[LegalizeVectorTypes] Allow single loads and stores for more short vectors

When lowering a load or store for TypeWidenVector, the type legalizer
would use a single load or store if the associated integer type was legal
or promoted. E.g. it loads a v4i8 as an i32 if i32 is legal/promotable.
(See https://reviews.llvm.org/rL236528 for reference.)

This applies that behaviour to vector types. If the vector type is
TypePromoteInteger, the element type is going to be TypePromoteInteger
as well, which will lead to have a single promoting load rather than N
individual promoting loads. For instance, if we have a v3i1, we would
now have a load of v4i1 instead of 3 loads of i1.

Patch by Guillaume Marques. Thanks!

Differential Revision: https://reviews.llvm.org/D56201

llvm-svn: 357120

llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp

@@ -4380,6 +4380,8 @@ static EVT FindMemType(SelectionDAG& DAG, const TargetLowering &TLI,
         isPowerOf2_32(WidenWidth / MemVTWidth) &&
         (MemVTWidth <= Width ||
          (Align!=0 && MemVTWidth<=AlignInBits && MemVTWidth<=Width+WidenEx))) {
+      if (MemVTWidth == WidenWidth)
+        return MemVT;
       RetVT = MemVT;
       break;
     }
@@ -4391,7 +4393,10 @@ static EVT FindMemType(SelectionDAG& DAG, const TargetLowering &TLI,
        VT >= (unsigned)MVT::FIRST_VECTOR_VALUETYPE; --VT) {
     EVT MemVT = (MVT::SimpleValueType) VT;
     unsigned MemVTWidth = MemVT.getSizeInBits();
-    if (TLI.isTypeLegal(MemVT) && WidenEltVT == MemVT.getVectorElementType() &&
+    auto Action = TLI.getTypeAction(*DAG.getContext(), MemVT);
+    if ((Action == TargetLowering::TypeLegal ||
+         Action == TargetLowering::TypePromoteInteger) &&
+        WidenEltVT == MemVT.getVectorElementType() &&
         (WidenWidth % MemVTWidth) == 0 &&
         isPowerOf2_32(WidenWidth / MemVTWidth) &&
         (MemVTWidth <= Width ||

llvm/lib/Target/AMDGPU/R600ISelLowering.cpp

@@ -1239,11 +1239,13 @@ SDValue R600TargetLowering::LowerSTORE(SDValue Op, SelectionDAG &DAG) const {
 
   SDLoc DL(Op);
 
+  const bool TruncatingStore = StoreNode->isTruncatingStore();
+
   // Neither LOCAL nor PRIVATE can do vectors at the moment
-  if ((AS == AMDGPUAS::LOCAL_ADDRESS || AS == AMDGPUAS::PRIVATE_ADDRESS) &&
+  if ((AS == AMDGPUAS::LOCAL_ADDRESS || AS == AMDGPUAS::PRIVATE_ADDRESS ||
+       TruncatingStore) &&
       VT.isVector()) {
-    if ((AS == AMDGPUAS::PRIVATE_ADDRESS) &&
+    if ((AS == AMDGPUAS::PRIVATE_ADDRESS) && TruncatingStore) {
-         StoreNode->isTruncatingStore()) {
       // Add an extra level of chain to isolate this vector
       SDValue NewChain = DAG.getNode(AMDGPUISD::DUMMY_CHAIN, DL, MVT::Other, Chain);
       // TODO: can the chain be replaced without creating a new store?
@@ -1269,7 +1271,7 @@ SDValue R600TargetLowering::LowerSTORE(SDValue Op, SelectionDAG &DAG) const {
   if (AS == AMDGPUAS::GLOBAL_ADDRESS) {
     // It is beneficial to create MSKOR here instead of combiner to avoid
     // artificial dependencies introduced by RMW
-    if (StoreNode->isTruncatingStore()) {
+    if (TruncatingStore) {
       assert(VT.bitsLE(MVT::i32));
       SDValue MaskConstant;
       if (MemVT == MVT::i8) {
@@ -1309,8 +1311,8 @@ SDValue R600TargetLowering::LowerSTORE(SDValue Op, SelectionDAG &DAG) const {
       // Convert pointer from byte address to dword address.
       Ptr = DAG.getNode(AMDGPUISD::DWORDADDR, DL, PtrVT, DWordAddr);
 
