[X86] Add avx1 command line to madd.ll to show splitting and concatenating 256-bit...

llvm-svn: 326068

diff --git a/llvm/test/CodeGen/X86/madd.ll b/llvm/test/CodeGen/X86/madd.ll
index c6e5d44..d21fd4e 100644 (file)
--- a/llvm/test/CodeGen/X86/madd.ll
+++ b/llvm/test/CodeGen/X86/madd.ll
@@ -1,8 +1,9 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=AVX,AVX512,AVX512F
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefixes=AVX,AVX512,AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX256,AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=AVX,AVX256,AVX512,AVX512F
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefixes=AVX,AVX256,AVX512,AVX512BW
 
 define i32 @_Z10test_shortPsS_i(i16* nocapture readonly, i16* nocapture readonly, i32) local_unnamed_addr #0 {
 ; SSE2-LABEL: _Z10test_shortPsS_i:
@@ -30,29 +31,55 @@ define i32 @_Z10test_shortPsS_i(i16* nocapture readonly, i16* nocapture readonly
 ; SSE2-NEXT:    movd %xmm1, %eax
 ; SSE2-NEXT:    retq
 ;
-; AVX-LABEL: _Z10test_shortPsS_i:
-; AVX:       # %bb.0: # %entry
-; AVX-NEXT:    movl %edx, %eax
-; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
-; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
-; AVX-NEXT:  .LBB0_1: # %vector.body
-; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
-; AVX-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm1
-; AVX-NEXT:    vpmaddwd (%rdi,%rcx,2), %xmm1, %xmm1
-; AVX-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    addq $8, %rcx
-; AVX-NEXT:    cmpq %rcx, %rax
-; AVX-NEXT:    jne .LBB0_1
-; AVX-NEXT:  # %bb.2: # %middle.block
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
-; AVX-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vphaddd %ymm0, %ymm0, %ymm0
-; AVX-NEXT:    vmovd %xmm0, %eax
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: _Z10test_shortPsS_i:
+; AVX1:       # %bb.0: # %entry
+; AVX1-NEXT:    movl %edx, %eax
+; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; AVX1-NEXT:    xorl %ecx, %ecx
+; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:  .LBB0_1: # %vector.body
+; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
+; AVX1-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm1
+; AVX1-NEXT:    vpmaddwd (%rdi,%rcx,2), %xmm1, %xmm1
+; AVX1-NEXT:    vpaddd %xmm0, %xmm1, %xmm1
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
+; AVX1-NEXT:    addq $8, %rcx
+; AVX1-NEXT:    cmpq %rcx, %rax
+; AVX1-NEXT:    jne .LBB0_1
+; AVX1-NEXT:  # %bb.2: # %middle.block
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovd %xmm0, %eax
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX256-LABEL: _Z10test_shortPsS_i:
+; AVX256:       # %bb.0: # %entry
+; AVX256-NEXT:    movl %edx, %eax
+; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; AVX256-NEXT:    xorl %ecx, %ecx
+; AVX256-NEXT:    .p2align 4, 0x90
+; AVX256-NEXT:  .LBB0_1: # %vector.body
+; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
+; AVX256-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm1
+; AVX256-NEXT:    vpmaddwd (%rdi,%rcx,2), %xmm1, %xmm1
+; AVX256-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
+; AVX256-NEXT:    addq $8, %rcx
+; AVX256-NEXT:    cmpq %rcx, %rax
+; AVX256-NEXT:    jne .LBB0_1
+; AVX256-NEXT:  # %bb.2: # %middle.block
+; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX256-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
+; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX256-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
+; AVX256-NEXT:    vphaddd %ymm0, %ymm0, %ymm0
