[llvm] 8cc0b58 - [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic.
Galina Kistanova via llvm-commits
llvm-commits at lists.llvm.org
Wed Dec 18 12:23:11 PST 2019
Hello Pengfei,
This commit broke test to the builder:
http://lab.llvm.org:8011/builders/llvm-clang-x86_64-expensive-checks-win/builds/21139
. . .
Failing Tests (1):
LLVM :: CodeGen/X86/masked_gather.ll
Please have a look ASAP?
Thanks
Galina
On Tue, Dec 17, 2019 at 8:25 PM via llvm-commits <
llvm-commits at lists.llvm.org> wrote:
>
> Author: Wang, Pengfei
> Date: 2019-12-18T12:24:58+08:00
> New Revision: 8cc0b586738157728a93af145c8f8dec1bf59ee1
>
> URL:
> https://github.com/llvm/llvm-project/commit/8cc0b586738157728a93af145c8f8dec1bf59ee1
> DIFF:
> https://github.com/llvm/llvm-project/commit/8cc0b586738157728a93af145c8f8dec1bf59ee1.diff
>
> LOG: [X86] Add calculation for elements in structures in getting uniform
> base for the Gather/Scatter intrinsic.
>
> Summary: Add calculation for elements in structures in getting uniform
> base for the Gather/Scatter intrinsic.
>
> Reviewers: craig.topper, c-rhodes, RKSimon
>
> Subscribers: hiraditya, llvm-commits, annita.zhang, LuoYuanke
>
> Tags: #llvm
>
> Differential Revision: https://reviews.llvm.org/D71442
>
> Added:
>
>
> Modified:
> llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
> llvm/test/CodeGen/X86/masked_gather.ll
>
> Removed:
>
>
>
>
> ################################################################################
> diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
> b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
> index 7b2430a60995..27ac489b35b7 100644
> --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
> +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
> @@ -4353,9 +4353,10 @@ static bool getUniformBase(const Value *&Ptr,
> SDValue &Base, SDValue &Index,
>
> unsigned FinalIndex = GEP->getNumOperands() - 1;
> Value *IndexVal = GEP->getOperand(FinalIndex);
> + gep_type_iterator GTI = gep_type_begin(*GEP);
>
> // Ensure all the other indices are 0.
> - for (unsigned i = 1; i < FinalIndex; ++i) {
> + for (unsigned i = 1; i < FinalIndex; ++i, ++GTI) {
> auto *C = dyn_cast<Constant>(GEP->getOperand(i));
> if (!C)
> return false;
> @@ -4368,18 +4369,39 @@ static bool getUniformBase(const Value *&Ptr,
> SDValue &Base, SDValue &Index,
>
> // The operands of the GEP may be defined in another basic block.
> // In this case we'll not find nodes for the operands.
> - if (!SDB->findValue(Ptr) || !SDB->findValue(IndexVal))
> + if (!SDB->findValue(Ptr))
> + return false;
> + Constant *C = dyn_cast<Constant>(IndexVal);
> + if (!C && !SDB->findValue(IndexVal))
> return false;
>
> const TargetLowering &TLI = DAG.getTargetLoweringInfo();
> const DataLayout &DL = DAG.getDataLayout();
> - Scale =
> DAG.getTargetConstant(DL.getTypeAllocSize(GEP->getResultElementType()),
> - SDB->getCurSDLoc(), TLI.getPointerTy(DL));
> + StructType *STy = GTI.getStructTypeOrNull();
> +
> + if (STy) {
> + const StructLayout *SL = DL.getStructLayout(STy);
> + if (isa<VectorType>(C->getType())) {
> + C = C->getSplatValue();
> + // FIXME: If getSplatValue may return nullptr for a structure?
> + // If not, the following check can be removed.