-      if (StoreNode->isTruncatingStore() || StoreNode->isIndexed()) {
+      if (StoreNode->isIndexed()) {
-        llvm_unreachable("Truncated and indexed stores not supported yet");
+        llvm_unreachable("Indexed stores not supported yet");
       } else {
         Chain = DAG.getStore(Chain, DL, Value, Ptr, StoreNode->getMemOperand());
       }

llvm/test/CodeGen/AMDGPU/load-constant-i16.ll

@@ -29,7 +29,8 @@ entry:
 ; FUNC-LABEL: {{^}}constant_load_v3i16:
 ; GCN: s_load_dwordx2 s
 
-; EG-DAG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
+; EG-DAG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
+; EG-DAG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 2, #1
 ; EG-DAG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 4, #1
 define amdgpu_kernel void @constant_load_v3i16(<3 x i16> addrspace(1)* %out, <3 x i16> addrspace(4)* %in) {
 entry:
@@ -186,15 +187,11 @@ define amdgpu_kernel void @constant_sextload_v2i16_to_v2i32(<2 x i32> addrspace(
 ; EG-DAG: MEM_RAT_CACHELESS STORE_RAW [[ST_LO:T[0-9]]].XY, {{T[0-9].[XYZW]}},
 ; EG-DAG: MEM_RAT_CACHELESS STORE_RAW [[ST_HI:T[0-9]]].X, {{T[0-9].[XYZW]}},
 ; EG: CF_END
-; EG-DAG: VTX_READ_32 [[DST_LO:T[0-9]\.[XYZW]]], {{T[0-9]\.[XYZW]}}, 0, #1
+; EG-DAG: VTX_READ_16 [[ST_LO]].X, [[SRC:T[0-9]\.[XYZW]]], 0, #1
-; EG-DAG: VTX_READ_16 [[DST_HI:T[0-9]\.[XYZW]]], {{T[0-9]\.[XYZW]}}, 4, #1
+; EG-DAG: VTX_READ_16 {{T[0-9]\.[XYZW]}}, [[SRC]], 2, #1
-; TODO: This should use DST, but for some there are redundant MOVs
+; EG-DAG: VTX_READ_16 [[ST_HI]].X, [[SRC]], 4, #1
-; EG-DAG: LSHR {{[* ]*}}[[ST_LO]].Y, {{T[0-9]\.[XYZW]}}, literal
+; EG-DAG: LSHR {{[* ]*}}{{T[0-9]\.[XYZW]}}, {{T[0-9]\.[XYZW]}}, literal
 ; EG-DAG: 16
-; EG-DAG: AND_INT {{[* ]*}}[[ST_LO]].X, {{T[0-9]\.[XYZW]}}, literal
-; EG-DAG: AND_INT {{[* ]*}}[[ST_HI]].X, {{T[0-9]\.[XYZW]}}, literal
-; EG-DAG: 65535
-; EG-DAG: 65535
 define amdgpu_kernel void @constant_zextload_v3i16_to_v3i32(<3 x i32> addrspace(1)* %out, <3 x i16> addrspace(4)* %in) {
 entry:
   %ld = load <3 x i16>, <3 x i16> addrspace(4)* %in
@@ -209,11 +206,12 @@ entry:
 ; EG-DAG: MEM_RAT_CACHELESS STORE_RAW [[ST_LO:T[0-9]]].XY, {{T[0-9].[XYZW]}},
 ; EG-DAG: MEM_RAT_CACHELESS STORE_RAW [[ST_HI:T[0-9]]].X, {{T[0-9].[XYZW]}},
 ; v3i16 is naturally 8 byte aligned
-; EG-DAG: VTX_READ_32 [[DST_HI:T[0-9]\.[XYZW]]], [[PTR:T[0-9]\.[XYZW]]], 0, #1
+; EG-DAG: VTX_READ_16 [[ST_LO]].X, [[SRC:T[0-9]\.[XYZW]]], 0, #1
-; EG-DAG: VTX_READ_16 [[DST_LO:T[0-9]\.[XYZW]]], {{T[0-9]\.[XYZW]}}, 4, #1
+; EG-DAG: VTX_READ_16 [[DST_MID:T[0-9]\.[XYZW]]], [[SRC]], 2, #1
-; EG-DAG: ASHR {{[* ]*}}[[ST_LO]].Y, {{T[0-9]\.[XYZW]}}, literal
+; EG-DAG: VTX_READ_16 [[ST_HI]].X, [[SRC]], 4, #1
-; EG-DAG: BFE_INT {{[* ]*}}[[ST_LO]].X, {{T[0-9]\.[XYZW]}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}[[ST_LO]].X, [[ST_LO]].X, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}[[ST_HI]].X, {{T[0-9]\.[XYZW]}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}[[ST_LO]].Y, [[DST_MID]], 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}[[ST_HI]].X, [[ST_HI]].X, 0.0, literal
 ; EG-DAG: 16
 ; EG-DAG: 16
 define amdgpu_kernel void @constant_sextload_v3i16_to_v3i32(<3 x i32> addrspace(1)* %out, <3 x i16> addrspace(4)* %in) {

