     status.dma_cycle_count = n;
-      for(z=0;z<8;z++) {
-        if(channel[z].active == false)continue;
+    z = 0;
+    status.dma_state = DMASTATE_DMASYNC3;
+    break;
+  case DMASTATE_DMASYNC3:
+    if(channel[z].active == true) {
       add_cycles(8);
       status.dma_cycle_count += 8;
     }
-      status.cpu_state = CPUSTATE_DMA;
+    if(++z < 8)break;
     status.dma_state = DMASTATE_RUN;
     break;
   case DMASTATE_RUN:
-      status.dma_cycle_count += 8;
+    dma_run(); //updates status.dma_cycle_count
+    cycle_edge();
     break;
   case DMASTATE_CPUSYNC:
-      status.cpu_state = CPUSTATE_RUN;
-      status.dma_state = DMASTATE_CPUSYNC2;
+    exec_cycle();
     break;
-    case DMASTATE_CPUSYNC2:
-      c = status.cycle_count;
-      z = c - (status.dma_cycle_count % c);
-      if(!z)z = c;
-      add_cycles(z);
-      status.dma_state = DMASTATE_STOP;
-      break;
-    }
   }
 }
 
 void bCPU::exec_cycle() {
-//on first cycle?
-  if(status.cycle_pos == 0) {
-    snes->notify(SNES::CPU_EXEC_OPCODE_BEGIN);
-    status.opcode = op_read();
-    status.cycle_pos = 1;
+//irq active? run one bus cycle of the irq event and return
+  if(run_state.irq) {
+    irq_run();
     return;
   }
 
+  if(status.cycle_pos) {
     (this->*optbl[status.opcode])();
+  #ifdef DEBUGGER
     if(status.cycle_pos == 0) {
       snes->notify(SNES::CPU_EXEC_OPCODE_END);
     }
+  #endif
+    return;
+  }
+
+//on first cycle?
+#ifdef DEBUGGER
+  snes->notify(SNES::CPU_EXEC_OPCODE_BEGIN);
+#endif
+  status.opcode = op_read();
+  status.cycle_pos = 1;
 }
 
 //only return true when we are on an opcode edge
 bool bCPU::in_opcode() {
   return (status.cycle_pos != 0);
 }
-
-void bCPU::init_op_tables() {
-#include "bcpu_optable.cpp"
-}

src/cpu/bcpu/bcpu_int.cpp

@@ -1,43 +1,64 @@
 /*
 [IRQ cycles]
-  [1] pbr,pc ; opcode
-  [2] pbr,pc ; io
-  [3] 0,s    ; pbr
-  [4] 0,s-1  ; pch
-  [5] 0,s-2  ; pcl
-  [6] 0,s-3  ; p
-  [7] 0,va   ; aavl
-  [8] 0,va+1 ; aavh
+  [0] pbr,pc ; opcode
+  [1] pbr,pc ; io
+  [2] 0,s    ; pbr
+  [3] 0,s-1  ; pch
+  [4] 0,s-2  ; pcl
+  [5] 0,s-3  ; p
+  [6] 0,va   ; aavl
+  [7] 0,va+1 ; aavh
 */
-void bCPU::irq(uint16 addr) {
+void bCPU::irq_run() {
 //WDC documentation is incorrect, first cycle
 //is a memory read fetch from PBR:PC
-  add_cycles(mem_bus->speed(regs.pc.d));
-  add_cycles(6);
+  switch(status.cycle_pos++) {
+  case 0:
+  //read from PBR:PC, but do not increment PC counter
+    mem_read(regs.pc.d);
+    break;
+  case 1:
+    cpu_io();
+    if(regs.e)status.cycle_pos++;
+    break;
+  case 2:
     stack_write(regs.pc.b);
+    break;
+  case 3:
     stack_write(regs.pc.h);
+    break;
+  case 4:
     stack_write(regs.pc.l);
-  stack_write(regs.p);
-  rd.l = op_read(OPMODE_ADDR, addr);
-  rd.h = op_read(OPMODE_ADDR, addr + 1);
-
+    break;
+  case 5:
+  //emulation-mode irqs clear brk bit 0x10
+    stack_write((regs.e) ? (regs.p & ~0x10) : regs.p);
+    break;
+  case 6:
+  //todo: test if NMI can override IRQ here...
+    rd.l = op_read(OPMODE_ADDR, aa.w);
     regs.pc.b = 0x00;
-  regs.pc.w = rd.w;
     regs.p.i  = 1;
     regs.p.d  = 0;
-
-//let debugger know the new IRQ opcode address
+    break;
+  case 7:
+    rd.h = op_read(OPMODE_ADDR, aa.w + 1);
+    regs.pc.w = rd.w;
+  #ifdef DEBUGGER
+  //let debugger know the new IRQ opcode address
     snes->notify(SNES::CPU_EXEC_OPCODE_END);
+  #endif
+    status.cycle_pos = 0;
+    run_state.irq = false;
+    break;
+  }
 }
 
 bool bCPU::nmi_test() {
   if(time.nmi_transition == 0)return false;
   time.nmi_transition = 0;
 
-  if(status.cpu_state == CPUSTATE_WAI) {
-    status.cpu_state = CPUSTATE_RUN;
-  }
-
+  run_state.wai = false;
   return true;
 }
 
@@ -61,10 +82,7 @@ bool bCPU::irq_test() {
 _true:
   time.irq_transition = 0;
 
-  if(status.cpu_state == CPUSTATE_WAI) {
-    status.cpu_state = CPUSTATE_RUN;
-  }
-
+  run_state.wai = false;
   if(regs.p.i)return false;
   return true;
 }

src/cpu/bcpu/bcpu_mmio.cpp

@@ -2,9 +2,10 @@ void bCPU::mmio_reset() {
 //$2181-$2183
   status.wram_addr = 0x000000;
 
-//$4016
-  status.joypad1_strobe_value = 0x00;
+//$4016-$4017
+  status.joypad_strobe_latch = 0;
   status.joypad1_read_pos    = 0;
+  status.joypad2_read_pos    = 0;
 
 //$4200
   status.nmi_enabled      = false;
@@ -16,16 +17,16 @@ void bCPU::mmio_reset() {
   status.pio = 0xff;
 
 //$4202-$4203
-  status.mul_a = 0x00;
-  status.mul_b = 0x00;
+  status.mul_a = 0xff;
+  status.mul_b = 0xff;
 
 //$4204-$4206
-  status.div_a = 0x0000;
-  status.div_b = 0x00;
+  status.div_a = 0xffff;
+  status.div_b = 0xff;
 
 //$4207-$420a
-  status.hirq_pos = 0;
-  status.virq_pos = 0;
+  status.hirq_pos = 0x01ff;
+  status.virq_pos = 0x01ff;
 
 //$4214-$4217
   status.r4214 = 0x0000;
@@ -35,7 +36,7 @@ void bCPU::mmio_reset() {
 //WMDATA
 uint8 bCPU::mmio_r2180() {
 uint8 r;
-  r = mem_bus->read(0x7e0000 | status.wram_addr);
+  r = r_mem->read(0x7e0000 | status.wram_addr);
   status.wram_addr++;
   status.wram_addr &= 0x01ffff;
   return r;
@@ -57,26 +58,30 @@ uint8 bCPU::mmio_r4016() {
 uint8 r;
   r = regs.mdr & 0xfc;
 
-  if(status.joypad1_strobe_value == 1) {
+  if(status.joypad_strobe_latch == 1) {
     r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_B);
   } else {
     switch(status.joypad1_read_pos) {
-    case  0:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_B);     break;
-    case  1:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_Y);     break;
-    case  2:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_SELECT);break;
-    case  3:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_START); break;
-    case  4:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_UP);    break;
-    case  5:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_DOWN);  break;
-    case  6:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_LEFT);  break;
-    case  7:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_RIGHT); break;
-    case  8:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_A);     break;
-    case  9:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_X);     break;
-    case 10:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_L);     break;
-    case 11:r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_R);     break;
-    case 16:r |= 1;break; //joypad connected bit
-    default:r |= 1;break; //after 16th read, all subsequent reads return 1
+    case  0: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_B);      break;
+    case  1: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_Y);      break;
+    case  2: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_SELECT); break;
+    case  3: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_START);  break;
+    case  4: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_UP);     break;
+    case  5: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_DOWN);   break;
+    case  6: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_LEFT);   break;
+    case  7: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_RIGHT);  break;
+    case  8: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_A);      break;
+    case  9: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_X);      break;
+    case 10: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_L);      break;
+    case 11: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD1, SNES::JOYPAD_R);      break;
+    case 12: break;
+    case 13: break;
+    case 14: break;
+    case 15: break; //bits 12-15 always return 0
+  //all subsequent reads return joypad connection status
+    case 16: r |= 1; break; //joypad connected bit
     }
-    if(++status.joypad1_read_pos > 17)status.joypad1_read_pos = 17;
+    if(++status.joypad1_read_pos > 16)status.joypad1_read_pos = 16;
   }
 
   return r;
@@ -84,13 +89,39 @@ uint8 r;
 
 //JOYSER1
 //7-5 = MDR
-//4-2 = Always 1
+//4-2 = Always 1 (pins are connected to GND)
 //1-0 = Joypad serial data
 uint8 bCPU::mmio_r4017() {
 uint8 r;
   r  = regs.mdr & 0xe0;
   r |= 0x1c;
 
+  if(status.joypad_strobe_latch == 1) {
+    r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_B);
+  } else {
+    switch(status.joypad2_read_pos) {
+    case  0: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_B);      break;
+    case  1: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_Y);      break;
+    case  2: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_SELECT); break;
+    case  3: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_START);  break;
+    case  4: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_UP);     break;
+    case  5: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_DOWN);   break;
+    case  6: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_LEFT);   break;
+    case  7: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_RIGHT);  break;
+    case  8: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_A);      break;
+    case  9: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_X);      break;
+    case 10: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_L);      break;
+    case 11: r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_R);      break;
+    case 12: break;
+    case 13: break;
+    case 14: break;
+    case 15: break; //bits 12-15 always return 0
+  //all subsequent reads return joypad connection status
+    case 16: r |= 1; break; //joypad connected bit
+    }
+    if(++status.joypad2_read_pos > 16)status.joypad2_read_pos = 16;
+  }
+
   return r;
 }
 
@@ -206,6 +237,36 @@ uint16 v = vcounter();
   return r;
 }
 
+//JOY2L
+uint8 bCPU::mmio_r421a() {
+uint8  r = 0x00;
+uint16 v = vcounter();
+  if(status.auto_joypad_poll == false)return 0x00; //can't read joypad if auto polling not enabled
+//if(v >= 225 && v <= 227)return 0x00; //can't read joypad while SNES is polling input
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_A) << 7;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_X) << 6;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_L) << 5;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_R) << 4;
+  return r;
+}
+
+//JOY2H
+uint8 bCPU::mmio_r421b() {
+uint8  r = 0x00;
+uint16 v = vcounter();
+  if(status.auto_joypad_poll == false)return 0x00; //can't read joypad if auto polling not enabled
+//if(v >= 225 && v <= 227)return 0x00; //can't read joypad while SNES is polling input
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_B)      << 7;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_Y)      << 6;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_SELECT) << 5;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_START)  << 4;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_UP)     << 3;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_DOWN)   << 2;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_LEFT)   << 1;
+  r |= (uint8)snes->get_input_status(SNES::DEV_JOYPAD2, SNES::JOYPAD_RIGHT);
+  return r;
+}
+
 //DMAPx
 uint8 bCPU::mmio_r43x0(uint8 i) {
   return channel[i].dmap;
@@ -266,61 +327,63 @@ uint8 bCPU::mmio_r43xb(uint8 i) {
   return channel[i].hdma_unknown;
 }
 
