mirror of
https://github.com/bsnes-emu/bsnes.git
synced 2025-02-22 06:02:28 +01:00
byuu says: (Windows: compile with -fpermissive to silence an annoying error. I'll fix it in the next WIP.) I completely replaced the time management system in higan and overhauled the scheduler. Before, processor threads would have "int64 clock"; and there would be a 1:1 relationship between two threads. When thread A ran for X cycles, it'd subtract X * B.Frequency from clock; and when thread B ran for Y cycles, it'd add Y * A.Frequency from clock. This worked well and allowed perfect precision; but it doesn't work when you have more complicated relationships: eg the 68K can sync to the Z80 and PSG; the Z80 to the 68K and PSG; so the PSG needs two counters. The new system instead uses a "uint64 clock" variable that represents time in attoseconds. Every time the scheduler exits, it subtracts the smallest clock count from all threads, to prevent an overflow scenario. The only real downside is that rounding errors mean that roughly every 20 minutes, we have a rounding error of one clock cycle (one 20,000,000th of a second.) However, this only applies to systems with multiple oscillators, like the SNES. And when you're in that situation ... there's no such thing as a perfect oscillator anyway. A real SNES will be thousands of times less out of spec than 1hz per 20 minutes. The advantages are pretty immense. First, we obviously can now support more complex relationships between threads. Second, we can build a much more abstracted scheduler. All of libco is now abstracted away completely, which may permit a state-machine / coroutine version of Thread in the future. We've basically gone from this: auto SMP::step(uint clocks) -> void { clock += clocks * (uint64)cpu.frequency; dsp.clock -= clocks; if(dsp.clock < 0 && !scheduler.synchronizing()) co_switch(dsp.thread); if(clock >= 0 && !scheduler.synchronizing()) co_switch(cpu.thread); } To this: auto SMP::step(uint clocks) -> void { Thread::step(clocks); synchronize(dsp); synchronize(cpu); } As you can see, we don't have to do multiple clock adjustments anymore. This is a huge win for the SNES CPU that had to update the SMP, DSP, all peripherals and all coprocessors. Likewise, we don't have to synchronize all coprocessors when one runs, now we can just synchronize the active one to the CPU. Third, when changing the frequencies of threads (think SGB speed setting modes, GBC double-speed mode, etc), it no longer causes the "int64 clock" value to be erroneous. Fourth, this results in a fairly decent speedup, mostly across the board. Aside from the GBA being mostly a wash (for unknown reasons), it's about an 8% - 12% speedup in every other emulation core. Now, all of this said ... this was an unbelievably massive change, so ... you know what that means >_> If anyone can help test all types of SNES coprocessors, and some other system games, it'd be appreciated. ---- Lastly, we have a bitchin' new about screen. It unfortunately adds ~200KiB onto the binary size, because the PNG->C++ header file transformation doesn't compress very well, and I want to keep the original resource files in with the higan archive. I might try some things to work around this file size increase in the future, but for now ... yeah, slightly larger archive sizes, sorry. The logo's a bit busted on Windows (the Label control's background transparency and alignment settings aren't working), but works well on GTK. I'll have to fix Windows before the next official release. For now, look on my Twitter feed if you want to see what it's supposed to look like. ---- EDIT: forgot about ICD2::Enter. It's doing some weird inverse run-to-save thing that I need to implement support for somehow. So, save states on the SGB core probably won't work with this WIP.
311 lines
6.8 KiB
C++
311 lines
6.8 KiB
C++
auto CPU::readAPU(uint24 addr, uint8 data) -> uint8 {
|
|
synchronize(smp);
|
|
return smp.readPort(addr.bits(0,1));
|
|
}
|
|
|
|
auto CPU::readCPU(uint24 addr, uint8 data) -> uint8 {