llvm/test/CodeGen/AMDGPU/load-global-i16.ll

@@ -34,7 +34,8 @@ entry:
 ; GCN-NOHSA: buffer_load_dwordx2 v
 ; GCN-HSA: flat_load_dwordx2 v
 
-; EGCM-DAG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
+; EGCM-DAG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0, #1
+; EGCM-DAG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 2, #1
 ; EGCM-DAG: VTX_READ_16 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 4, #1
 define amdgpu_kernel void @global_load_v3i16(<3 x i16> addrspace(1)* %out, <3 x i16> addrspace(1)* %in) {
 entry:
@@ -195,10 +196,9 @@ define amdgpu_kernel void @global_sextload_v2i16_to_v2i32(<2 x i32> addrspace(1)
 ; CM: MEM_RAT_CACHELESS STORE_DWORD [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}}
 ; EG: MEM_RAT_CACHELESS STORE_RAW [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}},
 ; EG: MEM_RAT_CACHELESS STORE_RAW [[ST_LO:T[0-9]]].XY, {{T[0-9]\.[XYZW]}},
-; EGCM-DAG: VTX_READ_32 [[DST_LO:T[0-9]\.[XYZW]]], {{T[0-9]\.[XYZW]}}, 0, #1
+; EGCM-DAG: VTX_READ_16 [[ST_LO]].X, [[SRC:T[0-9]\.[XYZW]]], 0, #1
-; EGCM-DAG: VTX_READ_16 [[DST_HI:T[0-9]\.[XYZW]]], {{T[0-9]\.[XYZW]}}, 4, #1
+; EGCM-DAG: VTX_READ_16 {{T[0-9]\.[XYZW]}}, [[SRC]], 2, #1
-; TODO: This should use DST, but for some there are redundant MOVs
+; EGCM-DAG: VTX_READ_16 [[ST_HI]].X, [[SRC]], 4, #1
-; EGCM: LSHR {{[* ]*}}[[ST_LO]].Y, {{T[0-9]\.[XYZW]}}, literal
 ; EGCM: 16
 define amdgpu_kernel void @global_zextload_v3i16_to_v3i32(<3 x i32> addrspace(1)* %out, <3 x i16> addrspace(1)* %in) {
 entry:
@@ -216,11 +216,11 @@ entry:
 ; CM: MEM_RAT_CACHELESS STORE_DWORD [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}}
 ; EG: MEM_RAT_CACHELESS STORE_RAW [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}},
 ; EG: MEM_RAT_CACHELESS STORE_RAW [[ST_LO:T[0-9]]].XY, {{T[0-9]\.[XYZW]}},
-; EGCM-DAG: VTX_READ_32 [[DST_LO:T[0-9]\.[XYZW]]], {{T[0-9].[XYZW]}}, 0, #1
+; EGCM-DAG: VTX_READ_16 [[DST_LO:T[0-9]\.[XYZW]]], [[SRC:T[0-9].[XYZW]]], 0, #1
-; EGCM-DAG: VTX_READ_16 [[DST_HI:T[0-9]\.[XYZW]]], {{T[0-9].[XYZW]}}, 4, #1
+; EGCM-DAG: VTX_READ_16 [[DST_MID:T[0-9]\.[XYZW]]], [[SRC]], 2, #1
-; TODO: This should use DST, but for some there are redundant MOVs
+; EGCM-DAG: VTX_READ_16 [[DST_HI:T[0-9]\.[XYZW]]], [[SRC]], 4, #1
-; EGCM-DAG: ASHR {{[* ]*}}[[ST_LO]].Y, {{T[0-9]\.[XYZW]}}, literal
+; EGCM-DAG: BFE_INT {{[* ]*}}[[ST_LO]].X, [[DST_LO]], 0.0, literal
-; EGCM-DAG: BFE_INT {{[* ]*}}[[ST_LO]].X, {{T[0-9]\.[XYZW]}}, 0.0, literal
+; EGCM-DAG: BFE_INT {{[* ]*}}[[ST_LO]].Y, [[DST_MID]], 0.0, literal
 ; EGCM-DAG: BFE_INT {{[* ]*}}[[ST_HI]].X, [[DST_HI]], 0.0, literal
 ; EGCM-DAG: 16
 ; EGCM-DAG: 16