-uint8 bCPUMMIO::read(uint32 addr) {
-uint i;
+uint8 bCPU::mmio_read(uint16 addr) {
 //APU
   if(addr >= 0x2140 && addr <= 0x217f) {
-    return apu->port_read(addr & 3);
+    return r_apu->port_read(addr & 3);
   }
 
 //HDMA
   if(addr >= 0x4300 && addr <= 0x437f) {
-    i = (addr >> 4) & 7;
+  uint i = (addr >> 4) & 7;
     switch(addr & 0xf) {
-    case 0x0:return cpu->mmio_r43x0(i);
-    case 0x1:return cpu->mmio_r43x1(i);
-    case 0x2:return cpu->mmio_r43x2(i);
-    case 0x3:return cpu->mmio_r43x3(i);
-    case 0x4:return cpu->mmio_r43x4(i);
-    case 0x5:return cpu->mmio_r43x5(i);
-    case 0x6:return cpu->mmio_r43x6(i);
-    case 0x7:return cpu->mmio_r43x7(i);
-    case 0x8:return cpu->mmio_r43x8(i);
-    case 0x9:return cpu->mmio_r43x9(i);
-    case 0xa:return cpu->mmio_r43xa(i);
-    case 0xb:return cpu->mmio_r43xb(i);
-    case 0xc:return cpu->regs.mdr; //unmapped
-    case 0xd:return cpu->regs.mdr; //unmapped
-    case 0xe:return cpu->regs.mdr; //unmapped
-    case 0xf:return cpu->mmio_r43xb(i); //mirror of 43xb
+    case 0x0: return mmio_r43x0(i);
+    case 0x1: return mmio_r43x1(i);
+    case 0x2: return mmio_r43x2(i);
+    case 0x3: return mmio_r43x3(i);
+    case 0x4: return mmio_r43x4(i);
+    case 0x5: return mmio_r43x5(i);
+    case 0x6: return mmio_r43x6(i);
+    case 0x7: return mmio_r43x7(i);
+    case 0x8: return mmio_r43x8(i);
+    case 0x9: return mmio_r43x9(i);
+    case 0xa: return mmio_r43xa(i);
+    case 0xb: return mmio_r43xb(i);
+    case 0xc: return regs.mdr; //unmapped
+    case 0xd: return regs.mdr; //unmapped
+    case 0xe: return regs.mdr; //unmapped
+    case 0xf: return mmio_r43xb(i); //mirror of 43xb
     }
   }
 
   switch(addr) {
-  case 0x2180:return cpu->mmio_r2180(); //WMDATA
-  case 0x4016:return cpu->mmio_r4016(); //JOYSER0
-  case 0x4017:return cpu->mmio_r4017(); //JOYSER1
-  case 0x4210:return cpu->mmio_r4210(); //RDNMI
-  case 0x4211:return cpu->mmio_r4211(); //TIMEUP
-  case 0x4212:return cpu->mmio_r4212(); //HVBJOY
-  case 0x4213:return cpu->mmio_r4213(); //RDIO
-  case 0x4214:return cpu->mmio_r4214(); //RDDIVL
-  case 0x4215:return cpu->mmio_r4215(); //RDDIVH
-  case 0x4216:return cpu->mmio_r4216(); //RDMPYL
-  case 0x4217:return cpu->mmio_r4217(); //RDMPYH
-  case 0x4218:return cpu->mmio_r4218(); //JOY1L
-  case 0x4219:return cpu->mmio_r4219(); //JOY1H
-  case 0x421a:case 0x421b:case 0x421c:case 0x421d:case 0x421e:case 0x421f:return 0x00;
-case 0x4000:dprintf("* 4000 read at %3d,%4d <%d>", cpu->time.v, cpu->time.hc, cpu->status.cycle_count);break;
-case 0x4200:dprintf("* 4200 read at %3d,%4d", cpu->time.v, cpu->time.hc);break;
+  case 0x2180: return mmio_r2180(); //WMDATA
+  case 0x4016: return mmio_r4016(); //JOYSER0
+  case 0x4017: return mmio_r4017(); //JOYSER1
+  case 0x4210: return mmio_r4210(); //RDNMI
+  case 0x4211: return mmio_r4211(); //TIMEUP
+  case 0x4212: return mmio_r4212(); //HVBJOY
+  case 0x4213: return mmio_r4213(); //RDIO
+  case 0x4214: return mmio_r4214(); //RDDIVL
+  case 0x4215: return mmio_r4215(); //RDDIVH
+  case 0x4216: return mmio_r4216(); //RDMPYL
+  case 0x4217: return mmio_r4217(); //RDMPYH
+  case 0x4218: return mmio_r4218(); //JOY1L
+  case 0x4219: return mmio_r4219(); //JOY1H
+  case 0x421a: return mmio_r421a(); //JOY2L
+  case 0x421b: return mmio_r421b(); //JOY2H
+  case 0x421c: return 0x00;
+  case 0x421d: return 0x00;
+  case 0x421e: return 0x00;
+  case 0x421f: return 0x00;
   }
 
-  return cpu->regs.mdr;
+  return regs.mdr;
 }
 
 //WMDATA
 void bCPU::mmio_w2180(uint8 value) {
-  mem_bus->write(0x7e0000 | status.wram_addr, value);
+  r_mem->write(0x7e0000 | status.wram_addr, value);
   status.wram_addr++;
   status.wram_addr &= 0x01ffff;
 }
@@ -344,20 +407,26 @@ void bCPU::mmio_w2183(uint8 value) {
 }
 
 //JOYSER0
+//bit 0 is shared between JOYSER0 and JOYSER1, therefore
+//strobing $4016.d0 affects both controller port latches.
+//$4017 bit 0 writes are ignored.
 void bCPU::mmio_w4016(uint8 value) {
-  status.joypad1_strobe_value = (value & 1);
-  if(value == 1) {
-    snes->poll_input();
+  status.joypad_strobe_latch = bool(value & 1);
+
+  if(status.joypad_strobe_latch == 1) {
+    snes->poll_input(SNES::DEV_JOYPAD1);
+    snes->poll_input(SNES::DEV_JOYPAD2);
     status.joypad1_read_pos = 0;
+    status.joypad2_read_pos = 0;
   }
 }
 
 //NMITIMEN
 void bCPU::mmio_w4200(uint8 value) {
-  status.nmi_enabled      = !!(value & 0x80);
-  status.virq_enabled     = !!(value & 0x20);
-  status.hirq_enabled     = !!(value & 0x10);
-  status.auto_joypad_poll = !!(value & 0x01);
+  status.nmi_enabled      = bool(value & 0x80);
+  status.virq_enabled     = bool(value & 0x20);
+  status.hirq_enabled     = bool(value & 0x10);
+  status.auto_joypad_poll = bool(value & 0x01);
 
   if(time.nmi_read == 0) {
     if(time.nmi_line == 1 && !status.nmi_enabled == 0) {
@@ -378,7 +447,7 @@ void bCPU::mmio_w4200(uint8 value) {
 //WRIO
 void bCPU::mmio_w4201(uint8 value) {
   if((status.pio & 0x80) && !(value & 0x80)) {
-    ppu->latch_counters();
+    r_ppu->latch_counters();
   }
   status.pio = value;
 }
@@ -436,16 +505,15 @@ void bCPU::mmio_w420a(uint8 value) {
 
 //DMAEN
 void bCPU::mmio_w420b(uint8 value) {
-int len;
   if(value != 0x00) {
+    run_state.dma = true;
     status.dma_state = DMASTATE_DMASYNC;
   }
 
-  for(int i=0;i<8;i++) {
+  for(int i = 0; i < 8; i++) {
     if(value & (1 << i)) {
+    //DMA enable does not disable active HDMA channels
       channel[i].active     = true;
-      channel[i].hdma_enabled = false;
-      channel[i].hdma_active  = false;
       channel[i].read_index = 0;
     }
   }
@@ -453,24 +521,24 @@ int len;
 
 //HDMAEN
 void bCPU::mmio_w420c(uint8 value) {
-  for(int i=0;i<8;i++) {
-    channel[i].hdma_enabled = !!(value & (1 << i));
-    channel[i].hdma_active  = !!(value & (1 << i));
+  for(int i = 0; i < 8; i++) {
+    channel[i].hdma_enabled = bool(value & (1 << i));
+    channel[i].hdma_active  = bool(value & (1 << i));
   }
 }
 
 //MEMSEL
 void bCPU::mmio_w420d(uint8 value) {
-  mem_bus->set_speed(value & 1);
+  r_mem->set_speed(value & 1);
 }
 
 //DMAPx
 void bCPU::mmio_w43x0(uint8 value, uint8 i) {
   channel[i].dmap          = value;
-  channel[i].direction     = !!(value & 0x80);
-  channel[i].hdma_indirect = !!(value & 0x40);
-  channel[i].incmode       = (value & 0x10)?-1:1;
-  channel[i].fixedxfer     = !!(value & 0x08);
+  channel[i].direction     = bool(value & 0x80);
+  channel[i].hdma_indirect = bool(value & 0x40);
+  channel[i].incmode       = (value & 0x10) ? -1 : 1;
+  channel[i].fixedxfer     = bool(value & 0x08);
   channel[i].xfermode      = value & 7;
 }
 
@@ -529,61 +597,56 @@ void bCPU::mmio_w43xb(uint8 value, uint8 i) {
   channel[i].hdma_unknown = value;
 }
 
-void bCPUMMIO::write(uint32 addr, uint8 value) {
-uint8 i;
+void bCPU::mmio_write(uint16 addr, uint8 data) {
 //APU
   if(addr >= 0x2140 && addr <= 0x217f) {
-    cpu->port_write(addr & 3, value);
+    port_write(addr & 3, data);
     return;
   }
 
