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

[X86][SSE] Added or combine tests for known bits of vectors 

Part of the yak shaving for D24253

llvm-svn: 280813
This commit is contained in:
Simon Pilgrim 2016-09-07 14:49:50 +00:00
parent 25ad7b52c3
commit 32cfa5ba83
1 changed files with 51 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
llvm/test/CodeGen/X86/combine-or.ll
View File

@ -415,3 +415,54 @@ define <4 x i32> @test2f(<4 x i32> %a, <4 x i32> %b) {
%or = or <4 x i32> %shuf1, %shuf2
ret <4 x i32> %or
}
; (or (and X, c1), c2) -> (and (or X, c2), c1|c2)
define <2 x i64> @or_and_v2i64(<2 x i64> %a0) {
; CHECK-LABEL: or_and_v2i64:
; CHECK: # BB#0:
; CHECK-NEXT: andps {{.*}}(%rip), %xmm0
; CHECK-NEXT: orps {{.*}}(%rip), %xmm0
; CHECK-NEXT: retq
%1 = and <2 x i64> %a0, <i64 1, i64 1>
%2 = or <2 x i64> %1, <i64 3, i64 3>
ret <2 x i64> %2
}
define <4 x i32> @or_and_v4i32(<4 x i32> %a0) {
; CHECK-LABEL: or_and_v4i32:
; CHECK: # BB#0:
; CHECK-NEXT: andps {{.*}}(%rip), %xmm0
; CHECK-NEXT: orps {{.*}}(%rip), %xmm0
; CHECK-NEXT: retq
%1 = and <4 x i32> %a0, <i32 1, i32 1, i32 1, i32 1>
%2 = or <4 x i32> %1, <i32 3, i32 3, i32 3, i32 3>
ret <4 x i32> %2
}
; fold (or x, c) -> c iff (x & ~c) == 0
define <2 x i64> @or_zext_v2i32(<2 x i32> %a0) {
; CHECK-LABEL: or_zext_v2i32:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-NEXT: por {{.*}}(%rip), %xmm0
; CHECK-NEXT: retq
%1 = zext <2 x i32> %a0 to <2 x i64>
%2 = or <2 x i64> %1, <i64 4294967295, i64 4294967295>
ret <2 x i64> %2
}
define <4 x i32> @or_zext_v4i16(<4 x i16> %a0) {
; CHECK-LABEL: or_zext_v4i16:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
; CHECK-NEXT: por {{.*}}(%rip), %xmm0
; CHECK-NEXT: retq
%1 = zext <4 x i16> %a0 to <4 x i32>
%2 = or <4 x i32> %1, <i32 65536, i32 65536, i32 65536, i32 65536>
ret <4 x i32> %2
}