llvm/test/CodeGen/AMDGPU/load-local-i16.ll

@@ -52,7 +52,7 @@ entry:
 ; GCN-DAG: ds_write_b16
 
 ; EG-DAG: LDS_USHORT_READ_RET
-; EG-DAG: LDS_READ_RET
+; EG-DAG: LDS_USHORT_READ_RET
 define amdgpu_kernel void @local_load_v3i16(<3 x i16> addrspace(3)* %out, <3 x i16> addrspace(3)* %in) {
 entry:
   %ld = load <3 x i16>, <3 x i16> addrspace(3)* %in
@@ -235,7 +235,9 @@ define amdgpu_kernel void @local_sextload_v2i16_to_v2i32(<2 x i32> addrspace(3)*
 ; GCN-DAG: ds_write_b32
 ; GCN-DAG: ds_write_b64
 
-; EG: LDS_READ_RET
+; EG: LDS_USHORT_READ_RET
+; EG: LDS_USHORT_READ_RET
+; EG: LDS_USHORT_READ_RET
 define amdgpu_kernel void @local_local_zextload_v3i16_to_v3i32(<3 x i32> addrspace(3)* %out, <3 x i16> addrspace(3)* %in) {
 entry:
   %ld = load <3 x i16>, <3 x i16> addrspace(3)* %in
@@ -252,7 +254,9 @@ entry:
 ; GCN-DAG: ds_write_b32
 ; GCN-DAG: ds_write_b64
 
-; EG: LDS_READ_RET
+; EG: LDS_USHORT_READ_RET
+; EG: LDS_USHORT_READ_RET
+; EG: LDS_USHORT_READ_RET
 ; EG-DAG: BFE_INT
 ; EG-DAG: BFE_INT
 ; EG-DAG: BFE_INT

