aboutsummaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/vector-idiv-udiv-128.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/X86/vector-idiv-udiv-128.ll')
-rw-r--r--test/CodeGen/X86/vector-idiv-udiv-128.ll71
1 files changed, 33 insertions, 38 deletions
diff --git a/test/CodeGen/X86/vector-idiv-udiv-128.ll b/test/CodeGen/X86/vector-idiv-udiv-128.ll
index c4ecaa4a1bcf..1b35e2fdddae 100644
--- a/test/CodeGen/X86/vector-idiv-udiv-128.ll
+++ b/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
@@ -195,7 +194,7 @@ define <16 x i8> @test_div7_16i8(<16 x i8> %a) nounwind {
; SSE41-LABEL: test_div7_16i8:
; SSE41: # BB#0:
; SSE41-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
-; SSE41-NEXT: pmovzxbw {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
+; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [37,37,37,37,37,37,37,37]
; SSE41-NEXT: pmullw %xmm2, %xmm1
; SSE41-NEXT: psrlw $8, %xmm1
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
@@ -214,7 +213,7 @@ define <16 x i8> @test_div7_16i8(<16 x i8> %a) nounwind {
; AVX1-LABEL: test_div7_16i8:
; AVX1: # BB#0:
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
-; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
+; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [37,37,37,37,37,37,37,37]
; AVX1-NEXT: vpmullw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpsrlw $8, %xmm1, %xmm1
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
@@ -233,8 +232,7 @@ define <16 x i8> @test_div7_16i8(<16 x i8> %a) nounwind {
; AVX2-LABEL: test_div7_16i8:
; AVX2: # BB#0:
; AVX2-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
-; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
-; AVX2-NEXT: vpmullw %ymm2, %ymm1, %ymm1
+; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1
; AVX2-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
@@ -464,30 +462,28 @@ 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
; SSE2-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; SSE2-NEXT: psraw $8, %xmm2
-; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7]
-; SSE2-NEXT: psraw $8, %xmm3
+; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [7,7,7,7,7,7,7,7]
; SSE2-NEXT: pmullw %xmm3, %xmm2
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm4, %xmm2
@@ -502,7 +498,7 @@ define <16 x i8> @test_rem7_16i8(<16 x i8> %a) nounwind {
; SSE41-LABEL: test_rem7_16i8:
; SSE41: # BB#0:
; SSE41-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
-; SSE41-NEXT: pmovzxbw {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
+; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [37,37,37,37,37,37,37,37]
; SSE41-NEXT: pmullw %xmm2, %xmm1
; SSE41-NEXT: psrlw $8, %xmm1
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
@@ -533,7 +529,7 @@ define <16 x i8> @test_rem7_16i8(<16 x i8> %a) nounwind {
; AVX1-LABEL: test_rem7_16i8:
; AVX1: # BB#0:
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
-; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
+; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [37,37,37,37,37,37,37,37]
; AVX1-NEXT: vpmullw %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpsrlw $8, %xmm1, %xmm1
; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm0[2,3,0,1]
@@ -563,8 +559,7 @@ define <16 x i8> @test_rem7_16i8(<16 x i8> %a) nounwind {
; AVX2-LABEL: test_rem7_16i8:
; AVX2: # BB#0:
; AVX2-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
-; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
-; AVX2-NEXT: vpmullw %ymm2, %ymm1, %ymm1
+; AVX2-NEXT: vpmullw {{.*}}(%rip), %ymm1, %ymm1
; AVX2-NEXT: vpsrlw $8, %ymm1, %ymm1
; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX2-NEXT: vpackuswb %xmm2, %xmm1, %xmm1
generated by cgit v1.2.3 (git 2.25.1) at 2025-03-06 21:45:39 +0000