 //HDMA
   if(addr >= 0x4300 && addr <= 0x437f) {
-    i = (addr >> 4) & 7;
+  uint i = (addr >> 4) & 7;
     switch(addr & 0xf) {
-    case 0x0:cpu->mmio_w43x0(value, i);return;
-    case 0x1:cpu->mmio_w43x1(value, i);return;
-    case 0x2:cpu->mmio_w43x2(value, i);return;
-    case 0x3:cpu->mmio_w43x3(value, i);return;
-    case 0x4:cpu->mmio_w43x4(value, i);return;
-    case 0x5:cpu->mmio_w43x5(value, i);return;
-    case 0x6:cpu->mmio_w43x6(value, i);return;
-    case 0x7:cpu->mmio_w43x7(value, i);return;
-    case 0x8:cpu->mmio_w43x8(value, i);return;
-    case 0x9:cpu->mmio_w43x9(value, i);return;
-    case 0xa:cpu->mmio_w43xa(value, i);return;
-    case 0xb:cpu->mmio_w43xb(value, i);return;
-    case 0xc:return; //unmapped
-    case 0xd:return; //unmapped
-    case 0xe:return; //unmapped
-    case 0xf:cpu->mmio_w43xb(value, i);return; //mirror of 43xb
+    case 0x0: mmio_w43x0(data, i); return;
+    case 0x1: mmio_w43x1(data, i); return;
+    case 0x2: mmio_w43x2(data, i); return;
+    case 0x3: mmio_w43x3(data, i); return;
+    case 0x4: mmio_w43x4(data, i); return;
+    case 0x5: mmio_w43x5(data, i); return;
+    case 0x6: mmio_w43x6(data, i); return;
+    case 0x7: mmio_w43x7(data, i); return;
+    case 0x8: mmio_w43x8(data, i); return;
+    case 0x9: mmio_w43x9(data, i); return;
+    case 0xa: mmio_w43xa(data, i); return;
+    case 0xb: mmio_w43xb(data, i); return;
+    case 0xc: return; //unmapped
+    case 0xd: return; //unmapped
+    case 0xe: return; //unmapped
+    case 0xf: mmio_w43xb(data, i); return; //mirror of 43xb
     }
   }
 
   switch(addr) {
-  case 0x2180:cpu->mmio_w2180(value);return; //WMDATA
-  case 0x2181:cpu->mmio_w2181(value);return; //WMADDL
-  case 0x2182:cpu->mmio_w2182(value);return; //WMADDM
-  case 0x2183:cpu->mmio_w2183(value);return; //WMADDH
-  case 0x4016:cpu->mmio_w4016(value);return; //JOYSER0
-  case 0x4200:cpu->mmio_w4200(value);return; //NMITIMEN
-  case 0x4201:cpu->mmio_w4201(value);return; //WRIO
-  case 0x4202:cpu->mmio_w4202(value);return; //WRMPYA
-  case 0x4203:cpu->mmio_w4203(value);return; //WRMPYB
-  case 0x4204:cpu->mmio_w4204(value);return; //WRDIVL
-  case 0x4205:cpu->mmio_w4205(value);return; //WRDIVH
-  case 0x4206:cpu->mmio_w4206(value);return; //WRDIVB
-  case 0x4207:cpu->mmio_w4207(value);return; //HTIMEL
-  case 0x4208:cpu->mmio_w4208(value);return; //HTIMEH
-  case 0x4209:cpu->mmio_w4209(value);return; //VTIMEL
-  case 0x420a:cpu->mmio_w420a(value);return; //VTIMEH
-  case 0x420b:cpu->mmio_w420b(value);return; //DMAEN
-  case 0x420c:cpu->mmio_w420c(value);return; //HDMAEN
-  case 0x420d:cpu->mmio_w420d(value);return; //MEMSEL
-case 0x4000:dprintf("* 4000 write at %3d,%4d", cpu->time.v, cpu->time.hc);break;
+  case 0x2180: mmio_w2180(data); return; //WMDATA
+  case 0x2181: mmio_w2181(data); return; //WMADDL
+  case 0x2182: mmio_w2182(data); return; //WMADDM
+  case 0x2183: mmio_w2183(data); return; //WMADDH
+  case 0x4016: mmio_w4016(data); return; //JOYSER0
+  case 0x4017: return; //unmapped
+  case 0x4200: mmio_w4200(data); return; //NMITIMEN
+  case 0x4201: mmio_w4201(data); return; //WRIO
+  case 0x4202: mmio_w4202(data); return; //WRMPYA
+  case 0x4203: mmio_w4203(data); return; //WRMPYB
+  case 0x4204: mmio_w4204(data); return; //WRDIVL
+  case 0x4205: mmio_w4205(data); return; //WRDIVH
+  case 0x4206: mmio_w4206(data); return; //WRDIVB
+  case 0x4207: mmio_w4207(data); return; //HTIMEL
+  case 0x4208: mmio_w4208(data); return; //HTIMEH
+  case 0x4209: mmio_w4209(data); return; //VTIMEL
+  case 0x420a: mmio_w420a(data); return; //VTIMEH
+  case 0x420b: mmio_w420b(data); return; //DMAEN
+  case 0x420c: mmio_w420c(data); return; //HDMAEN
+  case 0x420d: mmio_w420d(data); return; //MEMSEL
   }
 }
-
-bCPUMMIO::bCPUMMIO(bCPU *_cpu) {
-  cpu = _cpu;
-}

src/cpu/bcpu/cc.bat

@@ -1,3 +0,0 @@
-cl /ML /O2 bcpugen.cpp
-@pause
-@del *.obj

src/cpu/bcpu/clean.bat

@@ -1,8 +0,0 @@
-@del *.exe
-@del bcpu_op_misc.cpp
-@del bcpu_op_pc.cpp
-@del bcpu_op_read.cpp
-@del bcpu_op_rmw.cpp
-@del bcpu_op_write.cpp
-@del bcpu_optable.cpp
-@del bcpu_op.h

src/cpu/bcpu/core/bcpugen.cpp

@@ -0,0 +1,18 @@
+#define CLASS_NAME "bCPU"
+#include "../../../lib/opgen.cpp"
+
+int main() {
+  fph = fopen("op.h", "wb");
+  fpt = fopen("optable.cpp", "wb");
+
+  generate("op_read.cpp",  "op_read.b");
+  generate("op_rmw.cpp",   "op_rmw.b");
+  generate("op_write.cpp", "op_write.b");
+  generate("op_pc.cpp",    "op_pc.b");
+  generate("op_misc.cpp",  "op_misc.b");
+
+  fclose(fph);
+  fclose(fpt);
+
+  return 0;
+}

src/cpu/bcpu/core/cc.bat

@@ -0,0 +1,3 @@
+cl /O2 /wd4996 bcpugen.cpp
+@pause
+@del *.obj

src/cpu/bcpu/core/clean.bat

@@ -0,0 +1,8 @@
+@del *.exe
+@del op_misc.cpp
+@del op_pc.cpp
+@del op_read.cpp
+@del op_rmw.cpp
+@del op_write.cpp
+@del optable.cpp
+@del op.h

src/cpu/bcpu/core/core.cpp

@@ -0,0 +1,90 @@
+#include "opfn.cpp"
+#include "op_read.cpp"
+#include "op_rmw.cpp"
+#include "op_write.cpp"
+#include "op_pc.cpp"
+#include "op_misc.cpp"
+
+void bCPU::cpu_c2() {
+  if(regs.d.l != 0x00) {
+    cpu_io();
+  }
+}
+
+void bCPU::cpu_c4(uint16 x, uint16 y) {
+  if(!regs.p.x && (x & 0xff00) != (y & 0xff00)) {
+    cpu_io();
+  }
+}
+
+void bCPU::cpu_c6(uint16 addr) {
+  if(regs.e && (regs.pc.w & 0xff00) != (addr & 0xff00)) {
+    cpu_io();
+  }
+}
+
+uint32 bCPU::op_addr(uint8 mode, uint32 addr) {
+  switch(mode) {
+  case OPMODE_ADDR:
+    addr &= 0xffff;
+    break;
+  case OPMODE_LONG:
+    addr &= 0xffffff;
+    break;
+  case OPMODE_DBR:
+    addr = ((regs.db << 16) + addr) & 0xffffff;
+    break;
+  case OPMODE_PBR:
+    addr &= 0xffff;
+    addr = (regs.pc.b << 16) + addr;
+    break;
+  case OPMODE_DP:
+    addr &= 0xffff;
+    addr = (regs.d + addr) & 0xffff;
+    break;
+  case OPMODE_SP:
+    addr &= 0xffff;
+    addr = (regs.s + addr) & 0xffff;
+    break;
+  }
+  return addr;
+}
+
+uint8 bCPU::op_read() {
+uint8 r;
+  r = mem_read(regs.pc.d);
+  regs.pc.w++;
+  return r;
+}
+
+uint8 bCPU::op_read(uint8 mode, uint32 addr) {
+  addr = op_addr(mode, addr);
+  return mem_read(addr);
+}
+
+void bCPU::op_write(uint8 mode, uint32 addr, uint8 value) {
+  addr = op_addr(mode, addr);
+  mem_write(addr, value);
+}
+
+uint8 bCPU::stack_read() {
+  if(regs.e) {
+    regs.s.l++;
+  } else {
+    regs.s.w++;
+  }
+  return mem_read(regs.s);
+}
+
+void bCPU::stack_write(uint8 value) {
+  mem_write(regs.s, value);
+  if(regs.e) {
+    regs.s.l--;
+  } else {
+    regs.s.w--;
+  }
+}
+
+void bCPU::init_op_tables() {
+  #include "optable.cpp"
+}

src/cpu/bcpu/core/core.h

@@ -0,0 +1,74 @@
+/* External functions:
+ *   void   last_cycle();
+ *   void   cpu_io();
+ *   uint8  mem_read(uint32 addr);
+ *   void   mem_write(uint32 addr, uint8 value);
+ */
+
+void (bCPU::*optbl[256])();
+
+CPUReg24 aa, rd;
+uint8    dp, sp;
+
+//op_read
+  inline void   op_adc_b();
+  inline void   op_adc_w();
+  inline void   op_and_b();
+  inline void   op_and_w();
+  inline void   op_bit_b();
+  inline void   op_bit_w();
+  inline void   op_cmp_b();
+  inline void   op_cmp_w();
+  inline void   op_cpx_b();
+  inline void   op_cpx_w();
+  inline void   op_cpy_b();
+  inline void   op_cpy_w();
+  inline void   op_eor_b();
+  inline void   op_eor_w();
+  inline void   op_lda_b();
+  inline void   op_lda_w();
+  inline void   op_ldx_b();
+  inline void   op_ldx_w();
+  inline void   op_ldy_b();
+  inline void   op_ldy_w();
+  inline void   op_ora_b();
+  inline void   op_ora_w();
+  inline void   op_sbc_b();
+  inline void   op_sbc_w();
+//op_rmw
+  inline void   op_inc_b();
+  inline void   op_inc_w();
+  inline void   op_dec_b();
+  inline void   op_dec_w();
+  inline void   op_asl_b();
+  inline void   op_asl_w();
+  inline void   op_lsr_b();
+  inline void   op_lsr_w();
+  inline void   op_rol_b();
+  inline void   op_rol_w();
+  inline void   op_ror_b();
+  inline void   op_ror_w();
+  inline void   op_trb_b();
+  inline void   op_trb_w();
+  inline void   op_tsb_b();
+  inline void   op_tsb_w();
+
+  inline void   cpu_c2();
+  inline void   cpu_c4(uint16 x, uint16 y);
+  inline void   cpu_c6(uint16 addr);
+
+enum {
+  OPMODE_ADDR, OPMODE_LONG,
+  OPMODE_DBR,  OPMODE_PBR,
+  OPMODE_DP,   OPMODE_SP
+};
+  inline uint32 op_addr(uint8 mode, uint32 addr);
+  inline uint8  op_read();
+  inline uint8  op_read(uint8 mode, uint32 addr);
+  inline void   op_write(uint8 mode, uint32 addr, uint8 value);
+  inline uint8  stack_read();
+  inline void   stack_write(uint8 value);
+
+  inline void   init_op_tables();
+
+#include "op.h"

