RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 03:33:20 +01:00
Code Issues Projects Releases Wiki Activity

Fixed vsqrt.ss intrinsic usage - order of input operands was wrong.

Browse Source 
Added a test.
Thanks Bruno for reviewing the patch.

llvm-svn: 145403
This commit is contained in:
Elena Demikhovsky 2011-11-29 15:00:45 +00:00
parent 637e60afdd
commit 735cff1fa8
2 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/Target/X86/X86InstrSSE.td
View File

@ -2872,7 +2872,7 @@ multiclass sse1_fp_unop_s_avx<bits<8> opc, string OpcodeStr> {
!strconcat(OpcodeStr,
"ss\t{$src2, $src1, $dst|$dst, $src1, $src2}"), []>;
def SSm_Int : SSI<opc, MRMSrcMem, (outs VR128:$dst),
(ins ssmem:$src1, VR128:$src2),
(ins VR128:$src1, ssmem:$src2),
!strconcat(OpcodeStr,
"ss\t{$src2, $src1, $dst|$dst, $src1, $src2}"), []>;
}

11
test/CodeGen/X86/avx-arith.ll
View File

@ -259,3 +259,14 @@ define <4 x i64> @mul-v4i64(<4 x i64> %i, <4 x i64> %j) nounwind readnone {
ret <4 x i64> %x
}
declare <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float>) nounwind readnone
define <4 x float> @int_sqrt_ss() {
; CHECK: int_sqrt_ss
; CHECK: vsqrtss
%x0 = load float addrspace(1)* undef, align 8
%x1 = insertelement <4 x float> undef, float %x0, i32 0
%x2 = call <4 x float> @llvm.x86.sse.sqrt.ss(<4 x float> %x1) nounwind
ret <4 x float> %x2
}