1 files changed, 34 insertions, 38 deletions
diff --git a/llvm/test/CodeGen/X86/vector-trunc-widen.ll b/llvm/test/CodeGen/X86/vector-trunc-widen.ll
index c6b36e4aae7..327cc7917e9 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-widen.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-widen.ll
@@ -668,14 +668,14 @@ define void @trunc16i32_16i16(<16 x i32> %a) {
 ; AVX1-LABEL: trunc16i32_16i16:
 ; AVX1:       # %bb.0: # %entry
 ; AVX1-NEXT:    vmovaps {{.*#+}} ymm2 = [65535,65535,65535,65535,65535,65535,65535,65535]
-; AVX1-NEXT:    vandps %ymm2, %ymm1, %ymm1
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT:    vpackusdw %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vandps %ymm2, %ymm0, %ymm0
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT:    vmovups %ymm0, (%rax)
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vpackusdw %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vandps %ymm2, %ymm1, %ymm1
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vmovdqu %xmm1, (%rax)
+; AVX1-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
@@ -686,8 +686,8 @@ define void @trunc16i32_16i16(<16 x i32> %a) {
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
-; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-NEXT:    vmovdqu %ymm0, (%rax)
+; AVX2-NEXT:    vmovdqu %xmm1, (%rax)
+; AVX2-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
@@ -717,16 +717,16 @@ define void @trunc16i32_16i16_ashr(<16 x i32> %a) {
 ;
 ; AVX1-LABEL: trunc16i32_16i16_ashr:
 ; AVX1:       # %bb.0: # %entry
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpsrad $16, %xmm2, %xmm2
-; AVX1-NEXT:    vpsrad $16, %xmm0, %xmm0
-; AVX1-NEXT:    vpackssdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vpsrad $16, %xmm2, %xmm2
 ; AVX1-NEXT:    vpsrad $16, %xmm1, %xmm1
 ; AVX1-NEXT:    vpackssdw %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT:    vmovups %ymm0, (%rax)
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpsrad $16, %xmm2, %xmm2
+; AVX1-NEXT:    vpsrad $16, %xmm0, %xmm0
+; AVX1-NEXT:    vpackssdw %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqu %xmm1, (%rax)
+; AVX1-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
@@ -792,16 +792,16 @@ define void @trunc16i32_16i16_lshr(<16 x i32> %a) {
 ;
 ; AVX1-LABEL: trunc16i32_16i16_lshr:
 ; AVX1:       # %bb.0: # %entry
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpsrld $16, %xmm2, %xmm2
-; AVX1-NEXT:    vpsrld $16, %xmm0, %xmm0
-; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vpsrld $16, %xmm2, %xmm2
 ; AVX1-NEXT:    vpsrld $16, %xmm1, %xmm1
 ; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT:    vmovups %ymm0, (%rax)
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpsrld $16, %xmm2, %xmm2
+; AVX1-NEXT:    vpsrld $16, %xmm0, %xmm0
+; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vmovdqu %xmm1, (%rax)
+; AVX1-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
@@ -1291,14 +1291,14 @@ define void @trunc32i16_32i8(<32 x i16> %a) {
 ; AVX1-LABEL: trunc32i16_32i8:
 ; AVX1:       # %bb.0: # %entry
 ; AVX1-NEXT:    vmovaps {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
-; AVX1-NEXT:    vandps %ymm2, %ymm1, %ymm1
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT:    vpackuswb %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vandps %ymm2, %ymm0, %ymm0
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT:    vmovups %ymm0, (%rax)
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vpackuswb %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vandps %ymm2, %ymm1, %ymm1
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vmovdqu %xmm1, (%rax)
+; AVX1-NEXT:    vmovdqu %xmm0, (%rax)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
@@ -1317,23 +1317,19 @@ define void @trunc32i16_32i8(<32 x i16> %a) {
 ;
 ; AVX512F-LABEL: trunc32i16_32i8:
 ; AVX512F:       # %bb.0: # %entry
-; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
-; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
-; AVX512F-NEXT:    vpmovdb %zmm1, %xmm1
-; AVX512F-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
-; AVX512F-NEXT:    vmovdqu %ymm0, (%rax)
+; AVX512F-NEXT:    vpmovdb %zmm1, (%rax)
+; AVX512F-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512F-NEXT:    vpmovdb %zmm0, (%rax)
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512VL-LABEL: trunc32i16_32i8:
 ; AVX512VL:       # %bb.0: # %entry
-; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
-; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
 ; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
-; AVX512VL-NEXT:    vpmovdb %zmm1, %xmm1
-; AVX512VL-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
-; AVX512VL-NEXT:    vmovdqu %ymm0, (%rax)
+; AVX512VL-NEXT:    vpmovdb %zmm1, (%rax)
+; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
+; AVX512VL-NEXT:    vpmovdb %zmm0, (%rax)
 ; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;