summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/X86/vector-zext.ll
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/X86/vector-zext.ll')
-rw-r--r--llvm/test/CodeGen/X86/vector-zext.ll113
1 files changed, 61 insertions, 52 deletions
diff --git a/llvm/test/CodeGen/X86/vector-zext.ll b/llvm/test/CodeGen/X86/vector-zext.ll
index a7bf74e0c42..590d61f9173 100644
--- a/llvm/test/CodeGen/X86/vector-zext.ll
+++ b/llvm/test/CodeGen/X86/vector-zext.ll
@@ -397,15 +397,16 @@ entry:
define <8 x i64> @zext_16i8_to_8i64(<16 x i8> %A) nounwind uwtable readnone ssp {
; SSE2-LABEL: zext_16i8_to_8i64:
; SSE2: # %bb.0: # %entry
-; SSE2-NEXT: movdqa %xmm0, %xmm3
+; SSE2-NEXT: movdqa %xmm0, %xmm1
; SSE2-NEXT: pxor %xmm4, %xmm4
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3],xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; SSE2-NEXT: movdqa %xmm3, %xmm1
+; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,2,3]
+; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
+; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3],xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
+; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
; SSE2-NEXT: movdqa %xmm3, %xmm2
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; SSE2-NEXT: punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm4[2],xmm3[3],xmm4[3]
@@ -413,13 +414,15 @@ define <8 x i64> @zext_16i8_to_8i64(<16 x i8> %A) nounwind uwtable readnone ssp
;
; SSSE3-LABEL: zext_16i8_to_8i64:
; SSSE3: # %bb.0: # %entry
-; SSSE3-NEXT: movdqa %xmm0, %xmm3
-; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
-; SSSE3-NEXT: movdqa %xmm3, %xmm1
-; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[2],zero,zero,zero,zero,zero,zero,zero,xmm1[3],zero,zero,zero,zero,zero,zero,zero
+; SSSE3-NEXT: movdqa %xmm0, %xmm1
+; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [0,128,128,128,128,128,128,128,1,128,128,128,128,128,128,128]
+; SSSE3-NEXT: pshufb %xmm4, %xmm0
+; SSSE3-NEXT: movdqa {{.*#+}} xmm5 = [2,128,128,128,128,128,128,128,3,128,128,128,128,128,128,128]
+; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,2,3]
+; SSSE3-NEXT: pshufb %xmm5, %xmm1
; SSSE3-NEXT: movdqa %xmm3, %xmm2
-; SSSE3-NEXT: pshufb {{.*#+}} xmm2 = xmm2[4],zero,zero,zero,zero,zero,zero,zero,xmm2[5],zero,zero,zero,zero,zero,zero,zero
-; SSSE3-NEXT: pshufb {{.*#+}} xmm3 = xmm3[6],zero,zero,zero,zero,zero,zero,zero,xmm3[7],zero,zero,zero,zero,zero,zero,zero
+; SSSE3-NEXT: pshufb %xmm4, %xmm2
+; SSSE3-NEXT: pshufb %xmm5, %xmm3
; SSSE3-NEXT: retq
;
; SSE41-LABEL: zext_16i8_to_8i64:
@@ -1156,15 +1159,16 @@ entry:
define <8 x i64> @load_zext_8i8_to_8i64(<8 x i8> *%ptr) {
; SSE2-LABEL: load_zext_8i8_to_8i64:
; SSE2: # %bb.0: # %entry
-; SSE2-NEXT: movq {{.*#+}} xmm3 = mem[0],zero
+; SSE2-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
; SSE2-NEXT: pxor %xmm4, %xmm4
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3],xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
-; SSE2-NEXT: movdqa %xmm3, %xmm1
+; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,2,3]
+; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE2-NEXT: punpckhdq {{.*#+}} xmm1 = xmm1[2],xmm4[2],xmm1[3],xmm4[3]
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
+; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3],xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
+; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
; SSE2-NEXT: movdqa %xmm3, %xmm2
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; SSE2-NEXT: punpckhdq {{.*#+}} xmm3 = xmm3[2],xmm4[2],xmm3[3],xmm4[3]
@@ -1172,14 +1176,16 @@ define <8 x i64> @load_zext_8i8_to_8i64(<8 x i8> *%ptr) {
;
; SSSE3-LABEL: load_zext_8i8_to_8i64:
; SSSE3: # %bb.0: # %entry
