maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][XOP] Add test case for PR31296 

llvm-svn: 288858
This commit is contained in:
Simon Pilgrim 2016-12-06 22:50:13 +00:00
parent 0a76e3241f
commit 0559b9e557
1 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll
View File

@ -341,3 +341,23 @@ define <16 x i8> @constant_fold_vpperm() {
%1 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> <i8 0, i8 -1, i8 -2, i8 -3, i8 -4, i8 -5, i8 -6, i8 -7, i8 -8, i8 -9, i8 -10, i8 -11, i8 -12, i8 -13, i8 -14, i8 -15>, <16 x i8> <i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>, <16 x i8> <i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16>) %1 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> <i8 0, i8 -1, i8 -2, i8 -3, i8 -4, i8 -5, i8 -6, i8 -7, i8 -8, i8 -9, i8 -10, i8 -11, i8 -12, i8 -13, i8 -14, i8 -15>, <16 x i8> <i8 15, i8 14, i8 13, i8 12, i8 11, i8 10, i8 9, i8 8, i8 7, i8 6, i8 5, i8 4, i8 3, i8 2, i8 1, i8 0>, <16 x i8> <i8 31, i8 30, i8 29, i8 28, i8 27, i8 26, i8 25, i8 24, i8 23, i8 22, i8 21, i8 20, i8 19, i8 18, i8 17, i8 16>)
ret <16 x i8> %1 ret <16 x i8> %1
} }
define <4 x float> @PR31296(i8* %in) {
; X32-LABEL: PR31296:
; X32: # BB#0: # %entry
; X32-NEXT: vmovaps {{.*#+}} xmm0 = [1.000000e+00,0.000000e+00,0.000000e+00,1.000000e+00]
; X32-NEXT: retl
;
; X64-LABEL: PR31296:
; X64: # BB#0: # %entry
; X64-NEXT: vmovaps {{.*#+}} xmm0 = [1.000000e+00,0.000000e+00,0.000000e+00,1.000000e+00]
; X64-NEXT: retq
entry:
%0 = getelementptr i8, i8* %in, i32 0
%1 = bitcast i8* %0 to i32*
%2 = load i32, i32* %1
%3 = zext i32 %2 to i128
%4 = bitcast i128 %3 to <4 x float>
%5 = shufflevector <4 x float> %4, <4 x float> <float 0.000000e+00, float 1.000000e+00, float undef, float undef>, <4 x i32> <i32 0, i32 4, i32 4, i32 5>
ret <4 x float> %5
}