> + if (!C)
> + return false;
> + }
> + auto *CI = cast<ConstantInt>(C);
> + Scale = DAG.getTargetConstant(1, SDB->getCurSDLoc(),
> TLI.getPointerTy(DL));
> + Index =
> DAG.getTargetConstant(SL->getElementOffset(CI->getZExtValue()),
> + SDB->getCurSDLoc(),
> TLI.getPointerTy(DL));
> + } else {
> + Scale = DAG.getTargetConstant(
> + DL.getTypeAllocSize(GEP->getResultElementType()),
> + SDB->getCurSDLoc(), TLI.getPointerTy(DL));
> + Index = SDB->getValue(IndexVal);
> + }
> Base = SDB->getValue(Ptr);
> - Index = SDB->getValue(IndexVal);
> IndexType = ISD::SIGNED_SCALED;
>
> - if (!Index.getValueType().isVector()) {
> + if (STy || !Index.getValueType().isVector()) {
> unsigned GEPWidth = GEP->getType()->getVectorNumElements();
> EVT VT = EVT::getVectorVT(Context, Index.getValueType(), GEPWidth);
> Index = DAG.getSplatBuildVector(VT, SDLoc(Index), Index);
>
> diff --git a/llvm/test/CodeGen/X86/masked_gather.ll
> b/llvm/test/CodeGen/X86/masked_gather.ll
> index 0dabe546a145..dd41009a9aee 100644
> --- a/llvm/test/CodeGen/X86/masked_gather.ll
> +++ b/llvm/test/CodeGen/X86/masked_gather.ll
> @@ -8,6 +8,10 @@
> ; vXf32
> ;
>
> +%struct.a = type { [4 x i32], [4 x i8], %struct.b, i32 }
> +%struct.b = type { i32, i32 }
> + at c = external dso_local global %struct.a, align 4
> +
> define <4 x float> @gather_v4f32_ptr_v4i32(<4 x float*> %ptr, <4 x i32>
> %trigger, <4 x float> %passthru) {
> ; SSE-LABEL: gather_v4f32_ptr_v4i32:
> ; SSE: # %bb.0:
> @@ -1016,6 +1020,735 @@ define <16 x i8> @gather_v16i8_v16i32_v16i8(i8*
> %base, <16 x i32> %idx, <16 x i8
> ret <16 x i8> %res
> }
>
> +define <8 x i32> @gather_v8i32_v8i32(<8 x i32> %trigger) {
> +; SSE-LABEL: gather_v8i32_v8i32:
> +; SSE: # %bb.0:
> +; SSE-NEXT: movdqa %xmm1, %xmm3
> +; SSE-NEXT: movdqa %xmm0, %xmm2
> +; SSE-NEXT: movl $c, %eax
> +; SSE-NEXT: movq %rax, %xmm0
> +; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm0[0,1,0,1]
> +; SSE-NEXT: movdqa {{.*#+}} xmm5 = [12,12]
> +; SSE-NEXT: paddq %xmm4, %xmm5
> +; SSE-NEXT: pxor %xmm0, %xmm0
> +; SSE-NEXT: pcmpeqd %xmm0, %xmm1
> +; SSE-NEXT: pcmpeqd %xmm2, %xmm0
> +; SSE-NEXT: packssdw %xmm1, %xmm0
> +; SSE-NEXT: packsswb %xmm0, %xmm0
> +; SSE-NEXT: pmovmskb %xmm0, %eax
> +; SSE-NEXT: testb $1, %al
> +; SSE-NEXT: je .LBB4_1
> +; SSE-NEXT: # %bb.2: # %cond.load
> +; SSE-NEXT: movq %xmm5, %rcx
> +; SSE-NEXT: movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
> +; SSE-NEXT: testb $2, %al
> +; SSE-NEXT: jne .LBB4_4
> +; SSE-NEXT: jmp .LBB4_5
> +; SSE-NEXT: .LBB4_1:
> +; SSE-NEXT: # implicit-def: $xmm0
> +; SSE-NEXT: testb $2, %al
> +; SSE-NEXT: je .LBB4_5
> +; SSE-NEXT: .LBB4_4: # %cond.load1
> +; SSE-NEXT: pextrq $1, %xmm5, %rcx
> +; SSE-NEXT: pinsrd $1, (%rcx), %xmm0
> +; SSE-NEXT: .LBB4_5: # %else2
> +; SSE-NEXT: testb $4, %al
> +; SSE-NEXT: jne .LBB4_6
> +; SSE-NEXT: # %bb.7: # %else5
> +; SSE-NEXT: testb $8, %al
> +; SSE-NEXT: jne .LBB4_8
> +; SSE-NEXT: .LBB4_9: # %else8
> +; SSE-NEXT: testb $16, %al
> +; SSE-NEXT: je .LBB4_10
> +; SSE-NEXT: .LBB4_11: # %cond.load10
> +; SSE-NEXT: movq %xmm5, %rcx
> +; SSE-NEXT: pinsrd $0, (%rcx), %xmm1
> +; SSE-NEXT: testb $32, %al
> +; SSE-NEXT: jne .LBB4_13
> +; SSE-NEXT: jmp .LBB4_14
> +; SSE-NEXT: .LBB4_6: # %cond.load4
