eden-emu/eden
24
3
Fork 15
Code Issues 138 Pull requests 56 Projects 1 Releases Packages Wiki Activity Actions

[dynarmic] regalloc use scratchimpl that uses all instead of iteraiting
All checks were successful
eden-license / license-header (pull_request) Successful in 34s
Details

Browse source 
Signed-off-by: lizzie <lizzie@eden-emu.dev>
This commit is contained in:
lizzie 2025-09-09 14:46:35 +00:00
parent 615f2935aa
commit 7b7588e9fb
Signed by: Lizzie
GPG key ID: 00287378CADCAB13
2 changed files with 18 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/dynarmic/src/dynarmic/backend/x64/a64_emit_x64.cpp
View file

@ -122,9 +122,9 @@ A64EmitX64::BlockDescriptor A64EmitX64::Emit(IR::Block& block) noexcept {
auto const opcode = inst.GetOpcode(); auto const opcode = inst.GetOpcode();
// Call the relevant Emit* member function. // Call the relevant Emit* member function.
switch (opcode) { switch (opcode) {
#define OPCODE(name, type, ...) [[likely]] case IR::Opcode::name: goto opcode_branch; #define OPCODE(name, type, ...) case IR::Opcode::name: goto opcode_branch;
#define A32OPC(name, type, ...) #define A32OPC(name, type, ...)
#define A64OPC(name, type, ...) [[likely]] case IR::Opcode::A64##name: goto a64_branch; #define A64OPC(name, type, ...) case IR::Opcode::A64##name: goto a64_branch;
#include "dynarmic/ir/opcodes.inc" #include "dynarmic/ir/opcodes.inc"
#undef OPCODE #undef OPCODE
#undef A32OPC #undef A32OPC

30
src/dynarmic/src/dynarmic/backend/x64/reg_alloc.cpp
View file

@ -367,10 +367,20 @@ void RegAlloc::HostCall(IR::Inst* result_def,
if (result_def) { if (result_def) {
DefineValueImpl(result_def, ABI_RETURN); DefineValueImpl(result_def, ABI_RETURN);
} }
for (size_t i = 0; i < args.size(); i++) {
if (args[i]) {
UseScratch(*args[i], args_hostloc[i]);
} else {
ScratchGpr(args_hostloc[i]); // TODO: Force spill
}
}
// Must match with with ScratchImpl
for (auto const gpr : other_caller_save) {
MoveOutOfTheWay(gpr);
LocInfo(gpr).WriteLock();
}
for (size_t i = 0; i < args.size(); i++) { for (size_t i = 0; i < args.size(); i++) {
if (args[i] && !args[i]->get().IsVoid()) { if (args[i] && !args[i]->get().IsVoid()) {
UseScratch(*args[i], args_hostloc[i]);
// LLVM puts the burden of zero-extension of 8 and 16 bit values on the caller instead of the callee // LLVM puts the burden of zero-extension of 8 and 16 bit values on the caller instead of the callee
const Xbyak::Reg64 reg = HostLocToReg64(args_hostloc[i]); const Xbyak::Reg64 reg = HostLocToReg64(args_hostloc[i]);
switch (args[i]->get().GetType()) { switch (args[i]->get().GetType()) {
@ -390,14 +400,6 @@ void RegAlloc::HostCall(IR::Inst* result_def,
} }
} }
} }
for (size_t i = 0; i < args.size(); i++)
if (!args[i]) {
// TODO: Force spill
ScratchGpr(args_hostloc[i]);
}
for (auto const caller_saved : other_caller_save)
ScratchImpl({caller_saved});
} }
void RegAlloc::AllocStackSpace(const size_t stack_space) noexcept { void RegAlloc::AllocStackSpace(const size_t stack_space) noexcept {
@ -560,13 +562,12 @@ void RegAlloc::SpillRegister(HostLoc loc) noexcept {
} }
HostLoc RegAlloc::FindFreeSpill(bool is_xmm) const noexcept { HostLoc RegAlloc::FindFreeSpill(bool is_xmm) const noexcept {
#if 0
// TODO(lizzie): Ok, Windows hates XMM spills, this means less perf for windows // TODO(lizzie): Ok, Windows hates XMM spills, this means less perf for windows
// but it's fine anyways. We can find other ways to cheat it later - but which?!?! // but it's fine anyways. We can find other ways to cheat it later - but which?!?!
// we should NOT save xmm each block entering... MAYBE xbyak has a bug on start/end? // we should NOT save xmm each block entering... MAYBE xbyak has a bug on start/end?
// TODO(lizzie): This needs to be investigated further later. // TODO(lizzie): This needs to be investigated further later.
// Do not spill XMM into other XMM silly // Do not spill XMM into other XMM silly
if (!is_xmm) { /*if (!is_xmm) {
// TODO(lizzie): Using lower (xmm0 and such) registers results in issues/crashes - INVESTIGATE WHY // TODO(lizzie): Using lower (xmm0 and such) registers results in issues/crashes - INVESTIGATE WHY
// Intel recommends to spill GPR onto XMM registers IF POSSIBLE // Intel recommends to spill GPR onto XMM registers IF POSSIBLE
// TODO(lizzie): Issues on DBZ, theory: Scratch XMM not properly restored after a function call? // TODO(lizzie): Issues on DBZ, theory: Scratch XMM not properly restored after a function call?
@ -574,8 +575,9 @@ HostLoc RegAlloc::FindFreeSpill(bool is_xmm) const noexcept {
for (size_t i = size_t(HostLoc::XMM15); i >= size_t(HostLoc::XMM3); --i) for (size_t i = size_t(HostLoc::XMM15); i >= size_t(HostLoc::XMM3); --i)
if (const auto loc = HostLoc(i); LocInfo(loc).IsEmpty()) if (const auto loc = HostLoc(i); LocInfo(loc).IsEmpty())
return loc; return loc;
} }*/
#endif // TODO: Doing this would mean saving XMM on each call... need to benchmark the benefits
// of spilling on XMM versus the potential cost of using XMM registers.....
// Otherwise go to stack spilling // Otherwise go to stack spilling
for (size_t i = size_t(HostLoc::FirstSpill); i < hostloc_info.size(); ++i) for (size_t i = size_t(HostLoc::FirstSpill); i < hostloc_info.size(); ++i)
if (const auto loc = HostLoc(i); LocInfo(loc).IsEmpty()) if (const auto loc = HostLoc(i); LocInfo(loc).IsEmpty())