src/cpu/bcpu/core/op_misc.b

@@ -42,18 +42,18 @@ cop(0x02, 0xfff4, 0xfff5, 0xffe4, 0xffe5) {
 3:stack_write(regs.pc.h);
 4:stack_write(regs.pc.l);
 5:stack_write(regs.p);
-6:rd.l = op_read(OPMODE_LONG, (regs.e)?$1:$3);
-7:last_cycle();
-  rd.h = op_read(OPMODE_LONG, (regs.e)?$2:$4);
+6:rd.l = op_read(OPMODE_LONG, (regs.e) ? $1 : $3);
   regs.pc.b = 0x00;
-  regs.pc.w = rd.w;
   regs.p.i  = 1;
   regs.p.d  = 0;
+7:last_cycle();
+  rd.h = op_read(OPMODE_LONG, (regs.e) ? $2 : $4);
+  regs.pc.w = rd.w;
 }
 
 stp(0xdb) {
 1:cpu_io();
-  status.cpu_state = CPUSTATE_STP;
+  run_state.stp = true;
 2:last_cycle();
   cpu_io();
   regs.pc.w--;
@@ -61,12 +61,19 @@ stp(0xdb) {
 
 wai(0xcb) {
 1:cpu_io();
-  status.cpu_state = CPUSTATE_WAI;
+  run_state.wai = true;
 2:last_cycle();
   cpu_io();
-  if(status.cpu_state == CPUSTATE_WAI) {
-    regs.pc.w--;
-  }
+//no wakeup delay if last_cycle() cancelled wai
+  if(run_state.wai == false)end;
+3:last_cycle();
+  cpu_io();
+//sleep another i/o cycle
+//note: this should alert the debugger that wai is continuing...
+  if(run_state.wai == true)status.cycle_pos--;
+//wai wakeup delay (one i/o cycle)
+4:last_cycle();
+  cpu_io();
 }
 
 xce(0xfb) {
@@ -182,12 +189,8 @@ txs(0x9a) {
   cpu_io();
   if(regs.e) {
     regs.s.l = regs.x.l;
-    regs.p.n = !!(regs.s.l & 0x80);
-    regs.p.z = (regs.s.l == 0);
   } else {
     regs.s.w = regs.x.w;
-    regs.p.n = !!(regs.s.w & 0x8000);
-    regs.p.z = (regs.s.w == 0);
   }
 }
 

src/cpu/bcpu/core/op_pc.b

@@ -126,7 +126,8 @@ rti(0x40) {
     regs.y.h = 0x00;
   }
 4:rd.l = stack_read();
-5:rd.h = stack_read();
+5:if(regs.e)last_cycle();
+  rd.h = stack_read();
   if(regs.e) {
     regs.pc.w = rd.w;
     end;

src/cpu/bcpu/core/op_pc.cpp

@@ -1,6 +1,6 @@
 void bCPU::op_bcc() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     if(!!regs.p.c)last_cycle();
     rd.l = op_read();
     if(!regs.p.c) {
@@ -9,21 +9,21 @@ void bCPU::op_bcc() {
     } else {
       status.cycle_pos = 0;
     }
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_bcs() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     if(!regs.p.c)last_cycle();
     rd.l = op_read();
     if(regs.p.c) {
@@ -32,21 +32,21 @@ void bCPU::op_bcs() {
     } else {
       status.cycle_pos = 0;
     }
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_bne() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     if(!!regs.p.z)last_cycle();
     rd.l = op_read();
     if(!regs.p.z) {
@@ -55,21 +55,21 @@ void bCPU::op_bne() {
     } else {
       status.cycle_pos = 0;
     }
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_beq() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     if(!regs.p.z)last_cycle();
     rd.l = op_read();
     if(regs.p.z) {
@@ -78,21 +78,21 @@ void bCPU::op_beq() {
     } else {
       status.cycle_pos = 0;
     }
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_bpl() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     if(!!regs.p.n)last_cycle();
     rd.l = op_read();
     if(!regs.p.n) {
@@ -101,21 +101,21 @@ void bCPU::op_bpl() {
     } else {
       status.cycle_pos = 0;
     }
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_bmi() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     if(!regs.p.n)last_cycle();
     rd.l = op_read();
     if(regs.p.n) {
@@ -124,21 +124,21 @@ void bCPU::op_bmi() {
     } else {
       status.cycle_pos = 0;
     }
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_bvc() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     if(!!regs.p.v)last_cycle();
     rd.l = op_read();
     if(!regs.p.v) {
@@ -147,21 +147,21 @@ void bCPU::op_bvc() {
     } else {
       status.cycle_pos = 0;
     }
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_bvs() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     if(!regs.p.v)last_cycle();
     rd.l = op_read();
     if(regs.p.v) {
@@ -170,313 +170,314 @@ void bCPU::op_bvs() {
     } else {
       status.cycle_pos = 0;
     }
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_bra() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     rd.l = op_read();
     aa.w = regs.pc.d + (int8)rd.l;
     regs.pc.w = aa.w;
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c6(aa.w);
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_brl() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     rd.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     cpu_io();
     regs.pc.w = regs.pc.d + (int16)rd.w;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_jmp_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     rd.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     last_cycle();
     rd.h = op_read();
     regs.pc.w = rd.w;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_jmp_long() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     rd.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     rd.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     last_cycle();
     rd.b = op_read();
     regs.pc.d = rd.d & 0xffffff;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_jmp_iaddr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd.l = op_read(OPMODE_ADDR, aa.w);
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     rd.h = op_read(OPMODE_ADDR, aa.w + 1);
     regs.pc.w = rd.w;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_jmp_iaddrx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_io();
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd.l = op_read(OPMODE_PBR, aa.w + regs.x.w);
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     rd.h = op_read(OPMODE_PBR, aa.w + regs.x.w + 1);
     regs.pc.w = rd.w;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_jmp_iladdr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd.l = op_read(OPMODE_ADDR, aa.w);
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd.h = op_read(OPMODE_ADDR, aa.w + 1);
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     rd.b = op_read(OPMODE_ADDR, aa.w + 2);
     regs.pc.d = rd.d & 0xffffff;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_jsr_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_io();
-    break;
-  case 4:
+    } break;
+  case 4: {
     regs.pc.w--;
     stack_write(regs.pc.h);
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     stack_write(regs.pc.l);
     regs.pc.w = aa.w;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_jsr_long() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     stack_write(regs.pc.b);
-    break;
-  case 4:
+    } break;
+  case 4: {
     cpu_io();
-    break;
-  case 5:
+    } break;
+  case 5: {
     aa.b = op_read();
-    break;
-  case 6:
+    } break;
+  case 6: {
     regs.pc.w--;
     stack_write(regs.pc.h);
-    break;
-  case 7:
+    } break;
+  case 7: {
     last_cycle();
     stack_write(regs.pc.l);
     regs.pc.d = aa.d & 0xffffff;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_jsr_iaddrx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     stack_write(regs.pc.h);
-    break;
-  case 3:
+    } break;
+  case 3: {
     stack_write(regs.pc.l);
-    break;
-  case 4:
+    } break;
+  case 4: {
     aa.h = op_read();
-    break;
-  case 5:
+    } break;
+  case 5: {
     cpu_io();
-    break;
-  case 6:
+    } break;
+  case 6: {
     rd.l = op_read(OPMODE_PBR, aa.w + regs.x.w);
-    break;
-  case 7:
+    } break;
+  case 7: {
     last_cycle();
     rd.h = op_read(OPMODE_PBR, aa.w + regs.x.w + 1);
     regs.pc.w = rd.w;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_rti() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     cpu_io();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_io();
-    break;
-  case 3:
+    } break;
+  case 3: {
     regs.p = stack_read();
     if(regs.e)regs.p |= 0x30;
     if(regs.p.x) {
       regs.x.h = 0x00;
       regs.y.h = 0x00;
     }
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd.l = stack_read();
-    break;
-  case 5:
+    } break;
+  case 5: {
+    if(regs.e)last_cycle();
     rd.h = stack_read();
     if(regs.e) {
       regs.pc.w = rd.w;
       status.cycle_pos = 0;
     }
-    break;
-  case 6:
+    } break;
+  case 6: {
     last_cycle();
     rd.b = stack_read();
     regs.pc.d = rd.d & 0xffffff;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_rts() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     cpu_io();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_io();
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd.l = stack_read();
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd.h = stack_read();
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     cpu_io();
     regs.pc.w = rd.w;
     regs.pc.w++;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_rtl() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     cpu_io();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_io();
-    break;
-  case 3:
+    } break;
+  case 3: {
     rd.l = stack_read();
-    break;
-  case 4:
+    } break;
+  case 4: {
     rd.h = stack_read();
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     rd.b = stack_read();
     regs.pc.d = rd.d & 0xffffff;
     regs.pc.w++;
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 