> +; SSE-NEXT: movq %xmm5, %rcx
> +; SSE-NEXT: pinsrd $2, (%rcx), %xmm0
> +; SSE-NEXT: testb $8, %al
> +; SSE-NEXT: je .LBB4_9
> +; SSE-NEXT: .LBB4_8: # %cond.load7
> +; SSE-NEXT: pextrq $1, %xmm5, %rcx
> +; SSE-NEXT: pinsrd $3, (%rcx), %xmm0
> +; SSE-NEXT: testb $16, %al
> +; SSE-NEXT: jne .LBB4_11
> +; SSE-NEXT: .LBB4_10:
> +; SSE-NEXT: # implicit-def: $xmm1
> +; SSE-NEXT: testb $32, %al
> +; SSE-NEXT: je .LBB4_14
> +; SSE-NEXT: .LBB4_13: # %cond.load13
> +; SSE-NEXT: pextrq $1, %xmm5, %rcx
> +; SSE-NEXT: pinsrd $1, (%rcx), %xmm1
> +; SSE-NEXT: .LBB4_14: # %else14
> +; SSE-NEXT: testb $64, %al
> +; SSE-NEXT: jne .LBB4_15
> +; SSE-NEXT: # %bb.16: # %else17
> +; SSE-NEXT: testb $-128, %al
> +; SSE-NEXT: je .LBB4_18
> +; SSE-NEXT: .LBB4_17: # %cond.load19
> +; SSE-NEXT: pextrq $1, %xmm5, %rax
> +; SSE-NEXT: pinsrd $3, (%rax), %xmm1
> +; SSE-NEXT: .LBB4_18: # %else20
> +; SSE-NEXT: pxor %xmm5, %xmm5
> +; SSE-NEXT: paddq {{.*}}(%rip), %xmm4
> +; SSE-NEXT: movdqa %xmm2, %xmm6
> +; SSE-NEXT: pcmpeqd %xmm5, %xmm6
> +; SSE-NEXT: pcmpeqd %xmm3, %xmm5
> +; SSE-NEXT: packssdw %xmm5, %xmm6
> +; SSE-NEXT: packsswb %xmm0, %xmm6
> +; SSE-NEXT: pmovmskb %xmm6, %eax
> +; SSE-NEXT: testb $1, %al
> +; SSE-NEXT: je .LBB4_19
> +; SSE-NEXT: # %bb.20: # %cond.load23
> +; SSE-NEXT: movq %xmm4, %rcx
> +; SSE-NEXT: movd {{.*#+}} xmm5 = mem[0],zero,zero,zero
> +; SSE-NEXT: testb $2, %al
> +; SSE-NEXT: jne .LBB4_22
> +; SSE-NEXT: jmp .LBB4_23
> +; SSE-NEXT: .LBB4_15: # %cond.load16
> +; SSE-NEXT: movq %xmm5, %rcx
> +; SSE-NEXT: pinsrd $2, (%rcx), %xmm1
> +; SSE-NEXT: testb $-128, %al
> +; SSE-NEXT: jne .LBB4_17
> +; SSE-NEXT: jmp .LBB4_18
> +; SSE-NEXT: .LBB4_19:
> +; SSE-NEXT: # implicit-def: $xmm5
> +; SSE-NEXT: testb $2, %al
> +; SSE-NEXT: je .LBB4_23
> +; SSE-NEXT: .LBB4_22: # %cond.load29
> +; SSE-NEXT: pextrq $1, %xmm4, %rcx
> +; SSE-NEXT: pinsrd $1, (%rcx), %xmm5
> +; SSE-NEXT: .LBB4_23: # %else33
> +; SSE-NEXT: testb $4, %al
> +; SSE-NEXT: jne .LBB4_24
> +; SSE-NEXT: # %bb.25: # %else39
> +; SSE-NEXT: testb $8, %al
> +; SSE-NEXT: jne .LBB4_26
> +; SSE-NEXT: .LBB4_27: # %else45
> +; SSE-NEXT: testb $16, %al
> +; SSE-NEXT: je .LBB4_28
> +; SSE-NEXT: .LBB4_29: # %cond.load47
> +; SSE-NEXT: movq %xmm4, %rcx
> +; SSE-NEXT: pinsrd $0, (%rcx), %xmm6
> +; SSE-NEXT: testb $32, %al
> +; SSE-NEXT: jne .LBB4_31
> +; SSE-NEXT: jmp .LBB4_32
> +; SSE-NEXT: .LBB4_24: # %cond.load35
> +; SSE-NEXT: movq %xmm4, %rcx
> +; SSE-NEXT: pinsrd $2, (%rcx), %xmm5
> +; SSE-NEXT: testb $8, %al
> +; SSE-NEXT: je .LBB4_27
> +; SSE-NEXT: .LBB4_26: # %cond.load41
> +; SSE-NEXT: pextrq $1, %xmm4, %rcx
> +; SSE-NEXT: pinsrd $3, (%rcx), %xmm5
> +; SSE-NEXT: testb $16, %al
> +; SSE-NEXT: jne .LBB4_29
> +; SSE-NEXT: .LBB4_28:
> +; SSE-NEXT: # implicit-def: $xmm6
> +; SSE-NEXT: testb $32, %al
> +; SSE-NEXT: je .LBB4_32
> +; SSE-NEXT: .LBB4_31: # %cond.load53
> +; SSE-NEXT: pextrq $1, %xmm4, %rcx
> +; SSE-NEXT: pinsrd $1, (%rcx), %xmm6
> +; SSE-NEXT: .LBB4_32: # %else57
> +; SSE-NEXT: testb $64, %al
> +; SSE-NEXT: jne .LBB4_33
> +; SSE-NEXT: # %bb.34: # %else63
> +; SSE-NEXT: testb $-128, %al
> +; SSE-NEXT: je .LBB4_36
> +; SSE-NEXT: .LBB4_35: # %cond.load65
> +; SSE-NEXT: pextrq $1, %xmm4, %rax
