mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 19:52:54 +01:00
1cde11aa95
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.
llvm-svn: 17707
|
||
|---|---|---|
| .. | ||
| Analysis | ||
| AsmParser | ||
| Bytecode | ||
| CodeGen | ||
| Debugger | ||
| ExecutionEngine | ||
| Linker | ||
| Support | ||
| System | ||
| Target | ||
| Transforms | ||
| VMCore | ||
| Makefile | ||