src/cpu/bcpu/core/op_write.cpp

@@ -1,582 +1,582 @@
 void bCPU::op_sta_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w,     regs.a.w);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + 1, regs.a.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_stx_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.x)last_cycle();
     op_write(OPMODE_DBR, aa.w,     regs.x.w);
     if(regs.p.x)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + 1, regs.x.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sty_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.x)last_cycle();
     op_write(OPMODE_DBR, aa.w,     regs.y.w);
     if(regs.p.x)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + 1, regs.y.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_stz_addr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w,     0x0000);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + 1, 0x0000 >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_addrx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_c4(aa.w, aa.w + regs.x.w);
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.x.w,     regs.a.w);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.x.w + 1, regs.a.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_stz_addrx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_c4(aa.w, aa.w + regs.x.w);
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.x.w,     0x0000);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.x.w + 1, 0x0000 >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_addry() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_c4(aa.w, aa.w + regs.y.w);
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.y.w,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.y.w + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_long() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     aa.b = op_read();
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_LONG, aa.d,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_LONG, aa.d + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_longx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     aa.l = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     aa.h = op_read();
-    break;
-  case 3:
+    } break;
+  case 3: {
     aa.b = op_read();
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_LONG, aa.d + regs.x.w,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_LONG, aa.d + regs.x.w + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DP, dp,     regs.a.w);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_DP, dp + 1, regs.a.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_stx_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.x)last_cycle();
     op_write(OPMODE_DP, dp,     regs.x.w);
     if(regs.p.x)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_DP, dp + 1, regs.x.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sty_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.x)last_cycle();
     op_write(OPMODE_DP, dp,     regs.y.w);
     if(regs.p.x)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_DP, dp + 1, regs.y.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_stz_dp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DP, dp,     0x0000);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_DP, dp + 1, 0x0000 >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_io();
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DP, dp + regs.x.w,     regs.a.w);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_DP, dp + regs.x.w + 1, regs.a.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sty_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_io();
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.x)last_cycle();
     op_write(OPMODE_DP, dp + regs.x.w,     regs.y.w);
     if(regs.p.x)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_DP, dp + regs.x.w + 1, regs.y.w >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_stz_dpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_io();
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DP, dp + regs.x.w,     0x0000);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_DP, dp + regs.x.w + 1, 0x0000 >> 8);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_stx_dpy() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_io();
-    break;
-  case 4:
+    } break;
+  case 4: {
     if(regs.p.x)last_cycle();
     op_write(OPMODE_DP, dp + regs.y.w,     regs.x.l);
     if(regs.p.x)status.cycle_pos = 0;
-    break;
-  case 5:
+    } break;
+  case 5: {
     last_cycle();
     op_write(OPMODE_DP, dp + regs.y.w + 1, regs.x.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_idp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     aa.l = op_read(OPMODE_DP, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     aa.h = op_read(OPMODE_DP, dp + 1);
-    break;
-  case 5:
+    } break;
+  case 5: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 6:
+    } break;
+  case 6: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_ildp() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     aa.l = op_read(OPMODE_DP, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     aa.h = op_read(OPMODE_DP, dp + 1);
-    break;
-  case 5:
+    } break;
+  case 5: {
     aa.b = op_read(OPMODE_DP, dp + 2);
-    break;
-  case 6:
+    } break;
+  case 6: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_LONG, aa.d,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 7:
+    } break;
+  case 7: {
     last_cycle();
     op_write(OPMODE_LONG, aa.d + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_idpx() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     cpu_io();
-    break;
-  case 4:
+    } break;
+  case 4: {
     aa.l = op_read(OPMODE_DP, dp + regs.x.w);
-    break;
-  case 5:
+    } break;
+  case 5: {
     aa.h = op_read(OPMODE_DP, dp + regs.x.w + 1);
-    break;
-  case 6:
+    } break;
+  case 6: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 7:
+    } break;
+  case 7: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_idpy() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     aa.l = op_read(OPMODE_DP, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     aa.h = op_read(OPMODE_DP, dp + 1);
-    break;
-  case 5:
+    } break;
+  case 5: {
     cpu_c4(aa.w, aa.w + regs.y.w);
-    break;
-  case 6:
+    } break;
+  case 6: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.y.w,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 7:
+    } break;
+  case 7: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.y.w + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_ildpy() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     dp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_c2();
-    break;
-  case 3:
+    } break;
+  case 3: {
     aa.l = op_read(OPMODE_DP, dp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     aa.h = op_read(OPMODE_DP, dp + 1);
-    break;
-  case 5:
+    } break;
+  case 5: {
     aa.b = op_read(OPMODE_DP, dp + 2);
-    break;
-  case 6:
+    } break;
+  case 6: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_LONG, aa.d + regs.y.w,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 7:
+    } break;
+  case 7: {
     last_cycle();
     op_write(OPMODE_LONG, aa.d + regs.y.w + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_sr() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_io();
-    break;
-  case 3:
+    } break;
+  case 3: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_SP, sp,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 4:
+    } break;
+  case 4: {
     last_cycle();
     op_write(OPMODE_SP, sp + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 
 void bCPU::op_sta_isry() {
   switch(status.cycle_pos++) {
-  case 1:
+  case 1: {
     sp = op_read();
-    break;
-  case 2:
+    } break;
+  case 2: {
     cpu_io();
-    break;
-  case 3:
+    } break;
+  case 3: {
     aa.l = op_read(OPMODE_SP, sp);
-    break;
-  case 4:
+    } break;
+  case 4: {
     aa.h = op_read(OPMODE_SP, sp + 1);
-    break;
-  case 5:
+    } break;
+  case 5: {
     cpu_io();
-    break;
-  case 6:
+    } break;
+  case 6: {
     if(regs.p.m)last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.y.w,     regs.a.l);
     if(regs.p.m)status.cycle_pos = 0;
-    break;
-  case 7:
+    } break;
+  case 7: {
     last_cycle();
     op_write(OPMODE_DBR, aa.w + regs.y.w + 1, regs.a.h);
     status.cycle_pos = 0;
-    break;
+    } break;
   }
 }
 

src/cpu/bcpu/core/opfn.cpp

@@ -1,31 +1,75 @@
 //op_read
 inline void bCPU::op_adc_b() {
 int32 r = regs.a.l + rd.l + regs.p.c;
-//bcd
   if(regs.p.d) {
-    if(((r     ) & 15) > 9)r += 6;
-    if(((r >> 4) & 15) > 9)r += 6 << 4;
+  uint8 n0 = (regs.a.l     ) & 15;
+  uint8 n1 = (regs.a.l >> 4) & 15;
+    n0 += ((rd.l) & 15) + regs.p.c;
+    if(n0 > 9) {
+      n0 -= 10;
+      n0 &= 15;
+      n1++;
+    }
+    n1 += ((rd.l >> 4) & 15);
+    if(n1 > 9) {
+      n1 -= 10;
+      n1 &= 15;
+      regs.p.c = 1;
+    } else {
+      regs.p.c = 0;
+    }
+    r = (n1 << 4) | (n0);
+  } else {
+    r = regs.a.l + rd.l + regs.p.c;
+    regs.p.c = (r > 0xff);
   }
   regs.p.n = !!(r & 0x80);
   regs.p.v = !!(~(regs.a.l ^ rd.l) & (regs.a.l ^ r) & 0x80);
   regs.p.z = ((uint8)r == 0);
-  regs.p.c = (r > 0xff);
   regs.a.l = r;
 }
 
 inline void bCPU::op_adc_w() {
-int32 r = regs.a.w + rd.w + regs.p.c;
-//bcd
+int32 r;
   if(regs.p.d) {
-    if(((r      ) & 15) > 9)r += 6;
-    if(((r >>  4) & 15) > 9)r += 6 <<  4;
-    if(((r >>  8) & 15) > 9)r += 6 <<  8;
-    if(((r >> 12) & 15) > 9)r += 6 << 12;
+  uint8 n0 = (regs.a.w      ) & 15;
+  uint8 n1 = (regs.a.w >>  4) & 15;
+  uint8 n2 = (regs.a.w >>  8) & 15;
+  uint8 n3 = (regs.a.w >> 12) & 15;
+    n0 += ((rd.w) & 15) + regs.p.c;
+    if(n0 > 9) {
+      n0 -= 10;
+      n0 &= 15;
+      n1++;
+    }
+    n1 += ((rd.w >> 4) & 15);
+    if(n1 > 9) {
+      n1 -= 10;
+      n1 &= 15;
+      n2++;
+    }
+    n2 += ((rd.w >> 8) & 15);
+    if(n2 > 9) {
+      n2 -= 10;
+      n2 &= 15;
+      n3++;
+    }
+    n3 += ((rd.w >> 12) & 15);
+    if(n3 > 9) {
+      n3 -= 10;
+      n3 &= 15;
+      regs.p.c = 1;
+    } else {
+      regs.p.c = 0;
+    }
+    r = (n3 << 12) | (n2 << 8) | (n1 << 4) | (n0);
+  } else {
+    r = regs.a.w + rd.w + regs.p.c;
+    regs.p.c = (r > 0xffff);
   }
   regs.p.n = !!(r & 0x8000);
   regs.p.v = !!(~(regs.a.w ^ rd.w) & (regs.a.w ^ r) & 0x8000);
   regs.p.z = ((uint16)r == 0);
-  regs.p.c = (r > 0xffff);
   regs.a.w = r;
 }
 
@@ -156,32 +200,70 @@ inline void bCPU::op_ora_w() {
 }
 
 inline void bCPU::op_sbc_b() {
-int32 r = regs.a.l - rd.l - !regs.p.c;
-//bcd
+int32 r;
   if(regs.p.d) {
-    if(((r     ) & 15) > 9)r -= 6;
-    if(((r >> 4) & 15) > 9)r -= 6 << 4;
+  uint8 n0 = (regs.a.l     ) & 15;
+  uint8 n1 = (regs.a.l >> 4) & 15;
+    n0 -= ((rd.l     ) & 15) + !regs.p.c;
+    n1 -= ((rd.l >> 4) & 15);
+    if(n0 > 9) {
+      n0 += 10;
+      n1--;
+    }
+    if(n1 > 9) {
+      n1 += 10;
+      regs.p.c = 0;
+    } else {
+      regs.p.c = 1;
+    }
+    r = (n1 << 4) | (n0);
+  } else {
+    r = regs.a.l - rd.l - !regs.p.c;
+    regs.p.c = (r >= 0);
   }
   regs.p.n = !!(r & 0x80);
   regs.p.v = !!((regs.a.l ^ rd.l) & (regs.a.l ^ r) & 0x80);
-  regs.p.z = ((byte)r == 0);
-  regs.p.c = (r >= 0);
+  regs.p.z = ((uint8)r == 0);
   regs.a.l = r;
 }
 
 inline void bCPU::op_sbc_w() {
-int32 r = regs.a.w - rd.w - !regs.p.c;
-//bcd
+int32 r;
   if(regs.p.d) {
-    if(((r      ) & 15) > 9)r -= 6;
-    if(((r >>  4) & 15) > 9)r -= 6 <<  4;
-    if(((r >>  8) & 15) > 9)r -= 6 <<  8;
-    if(((r >> 12) & 15) > 9)r -= 6 << 12;
+  uint8 n0 = (regs.a.w      ) & 15;
+  uint8 n1 = (regs.a.w >>  4) & 15;
+  uint8 n2 = (regs.a.w >>  8) & 15;
+  uint8 n3 = (regs.a.w >> 12) & 15;
+    n0 -= ((rd.w      ) & 15) + !regs.p.c;
+    n1 -= ((rd.w >>  4) & 15);
+    n2 -= ((rd.w >>  8) & 15);
+    n3 -= ((rd.w >> 12) & 15);
+    if(n0 > 9) {
+      n0 += 10;
+      n1--;
+    }
+    if(n1 > 9) {
+      n1 += 10;
+      n2--;
+    }
+    if(n2 > 9) {
+      n2 += 10;
+      n3--;
+    }
+    if(n3 > 9) {
+      n3 += 10;
+      regs.p.c = 0;
+    } else {
+      regs.p.c = 1;
+    }
+    r = (n3 << 12) | (n2 << 8) | (n1 << 4) | (n0);
+  } else {
+    r = regs.a.w - rd.w - !regs.p.c;
+    regs.p.c = (r >= 0);
   }
   regs.p.n = !!(r & 0x8000);
   regs.p.v = !!((regs.a.w ^ rd.w) & (regs.a.w ^ r) & 0x8000);
-  regs.p.z = ((word)r == 0);
-  regs.p.c = (r >= 0);
+  regs.p.z = ((uint16)r == 0);
   regs.a.w = r;
 }
 