+; AVX256-NEXT:    vmovd %xmm0, %eax
+; AVX256-NEXT:    vzeroupper
+; AVX256-NEXT:    retq
 entry:
   %3 = zext i32 %2 to i64
   br label %vector.body
@@ -131,6 +158,50 @@ define i32 @_Z10test_shortPsS_i_512(i16* nocapture readonly, i16* nocapture read
 ; SSE2-NEXT:    movd %xmm1, %eax
 ; SSE2-NEXT:    retq
 ;
+; AVX1-LABEL: _Z10test_shortPsS_i_512:
+; AVX1:       # %bb.0: # %entry
+; AVX1-NEXT:    movl %edx, %eax
+; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; AVX1-NEXT:    xorl %ecx, %ecx
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:  .LBB1_1: # %vector.body
+; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
+; AVX1-NEXT:    vpmovsxwd 8(%rdi,%rcx,2), %xmm2
+; AVX1-NEXT:    vpmovsxwd (%rdi,%rcx,2), %xmm3
+; AVX1-NEXT:    vpackssdw %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpmovsxwd 24(%rdi,%rcx,2), %xmm3
+; AVX1-NEXT:    vpmovsxwd 16(%rdi,%rcx,2), %xmm4
+; AVX1-NEXT:    vpackssdw %xmm3, %xmm4, %xmm3
+; AVX1-NEXT:    vpmovsxwd 8(%rsi,%rcx,2), %xmm4
+; AVX1-NEXT:    vpmovsxwd (%rsi,%rcx,2), %xmm5
+; AVX1-NEXT:    vpackssdw %xmm4, %xmm5, %xmm4
+; AVX1-NEXT:    vpmaddwd %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpmovsxwd 24(%rsi,%rcx,2), %xmm4
+; AVX1-NEXT:    vpmovsxwd 16(%rsi,%rcx,2), %xmm5
+; AVX1-NEXT:    vpackssdw %xmm4, %xmm5, %xmm4
+; AVX1-NEXT:    vpmaddwd %xmm3, %xmm4, %xmm3
+; AVX1-NEXT:    vpaddd %xmm1, %xmm3, %xmm3
+; AVX1-NEXT:    vblendps {{.*#+}} ymm1 = ymm3[0,1,2,3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vpaddd %xmm0, %xmm2, %xmm2
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
+; AVX1-NEXT:    addq $16, %rcx
+; AVX1-NEXT:    cmpq %rcx, %rax
+; AVX1-NEXT:    jne .LBB1_1
+; AVX1-NEXT:  # %bb.2: # %middle.block
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovd %xmm0, %eax
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
 ; AVX2-LABEL: _Z10test_shortPsS_i_512:
 ; AVX2:       # %bb.0: # %entry
 ; AVX2-NEXT:    movl %edx, %eax
@@ -249,30 +320,62 @@ define i32 @test_unsigned_short(i16* nocapture readonly, i16* nocapture readonly
 ; SSE2-NEXT:    movd %xmm0, %eax
 ; SSE2-NEXT:    retq
 ;
-; AVX-LABEL: test_unsigned_short:
-; AVX:       # %bb.0: # %entry
-; AVX-NEXT:    movl %edx, %eax
-; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
-; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
-; AVX-NEXT:  .LBB2_1: # %vector.body
-; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
-; AVX-NEXT:    vpmovzxwd {{.*#+}} ymm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
-; AVX-NEXT:    vpmovzxwd {{.*#+}} 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
-; AVX-NEXT:    vpmulld %ymm1, %ymm2, %ymm1
-; AVX-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    addq $8, %rcx
-; AVX-NEXT:    cmpq %rcx, %rax
-; AVX-NEXT:    jne .LBB2_1
-; AVX-NEXT:  # %bb.2: # %middle.block
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
-; AVX-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vphaddd %ymm0, %ymm0, %ymm0
-; AVX-NEXT:    vmovd %xmm0, %eax
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: test_unsigned_short:
+; AVX1:       # %bb.0: # %entry
+; AVX1-NEXT:    movl %edx, %eax
+; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; AVX1-NEXT:    xorl %ecx, %ecx
+; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:  .LBB2_1: # %vector.body
+; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmulld %xmm1, %xmm3, %xmm1
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmulld %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vpaddd %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vpaddd %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    addq $8, %rcx