llvm/test/CodeGen/X86/load-local-v3i1.ll

@@ -0,0 +1,70 @@
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s
+
+; widen a v3i1 to v4i1 to do a vector load/store. We would previously
+; reconstruct the said v3i1 from the first element of the vector by filling all
+; the lanes of the vector with that first element, which was obviously wrong.
+; This was done in the type-legalizing of the DAG, when legalizing the load.
+
+; Function Attrs: argmemonly nounwind readonly
+declare <3 x i32> @llvm.masked.load.v3i32.p1v3i32(<3 x i32> addrspace(1)*, i32, <3 x i1>, <3 x i32>)
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.masked.store.v3i32.p1v3i32(<3 x i32>, <3 x i32> addrspace(1)*, i32, <3 x i1>)
+
+define  <3 x i32> @masked_load_v3(i32 addrspace(1)*, <3 x i1>) {
+entry:
+  %2 = bitcast i32 addrspace(1)* %0 to <3 x i32> addrspace(1)*
+  %3 = call <3 x i32> @llvm.masked.load.v3i32.p1v3i32(<3 x i32> addrspace(1)* %2, i32 4, <3 x i1> %1, <3 x i32> undef)
+  ret <3 x i32> %3
+}
+
+define void @masked_store4_v3(<3 x i32>, i32 addrspace(1)*, <3 x i1>) {
+entry:
+  %3 = bitcast i32 addrspace(1)* %1 to <3 x i32> addrspace(1)*
+  call void @llvm.masked.store.v3i32.p1v3i32(<3 x i32> %0, <3 x i32> addrspace(1)* %3, i32 4, <3 x i1> %2)
+  ret void
+}
+
+define void @local_load_v3i1(i32 addrspace(1)* %out, i32 addrspace(1)* %in, <3 x i1>* %predicate_ptr) nounwind {
+; CHECK-LABEL: local_load_v3i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT: pushq   %rbp
+; CHECK-NEXT: pushq   %r15
+; CHECK-NEXT: pushq   %r14
+; CHECK-NEXT: pushq   %rbx
+; CHECK-NEXT: pushq   %rax
+; CHECK-NEXT: movq    %rdi, %r14
+; CHECK-NEXT: movzbl  (%rdx), %ebp
+; CHECK-NEXT: movl    %ebp, %eax
+; CHECK-NEXT: shrl    %eax
+; CHECK-NEXT: andl    $1, %eax
+; CHECK-NEXT: movl    %ebp, %ecx
+; CHECK-NEXT: andl    $1, %ecx
+; CHECK-NEXT: movd    %ecx, %xmm0
+; CHECK-NEXT: pinsrd  $1, %eax, %xmm0
+; CHECK-NEXT: shrl    $2, %ebp
+; CHECK-NEXT: andl    $1, %ebp
+; CHECK-NEXT: pinsrd  $2, %ebp, %xmm0
+; CHECK-NEXT: movd    %xmm0, %ebx
+; CHECK-NEXT: pextrd  $1, %xmm0, %r15d
+; CHECK-NEXT: movq    %rsi, %rdi
+; CHECK-NEXT: movl    %ebx, %esi
+; CHECK-NEXT: movl    %r15d, %edx
+; CHECK-NEXT: movl    %ebp, %ecx
+; CHECK-NEXT: callq   masked_load_v3
+; CHECK-NEXT: movq    %r14, %rdi
+; CHECK-NEXT: movl    %ebx, %esi
+; CHECK-NEXT: movl    %r15d, %edx
+; CHECK-NEXT: movl    %ebp, %ecx
+; CHECK-NEXT: callq   masked_store4_v3
+; CHECK-NEXT: addq    $8, %rsp
+; CHECK-NEXT: popq    %rbx
+; CHECK-NEXT: popq    %r14
+; CHECK-NEXT: popq    %r15
+; CHECK-NEXT: popq    %rbp
+; CHECK-NEXT: retq
+  %predicate = load <3 x i1>, <3 x i1>* %predicate_ptr
+  %load1 = call <3 x i32> @masked_load_v3(i32 addrspace(1)* %in, <3 x i1> %predicate)
+  call void @masked_store4_v3(<3 x i32> %load1, i32 addrspace(1)* %out, <3 x i1> %predicate)
+  ret void
+}