|
|
switch((uint16)addr) {
|
|
|
|
//WMDATA
|
|
case 0x2180: {
|
|
return bus.read(0x7e0000 | io.wramAddress++, r.mdr);
|
|
}
|
|
|
|
//JOYSER0
|
|
//7-2 = MDR
|
|
//1-0 = Joypad serial data
|
|
case 0x4016: {
|
|
uint8 v = r.mdr & 0xfc;
|
|
v |= SuperFamicom::peripherals.controllerPort1->data();
|
|
return v;
|
|
}
|
|
|
|
//JOYSER1
|
|
case 0x4017: {
|
|
//7-5 = MDR
|
|
//4-2 = Always 1 (pins are connected to GND)
|
|
//1-0 = Joypad serial data
|
|
uint8 v = (r.mdr & 0xe0) | 0x1c;
|
|
v |= SuperFamicom::peripherals.controllerPort2->data();
|
|
return v;
|
|
}
|
|
|
|
//RDNMI
|
|
case 0x4210: {
|
|
//7 = NMI acknowledge
|
|
//6-4 = MDR
|
|
//3-0 = CPU (5a22) version
|
|
uint8 v = (r.mdr & 0x70);
|
|
v |= (uint8)(rdnmi()) << 7;
|
|
v |= (version & 0x0f);
|
|
return v;
|
|
}
|
|
|
|
//TIMEUP
|
|
case 0x4211: {
|
|
//7 = IRQ acknowledge
|
|
//6-0 = MDR
|
|
uint8 v = (r.mdr & 0x7f);
|
|
v |= (uint8)(timeup()) << 7;
|
|
return v;
|
|
}
|
|
|
|
//HVBJOY
|
|
case 0x4212: {
|
|
//7 = VBLANK acknowledge
|
|
//6 = HBLANK acknowledge
|
|
//5-1 = MDR
|
|
//0 = JOYPAD acknowledge
|
|
uint8 v = (r.mdr & 0x3e);
|
|
if(status.autoJoypadActive) v |= 0x01;
|
|
if(hcounter() <= 2 || hcounter() >= 1096) v |= 0x40; //hblank
|
|
if(vcounter() >= ppu.vdisp()) v |= 0x80; //vblank
|
|
return v;
|
|
}
|
|
|
|
//RDIO
|
|
case 0x4213: {
|
|
return io.pio;
|
|
}
|
|
|
|
//RDDIVL
|
|
case 0x4214: {
|
|
return io.rddiv.byte(0);
|
|
}
|
|
|
|
//RDDIVH
|
|
case 0x4215: {
|
|
return io.rddiv.byte(1);
|
|
}
|
|
|
|
//RDMPYL
|
|
case 0x4216: {
|
|
return io.rdmpy.byte(0);
|
|
}
|
|
|
|
//RDMPYH
|
|
case 0x4217: {
|
|
return io.rdmpy.byte(1);
|
|
}
|
|
|
|
case 0x4218: return io.joy1.byte(0); //JOY1L
|
|
case 0x4219: return io.joy1.byte(1); //JOY1H
|
|
case 0x421a: return io.joy2.byte(0); //JOY2L
|
|
case 0x421b: return io.joy2.byte(1); //JOY2H
|
|
case 0x421c: return io.joy3.byte(0); //JOY3L
|
|
case 0x421d: return io.joy3.byte(1); //JOY3H
|
|
case 0x421e: return io.joy4.byte(0); //JOY4L
|
|
case 0x421f: return io.joy4.byte(1); //JOY4H
|
|
|
|
}
|
|
|
|
return data;
|
|
}
|
|
|
|
auto CPU::readDMA(uint24 addr, uint8 data) -> uint8 {
|
|
auto& channel = this->channel[addr.bits(4,6)];
|
|
|
|
switch(addr & 0xff0f) {
|
|
|
|
//DMAPx
|
|
case 0x4300: return (
|
|
channel.transferMode << 0
|
|
| channel.fixedTransfer << 3
|
|
| channel.reverseTransfer << 4
|
|
| channel.unused << 5
|
|
| channel.indirect << 6
|
|
| channel.direction << 7
|
|
);
|
|
|
|
//BBADx
|
|
case 0x4301: return channel.targetAddress;
|
|
|
|
//A1TxL
|
|
case 0x4302: return channel.sourceAddress >> 0;
|
|
|
|
//A1TxH
|
|
case 0x4303: return channel.sourceAddress >> 8;
|
|
|
|
//A1Bx
|
|
case 0x4304: return channel.sourceBank;
|
|
|
|
//DASxL -- union { uint16 transferSize; uint16 indirectAddress; };
|
|
case 0x4305: return channel.transferSize.byte(0);
|
|
|
|
//DASxH -- union { uint16 transferSize; uint16 indirectAddress; };
|
|
case 0x4306: return channel.transferSize.byte(1);
|
|
|
|
//DASBx
|
|
case 0x4307: return channel.indirectBank;
|
|
|
|
//A2AxL
|
|
case 0x4308: return channel.hdmaAddress.byte(0);
|
|
|
|
//A2AxH
|
|
case 0x4309: return channel.hdmaAddress.byte(1);
|
|
|
|
//NTRLx
|
|
case 0x430a: return channel.lineCounter;
|
|
|
|
//???
|
|
case 0x430b:
|
|
case 0x430f: return channel.unknown;
|
|
|
|
}
|
|
|
|
return data;
|
|
}
|
|
|
|
auto CPU::writeAPU(uint24 addr, uint8 data) -> void {
|
|
synchronize(smp);
|
|
return writePort(addr.bits(0,1), data);
|
|
}
|
|
|
|
auto CPU::writeCPU(uint24 addr, uint8 data) -> void {
|
|
switch((uint16)addr) {
|
|
|
|
//WMDATA
|
|
case 0x2180: {
|
|
return bus.write(0x7e0000 | io.wramAddress++, data);
|
|
}
|
|
|
|
case 0x2181: io.wramAddress.bits( 0, 7) = data; return; //WMADDL
|
|
case 0x2182: io.wramAddress.bits( 8,15) = data; return; //WMADDM
|
|
case 0x2183: io.wramAddress.bit (16 ) = data.bit(0); return; //WMADDH
|
|
|
|
//JOYSER0
|
|
case 0x4016: {
|
|
//bit 0 is shared between JOYSER0 and JOYSER1, therefore
|
|
//strobing $4016.d0 affects both controller port latches.