+; AVX1-NEXT:    cmpq %rcx, %rax
+; AVX1-NEXT:    jne .LBB2_1
+; AVX1-NEXT:  # %bb.2: # %middle.block
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovd %xmm0, %eax
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX256-LABEL: test_unsigned_short:
+; AVX256:       # %bb.0: # %entry
+; AVX256-NEXT:    movl %edx, %eax
+; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; AVX256-NEXT:    xorl %ecx, %ecx
+; AVX256-NEXT:    .p2align 4, 0x90
+; AVX256-NEXT:  .LBB2_1: # %vector.body
+; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
+; AVX256-NEXT:    vpmovzxwd {{.*#+}} ymm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
+; AVX256-NEXT:    vpmovzxwd {{.*#+}} 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
+; AVX256-NEXT:    vpmulld %ymm1, %ymm2, %ymm1
+; AVX256-NEXT:    vpaddd %ymm0, %ymm1, %ymm0
+; AVX256-NEXT:    addq $8, %rcx
+; AVX256-NEXT:    cmpq %rcx, %rax
+; AVX256-NEXT:    jne .LBB2_1
+; AVX256-NEXT:  # %bb.2: # %middle.block
+; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX256-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
+; AVX256-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX256-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
+; AVX256-NEXT:    vphaddd %ymm0, %ymm0, %ymm0
+; AVX256-NEXT:    vmovd %xmm0, %eax
+; AVX256-NEXT:    vzeroupper
+; AVX256-NEXT:    retq
 entry:
   %3 = zext i32 %2 to i64
   br label %vector.body
@@ -351,6 +454,52 @@ define i32 @test_unsigned_short_512(i16* nocapture readonly, i16* nocapture read
 ; SSE2-NEXT:    movd %xmm1, %eax
 ; SSE2-NEXT:    retq
 ;
+; AVX1-LABEL: test_unsigned_short_512:
+; AVX1:       # %bb.0: # %entry
+; AVX1-NEXT:    movl %edx, %eax
+; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; AVX1-NEXT:    xorl %ecx, %ecx
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:  .LBB3_1: # %vector.body
+; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm5 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmulld %xmm2, %xmm6, %xmm2
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmulld %xmm3, %xmm6, %xmm3
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmulld %xmm4, %xmm6, %xmm4
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm6 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
+; AVX1-NEXT:    vpmulld %xmm5, %xmm6, %xmm5
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm6
+; AVX1-NEXT:    vpaddd %xmm6, %xmm2, %xmm2
+; AVX1-NEXT:    vpaddd %xmm1, %xmm3, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpaddd %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpaddd %xmm0, %xmm5, %xmm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    addq $16, %rcx
+; AVX1-NEXT:    cmpq %rcx, %rax
+; AVX1-NEXT:    jne .LBB3_1
+; AVX1-NEXT:  # %bb.2: # %middle.block
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovd %xmm0, %eax
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
 ; AVX2-LABEL: test_unsigned_short_512:
 ; AVX2:       # %bb.0: # %entry
 ; AVX2-NEXT:    movl %edx, %eax
@@ -495,6 +644,42 @@ define i32 @_Z9test_charPcS_i(i8* nocapture readonly, i8* nocapture readonly, i3
 ; SSE2-NEXT:    movd %xmm1, %eax
 ; SSE2-NEXT:    retq
 ;
+; AVX1-LABEL: _Z9test_charPcS_i:
+; AVX1:       # %bb.0: # %entry
+; AVX1-NEXT:    movl %edx, %eax
+; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; AVX1-NEXT:    xorl %ecx, %ecx
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:  .LBB4_1: # %vector.body
+; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
