RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 19:52:54 +01:00
Code Issues Projects Releases Wiki Activity

fix PR8900, a shuffle miscompilation. Patch by Nadav Rotem!

Browse Source 
llvm-svn: 122921
This commit is contained in:
Chris Lattner 2011-01-05 22:28:46 +00:00
parent 0caa2500c0
commit 3ef9db5cd4
2 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/X86/X86InstrSSE.td
View File

@ -5597,9 +5597,9 @@ def : Pat<(v4f32 (X86Unpckhps VR128:$src1, VR128:$src2)),
// Shuffle with UNPCKLPD
def : Pat<(v2f64 (X86Unpcklpd VR128:$src1, (memopv2f64 addr:$src2))),
(VUNPCKLPSrm VR128:$src1, addr:$src2)>, Requires<[HasAVX]>;
(VUNPCKLPDrm VR128:$src1, addr:$src2)>, Requires<[HasAVX]>;
def : Pat<(v2f64 (X86Unpcklpd VR128:$src1, (memopv2f64 addr:$src2))),
(UNPCKLPSrm VR128:$src1, addr:$src2)>;
(UNPCKLPDrm VR128:$src1, addr:$src2)>;
def : Pat<(v2f64 (X86Unpcklpd VR128:$src1, VR128:$src2)),
(VUNPCKLPDrr VR128:$src1, VR128:$src2)>, Requires<[HasAVX]>;
@ -5608,9 +5608,9 @@ def : Pat<(v2f64 (X86Unpcklpd VR128:$src1, VR128:$src2)),
// Shuffle with UNPCKHPD
def : Pat<(v2f64 (X86Unpckhpd VR128:$src1, (memopv2f64 addr:$src2))),
(VUNPCKLPSrm VR128:$src1, addr:$src2)>, Requires<[HasAVX]>;
(VUNPCKHPDrm VR128:$src1, addr:$src2)>, Requires<[HasAVX]>;
def : Pat<(v2f64 (X86Unpckhpd VR128:$src1, (memopv2f64 addr:$src2))),
(UNPCKLPSrm VR128:$src1, addr:$src2)>;
(UNPCKHPDrm VR128:$src1, addr:$src2)>;
def : Pat<(v2f64 (X86Unpckhpd VR128:$src1, VR128:$src2)),
(VUNPCKHPDrr VR128:$src1, VR128:$src2)>, Requires<[HasAVX]>;

13
test/CodeGen/X86/sse2.ll
View File

@ -192,3 +192,16 @@ entry:
; CHECK: test15:
; CHECK: movhlps %xmm1, %xmm0
}
; PR8900
; CHECK: test16:
; CHECK: unpcklpd
; CHECK: ret
define <2 x double> @test16(<4 x double> * nocapture %srcA, <2 x double>* nocapture %dst) {
%i5 = getelementptr inbounds <4 x double>* %srcA, i32 3
%i6 = load <4 x double>* %i5, align 32
%i7 = shufflevector <4 x double> %i6, <4 x double> undef, <2 x i32> <i32 0, i32 2>
ret <2 x double> %i7
}