> +; SSE-NEXT: pinsrd $3, (%rax), %xmm6
> +; SSE-NEXT: .LBB4_36: # %else69
> +; SSE-NEXT: pxor %xmm7, %xmm7
> +; SSE-NEXT: pcmpeqd %xmm7, %xmm2
> +; SSE-NEXT: pcmpeqd %xmm7, %xmm3
> +; SSE-NEXT: packssdw %xmm3, %xmm2
> +; SSE-NEXT: packsswb %xmm0, %xmm2
> +; SSE-NEXT: pmovmskb %xmm2, %eax
> +; SSE-NEXT: testb $1, %al
> +; SSE-NEXT: je .LBB4_37
> +; SSE-NEXT: # %bb.38: # %cond.load72
> +; SSE-NEXT: movq %xmm4, %rcx
> +; SSE-NEXT: movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
> +; SSE-NEXT: testb $2, %al
> +; SSE-NEXT: jne .LBB4_40
> +; SSE-NEXT: jmp .LBB4_41
> +; SSE-NEXT: .LBB4_33: # %cond.load59
> +; SSE-NEXT: movq %xmm4, %rcx
> +; SSE-NEXT: pinsrd $2, (%rcx), %xmm6
> +; SSE-NEXT: testb $-128, %al
> +; SSE-NEXT: jne .LBB4_35
> +; SSE-NEXT: jmp .LBB4_36
> +; SSE-NEXT: .LBB4_37:
> +; SSE-NEXT: # implicit-def: $xmm2
> +; SSE-NEXT: testb $2, %al
> +; SSE-NEXT: je .LBB4_41
> +; SSE-NEXT: .LBB4_40: # %cond.load78
> +; SSE-NEXT: pextrq $1, %xmm4, %rcx
> +; SSE-NEXT: pinsrd $1, (%rcx), %xmm2
> +; SSE-NEXT: .LBB4_41: # %else82
> +; SSE-NEXT: testb $4, %al
> +; SSE-NEXT: jne .LBB4_42
> +; SSE-NEXT: # %bb.43: # %else88
> +; SSE-NEXT: testb $8, %al
> +; SSE-NEXT: jne .LBB4_44
> +; SSE-NEXT: .LBB4_45: # %else94
> +; SSE-NEXT: testb $16, %al
> +; SSE-NEXT: je .LBB4_46
> +; SSE-NEXT: .LBB4_47: # %cond.load96
> +; SSE-NEXT: movq %xmm4, %rcx
> +; SSE-NEXT: pinsrd $0, (%rcx), %xmm3
> +; SSE-NEXT: testb $32, %al
> +; SSE-NEXT: jne .LBB4_49
> +; SSE-NEXT: jmp .LBB4_50
> +; SSE-NEXT: .LBB4_42: # %cond.load84
> +; SSE-NEXT: movq %xmm4, %rcx
> +; SSE-NEXT: pinsrd $2, (%rcx), %xmm2
> +; SSE-NEXT: testb $8, %al
> +; SSE-NEXT: je .LBB4_45
> +; SSE-NEXT: .LBB4_44: # %cond.load90
> +; SSE-NEXT: pextrq $1, %xmm4, %rcx
> +; SSE-NEXT: pinsrd $3, (%rcx), %xmm2
> +; SSE-NEXT: testb $16, %al
> +; SSE-NEXT: jne .LBB4_47
> +; SSE-NEXT: .LBB4_46:
> +; SSE-NEXT: # implicit-def: $xmm3
> +; SSE-NEXT: testb $32, %al
> +; SSE-NEXT: je .LBB4_50
> +; SSE-NEXT: .LBB4_49: # %cond.load102
> +; SSE-NEXT: pextrq $1, %xmm4, %rcx
> +; SSE-NEXT: pinsrd $1, (%rcx), %xmm3
> +; SSE-NEXT: .LBB4_50: # %else106
> +; SSE-NEXT: testb $64, %al
> +; SSE-NEXT: je .LBB4_52
> +; SSE-NEXT: # %bb.51: # %cond.load108
> +; SSE-NEXT: movq %xmm4, %rcx
> +; SSE-NEXT: pinsrd $2, (%rcx), %xmm3
> +; SSE-NEXT: .LBB4_52: # %else112
> +; SSE-NEXT: paddd %xmm5, %xmm0
> +; SSE-NEXT: paddd %xmm6, %xmm1
> +; SSE-NEXT: testb $-128, %al
> +; SSE-NEXT: je .LBB4_54
> +; SSE-NEXT: # %bb.53: # %cond.load114
> +; SSE-NEXT: pextrq $1, %xmm4, %rax
> +; SSE-NEXT: pinsrd $3, (%rax), %xmm3
> +; SSE-NEXT: .LBB4_54: # %else118
> +; SSE-NEXT: paddd %xmm3, %xmm1
> +; SSE-NEXT: paddd %xmm2, %xmm0
> +; SSE-NEXT: retq
> +;
> +; AVX1-LABEL: gather_v8i32_v8i32:
> +; AVX1: # %bb.0:
> +; AVX1-NEXT: movl $c, %eax
> +; AVX1-NEXT: vmovq %rax, %xmm1
> +; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm1[0,1,0,1]
> +; AVX1-NEXT: vpaddq {{.*}}(%rip), %xmm3, %xmm1
> +; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm4
> +; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm9
> +; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
> +; AVX1-NEXT: vpcmpeqd %xmm1, %xmm9, %xmm5
> +; AVX1-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm1