+; AVX1-NEXT:    vpmovsxbw (%rdi,%rcx), %xmm2
+; AVX1-NEXT:    vpmovsxbw 8(%rdi,%rcx), %xmm3
+; AVX1-NEXT:    vpmovsxbw (%rsi,%rcx), %xmm4
+; AVX1-NEXT:    vpmaddwd %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpmovsxbw 8(%rsi,%rcx), %xmm4
+; AVX1-NEXT:    vpmaddwd %xmm3, %xmm4, %xmm3
+; AVX1-NEXT:    vpaddd %xmm1, %xmm3, %xmm3
+; AVX1-NEXT:    vblendps {{.*#+}} ymm1 = ymm3[0,1,2,3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vpaddd %xmm0, %xmm2, %xmm2
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
+; AVX1-NEXT:    addq $16, %rcx
+; AVX1-NEXT:    cmpq %rcx, %rax
+; AVX1-NEXT:    jne .LBB4_1
+; AVX1-NEXT:  # %bb.2: # %middle.block
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovd %xmm0, %eax
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
 ; AVX2-LABEL: _Z9test_charPcS_i:
 ; AVX2:       # %bb.0: # %entry
 ; AVX2-NEXT:    movl %edx, %eax
@@ -669,6 +854,60 @@ define i32 @_Z9test_charPcS_i_512(i8* nocapture readonly, i8* nocapture readonly
 ; SSE2-NEXT:    movd %xmm1, %eax
 ; SSE2-NEXT:    retq
 ;
+; AVX1-LABEL: _Z9test_charPcS_i_512:
+; AVX1:       # %bb.0: # %entry
+; AVX1-NEXT:    movl %edx, %eax
+; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
+; AVX1-NEXT:    xorl %ecx, %ecx
+; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
+; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
+; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:  .LBB5_1: # %vector.body
+; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
+; AVX1-NEXT:    vpmovsxbw 24(%rdi,%rcx), %xmm4
+; AVX1-NEXT:    vpmovsxbw 16(%rdi,%rcx), %xmm5
+; AVX1-NEXT:    vpmovsxbw (%rdi,%rcx), %xmm6
+; AVX1-NEXT:    vpmovsxbw 8(%rdi,%rcx), %xmm8
+; AVX1-NEXT:    vpmovsxbw 24(%rsi,%rcx), %xmm7
+; AVX1-NEXT:    vpmaddwd %xmm4, %xmm7, %xmm4
+; AVX1-NEXT:    vpmovsxbw 16(%rsi,%rcx), %xmm7
+; AVX1-NEXT:    vpmaddwd %xmm5, %xmm7, %xmm5
+; AVX1-NEXT:    vpmovsxbw (%rsi,%rcx), %xmm7
+; AVX1-NEXT:    vpmaddwd %xmm6, %xmm7, %xmm6
+; AVX1-NEXT:    vpmovsxbw 8(%rsi,%rcx), %xmm7
+; AVX1-NEXT:    vpmaddwd %xmm8, %xmm7, %xmm7
+; AVX1-NEXT:    vpaddd %xmm2, %xmm7, %xmm7
+; AVX1-NEXT:    vblendps {{.*#+}} ymm2 = ymm7[0,1,2,3],ymm2[4,5,6,7]
+; AVX1-NEXT:    vpaddd %xmm0, %xmm6, %xmm6
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm5, %xmm5
+; AVX1-NEXT:    vblendps {{.*#+}} ymm1 = ymm5[0,1,2,3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vpaddd %xmm3, %xmm4, %xmm4
+; AVX1-NEXT:    vblendps {{.*#+}} ymm3 = ymm4[0,1,2,3],ymm3[4,5,6,7]
+; AVX1-NEXT:    addq $32, %rcx
+; AVX1-NEXT:    cmpq %rcx, %rax
+; AVX1-NEXT:    jne .LBB5_1
+; AVX1-NEXT:  # %bb.2: # %middle.block
+; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm4
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm6
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm3
+; AVX1-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpaddd %xmm2, %xmm6, %xmm2
+; AVX1-NEXT:    vpaddd %xmm2, %xmm5, %xmm2
+; AVX1-NEXT:    vpaddd %xmm4, %xmm1, %xmm1
+; AVX1-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vmovd %xmm0, %eax
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
 ; AVX2-LABEL: _Z9test_charPcS_i_512:
 ; AVX2:       # %bb.0: # %entry
 ; AVX2-NEXT:    movl %edx, %eax
@@ -864,6 +1103,20 @@ define <4 x i32> @larger_mul(<16 x i16> %A, <16 x i16> %B) {
 ; SSE2-NEXT:    paddd %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
+; AVX1-LABEL: larger_mul:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vpmovsxwd %xmm0, %xmm2
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpmovsxwd %xmm0, %xmm0
