[X86][AVX] Add AVX1 shuffle truncation tests

llvm-svn: 305905
2017-06-21 12:58:56 +00:00 · 2017-06-21 12:58:56 +00:00 · 73814a2594
parent db6c3fa872
commit 73814a2594
1 changed files with 234 additions and 107 deletions
--- a/llvm/test/CodeGen/X86/shuffle-vs-trunc-256.ll
+++ b/llvm/test/CodeGen/X86/shuffle-vs-trunc-256.ll
@ -1,4 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512VL
@ -10,17 +11,29 @@
 ; Ideally, the shuffles should be lowered to code with the same quality as the truncates.

 define void @shuffle_v32i8_to_v16i8(<32 x i8>* %L, <16 x i8>* %S) nounwind {
-; AVX-LABEL: shuffle_v32i8_to_v16i8:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
-; AVX-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; AVX-NEXT:    vmovdqa %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v32i8_to_v16i8:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v32i8_to_v16i8:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: shuffle_v32i8_to_v16i8:
 ; AVX512F:       # BB#0:
@ -76,17 +89,29 @@ define void @shuffle_v32i8_to_v16i8(<32 x i8>* %L, <16 x i8>* %S) nounwind {
 }

 define void @trunc_v16i16_to_v16i8(<32 x i8>* %L, <16 x i8>* %S) nounwind {
-; AVX-LABEL: trunc_v16i16_to_v16i8:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
-; AVX-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; AVX-NEXT:    vmovdqa %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: trunc_v16i16_to_v16i8:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v16i16_to_v16i8:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_v16i16_to_v16i8:
 ; AVX512F:       # BB#0:
@ -126,17 +151,29 @@ define void @trunc_v16i16_to_v16i8(<32 x i8>* %L, <16 x i8>* %S) nounwind {
 }

 define void @shuffle_v16i16_to_v8i16(<16 x i16>* %L, <8 x i16>* %S) nounwind {
-; AVX-LABEL: shuffle_v16i16_to_v8i16:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
-; AVX-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; AVX-NEXT:    vmovdqa %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v16i16_to_v8i16:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v16i16_to_v8i16:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: shuffle_v16i16_to_v8i16:
 ; AVX512F:       # BB#0:
@ -198,14 +235,26 @@ define void @shuffle_v16i16_to_v8i16(<16 x i16>* %L, <8 x i16>* %S) nounwind {
 }

 define void @trunc_v8i32_to_v8i16(<16 x i16>* %L, <8 x i16>* %S) nounwind {
-; AVX-LABEL: trunc_v8i32_to_v8i16:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
-; AVX-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX-NEXT:    vmovdqa %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: trunc_v8i32_to_v8i16:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v8i32_to_v8i16:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_v8i32_to_v8i16:
 ; AVX512F:       # BB#0:
@ -295,13 +344,22 @@ define void @shuffle_v8i32_to_v4i32(<8 x i32>* %L, <4 x i32>* %S) nounwind {
 }

 define void @trunc_v4i64_to_v4i32(<8 x i32>* %L, <4 x i32>* %S) nounwind {
-; AVX-LABEL: trunc_v4i64_to_v4i32:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpshufd {{.*#+}} ymm0 = mem[0,2,2,3,4,6,6,7]
-; AVX-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX-NEXT:    vmovdqa %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: trunc_v4i64_to_v4i32:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovaps (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vmovaps %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v4i64_to_v4i32:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = mem[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vmovdqa %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_v4i64_to_v4i32:
 ; AVX512F:       # BB#0:
@ -340,17 +398,29 @@ define void @trunc_v4i64_to_v4i32(<8 x i32>* %L, <4 x i32>* %S) nounwind {
 }