|
|
//$4017 bit 0 writes are ignored.
|
|
SuperFamicom::peripherals.controllerPort1->latch(data.bit(0));
|
|
SuperFamicom::peripherals.controllerPort2->latch(data.bit(0));
|
|
return;
|
|
}
|
|
|
|
//NMITIMEN
|
|
case 0x4200: {
|
|
io.autoJoypadPoll = data.bit(0);
|
|
nmitimenUpdate(data);
|
|
return;
|
|
}
|
|
|
|
//WRIO
|
|
case 0x4201: {
|
|
if(io.pio.bit(7) && !data.bit(7)) ppu.latchCounters();
|
|
io.pio = data;
|
|
return;
|
|
}
|
|
|
|
//WRMPYA
|
|
case 0x4202: io.wrmpya = data; return;
|
|
|
|
//WRMPYB
|
|
case 0x4203: {
|
|
io.rdmpy = 0;
|
|
if(alu.mpyctr || alu.divctr) return;
|
|
|
|
io.wrmpyb = data;
|
|
io.rddiv = (io.wrmpyb << 8) | io.wrmpya;
|
|
|
|
alu.mpyctr = 8; //perform multiplication over the next eight cycles
|
|
alu.shift = io.wrmpyb;
|
|
return;
|
|
}
|
|
|
|
case 0x4204: { io.wrdiva.byte(0) = data; return; } //WRDIVL
|
|
case 0x4205: { io.wrdiva.byte(1) = data; return; } //WRDIVH
|
|
|
|
//WRDIVB
|
|
case 0x4206: {
|
|
io.rdmpy = io.wrdiva;
|
|
if(alu.mpyctr || alu.divctr) return;
|
|
|
|
io.wrdivb = data;
|
|
|
|
alu.divctr = 16; //perform division over the next sixteen cycles
|
|
alu.shift = io.wrdivb << 16;
|
|
return;
|
|
}
|
|
|
|
case 0x4207: io.hirqPos.bits(0,7) = data; return; //HTIMEL
|
|
case 0x4208: io.hirqPos.bit (8 ) = data.bit(0); return; //HTIMEH
|
|
|
|
case 0x4209: io.virqPos.bits(0,7) = data; return; //VTIMEL
|
|
case 0x420a: io.virqPos.bit (8 ) = data.bit(0); return; //VTIMEH
|
|
|
|
//DMAEN
|
|
case 0x420b: {
|
|
for(auto n : range(8)) channel[n].dmaEnabled = data.bit(n);
|
|
if(data) status.dmaPending = true;
|
|
return;
|
|
}
|
|
|
|
//HDMAEN
|
|
case 0x420c: {
|
|
for(auto n : range(8)) channel[n].hdmaEnabled = data.bit(n);
|
|
return;
|
|
}
|
|
|
|
//MEMSEL
|
|
case 0x420d: {
|
|
io.romSpeed = data.bit(0) ? 6 : 8;
|
|
return;
|
|
}
|
|
|
|
}
|
|
}
|
|
|
|
auto CPU::writeDMA(uint24 addr, uint8 data) -> void {
|
|
auto& channel = this->channel[addr.bits(4,6)];
|
|
|
|
switch(addr & 0xff0f) {
|
|
|
|
//DMAPx
|
|
case 0x4300: {
|
|
channel.transferMode = data.bits(0,2);
|
|
channel.fixedTransfer = data.bit (3);
|
|
channel.reverseTransfer = data.bit (4);
|
|
channel.unused = data.bit (5);
|
|
channel.indirect = data.bit (6);
|
|
channel.direction = data.bit (7);
|
|
return;
|
|
}
|
|
|
|
//DDBADx
|
|
case 0x4301: channel.targetAddress = data; return;
|
|
|
|
//A1TxL
|
|
case 0x4302: channel.sourceAddress.byte(0) = data; return;
|
|
|
|
//A1TxH
|
|
case 0x4303: channel.sourceAddress.byte(1) = data; return;
|
|
|
|
//A1Bx
|
|
case 0x4304: channel.sourceBank = data; return;
|
|
|
|
//DASxL -- union { uint16 transferSize; uint16 indirectAddress; };
|
|
case 0x4305: channel.transferSize.byte(0) = data; return;
|
|
|
|
//DASxH -- union { uint16 transferSize; uint16 indirectAddress; };
|
|
case 0x4306: channel.transferSize.byte(1) = data; return;
|
|
|
|
//DASBx
|
|
case 0x4307: channel.indirectBank = data; return;
|
|
|
|
//A2AxL
|
|
case 0x4308: channel.hdmaAddress.byte(0) = data; return;
|
|
|
|
//A2AxH
|
|
case 0x4309: channel.hdmaAddress.byte(1) = data; return;
|
|
|
|
//NTRLx
|
|
case 0x430a: channel.lineCounter = data; return;
|
|
|
|
//???
|
|
case 0x430b:
|
|
case 0x430f: channel.unknown = data; return;
|
|
|
|
}
|
|
}
|