mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-07 16:54:48 +00:00
addc55af6c
and is already available, instead of falling back to emitting a load, fall
back to emitting a reg-reg copy. This generates significantly better code
for some SSE testcases, as SSE has lots of two-address instructions and
none of them are read/modify/write. As one example, this change does:
pshufd %XMM5, XMMWORD PTR [%ESP + 84], 255
xorps %XMM2, %XMM5
cmpltps %XMM1, %XMM0
- movaps XMMWORD PTR [%ESP + 52], %XMM0
- movapd %XMM6, XMMWORD PTR [%ESP + 52]
+ movaps %XMM6, %XMM0
cmpltps %XMM6, XMMWORD PTR [%ESP + 68]
movapd XMMWORD PTR [%ESP + 52], %XMM6
movaps %XMM6, %XMM0
cmpltps %XMM6, XMMWORD PTR [%ESP + 36]
cmpltps %XMM3, %XMM0
- movaps XMMWORD PTR [%ESP + 20], %XMM0
- movapd %XMM7, XMMWORD PTR [%ESP + 20]
+ movaps %XMM7, %XMM0
cmpltps %XMM7, XMMWORD PTR [%ESP + 4]
movapd XMMWORD PTR [%ESP + 20], %XMM7
cmpltps %XMM4, %XMM0
... which is far better than a store followed by a load!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28001 91177308-0d34-0410-b5e6-96231b3b80d8
|
||
|---|---|---|
| .. | ||
| SelectionDAG | ||
| AsmPrinter.cpp | ||
| BranchFolding.cpp | ||
| DwarfWriter.cpp | ||
| ELFWriter.cpp | ||
| IntrinsicLowering.cpp | ||
| LiveInterval.cpp | ||
| LiveIntervalAnalysis.cpp | ||
| LiveVariables.cpp | ||
| MachineBasicBlock.cpp | ||
| MachineCodeEmitter.cpp | ||
| MachineDebugInfo.cpp | ||
| MachineFunction.cpp | ||
| MachineInstr.cpp | ||
| Makefile | ||
| Passes.cpp | ||
| PHIElimination.cpp | ||
| PhysRegTracker.h | ||
| PrologEpilogInserter.cpp | ||
| RegAllocLinearScan.cpp | ||
| RegAllocLocal.cpp | ||
| RegAllocSimple.cpp | ||
| TwoAddressInstructionPass.cpp | ||
| UnreachableBlockElim.cpp | ||
| VirtRegMap.cpp | ||
| VirtRegMap.h | ||