forked from OSchip/llvm-project
166 lines
6.7 KiB
LLVM
166 lines
6.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse2 | FileCheck %s --check-prefix=SSE
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2 | FileCheck %s --check-prefix=AVX
|
|
|
|
; xor undef, undef --> 0 because it's not worth fighting to make that return undef?
|
|
|
|
define <4 x i64> @xor_insert_insert(<2 x i64> %x, <2 x i64> %y) {
|
|
; SSE-LABEL: xor_insert_insert:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: xorps %xmm1, %xmm0
|
|
; SSE-NEXT: xorps %xmm1, %xmm1
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: xor_insert_insert:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vxorps %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%xw = shufflevector <2 x i64> %x, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
|
|
%yw = shufflevector <2 x i64> %y, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
|
|
%r = xor <4 x i64> %xw, %yw
|
|
ret <4 x i64> %r
|
|
}
|
|
|
|
define <4 x i64> @xor_insert_insert_high_half(<2 x i64> %x, <2 x i64> %y) {
|
|
; SSE-LABEL: xor_insert_insert_high_half:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: xorps %xmm0, %xmm1
|
|
; SSE-NEXT: xorps %xmm0, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: xor_insert_insert_high_half:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vxorps %xmm1, %xmm0, %xmm0
|
|
; AVX-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; AVX-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
|
; AVX-NEXT: retq
|
|
%xw = shufflevector <2 x i64> %x, <2 x i64> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1>
|
|
%yw = shufflevector <2 x i64> %y, <2 x i64> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1>
|
|
%r = xor <4 x i64> %xw, %yw
|
|
ret <4 x i64> %r
|
|
}
|
|
|
|
; All elements of the add are undefined:
|
|
; x[0] , x[1] , x[2] , x[3], u , u , u , u
|
|
; + u , u , u , u , 42 , 43 , 44 , 45
|
|
|
|
define <8 x i32> @add_undef_elts(<4 x i32> %x) {
|
|
; SSE-LABEL: add_undef_elts:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: add_undef_elts:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: retq
|
|
%extend = shufflevector <4 x i32> %x, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%bogus_bo = add <8 x i32> %extend, <i32 undef, i32 undef, i32 undef, i32 undef, i32 42, i32 43, i32 44, i32 12>
|
|
%arbitrary_shuf = shufflevector <8 x i32> %bogus_bo, <8 x i32> undef, <8 x i32> <i32 6, i32 0, i32 5, i32 4, i32 3, i32 2, i32 1, i32 7>
|
|
ret <8 x i32> %arbitrary_shuf
|
|
}
|
|
|
|
; Verify that constant operand 0 for a sub works too.
|
|
|
|
define <8 x i32> @sub_undef_elts(<4 x i32> %x) {
|
|
; SSE-LABEL: sub_undef_elts:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: sub_undef_elts:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: retq
|
|
%extend = shufflevector <4 x i32> %x, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%bogus_bo = sub <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 42, i32 43, i32 44, i32 12>, %extend
|
|
%arbitrary_shuf = shufflevector <8 x i32> %bogus_bo, <8 x i32> undef, <8 x i32> <i32 1, i32 0, i32 5, i32 4, i32 3, i32 2, i32 6, i32 7>
|
|
ret <8 x i32> %arbitrary_shuf
|
|
}
|
|
|
|
; and undef, C --> 0, so this tests that we are tracking known zero lanes.
|
|
|
|
define <4 x i64> @and_undef_elts(<2 x i64> %x) {
|
|
; SSE-LABEL: and_undef_elts:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: xorps %xmm0, %xmm0
|
|
; SSE-NEXT: xorps %xmm1, %xmm1
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: and_undef_elts:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
|
; AVX-NEXT: vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
|
|
; AVX-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[3,0,1,2]
|
|
; AVX-NEXT: retq
|
|
%extend = shufflevector <2 x i64> %x, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
|
|
%bogus_bo = and <4 x i64> %extend, <i64 undef, i64 undef, i64 42, i64 43>
|
|
%arbitrary_shuf = shufflevector <4 x i64> %bogus_bo, <4 x i64> undef, <4 x i32> <i32 3, i32 0, i32 1, i32 2>
|
|
ret <4 x i64> %arbitrary_shuf
|
|
}
|
|
|
|
; or undef, C --> -1, so this tests that we are tracking known all-ones lanes.
|
|
|
|
define <4 x i64> @or_undef_elts(<2 x i64> %x) {
|
|
; SSE-LABEL: or_undef_elts:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: pcmpeqd %xmm0, %xmm0
|
|
; SSE-NEXT: pcmpeqd %xmm1, %xmm1
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: or_undef_elts:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
|
; AVX-NEXT: vorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
|
|
; AVX-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[3,0,1,2]
|
|
; AVX-NEXT: retq
|
|
%extend = shufflevector <2 x i64> %x, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
|
|
%bogus_bo = or <4 x i64> %extend, <i64 undef, i64 undef, i64 42, i64 43>
|
|
%arbitrary_shuf = shufflevector <4 x i64> %bogus_bo, <4 x i64> undef, <4 x i32> <i32 3, i32 0, i32 1, i32 2>
|
|
ret <4 x i64> %arbitrary_shuf
|
|
}
|
|
|
|
; Verify that this isn't limited to high/low halves.
|
|
|
|
define <8 x i32> @xor_undef_elts(<4 x i32> %x) {
|
|
; SSE-LABEL: xor_undef_elts:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: xor_undef_elts:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: retq
|
|
%extend = shufflevector <4 x i32> %x, <4 x i32> undef, <8 x i32> <i32 undef, i32 undef, i32 1, i32 3, i32 0, i32 2, i32 undef, i32 undef>
|
|
%bogus_bo = xor <8 x i32> %extend, <i32 42, i32 43, i32 undef, i32 undef, i32 undef, i32 undef, i32 44, i32 12>
|
|
%arbitrary_shuf = shufflevector <8 x i32> %bogus_bo, <8 x i32> undef, <8 x i32> <i32 6, i32 1, i32 5, i32 4, i32 3, i32 2, i32 0, i32 7>
|
|
ret <8 x i32> %arbitrary_shuf
|
|
}
|
|
|
|
; Verify that this isn't limited to high/low halves
|
|
; Special case: the undef-ness of the 1st shuffle may be lost if we turn that into vector concat.
|
|
|
|
define <8 x i32> @xor_undef_elts_alt(<4 x i32> %x) {
|
|
; SSE-LABEL: xor_undef_elts_alt:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movaps %xmm0, %xmm1
|
|
; SSE-NEXT: movaps {{.*#+}} xmm2 = <u,u,44,12>
|
|
; SSE-NEXT: xorps %xmm0, %xmm2
|
|
; SSE-NEXT: xorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
|
|
; SSE-NEXT: movaps %xmm1, %xmm0
|
|
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,0],xmm2[2,0]
|
|
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[2,0],xmm2[1,0]
|
|
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[3,0],xmm1[0,0]
|
|
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,2],xmm2[2,0]
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: xor_undef_elts_alt:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
|
; AVX-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
|
; AVX-NEXT: vxorps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %ymm0, %ymm0
|
|
; AVX-NEXT: vmovaps {{.*#+}} ymm1 = [6,1,5,4,3,2,0,7]
|
|
; AVX-NEXT: vpermps %ymm0, %ymm1, %ymm0
|
|
; AVX-NEXT: retq
|
|
%extend = shufflevector <4 x i32> %x, <4 x i32> undef, <8 x i32> <i32 undef, i32 undef, i32 2, i32 3, i32 0, i32 1, i32 undef, i32 undef>
|
|
%bogus_bo = xor <8 x i32> %extend, <i32 42, i32 43, i32 undef, i32 undef, i32 undef, i32 undef, i32 44, i32 12>
|
|
%arbitrary_shuf = shufflevector <8 x i32> %bogus_bo, <8 x i32> undef, <8 x i32> <i32 6, i32 1, i32 5, i32 4, i32 3, i32 2, i32 0, i32 7>
|
|
ret <8 x i32> %arbitrary_shuf
|
|
}
|
|
|