llvm/test/CodeGen/X86/widen_arith-3.ll

@@ -12,7 +12,7 @@ define void @update(<3 x i16>* %dst, <3 x i16>* %src, i32 %n) nounwind {
 ; CHECK-NEXT:    pushl %ebp
 ; CHECK-NEXT:    movl %esp, %ebp
 ; CHECK-NEXT:    andl $-8, %esp
-; CHECK-NEXT:    subl $40, %esp
+; CHECK-NEXT:    subl $32, %esp
 ; CHECK-NEXT:    movl {{\.LCPI.*}}, %eax
 ; CHECK-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
 ; CHECK-NEXT:    pcmpeqd %xmm0, %xmm0
@@ -26,9 +26,7 @@ define void @update(<3 x i16>* %dst, <3 x i16>* %src, i32 %n) nounwind {
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    movl 12(%ebp), %edx
 ; CHECK-NEXT:    movl 8(%ebp), %ecx
-; CHECK-NEXT:    movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; CHECK-NEXT:    pmovzxwd {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
-; CHECK-NEXT:    pmovzxwd {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
-; CHECK-NEXT:    pinsrd $2, 4(%edx,%eax,8), %xmm2
 ; CHECK-NEXT:    psubd %xmm0, %xmm2
 ; CHECK-NEXT:    pextrw $4, %xmm2, 4(%ecx,%eax,8)
 ; CHECK-NEXT:    pshufb %xmm1, %xmm2

llvm/test/CodeGen/X86/widen_cast-2.ll

@@ -21,9 +21,8 @@ define void @convert(<7 x i32>* %dst, <14 x i16>* %src) nounwind {
 ; CHECK-NEXT:    movdqa 16(%edx,%eax), %xmm2
 ; CHECK-NEXT:    psubw %xmm0, %xmm1
 ; CHECK-NEXT:    psubw %xmm0, %xmm2
-; CHECK-NEXT:    movd %xmm2, 16(%ecx,%eax)
-; CHECK-NEXT:    pextrd $1, %xmm2, 20(%ecx,%eax)
 ; CHECK-NEXT:    pextrd $2, %xmm2, 24(%ecx,%eax)
+; CHECK-NEXT:    movq %xmm2, 16(%ecx,%eax)
 ; CHECK-NEXT:    movdqa %xmm1, (%ecx,%eax)
 ; CHECK-NEXT:    incl (%esp)
 ; CHECK-NEXT:    cmpl $3, (%esp)

llvm/test/CodeGen/X86/widen_cast-3.ll

@@ -11,8 +11,7 @@ define void @convert(<12 x i8>* %dst.addr, <3 x i32> %src) nounwind {
 ; X86-NEXT:    pcmpeqd %xmm1, %xmm1
 ; X86-NEXT:    psubd %xmm1, %xmm0
 ; X86-NEXT:    pextrd $2, %xmm0, 8(%eax)
-; X86-NEXT:    pextrd $1, %xmm0, 4(%eax)
+; X86-NEXT:    movq %xmm0, (%eax)
-; X86-NEXT:    movd %xmm0, (%eax)
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: convert:

