mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 04:30:12 +00:00
ce7cafa960
two or three, open code the equivalent operation which is faster on athlon
and P4 (by a substantial margin).
For example, instead of compiling this:
long long X2(long long Y) { return Y << 2; }
to:
X3_2:
movl 4(%esp), %eax
movl 8(%esp), %edx
shldl $2, %eax, %edx
shll $2, %eax
ret
Compile it to:
X2:
movl 4(%esp), %eax
movl 8(%esp), %ecx
movl %eax, %edx
shrl $30, %edx
leal (%edx,%ecx,4), %edx
shll $2, %eax
ret
Likewise, for << 3, compile to:
X3:
movl 4(%esp), %eax
movl 8(%esp), %ecx
movl %eax, %edx
shrl $29, %edx
leal (%edx,%ecx,8), %edx
shll $3, %eax
ret
This matches icc, except that icc open codes the shifts as adds on the P4.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@17707 91177308-0d34-0410-b5e6-96231b3b80d8
|
||
|---|---|---|
| .. | ||
| .cvsignore | ||
| Makefile | ||
| X86.h | ||
| X86.td | ||
| X86AsmPrinter.cpp | ||
| X86CodeEmitter.cpp | ||
| X86FloatingPoint.cpp | ||
| X86InstrBuilder.h | ||
| X86InstrInfo.cpp | ||
| X86InstrInfo.h | ||
| X86InstrInfo.td | ||
| X86ISelPattern.cpp | ||
| X86ISelSimple.cpp | ||
| X86JITInfo.h | ||
| X86PeepholeOpt.cpp | ||
| X86RegisterInfo.cpp | ||
| X86RegisterInfo.h | ||
| X86RegisterInfo.td | ||
| X86TargetMachine.cpp | ||
| X86TargetMachine.h | ||