+; AVX1-NEXT:    vpackssdw %xmm0, %xmm2, %xmm0
+; AVX1-NEXT:    vpmovsxwd %xmm1, %xmm2
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT:    vpmovsxwd %xmm1, %xmm1
+; AVX1-NEXT:    vpackssdw %xmm1, %xmm2, %xmm1
+; AVX1-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
 ; AVX2-LABEL: larger_mul:
 ; AVX2:       # %bb.0:
 ; AVX2-NEXT:    vpmovsxwd %xmm0, %ymm0
@@ -914,10 +1167,19 @@ define <8 x i32> @pmaddwd_16(<16 x i16> %A, <16 x i16> %B) {
 ; SSE2-NEXT:    pmaddwd %xmm3, %xmm1
 ; SSE2-NEXT:    retq
 ;
-; AVX-LABEL: pmaddwd_16:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    retq
+; AVX1-LABEL: pmaddwd_16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vpmaddwd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX256-LABEL: pmaddwd_16:
+; AVX256:       # %bb.0:
+; AVX256-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm0
+; AVX256-NEXT:    retq
    %a = sext <16 x i16> %A to <16 x i32>
    %b = sext <16 x i16> %B to <16 x i32>
    %m = mul nsw <16 x i32> %a, %b
@@ -936,6 +1198,20 @@ define <16 x i32> @pmaddwd_32(<32 x i16> %A, <32 x i16> %B) {
 ; SSE2-NEXT:    pmaddwd %xmm7, %xmm3
 ; SSE2-NEXT:    retq
 ;
+; AVX1-LABEL: pmaddwd_32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm6
+; AVX1-NEXT:    vpmaddwd %xmm6, %xmm4, %xmm4
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm6
+; AVX1-NEXT:    vpmaddwd %xmm6, %xmm5, %xmm5
+; AVX1-NEXT:    vpmaddwd %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm0, %ymm0
+; AVX1-NEXT:    vpmaddwd %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm1, %ymm1
+; AVX1-NEXT:    retq
+;
 ; AVX2-LABEL: pmaddwd_32:
 ; AVX2:       # %bb.0:
 ; AVX2-NEXT:    vpmaddwd %ymm2, %ymm0, %ymm0
@@ -996,15 +1272,28 @@ define <4 x i32> @pmaddwd_negative1(<8 x i16> %A, <8 x i16> %B) {
 ; SSE2-NEXT:    paddd %xmm2, %xmm0
 ; SSE2-NEXT:    retq
 ;
-; AVX-LABEL: pmaddwd_negative1:
-; AVX:       # %bb.0:
-; AVX-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
-; AVX-NEXT:    vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
-; AVX-NEXT:    vpmulld %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: pmaddwd_negative1:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm1[2,3,0,1]
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero
+; AVX1-NEXT:    vpmulld %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
+; AVX1-NEXT:    vpmulld %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vphaddd %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX256-LABEL: pmaddwd_negative1:
+; AVX256:       # %bb.0:
+; AVX256-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
+; AVX256-NEXT:    vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
+; AVX256-NEXT:    vpmulld %ymm1, %ymm0, %ymm0
+; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX256-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
+; AVX256-NEXT:    vzeroupper
+; AVX256-NEXT:    retq
    %a = zext <8 x i16> %A to <8 x i32>
    %b = zext <8 x i16> %B to <8 x i32>
    %m = mul nuw <8 x i32> %a, %b
@@ -1044,14 +1333,24 @@ define <4 x i32> @pmaddwd_negative2(<8 x i16> %A) {
 ; SSE2-NEXT:    paddd %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
-; AVX-LABEL: pmaddwd_negative2:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vpmovsxwd %xmm0, %ymm0
-; AVX-NEXT:    vpmulld {{.*}}(%rip), %ymm0, %ymm0
-; AVX-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: pmaddwd_negative2:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; AVX1-NEXT:    vpmovsxwd %xmm1, %xmm1
+; AVX1-NEXT:    vpmovsxwd %xmm0, %xmm0
