diff options
Diffstat (limited to 'llvm/test')
-rw-r--r-- | llvm/test/CodeGen/X86/combine-udiv.ll | 3 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll | 9 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll | 32 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/vector-reduce-mul.ll | 32 |
4 files changed, 26 insertions, 50 deletions
diff --git a/llvm/test/CodeGen/X86/combine-udiv.ll b/llvm/test/CodeGen/X86/combine-udiv.ll index bfd3095ab96..9da6a988e77 100644 --- a/llvm/test/CodeGen/X86/combine-udiv.ll +++ b/llvm/test/CodeGen/X86/combine-udiv.ll @@ -702,9 +702,6 @@ define <16 x i8> @combine_vec_udiv_nonuniform4(<16 x i8> %x) { ; AVX2-NEXT: vmovd %eax, %xmm2 ; AVX2-NEXT: vpmullw %ymm2, %ymm1, %ymm1 ; AVX2-NEXT: vpsrlw $8, %ymm1, %ymm1 -; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2 -; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1 -; 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 {{.*}}(%rip), %ymm1, %ymm1 ; AVX2-NEXT: vpsrlw $8, %ymm1, %ymm1 ; AVX2-NEXT: vpackuswb %xmm0, %xmm1, %xmm1 diff --git a/llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll b/llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll index ac6fe217e38..c34f46ba4d9 100644 --- a/llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll +++ b/llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll @@ -387,9 +387,6 @@ define <16 x i8> @test_divconstant_16i8(<16 x i8> %a) nounwind { ; AVX2NOBW-NEXT: vpmovzxbw {{.*#+}} ymm1 = 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 ; AVX2NOBW-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1 ; AVX2NOBW-NEXT: vpsrlw $8, %ymm1, %ymm1 -; AVX2NOBW-NEXT: vextracti128 $1, %ymm1, %xmm2 -; AVX2NOBW-NEXT: vpackuswb %xmm2, %xmm1, %xmm1 -; AVX2NOBW-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 ; AVX2NOBW-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1 ; AVX2NOBW-NEXT: vpsrlw $8, %ymm1, %ymm1 ; AVX2NOBW-NEXT: vextracti128 $1, %ymm1, %xmm2 @@ -910,9 +907,6 @@ define <16 x i8> @test_remconstant_16i8(<16 x i8> %a) nounwind { ; AVX2NOBW-NEXT: vpmovzxbw {{.*#+}} ymm1 = 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 ; AVX2NOBW-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1 ; AVX2NOBW-NEXT: vpsrlw $8, %ymm1, %ymm1 -; AVX2NOBW-NEXT: vextracti128 $1, %ymm1, %xmm2 -; AVX2NOBW-NEXT: vpackuswb %xmm2, %xmm1, %xmm1 -; AVX2NOBW-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 ; AVX2NOBW-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1 ; AVX2NOBW-NEXT: vpsrlw $8, %ymm1, %ymm1 ; AVX2NOBW-NEXT: vextracti128 $1, %ymm1, %xmm2 @@ -927,9 +921,6 @@ define <16 x i8> @test_remconstant_16i8(<16 x i8> %a) nounwind { ; AVX2NOBW-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 ; AVX2NOBW-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1 ; AVX2NOBW-NEXT: vpsrlw $8, %ymm1, %ymm1 -; AVX2NOBW-NEXT: vextracti128 $1, %ymm1, %xmm2 -; AVX2NOBW-NEXT: vpackuswb %xmm2, %xmm1, %xmm1 -; AVX2NOBW-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 ; AVX2NOBW-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1 ; AVX2NOBW-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm1 ; AVX2NOBW-NEXT: vextracti128 $1, %ymm1, %xmm2 diff --git a/llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll b/llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll index 360b605da78..e30da07e635 100644 --- a/llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll +++ b/llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll @@ -1840,27 +1840,21 @@ define i8 @test_v16i8(<16 x i8> %a0) { ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; 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: vmovdqa {{.*#+}} ymm1 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255] -; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2 -; AVX2-NEXT: vpackuswb %xmm2, %xmm0, %xmm0 -; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[1,1,2,3] -; 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: vpmullw %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255] +; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm2 +; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[1,1,2,3] ; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero,xmm2[8],zero,xmm2[9],zero,xmm2[10],zero,xmm2[11],zero,xmm2[12],zero,xmm2[13],zero,xmm2[14],zero,xmm2[15],zero -; AVX2-NEXT: vpmullw %ymm2, %ymm0, %ymm0 -; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2 -; AVX2-NEXT: vpackuswb %xmm2, %xmm0, %xmm0 -; AVX2-NEXT: vpsrld $16, %xmm0, %xmm2 -; 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: vpmullw %xmm2, %xmm0, %xmm0 +; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm2 +; AVX2-NEXT: vpsrld $16, %xmm2, %xmm2 ; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero,xmm2[8],zero,xmm2[9],zero,xmm2[10],zero,xmm2[11],zero,xmm2[12],zero,xmm2[13],zero,xmm2[14],zero,xmm2[15],zero -; AVX2-NEXT: vpmullw %ymm2, %ymm0, %ymm0 -; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 -; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0 -; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1 -; 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: vpmullw %xmm2, %xmm0, %xmm0 +; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm1 +; AVX2-NEXT: vpsrlw $8, %xmm1, %xmm1 ; 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 %xmm1, %xmm0, %xmm0 ; AVX2-NEXT: vpextrb $0, %xmm0, %eax diff --git a/llvm/test/CodeGen/X86/vector-reduce-mul.ll b/llvm/test/CodeGen/X86/vector-reduce-mul.ll index 32da534d42d..f5ce68807ce 100644 --- a/llvm/test/CodeGen/X86/vector-reduce-mul.ll +++ b/llvm/test/CodeGen/X86/vector-reduce-mul.ll @@ -1795,27 +1795,21 @@ define i8 @test_v16i8(<16 x i8> %a0) { ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; 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: vmovdqa {{.*#+}} ymm1 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255] -; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2 -; AVX2-NEXT: vpackuswb %xmm2, %xmm0, %xmm0 -; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[1,1,2,3] -; 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: vpmullw %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vmovdqa {{.*#+}} xmm1 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255] +; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm2 +; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[1,1,2,3] ; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero,xmm2[8],zero,xmm2[9],zero,xmm2[10],zero,xmm2[11],zero,xmm2[12],zero,xmm2[13],zero,xmm2[14],zero,xmm2[15],zero -; AVX2-NEXT: vpmullw %ymm2, %ymm0, %ymm0 -; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2 -; AVX2-NEXT: vpackuswb %xmm2, %xmm0, %xmm0 -; AVX2-NEXT: vpsrld $16, %xmm0, %xmm2 -; 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: vpmullw %xmm2, %xmm0, %xmm0 +; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm2 +; AVX2-NEXT: vpsrld $16, %xmm2, %xmm2 ; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero,xmm2[8],zero,xmm2[9],zero,xmm2[10],zero,xmm2[11],zero,xmm2[12],zero,xmm2[13],zero,xmm2[14],zero,xmm2[15],zero -; AVX2-NEXT: vpmullw %ymm2, %ymm0, %ymm0 -; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0 -; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 -; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0 -; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1 -; 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: vpmullw %xmm2, %xmm0, %xmm0 +; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0 +; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm1 +; AVX2-NEXT: vpsrlw $8, %xmm1, %xmm1 ; 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 %xmm1, %xmm0, %xmm0 ; AVX2-NEXT: vpextrb $0, %xmm0, %eax |