> +; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm1, %ymm1
> +; AVX1-NEXT: vmovmskps %ymm1, %eax
> +; AVX1-NEXT: testb $1, %al
> +; AVX1-NEXT: # implicit-def: $ymm1
> +; AVX1-NEXT: je .LBB4_2
> +; AVX1-NEXT: # %bb.1: # %cond.load
> +; AVX1-NEXT: vmovq %xmm4, %rcx
> +; AVX1-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
> +; AVX1-NEXT: .LBB4_2: # %else
> +; AVX1-NEXT: testb $2, %al
> +; AVX1-NEXT: je .LBB4_4
> +; AVX1-NEXT: # %bb.3: # %cond.load1
> +; AVX1-NEXT: vpextrq $1, %xmm4, %rcx
> +; AVX1-NEXT: vpinsrd $1, (%rcx), %xmm1, %xmm5
> +; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm5[0,1,2,3],ymm1[4,5,6,7]
> +; AVX1-NEXT: .LBB4_4: # %else2
> +; AVX1-NEXT: testb $4, %al
> +; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm6
> +; AVX1-NEXT: jne .LBB4_5
> +; AVX1-NEXT: # %bb.6: # %else5
> +; AVX1-NEXT: testb $8, %al
> +; AVX1-NEXT: jne .LBB4_7
> +; AVX1-NEXT: .LBB4_8: # %else8
> +; AVX1-NEXT: testb $16, %al
> +; AVX1-NEXT: jne .LBB4_9
> +; AVX1-NEXT: .LBB4_10: # %else11
> +; AVX1-NEXT: testb $32, %al
> +; AVX1-NEXT: jne .LBB4_11
> +; AVX1-NEXT: .LBB4_12: # %else14
> +; AVX1-NEXT: testb $64, %al
> +; AVX1-NEXT: je .LBB4_14
> +; AVX1-NEXT: .LBB4_13: # %cond.load16
> +; AVX1-NEXT: vmovq %xmm6, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
> +; AVX1-NEXT: vpinsrd $2, (%rcx), %xmm4, %xmm4
> +; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
> +; AVX1-NEXT: .LBB4_14: # %else17
> +; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm3, %ymm5
> +; AVX1-NEXT: testb $-128, %al
> +; AVX1-NEXT: je .LBB4_16
> +; AVX1-NEXT: # %bb.15: # %cond.load19
> +; AVX1-NEXT: vpextrq $1, %xmm6, %rax
> +; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
> +; AVX1-NEXT: vpinsrd $3, (%rax), %xmm3, %xmm3
> +; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm1, %ymm1
> +; AVX1-NEXT: .LBB4_16: # %else20
> +; AVX1-NEXT: vextractf128 $1, %ymm5, %xmm3
> +; AVX1-NEXT: vmovdqa {{.*#+}} xmm10 = [28,28]
> +; AVX1-NEXT: vpaddq %xmm3, %xmm10, %xmm3
> +; AVX1-NEXT: vpaddq %xmm5, %xmm10, %xmm4
> +; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm4, %ymm7
> +; AVX1-NEXT: vpxor %xmm4, %xmm4, %xmm4
> +; AVX1-NEXT: vpcmpeqd %xmm4, %xmm9, %xmm2
> +; AVX1-NEXT: vpcmpeqd %xmm4, %xmm0, %xmm4
> +; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm4, %ymm2
> +; AVX1-NEXT: vmovmskps %ymm2, %eax
> +; AVX1-NEXT: testb $1, %al
> +; AVX1-NEXT: # implicit-def: $ymm4
> +; AVX1-NEXT: je .LBB4_18
> +; AVX1-NEXT: # %bb.17: # %cond.load23
> +; AVX1-NEXT: vmovq %xmm7, %rcx
> +; AVX1-NEXT: vmovd {{.*#+}} xmm4 = mem[0],zero,zero,zero
> +; AVX1-NEXT: .LBB4_18: # %else27
> +; AVX1-NEXT: testb $2, %al
> +; AVX1-NEXT: je .LBB4_20
> +; AVX1-NEXT: # %bb.19: # %cond.load29
> +; AVX1-NEXT: vpextrq $1, %xmm7, %rcx
> +; AVX1-NEXT: vpinsrd $1, (%rcx), %xmm4, %xmm2
> +; AVX1-NEXT: vblendps {{.*#+}} ymm4 = ymm2[0,1,2,3],ymm4[4,5,6,7]
> +; AVX1-NEXT: .LBB4_20: # %else33
> +; AVX1-NEXT: vpaddq %xmm5, %xmm10, %xmm8
> +; AVX1-NEXT: testb $4, %al
> +; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm7
> +; AVX1-NEXT: je .LBB4_22
> +; AVX1-NEXT: # %bb.21: # %cond.load35
> +; AVX1-NEXT: vmovq %xmm7, %rcx
> +; AVX1-NEXT: vpinsrd $2, (%rcx), %xmm4, %xmm2
> +; AVX1-NEXT: vblendps {{.*#+}} ymm4 = ymm2[0,1,2,3],ymm4[4,5,6,7]