 define void @shuffle_v32i8_to_v8i8(<32 x i8>* %L, <8 x i8>* %S) nounwind {
-; AVX-LABEL: shuffle_v32i8_to_v8i8:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
-; AVX-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; AVX-NEXT:    vmovq %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v32i8_to_v8i8:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT:    vmovq %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v32i8_to_v8i8:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-NEXT:    vmovq %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: shuffle_v32i8_to_v8i8:
 ; AVX512F:       # BB#0:
@ -409,15 +479,27 @@ define void @shuffle_v32i8_to_v8i8(<32 x i8>* %L, <8 x i8>* %S) nounwind {
 }

 define void @trunc_v8i32_to_v8i8(<32 x i8>* %L, <8 x i8>* %S) nounwind {
-; AVX-LABEL: trunc_v8i32_to_v8i8:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
-; AVX-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
-; AVX-NEXT:    vmovq %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: trunc_v8i32_to_v8i8:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT:    vmovq %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v8i32_to_v8i8:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovq %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_v8i32_to_v8i8:
 ; AVX512F:       # BB#0:
@ -458,18 +540,31 @@ define void @trunc_v8i32_to_v8i8(<32 x i8>* %L, <8 x i8>* %S) nounwind {
 }

 define void @shuffle_v16i16_to_v4i16(<16 x i16>* %L, <4 x i16>* %S) nounwind {
-; AVX-LABEL: shuffle_v16i16_to_v4i16:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
-; AVX-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
-; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; AVX-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
-; AVX-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; AVX-NEXT:    vmovq %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v16i16_to_v4i16:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
+; AVX1-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT:    vmovq %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v16i16_to_v4i16:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
+; AVX2-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
+; AVX2-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; AVX2-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
+; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-NEXT:    vmovq %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: shuffle_v16i16_to_v4i16:
 ; AVX512F:       # BB#0:
@ -521,14 +616,24 @@ define void @shuffle_v16i16_to_v4i16(<16 x i16>* %L, <4 x i16>* %S) nounwind {
 }

 define void @trunc_v4i64_to_v4i16(<16 x i16>* %L, <4 x i16>* %S) nounwind {
-; AVX-LABEL: trunc_v4i64_to_v4i16:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpshufd {{.*#+}} ymm0 = mem[0,2,2,3,4,6,6,7]
-; AVX-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
-; AVX-NEXT:    vmovq %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: trunc_v4i64_to_v4i16:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovaps (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX1-NEXT:    vmovq %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v4i64_to_v4i16:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = mem[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
+; AVX2-NEXT:    vmovq %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_v4i64_to_v4i16:
 ; AVX512F:       # BB#0:
@ -569,17 +674,29 @@ define void @trunc_v4i64_to_v4i16(<16 x i16>* %L, <4 x i16>* %S) nounwind {
 }

 define void @shuffle_v32i8_to_v4i8(<32 x i8>* %L, <4 x i8>* %S) nounwind {
-; AVX-LABEL: shuffle_v32i8_to_v4i8:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
-; AVX-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
-; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX-NEXT:    vmovd %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v32i8_to_v4i8:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vmovd %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v32i8_to_v4i8:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
+; AVX2-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT:    vmovd %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: shuffle_v32i8_to_v4i8:
 ; AVX512F:       # BB#0:
@ -629,14 +746,24 @@ define void @shuffle_v32i8_to_v4i8(<32 x i8>* %L, <4 x i8>* %S) nounwind {
 }

 define void @trunc_v4i64_to_v4i8(<32 x i8>* %L, <4 x i8>* %S) nounwind {
-; AVX-LABEL: trunc_v4i64_to_v4i8:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpshufd {{.*#+}} ymm0 = mem[0,2,2,3,4,6,6,7]
-; AVX-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
-; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX-NEXT:    vmovd %xmm0, (%rsi)
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: trunc_v4i64_to_v4i8:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vmovaps (%rdi), %ymm0
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX1-NEXT:    vmovd %xmm0, (%rsi)
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: trunc_v4i64_to_v4i8:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = mem[0,2,2,3,4,6,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovd %xmm0, (%rsi)
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
 ;
 ; AVX512F-LABEL: trunc_v4i64_to_v4i8:
 ; AVX512F:       # BB#0: