diff options
Diffstat (limited to 'llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll | 21 |
1 files changed, 11 insertions, 10 deletions
diff --git a/llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll b/llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll index a31aebcab24..1b81d04c6e2 100644 --- a/llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll +++ b/llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll @@ -1820,17 +1820,17 @@ define i8 @test_v16i8(<16 x i8> %a0) { ; AVX2-LABEL: test_v16i8: ; AVX2: # %bb.0: ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] -; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero -; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero -; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero +; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero +; AVX2-NEXT: vpmullw %ymm1, %ymm0, %ymm0 +; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0 +; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm1 +; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3] +; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero +; AVX2-NEXT: vpmullw %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255] -; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 -; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm2 -; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[1,1,2,3] -; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero -; AVX2-NEXT: vpmullw %xmm2, %xmm0, %xmm0 -; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 -; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm2 +; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm2 +; AVX2-NEXT: vpackuswb %xmm0, %xmm2, %xmm2 ; AVX2-NEXT: vpsrld $16, %xmm2, %xmm2 ; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero ; AVX2-NEXT: vpmullw %xmm2, %xmm0, %xmm0 @@ -1840,6 +1840,7 @@ define i8 @test_v16i8(<16 x i8> %a0) { ; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0 ; AVX2-NEXT: vpextrb $0, %xmm0, %eax ; AVX2-NEXT: # kill: def $al killed $al killed $eax +; AVX2-NEXT: vzeroupper ; AVX2-NEXT: retq ; ; AVX512BW-LABEL: test_v16i8: |