> +; AVX1-NEXT: .LBB4_22: # %else39
> +; AVX1-NEXT: testb $8, %al
> +; AVX1-NEXT: je .LBB4_24
> +; AVX1-NEXT: # %bb.23: # %cond.load41
> +; AVX1-NEXT: vpextrq $1, %xmm7, %rcx
> +; AVX1-NEXT: vpinsrd $3, (%rcx), %xmm4, %xmm2
> +; AVX1-NEXT: vblendps {{.*#+}} ymm4 = ymm2[0,1,2,3],ymm4[4,5,6,7]
> +; AVX1-NEXT: .LBB4_24: # %else45
> +; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm8, %ymm7
> +; AVX1-NEXT: testb $16, %al
> +; AVX1-NEXT: je .LBB4_26
> +; AVX1-NEXT: # %bb.25: # %cond.load47
> +; AVX1-NEXT: vmovq %xmm7, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm2
> +; AVX1-NEXT: vpinsrd $0, (%rcx), %xmm2, %xmm2
> +; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm4, %ymm4
> +; AVX1-NEXT: .LBB4_26: # %else51
> +; AVX1-NEXT: testb $32, %al
> +; AVX1-NEXT: je .LBB4_28
> +; AVX1-NEXT: # %bb.27: # %cond.load53
> +; AVX1-NEXT: vpextrq $1, %xmm7, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm2
> +; AVX1-NEXT: vpinsrd $1, (%rcx), %xmm2, %xmm2
> +; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm4, %ymm4
> +; AVX1-NEXT: .LBB4_28: # %else57
> +; AVX1-NEXT: testb $64, %al
> +; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm7
> +; AVX1-NEXT: je .LBB4_30
> +; AVX1-NEXT: # %bb.29: # %cond.load59
> +; AVX1-NEXT: vmovq %xmm7, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm2
> +; AVX1-NEXT: vpinsrd $2, (%rcx), %xmm2, %xmm2
> +; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm4, %ymm4
> +; AVX1-NEXT: .LBB4_30: # %else63
> +; AVX1-NEXT: testb $-128, %al
> +; AVX1-NEXT: je .LBB4_32
> +; AVX1-NEXT: # %bb.31: # %cond.load65
> +; AVX1-NEXT: vpextrq $1, %xmm7, %rax
> +; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm2
> +; AVX1-NEXT: vpinsrd $3, (%rax), %xmm2, %xmm2
> +; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm4, %ymm4
> +; AVX1-NEXT: .LBB4_32: # %else69
> +; AVX1-NEXT: vpaddq %xmm5, %xmm10, %xmm2
> +; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm2, %ymm7
> +; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
> +; AVX1-NEXT: vpcmpeqd %xmm2, %xmm9, %xmm6
> +; AVX1-NEXT: vpcmpeqd %xmm2, %xmm0, %xmm0
> +; AVX1-NEXT: vinsertf128 $1, %xmm6, %ymm0, %ymm0
> +; AVX1-NEXT: vmovmskps %ymm0, %eax
> +; AVX1-NEXT: testb $1, %al
> +; AVX1-NEXT: # implicit-def: $ymm0
> +; AVX1-NEXT: je .LBB4_34
> +; AVX1-NEXT: # %bb.33: # %cond.load72
> +; AVX1-NEXT: vmovq %xmm7, %rcx
> +; AVX1-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
> +; AVX1-NEXT: .LBB4_34: # %else76
> +; AVX1-NEXT: testb $2, %al
> +; AVX1-NEXT: je .LBB4_36
> +; AVX1-NEXT: # %bb.35: # %cond.load78
> +; AVX1-NEXT: vpextrq $1, %xmm7, %rcx
> +; AVX1-NEXT: vpinsrd $1, (%rcx), %xmm0, %xmm2
> +; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5,6,7]
> +; AVX1-NEXT: .LBB4_36: # %else82
> +; AVX1-NEXT: vpaddq %xmm5, %xmm10, %xmm2
> +; AVX1-NEXT: testb $4, %al
> +; AVX1-NEXT: vextractf128 $1, %ymm7, %xmm5
> +; AVX1-NEXT: je .LBB4_38
> +; AVX1-NEXT: # %bb.37: # %cond.load84
> +; AVX1-NEXT: vmovq %xmm5, %rcx
> +; AVX1-NEXT: vpinsrd $2, (%rcx), %xmm0, %xmm6
> +; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm6[0,1,2,3],ymm0[4,5,6,7]
> +; AVX1-NEXT: .LBB4_38: # %else88
> +; AVX1-NEXT: testb $8, %al
> +; AVX1-NEXT: je .LBB4_40
> +; AVX1-NEXT: # %bb.39: # %cond.load90
