ShuriZma
/
dolphin
mirror of https://github.com/dolphin-emu/dolphin.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

JitArm64: Optiming shifting and masking PC in slow dispatcher 

Instead of shifting left by 1, we can first shift right by 2 and then
left by 3. This is both faster and smaller, because we get the right
shift for free with the masking and the left shift for free with the
address calculation. It also happens to match the pseudocode more
closely, which is always nice for readability.
This commit is contained in:
JosJuice 2023-08-19 13:51:03 +02:00
parent c9347a2a19
commit 9e970bcb30
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
Source/Core/Core/PowerPC/JitArm64/JitAsm.cpp
View File

@ -123,11 +123,10 @@ void JitArm64::GenerateAsm()
ARM64Reg msr2 = ARM64Reg::W13; ARM64Reg msr2 = ARM64Reg::W13;
// iCache[(address >> 2) & iCache_Mask]; // iCache[(address >> 2) & iCache_Mask];
ORR(pc_masked, ARM64Reg::WZR, UBFX(pc_masked, DISPATCHER_PC, 2,
LogicalImm(JitBaseBlockCache::FAST_BLOCK_MAP_FALLBACK_MASK << 3, 32)); MathUtil::IntLog2(JitBaseBlockCache::FAST_BLOCK_MAP_FALLBACK_ELEMENTS) - 2);
AND(pc_masked, pc_masked, DISPATCHER_PC, ArithOption(DISPATCHER_PC, ShiftType::LSL, 1));
MOVP2R(cache_base, GetBlockCache()->GetFastBlockMapFallback()); MOVP2R(cache_base, GetBlockCache()->GetFastBlockMapFallback());
LDR(block, cache_base, EncodeRegTo64(pc_masked)); LDR(block, cache_base, ArithOption(EncodeRegTo64(pc_masked), true));
FixupBranch not_found = CBZ(block); FixupBranch not_found = CBZ(block);
// b.effectiveAddress != addr || b.msrBits != msr // b.effectiveAddress != addr || b.msrBits != msr