llvm/test/CodeGen/X86/widen_load-2.ll

@@ -15,8 +15,7 @@ define void @add3i32(%i32vec3*  sret %ret, %i32vec3* %ap, %i32vec3* %bp)  {
 ; X86-NEXT:    movdqa (%edx), %xmm0
 ; X86-NEXT:    paddd (%ecx), %xmm0
 ; X86-NEXT:    pextrd $2, %xmm0, 8(%eax)
-; X86-NEXT:    pextrd $1, %xmm0, 4(%eax)
+; X86-NEXT:    movq %xmm0, (%eax)
-; X86-NEXT:    movd %xmm0, (%eax)
 ; X86-NEXT:    retl $4
 ;
 ; X64-LABEL: add3i32:
@@ -40,16 +39,13 @@ define void @add3i32_2(%i32vec3*  sret %ret, %i32vec3* %ap, %i32vec3* %bp)  {
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X86-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; X86-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
-; X86-NEXT:    pinsrd $1, 4(%edx), %xmm0
 ; X86-NEXT:    pinsrd $2, 8(%edx), %xmm0
-; X86-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; X86-NEXT:    movq {{.*#+}} xmm1 = mem[0],zero
-; X86-NEXT:    pinsrd $1, 4(%ecx), %xmm1
 ; X86-NEXT:    pinsrd $2, 8(%ecx), %xmm1
 ; X86-NEXT:    paddd %xmm0, %xmm1
-; X86-NEXT:    pextrd $1, %xmm1, 4(%eax)
+; X86-NEXT:    movq %xmm1, (%eax)
 ; X86-NEXT:    pextrd $2, %xmm1, 8(%eax)
-; X86-NEXT:    movd %xmm1, (%eax)
 ; X86-NEXT:    retl $4
 ;
 ; X64-LABEL: add3i32_2:
@@ -81,9 +77,8 @@ define void @add7i32(%i32vec7*  sret %ret, %i32vec7* %ap, %i32vec7* %bp)  {
 ; X86-NEXT:    movdqa 16(%edx), %xmm1
 ; X86-NEXT:    paddd (%ecx), %xmm0
 ; X86-NEXT:    paddd 16(%ecx), %xmm1
-; X86-NEXT:    movd %xmm1, 16(%eax)
-; X86-NEXT:    pextrd $1, %xmm1, 20(%eax)
 ; X86-NEXT:    pextrd $2, %xmm1, 24(%eax)
+; X86-NEXT:    movq %xmm1, 16(%eax)
 ; X86-NEXT:    movdqa %xmm0, (%eax)
 ; X86-NEXT:    retl $4
 ;
@@ -151,16 +146,12 @@ define void @add3i16(%i16vec3* nocapture sret %ret, %i16vec3* %ap, %i16vec3* %bp
 ; X86-NEXT:    pushl %ebp
 ; X86-NEXT:    movl %esp, %ebp
 ; X86-NEXT:    andl $-8, %esp
-; X86-NEXT:    subl $24, %esp
+; X86-NEXT:    subl $8, %esp
 ; X86-NEXT:    movl 8(%ebp), %eax
 ; X86-NEXT:    movl 16(%ebp), %ecx
 ; X86-NEXT:    movl 12(%ebp), %edx
-; X86-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; X86-NEXT:    pmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
-; X86-NEXT:    pmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; X86-NEXT:    pmovzxwd {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
-; X86-NEXT:    pinsrd $2, 4(%edx), %xmm0
-; X86-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
-; X86-NEXT:    pmovzxwd {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
-; X86-NEXT:    pinsrd $2, 4(%ecx), %xmm1
 ; X86-NEXT:    paddd %xmm0, %xmm1
 ; X86-NEXT:    pextrw $4, %xmm1, 4(%eax)
 ; X86-NEXT:    pshufb {{.*#+}} xmm1 = xmm1[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
@@ -225,8 +216,7 @@ define void @add12i16(%i16vec12* nocapture sret %ret, %i16vec12* %ap, %i16vec12*
 ; X86-NEXT:    movdqa 16(%edx), %xmm1
 ; X86-NEXT:    paddw (%ecx), %xmm0
 ; X86-NEXT:    paddw 16(%ecx), %xmm1
-; X86-NEXT:    movd %xmm1, 16(%eax)
+; X86-NEXT:    movq %xmm1, 16(%eax)
-; X86-NEXT:    pextrd $1, %xmm1, 20(%eax)
 ; X86-NEXT:    movdqa %xmm0, (%eax)
 ; X86-NEXT:    retl $4
 ;
@@ -331,11 +321,10 @@ define void @add31i8(%i8vec31* nocapture sret %ret, %i8vec31* %ap, %i8vec31* %bp
 ; X86-NEXT:    movdqa 16(%edx), %xmm1
 ; X86-NEXT:    paddb (%ecx), %xmm0
 ; X86-NEXT:    paddb 16(%ecx), %xmm1
-; X86-NEXT:    movd %xmm1, 16(%eax)
-; X86-NEXT:    pextrd $1, %xmm1, 20(%eax)
 ; X86-NEXT:    pextrd $2, %xmm1, 24(%eax)
 ; X86-NEXT:    pextrw $6, %xmm1, 28(%eax)
 ; X86-NEXT:    pextrb $14, %xmm1, 30(%eax)
+; X86-NEXT:    movq %xmm1, 16(%eax)
 ; X86-NEXT:    movdqa %xmm0, (%eax)
 ; X86-NEXT:    retl $4
 ;