diff options
Diffstat (limited to 'llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll | 54 |
1 files changed, 26 insertions, 28 deletions
diff --git a/llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll b/llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll index 87f2630346a..1b35e2fddda 100644 --- a/llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll +++ b/llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll @@ -172,22 +172,21 @@ define <8 x i16> @test_div7_8i16(<8 x i16> %a) nounwind { define <16 x i8> @test_div7_16i8(<16 x i8> %a) nounwind { ; SSE2-LABEL: test_div7_16i8: ; SSE2: # BB#0: -; SSE2-NEXT: movdqa %xmm0, %xmm1 -; SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15] -; SSE2-NEXT: psrlw $8, %xmm1 -; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [37,0,37,0,37,0,37,0,37,0,37,0,37,0,37,0] -; SSE2-NEXT: pmullw %xmm2, %xmm1 -; SSE2-NEXT: psrlw $8, %xmm1 -; SSE2-NEXT: movdqa %xmm0, %xmm3 -; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7] -; SSE2-NEXT: psrlw $8, %xmm3 -; SSE2-NEXT: pmullw %xmm2, %xmm3 -; SSE2-NEXT: psrlw $8, %xmm3 -; SSE2-NEXT: packuswb %xmm1, %xmm3 -; SSE2-NEXT: psubb %xmm3, %xmm0 +; SSE2-NEXT: pxor %xmm1, %xmm1 +; SSE2-NEXT: movdqa %xmm0, %xmm2 +; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15] +; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [37,0,37,0,37,0,37,0,37,0,37,0,37,0,37,0] +; SSE2-NEXT: pmullw %xmm3, %xmm2 +; SSE2-NEXT: psrlw $8, %xmm2 +; SSE2-NEXT: movdqa %xmm0, %xmm4 +; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3],xmm4[4],xmm1[4],xmm4[5],xmm1[5],xmm4[6],xmm1[6],xmm4[7],xmm1[7] +; SSE2-NEXT: pmullw %xmm3, %xmm4 +; SSE2-NEXT: psrlw $8, %xmm4 +; SSE2-NEXT: packuswb %xmm2, %xmm4 +; SSE2-NEXT: psubb %xmm4, %xmm0 ; SSE2-NEXT: psrlw $1, %xmm0 ; SSE2-NEXT: pand {{.*}}(%rip), %xmm0 -; SSE2-NEXT: paddb %xmm3, %xmm0 +; SSE2-NEXT: paddb %xmm4, %xmm0 ; SSE2-NEXT: psrlw $2, %xmm0 ; SSE2-NEXT: pand {{.*}}(%rip), %xmm0 ; SSE2-NEXT: retq @@ -463,23 +462,22 @@ define <8 x i16> @test_rem7_8i16(<8 x i16> %a) nounwind { define <16 x i8> @test_rem7_16i8(<16 x i8> %a) nounwind { ; SSE2-LABEL: test_rem7_16i8: ; SSE2: # BB#0: +; SSE2-NEXT: pxor %xmm1, %xmm1 +; SSE2-NEXT: movdqa %xmm0, %xmm2 +; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15] +; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [37,0,37,0,37,0,37,0,37,0,37,0,37,0,37,0] +; SSE2-NEXT: pmullw %xmm3, %xmm2 +; SSE2-NEXT: psrlw $8, %xmm2 +; SSE2-NEXT: movdqa %xmm0, %xmm4 +; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3],xmm4[4],xmm1[4],xmm4[5],xmm1[5],xmm4[6],xmm1[6],xmm4[7],xmm1[7] +; SSE2-NEXT: pmullw %xmm3, %xmm4 +; SSE2-NEXT: psrlw $8, %xmm4 +; SSE2-NEXT: packuswb %xmm2, %xmm4 ; SSE2-NEXT: movdqa %xmm0, %xmm1 -; SSE2-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15] -; SSE2-NEXT: psrlw $8, %xmm1 -; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [37,0,37,0,37,0,37,0,37,0,37,0,37,0,37,0] -; SSE2-NEXT: pmullw %xmm2, %xmm1 -; SSE2-NEXT: psrlw $8, %xmm1 -; SSE2-NEXT: movdqa %xmm0, %xmm3 -; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7] -; SSE2-NEXT: psrlw $8, %xmm3 -; SSE2-NEXT: pmullw %xmm2, %xmm3 -; SSE2-NEXT: psrlw $8, %xmm3 -; SSE2-NEXT: packuswb %xmm1, %xmm3 -; SSE2-NEXT: movdqa %xmm0, %xmm1 -; SSE2-NEXT: psubb %xmm3, %xmm1 +; SSE2-NEXT: psubb %xmm4, %xmm1 ; SSE2-NEXT: psrlw $1, %xmm1 ; SSE2-NEXT: pand {{.*}}(%rip), %xmm1 -; SSE2-NEXT: paddb %xmm3, %xmm1 +; SSE2-NEXT: paddb %xmm4, %xmm1 ; SSE2-NEXT: psrlw $2, %xmm1 ; SSE2-NEXT: pand {{.*}}(%rip), %xmm1 ; SSE2-NEXT: movdqa %xmm1, %xmm2 |