> +; AVX1-NEXT: vpextrq $1, %xmm5, %rcx
> +; AVX1-NEXT: vpinsrd $3, (%rcx), %xmm0, %xmm5
> +; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm5[0,1,2,3],ymm0[4,5,6,7]
> +; AVX1-NEXT: .LBB4_40: # %else94
> +; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm2, %ymm2
> +; AVX1-NEXT: testb $16, %al
> +; AVX1-NEXT: je .LBB4_42
> +; AVX1-NEXT: # %bb.41: # %cond.load96
> +; AVX1-NEXT: vmovq %xmm2, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm3
> +; AVX1-NEXT: vpinsrd $0, (%rcx), %xmm3, %xmm3
> +; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
> +; AVX1-NEXT: .LBB4_42: # %else100
> +; AVX1-NEXT: vextractf128 $1, %ymm4, %xmm3
> +; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
> +; AVX1-NEXT: vpaddd %xmm4, %xmm1, %xmm1
> +; AVX1-NEXT: testb $32, %al
> +; AVX1-NEXT: je .LBB4_44
> +; AVX1-NEXT: # %bb.43: # %cond.load102
> +; AVX1-NEXT: vpextrq $1, %xmm2, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
> +; AVX1-NEXT: vpinsrd $1, (%rcx), %xmm4, %xmm4
> +; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
> +; AVX1-NEXT: .LBB4_44: # %else106
> +; AVX1-NEXT: vpaddd %xmm3, %xmm5, %xmm3
> +; AVX1-NEXT: testb $64, %al
> +; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
> +; AVX1-NEXT: je .LBB4_46
> +; AVX1-NEXT: # %bb.45: # %cond.load108
> +; AVX1-NEXT: vmovq %xmm2, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm4
> +; AVX1-NEXT: vpinsrd $2, (%rcx), %xmm4, %xmm4
> +; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm0, %ymm0
> +; AVX1-NEXT: .LBB4_46: # %else112
> +; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm1, %ymm1
> +; AVX1-NEXT: testb $-128, %al
> +; AVX1-NEXT: je .LBB4_48
> +; AVX1-NEXT: # %bb.47: # %cond.load114
> +; AVX1-NEXT: vpextrq $1, %xmm2, %rax
> +; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
> +; AVX1-NEXT: vpinsrd $3, (%rax), %xmm2, %xmm2
> +; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
> +; AVX1-NEXT: .LBB4_48: # %else118
> +; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
> +; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm3
> +; AVX1-NEXT: vpaddd %xmm2, %xmm3, %xmm2
> +; AVX1-NEXT: vpaddd %xmm0, %xmm1, %xmm0
> +; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
> +; AVX1-NEXT: retq
> +; AVX1-NEXT: .LBB4_5: # %cond.load4
> +; AVX1-NEXT: vmovq %xmm6, %rcx
> +; AVX1-NEXT: vpinsrd $2, (%rcx), %xmm1, %xmm5
> +; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm5[0,1,2,3],ymm1[4,5,6,7]
> +; AVX1-NEXT: testb $8, %al
> +; AVX1-NEXT: je .LBB4_8
> +; AVX1-NEXT: .LBB4_7: # %cond.load7
> +; AVX1-NEXT: vpextrq $1, %xmm6, %rcx
> +; AVX1-NEXT: vpinsrd $3, (%rcx), %xmm1, %xmm5
> +; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm5[0,1,2,3],ymm1[4,5,6,7]
> +; AVX1-NEXT: testb $16, %al
> +; AVX1-NEXT: je .LBB4_10
> +; AVX1-NEXT: .LBB4_9: # %cond.load10
> +; AVX1-NEXT: vmovq %xmm4, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm5
> +; AVX1-NEXT: vpinsrd $0, (%rcx), %xmm5, %xmm5
> +; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm1, %ymm1
> +; AVX1-NEXT: testb $32, %al
> +; AVX1-NEXT: je .LBB4_12
> +; AVX1-NEXT: .LBB4_11: # %cond.load13
> +; AVX1-NEXT: vpextrq $1, %xmm4, %rcx
> +; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm4