+; AVX1-NEXT:    vpmulld {{.*}}(%rip), %xmm0, %xmm0
+; AVX1-NEXT:    vpmulld {{.*}}(%rip), %xmm1, %xmm1
+; AVX1-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    retq
+;
+; AVX256-LABEL: pmaddwd_negative2:
+; AVX256:       # %bb.0:
+; AVX256-NEXT:    vpmovsxwd %xmm0, %ymm0
+; AVX256-NEXT:    vpmulld {{.*}}(%rip), %ymm0, %ymm0
+; AVX256-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX256-NEXT:    vphaddd %xmm1, %xmm0, %xmm0
+; AVX256-NEXT:    vzeroupper
+; AVX256-NEXT:    retq
    %a = sext <8 x i16> %A to <8 x i32>
    %m = mul nsw <8 x i32> %a, <i32 32768, i32 -32768, i32 0, i32 0, i32 1, i32 7, i32 42, i32 32>
    %odd = shufflevector <8 x i32> %m, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
@@ -1086,10 +1385,19 @@ define <8 x i32> @jumbled_indices8(<16 x i16> %A, <16 x i16> %B) {
 ; SSE2-NEXT:    pmaddwd %xmm3, %xmm1
 ; SSE2-NEXT:    retq
 ;
-; AVX-LABEL: jumbled_indices8:
-; AVX:       # %bb.0:
-; AVX-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    retq
+; AVX1-LABEL: jumbled_indices8:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vpmaddwd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX256-LABEL: jumbled_indices8:
+; AVX256:       # %bb.0:
+; AVX256-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm0
+; AVX256-NEXT:    retq
   %exta = sext <16 x i16> %A to <16 x i32>
   %extb = sext <16 x i16> %B to <16 x i32>
   %m = mul <16 x i32> %exta, %extb
@@ -1108,6 +1416,20 @@ define <16 x i32> @jumbled_indices16(<32 x i16> %A, <32 x i16> %B) {
 ; SSE2-NEXT:    pmaddwd %xmm7, %xmm3
 ; SSE2-NEXT:    retq
 ;
+; AVX1-LABEL: jumbled_indices16:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm5
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm6
+; AVX1-NEXT:    vpmaddwd %xmm6, %xmm4, %xmm4
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm6
+; AVX1-NEXT:    vpmaddwd %xmm6, %xmm5, %xmm5
+; AVX1-NEXT:    vpmaddwd %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm0, %ymm0
+; AVX1-NEXT:    vpmaddwd %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm1, %ymm1
+; AVX1-NEXT:    retq
+;
 ; AVX2-LABEL: jumbled_indices16:
 ; AVX2:       # %bb.0:
 ; AVX2-NEXT:    vpmaddwd %ymm2, %ymm0, %ymm0
@@ -1156,6 +1478,30 @@ define <32 x i32> @jumbled_indices32(<64 x i16> %A, <64 x i16> %B) {
 ; SSE2-NEXT:    movq %rdi, %rax
 ; SSE2-NEXT:    retq
 ;
+; AVX1-LABEL: jumbled_indices32:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm8
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm9
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm10
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm11
+; AVX1-NEXT:    vextractf128 $1, %ymm7, %xmm12
+; AVX1-NEXT:    vpmaddwd %xmm12, %xmm8, %xmm8
+; AVX1-NEXT:    vextractf128 $1, %ymm6, %xmm12
+; AVX1-NEXT:    vpmaddwd %xmm12, %xmm9, %xmm9
+; AVX1-NEXT:    vextractf128 $1, %ymm5, %xmm12
+; AVX1-NEXT:    vpmaddwd %xmm12, %xmm10, %xmm10
+; AVX1-NEXT:    vextractf128 $1, %ymm4, %xmm12
+; AVX1-NEXT:    vpmaddwd %xmm12, %xmm11, %xmm11
+; AVX1-NEXT:    vpmaddwd %xmm4, %xmm0, %xmm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm11, %ymm0, %ymm0
+; AVX1-NEXT:    vpmaddwd %xmm5, %xmm1, %xmm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm10, %ymm1, %ymm1
+; AVX1-NEXT:    vpmaddwd %xmm6, %xmm2, %xmm2
+; AVX1-NEXT:    vinsertf128 $1, %xmm9, %ymm2, %ymm2
+; AVX1-NEXT:    vpmaddwd %xmm7, %xmm3, %xmm3
+; AVX1-NEXT:    vinsertf128 $1, %xmm8, %ymm3, %ymm3
+; AVX1-NEXT:    retq
+;
 ; AVX2-LABEL: jumbled_indices32:
 ; AVX2:       # %bb.0:
 ; AVX2-NEXT:    vpmaddwd %ymm4, %ymm0, %ymm0