src/cpu/bcpu/dma/dma.cpp

@@ -0,0 +1,265 @@
+/* used by both DMA and HDMA
+ * prevents transfer across same bus (a->a or b->b)
+ */
+void bCPU::dma_transfer_byte(bool direction, uint8 bbus, uint32 abus) {
+uint8 r;
+  if(direction == 0) {
+  //read from address bus a, write to address bus b
+
+  //DMA address bus a cannot read from or write to the following addresses:
+  //$[00-3f|80-bf]:21[00-ff] <address bus b>
+  //$[00-3f|80-bf]:43[00-7f] <DMA control registers>
+  //$[00-3f|80-bf]:420b      <DMA enable register>
+  //$[00-3f|80-bf]:420c      <HDMA enable register>
+    if((abus & 0x40ff00) == 0x2100 || (abus & 0x40ff80) == 0x4300 ||
+       (abus & 0x40ffff) == 0x420b || (abus & 0x40ffff) == 0x420c) {
+    //these invalid reads will return open bus
+      r = r_cpu->regs.mdr;
+    } else {
+      r = r_mem->read(abus);
+    }
+
+    r_mem->write(0x2100 | bbus, r);
+  } else {
+  //read from address bus b, write to address bus a
+
+  //block invalid writes, see comments above
+    r = (bbus == 0x80) ? r_cpu->regs.mdr : r_mem->read(0x2100 | bbus);
+    if((abus & 0x40ff00) == 0x2100 || (abus & 0x40ff80) == 0x4300 ||
+       (abus & 0x40ffff) == 0x420b || (abus & 0x40ffff) == 0x420c)return;
+    r_mem->write(abus, r);
+  }
+}
+
+void bCPU::dma_add_cycles(uint32 cycles) {
+  status.dma_cycle_count += cycles;
+}
+
+void bCPU::hdma_add_cycles(uint32 cycles) {
+  if(run_state.dma) {
+    status.dma_cycle_count += cycles;
+  }
+  status.hdma_cycle_count += cycles;
+}
+
+uint32 bCPU::dma_addr(uint8 i) {
+uint32 r;
+  r = (channel[i].srcbank << 16) | (channel[i].srcaddr);
+
+  if(channel[i].fixedxfer == false) {
+    channel[i].srcaddr += channel[i].incmode;
+  }
+
+  return r;
+}
+
+void bCPU::dma_cputommio(uint8 i, uint8 index) {
+  if(sdd1->dma_active() == true) {
+    r_mem->write(0x2100 | ((channel[i].destaddr + index) & 0xff), sdd1->dma_read());
+  } else {
+    dma_transfer_byte(0, ((channel[i].destaddr + index) & 0xff), dma_addr(i));
+  }
+
+  add_cycles(8);
+  channel[i].xfersize--;
+}
+
+void bCPU::dma_mmiotocpu(uint8 i, uint8 index) {
+  dma_transfer_byte(1, ((channel[i].destaddr + index) & 0xff), dma_addr(i));
+
+  add_cycles(8);
+  channel[i].xfersize--;
+}
+
+void bCPU::dma_write(uint8 i, uint8 index) {
+  if(channel[i].direction == 0) {
+    dma_cputommio(i, index);
+  } else {
+    dma_mmiotocpu(i, index);
+  }
+}
+
+void bCPU::dma_run() {
+  for(int i = 0; i < 8; i++) {
+    if(channel[i].active == false)continue;
+
+  //first byte transferred?
+    if(channel[i].read_index == 0) {
+      sdd1->dma_begin(i, (channel[i].srcbank << 16) | (channel[i].srcaddr),
+        channel[i].xfersize);
+    }
+
+    switch(channel[i].xfermode) {
+    case 0: dma_write(i, 0);                                break; //0
+    case 1: dma_write(i, channel[i].read_index & 1);        break; //0,1
+    case 2: dma_write(i, 0);                                break; //0,0
+    case 3: dma_write(i, (channel[i].read_index >> 1) & 1); break; //0,0,1,1
+    case 4: dma_write(i, channel[i].read_index & 3);        break; //0,1,2,3
+    case 5: dma_write(i, channel[i].read_index & 1);        break; //0,1,0,1
+    case 6: dma_write(i, 0);                                break; //0,0     [2]
+    case 7: dma_write(i, (channel[i].read_index >> 1) & 1); break; //0,0,1,1 [3]
+    }
+
+    channel[i].read_index++;
+    dma_add_cycles(8);
+
+    if(channel[i].xfersize == 0) {
+      channel[i].active = false;
+    }
+
+    return;
+  }
+
+  status.dma_state = DMASTATE_CPUSYNC;
+}
+
+uint32 bCPU::hdma_addr(uint8 i) {
+  return (channel[i].srcbank << 16) | (channel[i].hdma_addr++);
+}
+
+uint32 bCPU::hdma_iaddr(uint8 i) {
+  return (channel[i].hdma_ibank << 16) | (channel[i].hdma_iaddr++);
+}
+
+uint16 bCPU::hdma_mmio(uint8 i) {
+uint8  l = channel[i].read_index;
+uint16 index;
+  switch(channel[i].xfermode) {
+  case 0: index = 0;            break; //0
+  case 1: index = l & 1;        break; //0,1
+  case 2: index = 0;            break; //0,0
+  case 3: index = (l >> 1) & 1; break; //0,0,1,1
+  case 4: index = l & 3;        break; //0,1,2,3
+  case 5: index = l & 1;        break; //0,1,0,1
+  case 6: index = 0;            break; //0,0     [2]
+  case 7: index = (l >> 1) & 1; break; //0,0,1,1 [3]
+  }
+
+  return (0x2100 | ((channel[i].destaddr + index) & 0xff));
+}
+
+void bCPU::hdma_update(uint8 i) {
+  channel[i].hdma_line_counter = r_mem->read(hdma_addr(i));
+  add_cycles(8);
+  hdma_add_cycles(8);
+
+  if(channel[i].hdma_indirect) {
+    channel[i].hdma_iaddr = r_mem->read(hdma_addr(i)) << 8;
+    add_cycles(8);
+    hdma_add_cycles(8);
+  }
+
+  if(channel[i].hdma_line_counter == 0) {
+    channel[i].hdma_active      = false;
+    channel[i].hdma_do_transfer = false;
+    return;
+  }
+
+  channel[i].hdma_do_transfer = true;
+
+  if(channel[i].hdma_indirect) {
+    channel[i].hdma_iaddr >>= 8;
+    channel[i].hdma_iaddr  |= r_mem->read(hdma_addr(i)) << 8;
+    add_cycles(8);
+    hdma_add_cycles(8);
+  }
+}
+
+void bCPU::hdma_run() {
+static uint8 hdma_xferlen[8] = { 1, 2, 2, 4, 4, 4, 2, 4 };
+  for(int i = 0; i < 8; i++) {
+    if(!channel[i].hdma_enabled || !channel[i].hdma_active)continue;
+
+    if(channel[i].hdma_do_transfer) {
+    int xferlen = hdma_xferlen[channel[i].xfermode];
+      for(channel[i].read_index = 0; channel[i].read_index < xferlen; channel[i].read_index++) {
+        if(bool(config::cpu.hdma_enable) == true) {
+          dma_transfer_byte(channel[i].direction, hdma_mmio(i),
+            channel[i].hdma_indirect ? hdma_iaddr(i) : hdma_addr(i));
+        }
+        add_cycles(8);
+        hdma_add_cycles(8);
+      }
+    }
+
+    channel[i].hdma_line_counter--;
+    channel[i].hdma_do_transfer = bool(channel[i].hdma_line_counter & 0x80);
+    if((channel[i].hdma_line_counter & 0x7f) == 0) {
+      hdma_update(i);
+    }
+  }
+}
+
+uint8 bCPU::hdma_enabled_channels() {
+int r = 0;
+  for(int i = 0; i < 8; i++) {
+    if(channel[i].hdma_enabled)r++;
+  }
+  return r;
+}
+
+uint8 bCPU::hdma_active_channels() {
+int r = 0;
+  for(int i = 0; i < 8; i++) {
+    if(channel[i].hdma_enabled && channel[i].hdma_active)r++;
+  }
+  return r;
+}
+
+/* hdmainit_activate()
+ * hdma_activate()
+ *
+ * Functions are called by CPU timing routine
+ * when an HDMA event (init or run) occurs.
+ */
+
+void bCPU::hdmainit_activate() {
+  for(int i = 0; i < 8; i++) {
+    channel[i].hdma_active      = false;
+    channel[i].hdma_do_transfer = false;
+  }
+
+  if(hdma_enabled_channels() != 0) {
+    status.hdma_state = HDMASTATE_IDMASYNC;
+    run_state.hdma = true;
+  }
+}
+
+void bCPU::hdma_activate() {
+  if(hdma_active_channels() != 0) {
+    status.hdma_state = HDMASTATE_DMASYNC;
+    run_state.hdma = true;
+  }
+}
+
+void bCPU::dma_reset() {
+  status.dma_state        = DMASTATE_CPUSYNC;
+  status.hdma_state       = HDMASTATE_CPUSYNC;
+  status.dma_cycle_count  = 0;
+  status.hdma_cycle_count = 0;
+
+  for(int i = 0; i < 8; i++) {
+    channel[i].read_index        = 0;
+    channel[i].active            = false;
+    channel[i].hdma_enabled      = false;
+    channel[i].dmap              = 0xff;
+    channel[i].direction         = 1;
+    channel[i].hdma_indirect     = 1;
+    channel[i].incmode           = -1;
+    channel[i].fixedxfer         = 1;
+    channel[i].xfermode          = 7;
+    channel[i].destaddr          = 0xff;
+    channel[i].srcaddr           = 0xffff;
+    channel[i].srcbank           = 0xff;
+    channel[i].xfersize          = 0xffff;
+  //xfersize and hdma_iaddr are of union { uint16 };
+  //channel[i].hdma_iaddr        = 0xffff;
+    channel[i].hdma_ibank        = 0xff;
+    channel[i].hdma_addr         = 0xffff;
+    channel[i].hdma_line_counter = 0xff;
+    channel[i].hdma_unknown      = 0xff;
+
+    channel[i].hdma_active       = false;
+    channel[i].hdma_do_transfer  = false;
+  }
+}

src/cpu/bcpu/dma/dma.h

@@ -0,0 +1,60 @@
+struct {
+  uint32 read_index; //set to 0 at beginning of DMA/HDMA
+
+//$420b
+  bool   active;
+//$420c
+  bool   hdma_enabled;
+//$43x0
+  uint8  dmap;
+  bool   direction;
+  bool   hdma_indirect;
+  int8   incmode;
+  bool   fixedxfer;
+  uint8  xfermode;
+//$43x1
+  uint8  destaddr;
+//$43x2-$43x3
+  uint16 srcaddr;
+//$43x4
+  uint8  srcbank;
+//$43x5-$43x6
+  union {
+    uint16 xfersize;
+    uint16 hdma_iaddr;
+  };
+//$43x7
+  uint8  hdma_ibank;
+//$43x8-$43x9
+  uint16 hdma_addr;
+//$43xa
+  uint8  hdma_line_counter;
+//$43xb/$43xf
+  uint8  hdma_unknown;
+
+//hdma-specific
+  bool   hdma_active;
+  bool   hdma_do_transfer;
+
+  uint8  hdma_current_channel;
+  uint8  hdma_current_pos;
+} channel[8];
+
+  inline void   dma_transfer_byte(bool direction, uint8 bbus, uint32 abus);
+  inline void   dma_add_cycles(uint32 cycles);
+  inline void   hdma_add_cycles(uint32 cycles);
+  inline void   dma_run();
+  inline void   hdma_run();
+  inline void   hdma_update(uint8 i);
+  inline uint8  hdma_enabled_channels();
+  inline uint8  hdma_active_channels();
+  inline void   hdmainit_activate();
+  inline void   hdma_activate();
+  inline void   dma_cputommio(uint8 i, uint8 index);
+  inline void   dma_mmiotocpu(uint8 i, uint8 index);
+  inline void   dma_write(uint8 i, uint8 index);
+  inline uint32 dma_addr(uint8 i);
+  inline uint32 hdma_addr(uint8 i);
+  inline uint32 hdma_iaddr(uint8 i);
+  inline uint16 hdma_mmio(uint8 i);
+  inline void   dma_reset();

src/cpu/bcpu/memory/memory.cpp

@@ -0,0 +1,40 @@
+uint8 bCPU::port_read(uint8 port) {
+  return apu_port[port & 3];
+}
+
+void bCPU::port_write(uint8 port, uint8 value) {
+  apu_port[port & 3] = value;
+}
+
+/* The next 3 functions control bus timing for the CPU.
+ * cpu_io is an I/O cycle, and always 6 clock cycles long.
+ * mem_read / mem_write indicate memory access bus cycle,
+ * they are either 6, 8, or 12 bus cycles long, depending
+ * both on location and the $420d.d0 FastROM enable bit.
+ */
+
+void bCPU::cpu_io() {
+  status.cycle_count = 6;
+  pre_exec_cycle();
+  add_cycles(6);
+  cycle_edge();
+}
+
+uint8 bCPU::mem_read(uint32 addr) {
+  status.cycle_count = r_mem->speed(addr);
+  pre_exec_cycle();
+  add_cycles(status.cycle_count - 4);
+  regs.mdr = r_mem->read(addr);
+  add_cycles(4);
+  cycle_edge();
+  return regs.mdr;
+}
+
+void bCPU::mem_write(uint32 addr, uint8 value) {
+  status.cycle_count = r_mem->speed(addr);
+  pre_exec_cycle();
+  add_cycles(status.cycle_count);
+  regs.mdr = value;
+  r_mem->write(addr, value);
+  cycle_edge();
+}

src/cpu/bcpu/memory/memory.h

@@ -0,0 +1,7 @@
+uint8 apu_port[4];
+  inline uint8  port_read (uint8 port);
+  inline void   port_write(uint8 port, uint8 value);
+
+  inline void   cpu_io();
+  inline uint8  mem_read(uint32 addr);
+  inline void   mem_write(uint32 addr, uint8 value);

src/cpu/bcpu/timing/timing.cpp

@@ -200,14 +200,14 @@ void bCPU::inc_vcounter() {
     time.v = 0;
     time.interlace_field ^= 1;
 
-    if(time.interlace == true && time.interlace_field == 0) {
+    if(interlace() == true && interlace_field() == 0) {
       time.frame_lines = time.region_scanlines + 1;
     } else {
       time.frame_lines = time.region_scanlines;
     }
   }
 
-  time.dma_counter = time.line_cycles & 6;
+  time.dma_counter += time.line_cycles;
   if(time.v == 240 && time.interlace == false && time.interlace_field == 1) {
     time.line_cycles = 1360;
   } else {
@@ -239,6 +239,24 @@ uint32 r = status.cycles_executed;
   return r;
 }
 
+void bCPU::cycle_edge() {
+  if(time.hdmainit_triggered == false) {
+    if(time.hc >= time.hdmainit_trigger_pos || time.v) {
+      time.hdmainit_triggered = true;
+      hdmainit_activate();
+    }
+  }
+
+  if(time.hdma_triggered == false) {
+    if(time.v <= (overscan() ? 239 : 224)) {
+      if(time.hc >= 1106) {
+        time.hdma_triggered = true;
+        hdma_activate();
+      }
+    }
+  }
+}
+
 void bCPU::add_cycles(int cycles) {
   status.cycles_executed += cycles;
 
@@ -253,30 +271,16 @@ void bCPU::add_cycles(int cycles) {
 
     if(time.v == 0) {
       frame();
-      ppu->frame();
+      r_ppu->frame();
       snes->frame();
     }
 
     scanline();
-    ppu->scanline();
-//  ppu->render_scanline();
+    r_ppu->scanline();
     snes->scanline();
     time.line_rendered = false;
   }
 
-  if(time.line_rendered == false) {
-  //rendering should start at H=22, but due to inaccurate
-  //timing, and due to using a scanline-based renderer, use
-  //a higher value to allow more games to run properly...
-  //H=48 fixes off-by-one HDMA effects with FF6's battles
-    if(time.hc + cycles >= (48 * 4)) {
-      cycles  = (time.hc + cycles) - (48 * 4);
-      time.hc = (48 * 4);
-      time.line_rendered = true;
-      ppu->render_scanline();
-    }
-  }
-
   if(time.dram_refreshed == false) {
     if(time.hc + cycles >= time.dram_refresh_pos) {
       time.dram_refreshed = true;
@@ -296,15 +300,14 @@ void bCPU::add_cycles(int cycles) {
     }
   }
 
-  if(status.hdma_triggered == false) {
-  //vcounter range verified on hardware
-    if(time.v <= (overscan() ? 239 : 224)) {
-      if(time.hc + cycles >= 1112) { //278 * 4 = 1112
-        cycles  = (time.hc + cycles) - 1112;
-        time.hc = 1112;
-        status.hdma_triggered = true;
-        hdma_run();
-      }
+  if(time.line_rendered == false) {
+  //rendering should start at H=18 (+256=274), but since the
+  //current PPU emulation renders the entire scanline at once,
+  //PPU register changes mid-scanline do not show up.
+  //therefore, wait a few dots before rendering the scanline
+    if(time.hc + cycles >= (48 * 4)) {
+      time.line_rendered = true;
+      r_ppu->render_scanline();
     }
   }
 
@@ -312,15 +315,12 @@ void bCPU::add_cycles(int cycles) {
 }
 
 void bCPU::time_reset() {
-//initial latch values for $213c/$213d
-//[x]0035 : [y]0000 (53.0 -> 212) [lda $2137]
-//[x]0038 : [y]0000 (56.5 -> 226) [nop : lda $2137]
   time.v  = 0;
-  time.hc = 186;
+  time.hc = 0;
 
 //upon SNES reset, start at scanline 0 non-interlace
-  time.interlace       = false;
-  time.interlace_field = false;
+  time.interlace       = 0;
+  time.interlace_field = 0;
   time.overscan        = false;
   time.line_cycles     = 1364;
 
@@ -329,6 +329,12 @@ void bCPU::time_reset() {
 
   time.dma_counter = 0;
 
+//set at V=0,H=0
+  time.hdmainit_trigger_pos = 0;
+  time.hdmainit_triggered   = true;
+
+  time.hdma_triggered = false;
+
   time.nmi_pending = false;
   time.irq_pending = false;
   time.nmi_line = time.nmi_read = 1;

src/cpu/bcpu/timing/timing.h

@@ -11,6 +11,11 @@ struct {
 
   uint8  dma_counter;
 
+  uint16 hdmainit_trigger_pos;
+  bool   hdmainit_triggered;
+
+  bool   hdma_triggered;
+
   uint16 region_scanlines;
 
 //nmi_pending, irq_pending are used by last_cycle()
@@ -41,28 +46,29 @@ struct {
   int32  irq_read_trigger_pos, irq_line_trigger_pos;
 } time;
 
-inline uint16 vcounter();
-inline uint16 hcounter();
-inline uint16 hcycles();
-inline bool   interlace();
-inline bool   interlace_field();
-inline bool   overscan();
-inline uint16 region_scanlines();
+  inline uint16 vcounter();
+  inline uint16 hcounter();
+  inline uint16 hcycles();
+  inline bool   interlace();
+  inline bool   interlace_field();
+  inline bool   overscan();
+  inline uint16 region_scanlines();
 
-inline bool   nmi_trigger_pos_match(uint32 offset);
-inline bool   irq_trigger_pos_match(uint32 offset);
+  inline bool   nmi_trigger_pos_match(uint32 offset);
+  inline bool   irq_trigger_pos_match(uint32 offset);
 
-inline void   update_nmi();
-inline void   update_irq();
-inline void   update_interrupts();
-inline void   poll_interrupts(int cycles);
+  inline void   update_nmi();
+  inline void   update_irq();
+  inline void   update_interrupts();
+  inline void   poll_interrupts(int cycles);
 
-inline void   set_interlace(bool r);
-inline void   set_overscan (bool r);
+  inline void   set_interlace(bool r);
+  inline void   set_overscan (bool r);
 
-inline uint8  dma_counter();
+  inline uint8  dma_counter();
 
-inline void   inc_vcounter();
-inline uint16 get_hcounter();
-inline void   add_cycles(int cycles);
-inline void   time_reset();
+  inline void   inc_vcounter();
+  inline uint16 get_hcounter();
+  inline void   cycle_edge();
+  inline void   add_cycles(int cycles);
+  inline void   time_reset();

src/cpu/cpu.cpp

@@ -2,6 +2,5 @@
 #include "dcpu.cpp"
 
 CPU::CPU() {
-  cpu_version = 2;
-  mmio = &mmio_unmapped;
+  cpu_version = 1;
 }

src/cpu/cpu.h

@@ -1,6 +1,6 @@
 #include "cpuregs.h"
 
-class CPU {
+class CPU : public MMIO {
 public:
 //CPU version number
 //* 1 and 2 are known
@@ -12,13 +12,13 @@ uint8 cpu_version;
   virtual uint16 vcounter() = 0;
   virtual uint16 hcounter() = 0;
   virtual uint16 hcycles() = 0;
+  virtual bool   overscan() = 0;
   virtual bool   interlace() = 0;
   virtual bool   interlace_field() = 0;
-  virtual bool   overscan() = 0;
+  virtual uint16 region_scanlines() = 0;
   virtual void   set_interlace(bool r) = 0;
   virtual void   set_overscan (bool r) = 0;
 
-MMIO *mmio;
 CPURegs regs;
   virtual uint8 port_read (uint8 port) = 0;
   virtual void  port_write(uint8 port, uint8 value) = 0;
@@ -69,4 +69,5 @@ enum {
   uint16 __relw(int16 offset);
 
   CPU();
+  virtual ~CPU() {}
 };

src/cpu/cpuregs.h

@@ -13,7 +13,7 @@ private:
     inline bool operator ^= (bool i) { if(i)_b ^= B; return (_b & B); }
   };
 public:
-  union {
+union {
   uint8 _b;
   bit<0x80> n;
   bit<0x40> v;
@@ -23,7 +23,7 @@ public:
   bit<0x04> i;
   bit<0x02> z;
   bit<0x01> c;
-  };
+};
 
   CPURegFlags() { _b = 0; }
   inline operator uint8() { return _b; }
@@ -35,10 +35,14 @@ public:
 
 class CPUReg16 {
 public:
-  union {
+union {
   uint16 w;
+#ifdef ARCH_LSB
   struct { uint8 l, h; };
-  };
+#else
+  struct { uint8 h, l; };
+#endif
+};
 
   CPUReg16() { w = 0; }
   inline operator uint16() { return w; }
@@ -56,11 +60,16 @@ public:
 
 class CPUReg24 {
 public:
-  union {
-  uint16 w;
+union {
   uint32 d;
-  struct { uint8 l, h, b; };
-  };
+#ifdef ARCH_LSB
+  struct { uint16 w, null_w; };
+  struct { uint8  l, h, b, null_b; };
+#else
+  struct { uint16 null_w, w; };
+  struct { uint8  null_b, b, h, l; };
+#endif
+};
 
   CPUReg24() { d = 0; }
   inline operator uint32() { return (d & 0xffffff); }

src/cpu/dcpu.cpp

@@ -38,23 +38,23 @@ uint32 r = 0;
     break;
   case OPTYPE_IDP:
     addr = (regs.d + (addr & 0xffff)) & 0xffff;
-    r = (regs.db << 16) + mem_bus->read_word(addr);
+    r = (regs.db << 16) + r_mem->read_word(addr);
     break;
   case OPTYPE_IDPX:
     addr = (regs.d + regs.x + (addr & 0xffff)) & 0xffff;
-    r = (regs.db << 16) + mem_bus->read_word(addr);
+    r = (regs.db << 16) + r_mem->read_word(addr);
     break;
   case OPTYPE_IDPY:
     addr = (regs.d + (addr & 0xffff)) & 0xffff;
-    r = (regs.db << 16) + mem_bus->read_word(addr) + regs.y;
+    r = (regs.db << 16) + r_mem->read_word(addr) + regs.y;
     break;
   case OPTYPE_ILDP:
     addr = (regs.d + (addr & 0xffff)) & 0xffff;
-    r = mem_bus->read_long(addr);
+    r = r_mem->read_long(addr);
     break;
   case OPTYPE_ILDPY:
     addr = (regs.d + (addr & 0xffff)) & 0xffff;
-    r = mem_bus->read_long(addr) + regs.y;
+    r = r_mem->read_long(addr) + regs.y;
     break;
   case OPTYPE_ADDR:
     r = (regs.db << 16) + (addr & 0xffff);
@@ -88,7 +88,7 @@ uint32 r = 0;
     break;
   case OPTYPE_ISRY:
     addr = (regs.s + (addr & 0xff)) & 0xffff;
-    r = (regs.db << 16) + mem_bus->read_word(addr) + regs.y;
+    r = (regs.db << 16) + r_mem->read_word(addr) + regs.y;
     break;
   }
   return r;
@@ -109,10 +109,10 @@ static CPUReg24 pc;
   pc.d = regs.pc.d;
   sprintf(s, "%0.6x ", pc.d);
 
-  op  = mem_bus->read(pc.d); pc.w++;
-  op0 = mem_bus->read(pc.d); pc.w++;
-  op1 = mem_bus->read(pc.d); pc.w++;
-  op2 = mem_bus->read(pc.d);
+  op  = r_mem->read(pc.d); pc.w++;
+  op0 = r_mem->read(pc.d); pc.w++;
+  op1 = r_mem->read(pc.d); pc.w++;
+  op2 = r_mem->read(pc.d);
 
   switch(op) {
   case 0x00:sprintf(t, "brk #$%0.2x               ", op0);break;
@@ -457,7 +457,7 @@ static uint8 op_len_tbl[256] = {
     return 0;
   }
 
-  op = mem_bus->read(regs.pc.d);
+  op = r_mem->read(regs.pc.d);
   len = op_len_tbl[op];
   if(len == 5)return (regs.p.m)?2:3;
   if(len == 6)return (regs.p.x)?2:3;

src/dsp/bdsp/bdsp.cpp

@@ -1,10 +1,22 @@
 #include "../../base.h"
 #include "bdsp_tables.cpp"
 
-uint8  bDSP::read_8  (uint16 addr) { return (spcram[addr]); }
-uint16 bDSP::read_16 (uint16 addr) { return (spcram[(addr + 1) & 0xffff] << 8) + (spcram[addr]); }
-void   bDSP::write_8 (uint16 addr, uint8 data)  { spcram[addr] = data; }
-void   bDSP::write_16(uint16 addr, uint16 data) { spcram[addr++] = data; spcram[addr] = data >> 8; }
+uint8  bDSP::readb(uint16 addr) {
+  return spcram[addr];
+}
+
+void bDSP::writeb(uint16 addr, uint8 data) {
+  spcram[addr] = data;
+}
+
+uint16 bDSP::readw(uint16 addr) {
+  return (readb(addr)) | (readb(addr + 1) << 8);
+}
+
+void bDSP::writew(uint16 addr, uint16 data) {
+  writeb(addr,     data);
+  writeb(addr + 1, data >> 8);
+}
 
 uint8 bDSP::read(uint8 addr) {
 int i, v, n;
@@ -98,12 +110,14 @@ int i, v, n;
     break;
   case 0x04:case 0x14:case 0x24:case 0x34:
   case 0x44:case 0x54:case 0x64:case 0x74:
-  //voice[v].SRCN = data;
+    voice[v].SRCN = data;
+    break;
   //below is anomie's code, but TRAC says writing SRCN doesn't affect anything until a
   //BRR-with-end block is encountered, where it loads the loop address from the new SRCN
+  //anomie's code breaks MK2 sound completely...
     if(voice[v].SRCN != data) {
       voice[v].SRCN      = data;
-      voice[v].brr_ptr   = read_16((status.DIR << 8) + (voice[v].SRCN << 2) + ((voice[v].brr_looped)?2:0));
+      voice[v].brr_ptr   = readw((status.DIR << 8) + (voice[v].SRCN << 2) + ((voice[v].brr_looped) ? 2 : 0));
       voice[v].brr_index = 0;
     }
     break;
@@ -183,7 +197,7 @@ int i, v, n;
 
 void bDSP::power() {
 int v;
-  spcram = apu->get_spcram_handle();
+  spcram = r_apu->get_spcram_handle();
   memset(dspram, 0x00, 128);
 
   for(v=0;v<8;v++) {
@@ -238,7 +252,7 @@ int v;
     voice[v].pitch_ctr = 0;
 
     voice[v].brr_index      = 0;
-    voice[v].brr_ptr        = read_16((status.DIR << 8) + (voice[v].SRCN << 2));
+    voice[v].brr_ptr        = readw((status.DIR << 8) + (voice[v].SRCN << 2));
     voice[v].brr_looped     = false;
     voice[v].brr_data[0]    = 0;
     voice[v].brr_data[1]    = 0;
@@ -288,20 +302,27 @@ int32 esamplel, esampler;
 int32 fir_samplel, fir_sampler;
   pmon = status.PMON & ~status.NON & ~1;
 
-  if(!(dsp_counter++ & 1) && status.key_flag) {
+//if(!(dsp_counter++ & 1) && status.key_flag) {
+//TRAC believes KON/KOFF is polled every sample. further testing is needed
+  if(status.key_flag) {
     for(v=0;v<8;v++) {
+    uint8 mask = 1 << v;
       if(status.soft_reset()) {
         if(voice[v].env_state != SILENCE) {
           voice[v].env_state = SILENCE;
           voice[v].AdjustEnvelope();
         }
-      } else if(status.KOFF & (1 << v)) {
+      } else if(status.KOFF & mask) {
         if(voice[v].env_state != SILENCE && voice[v].env_state != RELEASE) {
           voice[v].env_state = RELEASE;
           voice[v].AdjustEnvelope();
         }
-      } else if(status.kon & (1 << v)) {
-        voice[v].brr_ptr     = read_16((status.DIR << 8) + (voice[v].SRCN << 2));
+      } else if(status.kon & mask) {
+      //new KON code
+        status.ENDX &= ~mask;
+        status.kon  &= ~mask;
+
+        voice[v].brr_ptr     = readw((status.DIR << 8) + (voice[v].SRCN << 2));
         voice[v].brr_index   = -9;
         voice[v].brr_looped  = false;
         voice[v].brr_data[0] = 0;
@@ -313,8 +334,9 @@ int32 fir_samplel, fir_sampler;
         voice[v].AdjustEnvelope();
       }
     }
-    status.ENDX &= ~status.kon;
-    status.kon      = 0;
+//old KON code, breaks sound effects in DL / SFA2
+//  status.ENDX    &= ~status.kon;
+//  status.kon      = 0;
     status.key_flag = false;
   }
 
@@ -356,13 +378,15 @@ int32 fir_samplel, fir_sampler;
       voice[v].brr_data_index &= 3;
 
       if(voice[v].brr_index == 0) {
-        voice[v].brr_header = read_8(voice[v].brr_ptr);
+        voice[v].brr_header = readb(voice[v].brr_ptr);
 
-        if(voice[v].brr_header_flags() & BRR_END) {
-          status.ENDX |= (1 << v);
-        }
+//moving status.ENDX bit set into == BRR_END condition per DMV27
+      //if(voice[v].brr_header_flags() & BRR_END) {
+      //  status.ENDX |= (1 << v);
+      //}
 
         if(voice[v].brr_header_flags() == BRR_END) {
+          status.ENDX |= (1 << v);
           voice[v].env_state = SILENCE;
           voice[v].AdjustEnvelope();
         }
@@ -370,7 +394,7 @@ int32 fir_samplel, fir_sampler;
 
 #define S(x) voice[v].brr_data[(voice[v].brr_data_index + (x)) & 3]
       if(voice[v].env_state != SILENCE) {
-        sample = read_8(voice[v].brr_ptr + 1 + (voice[v].brr_index >> 1));
+        sample = readb(voice[v].brr_ptr + 1 + (voice[v].brr_index >> 1));
         if(voice[v].brr_index & 1) {
           sample = clip(4, sample);
         } else {
@@ -407,7 +431,11 @@ int32 fir_samplel, fir_sampler;
       if(++voice[v].brr_index > 15) {
         voice[v].brr_index = 0;
         if(voice[v].brr_header_flags() & BRR_END) {
-          voice[v].brr_ptr    = read_16((status.DIR << 8) + (voice[v].SRCN << 2) + 2);
+        //below condition added by DMV27
+          if(voice[v].brr_header_flags() & BRR_LOOP) {
+            status.ENDX |= (1 << v);
+          }
+          voice[v].brr_ptr    = readw((status.DIR << 8) + (voice[v].SRCN << 2) + 2);
           voice[v].brr_looped = true;
         } else {
           voice[v].brr_ptr   += 9;
@@ -493,7 +521,7 @@ int32 fir_samplel, fir_sampler;
 
   //gaussian interpolation / noise
     if(status.NON & (1 << v)) {
-      sample = status.noise_sample;
+      sample  = clip(15, status.noise_sample);
     } else {
       d = voice[v].pitch_ctr >> 4; //-256 <= sample <= -1
       sample  = ((GaussTable[ -1-d] * S(-3)) >> 11);
@@ -524,8 +552,8 @@ int32 fir_samplel, fir_sampler;
 //echo (FIR) adjust
 #define F(c,x) status.fir_buffer[c][(status.fir_buffer_index+(x)) & 7]
   status.fir_buffer_index++;
-  F(0,0) = read_16((status.ESA << 8) + status.echo_index);
-  F(1,0) = read_16((status.ESA << 8) + status.echo_index + 2);
+  F(0,0) = readw((status.ESA << 8) + status.echo_index);
+  F(1,0) = readw((status.ESA << 8) + status.echo_index + 2);
 
   fir_samplel = (F(0,-0) * status.FIR[7] +
                  F(0,-1) * status.FIR[6] +
@@ -554,8 +582,8 @@ int32 fir_samplel, fir_sampler;
     esamplel = clamp(16, esamplel);
     esampler = clamp(16, esampler);
 
-    write_16((status.ESA << 8) + status.echo_index,     esamplel);
-    write_16((status.ESA << 8) + status.echo_index + 2, esampler);
+    writew((status.ESA << 8) + status.echo_index,     esamplel);
+    writew((status.ESA << 8) + status.echo_index + 2, esampler);
   }
 
   status.echo_index += 4;

src/dsp/bdsp/bdsp.h

@@ -10,10 +10,10 @@ enum {
   BRR_LOOP = 2
 };
 
-uint8  read_8  (uint16 addr);
-uint16 read_16 (uint16 addr);
-void   write_8 (uint16 addr, uint8 data);
-void   write_16(uint16 addr, uint16 data);
+uint8  readb (uint16 addr);
+uint16 readw (uint16 addr);
+void   writeb(uint16 addr, uint8  data);
+void   writew(uint16 addr, uint16 data);
 
 public:
 static const uint16 RateTable[32];

src/dsp/dsp.h

@@ -6,4 +6,7 @@ public:
   virtual void   power() = 0;
   virtual void   reset() = 0;
   virtual uint32 run()   = 0;
+
+  DSP() {}
+  virtual ~DSP() {}
 };