RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Code Issues Projects Releases Wiki Activity

we should pattern match the SSE complex arithmetic ops.

Browse Source 
llvm-svn: 112109
This commit is contained in:
Chris Lattner 2010-08-25 23:31:42 +00:00
parent b85b3cf91f
commit eb4c7e43cc
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
lib/Target/X86/README-SSE.txt
View File

@ -17,6 +17,32 @@ __m128i shift_right(__m128i value, unsigned long offset) {
_mm_loadu_si128((__m128 *) (___m128i_shift_right + offset)));
}
//===---------------------------------------------------------------------===//
SSE has instructions for doing operations on complex numbers, we should pattern
match them. Compiling this:
_Complex float f32(_Complex float A, _Complex float B) {
return A+B;
}
into:
_f32:
movdqa %xmm0, %xmm2
addss %xmm1, %xmm2
pshufd $16, %xmm2, %xmm2
pshufd $1, %xmm1, %xmm1
pshufd $1, %xmm0, %xmm0
addss %xmm1, %xmm0
pshufd $16, %xmm0, %xmm1
movdqa %xmm2, %xmm0
unpcklps %xmm1, %xmm0
ret
seems silly.
//===---------------------------------------------------------------------===//
Expand libm rounding functions inline: Significant speedups possible.