-; SSSE3-NEXT: movq {{.*#+}} xmm3 = mem[0],zero
-; SSSE3-NEXT: movdqa %xmm3, %xmm0
-; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
-; SSSE3-NEXT: movdqa %xmm3, %xmm1
-; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[2],zero,zero,zero,zero,zero,zero,zero,xmm1[3],zero,zero,zero,zero,zero,zero,zero
+; SSSE3-NEXT: movq {{.*#+}} xmm1 = mem[0],zero
+; SSSE3-NEXT: movdqa {{.*#+}} xmm4 = [0,128,128,128,128,128,128,128,1,128,128,128,128,128,128,128]
+; SSSE3-NEXT: movdqa %xmm1, %xmm0
+; SSSE3-NEXT: pshufb %xmm4, %xmm0
+; SSSE3-NEXT: movdqa {{.*#+}} xmm5 = [2,128,128,128,128,128,128,128,3,128,128,128,128,128,128,128]
+; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,2,3]
+; SSSE3-NEXT: pshufb %xmm5, %xmm1
; SSSE3-NEXT: movdqa %xmm3, %xmm2
-; SSSE3-NEXT: pshufb {{.*#+}} xmm2 = xmm2[4],zero,zero,zero,zero,zero,zero,zero,xmm2[5],zero,zero,zero,zero,zero,zero,zero
-; SSSE3-NEXT: pshufb {{.*#+}} xmm3 = xmm3[6],zero,zero,zero,zero,zero,zero,zero,xmm3[7],zero,zero,zero,zero,zero,zero,zero
+; SSSE3-NEXT: pshufb %xmm4, %xmm2
+; SSSE3-NEXT: pshufb %xmm5, %xmm3
; SSSE3-NEXT: retq
;
; SSE41-LABEL: load_zext_8i8_to_8i64:
@@ -1502,8 +1508,8 @@ define <8 x i32> @zext_8i8_to_8i32(<8 x i8> %z) {
; SSE2-LABEL: zext_8i8_to_8i32:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa %xmm0, %xmm1
+; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm2
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
@@ -1512,8 +1518,8 @@ define <8 x i32> @zext_8i8_to_8i32(<8 x i8> %z) {
; SSSE3-LABEL: zext_8i8_to_8i32:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa %xmm0, %xmm1
+; SSSE3-NEXT: pand {{.*}}(%rip), %xmm1
; SSSE3-NEXT: pxor %xmm2, %xmm2
-; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
@@ -1521,28 +1527,32 @@ define <8 x i32> @zext_8i8_to_8i32(<8 x i8> %z) {
;
; SSE41-LABEL: zext_8i8_to_8i32:
; SSE41: # %bb.0: # %entry
-; SSE41-NEXT: pmovzxbd {{.*#+}} xmm2 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
-; SSE41-NEXT: pmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
+; SSE41-NEXT: pand {{.*}}(%rip), %xmm0
+; SSE41-NEXT: pmovzxwd {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSE41-NEXT: pmovzxwd {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; SSE41-NEXT: movdqa %xmm2, %xmm0
; SSE41-NEXT: retq
;
; AVX1-LABEL: zext_8i8_to_8i32:
; AVX1: # %bb.0: # %entry
-; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
-; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: zext_8i8_to_8i32:
; AVX2: # %bb.0: # %entry
-; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
+; AVX2-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
+; AVX2-NEXT: vpmovzxwd {{.*#+}} 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
; AVX2-NEXT: retq
;
; AVX512-LABEL: zext_8i8_to_8i32:
; AVX512: # %bb.0: # %entry
-; AVX512-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
+; AVX512-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
+; AVX512-NEXT: vpmovzxwd {{.*#+}} 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
; AVX512-NEXT: retq
entry:
%t = zext <8 x i8> %z to <8 x i32>
@@ -1649,8 +1659,8 @@ define <8 x i32> @shuf_zext_8i8_to_8i32(<8 x i8> %A) {
; SSE2-LABEL: shuf_zext_8i8_to_8i32:
; SSE2: # %bb.0: # %entry
; SSE2-NEXT: movdqa %xmm0, %xmm1
+; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
; SSE2-NEXT: pxor %xmm2, %xmm2
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSE2-NEXT: movdqa %xmm1, %xmm0
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
@@ -1659,8 +1669,8 @@ define <8 x i32> @shuf_zext_8i8_to_8i32(<8 x i8> %A) {
; SSSE3-LABEL: shuf_zext_8i8_to_8i32:
; SSSE3: # %bb.0: # %entry
; SSSE3-NEXT: movdqa %xmm0, %xmm1
+; SSSE3-NEXT: pand {{.*}}(%rip), %xmm1
; SSSE3-NEXT: pxor %xmm2, %xmm2
-; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
; SSSE3-NEXT: movdqa %xmm1, %xmm0
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
@@ -1668,6 +1678,7 @@ define <8 x i32> @shuf_zext_8i8_to_8i32(<8 x i8> %A) {
;
; SSE41-LABEL: shuf_zext_8i8_to_8i32:
; SSE41: # %bb.0: # %entry
+; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm2 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE41-NEXT: pmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
@@ -1676,6 +1687,7 @@ define <8 x i32> @shuf_zext_8i8_to_8i32(<8 x i8> %A) {
;
; AVX1-LABEL: shuf_zext_8i8_to_8i32:
; AVX1: # %bb.0: # %entry
+; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
@@ -1684,11 +1696,13 @@ define <8 x i32> @shuf_zext_8i8_to_8i32(<8 x i8> %A) {
;
; AVX2-LABEL: shuf_zext_8i8_to_8i32:
; AVX2: # %bb.0: # %entry
+; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
; AVX2-NEXT: retq
;
; AVX512-LABEL: shuf_zext_8i8_to_8i32:
; AVX512: # %bb.0: # %entry
+; AVX512-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
; AVX512-NEXT: retq
entry:
@@ -2261,11 +2275,11 @@ define <32 x i32> @zext_32i8_to_32i32(<32 x i8> %x) {
; AVX2-LABEL: zext_32i8_to_32i32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm4 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
-; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm3
-; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm2 = xmm3[0],zero,zero,zero,xmm3[1],zero,zero,zero,xmm3[2],zero,zero,zero,xmm3[3],zero,zero,zero,xmm3[4],zero,zero,zero,xmm3[5],zero,zero,zero,xmm3[6],zero,zero,zero,xmm3[7],zero,zero,zero
-; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
-; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm3[2,3,0,1]
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm2 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero
+; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,1,2,3]
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm3 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
; AVX2-NEXT: vmovdqa %ymm4, %ymm0
; AVX2-NEXT: retq
@@ -2289,33 +2303,28 @@ define <2 x i32> @zext_2i8_to_2i32(<2 x i8>* %addr) {
; SSE2-NEXT: pxor %xmm1, %xmm1
; SSE2-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; SSE2-NEXT: paddd %xmm0, %xmm0
+; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,1,3]
+; SSE2-NEXT: paddq %xmm0, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: zext_2i8_to_2i32:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movzwl (%rdi), %eax
; SSSE3-NEXT: movd %eax, %xmm0
-; SSSE3-NEXT: pxor %xmm1, %xmm1
-; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
-; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; SSSE3-NEXT: paddd %xmm0, %xmm0
+; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[3],zero,zero,zero
+; SSSE3-NEXT: paddq %xmm0, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: zext_2i8_to_2i32:
; SSE41: # %bb.0:
-; SSE41-NEXT: movzwl (%rdi), %eax
-; SSE41-NEXT: movd %eax, %xmm0
-; SSE41-NEXT: pmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; SSE41-NEXT: paddd %xmm0, %xmm0
+; SSE41-NEXT: pmovzxbq {{.*#+}} xmm0 = mem[0],zero,zero,zero,zero,zero,zero,zero,mem[1],zero,zero,zero,zero,zero,zero,zero
+; SSE41-NEXT: paddq %xmm0, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: zext_2i8_to_2i32:
; AVX: # %bb.0:
-; AVX-NEXT: movzwl (%rdi), %eax
-; AVX-NEXT: vmovd %eax, %xmm0
-; AVX-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; AVX-NEXT: vpaddd %xmm0, %xmm0, %xmm0
+; AVX-NEXT: vpmovzxbq {{.*#+}} xmm0 = mem[0],zero,zero,zero,zero,zero,zero,zero,mem[1],zero,zero,zero,zero,zero,zero,zero
+; AVX-NEXT: vpaddq %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
%x = load <2 x i8>, <2 x i8>* %addr, align 1
%y = zext <2 x i8> %x to <2 x i32>
OpenPOWER on IntegriCloud