llvm-project/llvm/test/CodeGen/X86/combine-and.ll

231 lines
6.7 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s
;
; Verify that the DAGCombiner is able to fold a vector AND into a blend
; if one of the operands to the AND is a vector of all constants, and each
; constant element is either zero or all-ones.
;
define <4 x i32> @test1(<4 x i32> %A) {
; CHECK-LABEL: test1:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 0, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test2(<4 x i32> %A) {
; CHECK-LABEL: test2:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5,6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 0, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test3(<4 x i32> %A) {
; CHECK-LABEL: test3:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5],xmm1[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 -1, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test4(<4 x i32> %A) {
; CHECK-LABEL: test4:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3,4,5],xmm0[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test5(<4 x i32> %A) {
; CHECK-LABEL: test5:
; 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: retq
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 -1, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test6(<4 x i32> %A) {
; CHECK-LABEL: test6:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5],xmm0[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 0, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test7(<4 x i32> %A) {
; CHECK-LABEL: test7:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 -1, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test8(<4 x i32> %A) {
; CHECK-LABEL: test8:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5],xmm0[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 0, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test9(<4 x i32> %A) {
; CHECK-LABEL: test9:
; CHECK: # BB#0:
; CHECK-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 -1, i32 -1, i32 0, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test10(<4 x i32> %A) {
; CHECK-LABEL: test10:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3,4,5],xmm1[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 -1, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test11(<4 x i32> %A) {
; CHECK-LABEL: test11:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3,4,5,6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test12(<4 x i32> %A) {
; CHECK-LABEL: test12:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5],xmm1[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 -1, i32 -1, i32 -1, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test13(<4 x i32> %A) {
; CHECK-LABEL: test13:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5],xmm0[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 -1, i32 -1, i32 0, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test14(<4 x i32> %A) {
; CHECK-LABEL: test14:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 -1, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test15(<4 x i32> %A, <4 x i32> %B) {
; CHECK-LABEL: test15:
; CHECK: # BB#0:
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 -1, i32 -1>
%2 = and <4 x i32> %B, <i32 0, i32 -1, i32 0, i32 0>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @test16(<4 x i32> %A, <4 x i32> %B) {
; CHECK-LABEL: test16:
; CHECK: # BB#0:
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 -1, i32 0>
%2 = and <4 x i32> %B, <i32 0, i32 -1, i32 0, i32 -1>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @test17(<4 x i32> %A, <4 x i32> %B) {
; CHECK-LABEL: test17:
; CHECK: # BB#0:
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5],xmm0[6,7]
; CHECK-NEXT: retq
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 0, i32 -1>
%2 = and <4 x i32> %B, <i32 -1, i32 0, i32 -1, i32 0>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
;
; fold (and (or x, C), D) -> D if (C & D) == D
;
define <2 x i64> @and_or_v2i64(<2 x i64> %a0) {
; CHECK-LABEL: and_or_v2i64:
; CHECK: # BB#0:
; CHECK-NEXT: movaps {{.*#+}} xmm0 = [8,8]
; CHECK-NEXT: retq
%1 = or <2 x i64> %a0, <i64 255, i64 255>
%2 = and <2 x i64> %1, <i64 8, i64 8>
ret <2 x i64> %2
}
define <4 x i32> @and_or_v4i32(<4 x i32> %a0) {
; CHECK-LABEL: and_or_v4i32:
; CHECK: # BB#0:
; CHECK-NEXT: movaps {{.*#+}} xmm0 = [3,3,3,3]
; CHECK-NEXT: retq
%1 = or <4 x i32> %a0, <i32 15, i32 15, i32 15, i32 15>
%2 = and <4 x i32> %1, <i32 3, i32 3, i32 3, i32 3>
ret <4 x i32> %2
}
;
; known bits folding
;
define <2 x i64> @and_or_zext_v2i32(<2 x i32> %a0) {
; CHECK-LABEL: and_or_zext_v2i32:
; CHECK: # BB#0:
; CHECK-NEXT: xorps %xmm0, %xmm0
; CHECK-NEXT: retq
%1 = zext <2 x i32> %a0 to <2 x i64>
%2 = or <2 x i64> %1, <i64 1, i64 1>
%3 = and <2 x i64> %2, <i64 4294967296, i64 4294967296>
ret <2 x i64> %3
}
define <4 x i32> @and_or_zext_v4i16(<4 x i16> %a0) {
; CHECK-LABEL: and_or_zext_v4i16:
; CHECK: # BB#0:
; CHECK-NEXT: xorps %xmm0, %xmm0
; CHECK-NEXT: retq
%1 = zext <4 x i16> %a0 to <4 x i32>
%2 = or <4 x i32> %1, <i32 1, i32 1, i32 1, i32 1>
%3 = and <4 x i32> %2, <i32 65536, i32 65536, i32 65536, i32 65536>
ret <4 x i32> %3
}