> +; AVX1-NEXT: vpinsrd $1, (%rcx), %xmm4, %xmm4
> +; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm1, %ymm1
> +; AVX1-NEXT: testb $64, %al
> +; AVX1-NEXT: jne .LBB4_13
> +; AVX1-NEXT: jmp .LBB4_14
> +;
> +; AVX2-LABEL: gather_v8i32_v8i32:
> +; AVX2: # %bb.0:
> +; AVX2-NEXT: movl $c, %eax
> +; AVX2-NEXT: vmovq %rax, %xmm1
> +; AVX2-NEXT: vpbroadcastq %xmm1, %ymm2
> +; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm1 = [12,12,12,12]
> +; AVX2-NEXT: vpaddq %ymm1, %ymm2, %ymm3
> +; AVX2-NEXT: vpxor %xmm1, %xmm1, %xmm1
> +; AVX2-NEXT: vpcmpeqd %ymm1, %ymm0, %ymm1
> +; AVX2-NEXT: vmovmskps %ymm1, %eax
> +; AVX2-NEXT: testb $1, %al
> +; AVX2-NEXT: # implicit-def: $ymm1
> +; AVX2-NEXT: je .LBB4_2
> +; AVX2-NEXT: # %bb.1: # %cond.load
> +; AVX2-NEXT: vmovq %xmm3, %rcx
> +; AVX2-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
> +; AVX2-NEXT: .LBB4_2: # %else
> +; AVX2-NEXT: testb $2, %al
> +; AVX2-NEXT: je .LBB4_4
> +; AVX2-NEXT: # %bb.3: # %cond.load1
> +; AVX2-NEXT: vpextrq $1, %xmm3, %rcx
> +; AVX2-NEXT: vpinsrd $1, (%rcx), %xmm1, %xmm4
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm4[0,1,2,3],ymm1[4,5,6,7]
> +; AVX2-NEXT: .LBB4_4: # %else2
> +; AVX2-NEXT: testb $4, %al
> +; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm4
> +; AVX2-NEXT: jne .LBB4_5
> +; AVX2-NEXT: # %bb.6: # %else5
> +; AVX2-NEXT: testb $8, %al
> +; AVX2-NEXT: jne .LBB4_7
> +; AVX2-NEXT: .LBB4_8: # %else8
> +; AVX2-NEXT: testb $16, %al
> +; AVX2-NEXT: jne .LBB4_9
> +; AVX2-NEXT: .LBB4_10: # %else11
> +; AVX2-NEXT: testb $32, %al
> +; AVX2-NEXT: jne .LBB4_11
> +; AVX2-NEXT: .LBB4_12: # %else14
> +; AVX2-NEXT: testb $64, %al
> +; AVX2-NEXT: jne .LBB4_13
> +; AVX2-NEXT: .LBB4_14: # %else17
> +; AVX2-NEXT: testb $-128, %al
> +; AVX2-NEXT: je .LBB4_16
> +; AVX2-NEXT: .LBB4_15: # %cond.load19
> +; AVX2-NEXT: vpextrq $1, %xmm4, %rax
> +; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm3
> +; AVX2-NEXT: vpinsrd $3, (%rax), %xmm3, %xmm3
> +; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm1, %ymm1
> +; AVX2-NEXT: .LBB4_16: # %else20
> +; AVX2-NEXT: vpxor %xmm4, %xmm4, %xmm4
> +; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm3 = [28,28,28,28]
> +; AVX2-NEXT: vpaddq %ymm3, %ymm2, %ymm3
> +; AVX2-NEXT: vpcmpeqd %ymm4, %ymm0, %ymm2
> +; AVX2-NEXT: vmovmskps %ymm2, %eax
> +; AVX2-NEXT: testb $1, %al
> +; AVX2-NEXT: # implicit-def: $ymm2
> +; AVX2-NEXT: je .LBB4_18
> +; AVX2-NEXT: # %bb.17: # %cond.load23
> +; AVX2-NEXT: vmovq %xmm3, %rcx
> +; AVX2-NEXT: vmovd {{.*#+}} xmm2 = mem[0],zero,zero,zero
> +; AVX2-NEXT: .LBB4_18: # %else27
> +; AVX2-NEXT: testb $2, %al
> +; AVX2-NEXT: je .LBB4_20
> +; AVX2-NEXT: # %bb.19: # %cond.load29
> +; AVX2-NEXT: vpextrq $1, %xmm3, %rcx
> +; AVX2-NEXT: vpinsrd $1, (%rcx), %xmm2, %xmm4
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm4[0,1,2,3],ymm2[4,5,6,7]
> +; AVX2-NEXT: .LBB4_20: # %else33
> +; AVX2-NEXT: testb $4, %al
> +; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm4
> +; AVX2-NEXT: jne .LBB4_21
> +; AVX2-NEXT: # %bb.22: # %else39
> +; AVX2-NEXT: testb $8, %al
> +; AVX2-NEXT: jne .LBB4_23
> +; AVX2-NEXT: .LBB4_24: # %else45
> +; AVX2-NEXT: testb $16, %al
> +; AVX2-NEXT: jne .LBB4_25
> +; AVX2-NEXT: .LBB4_26: # %else51
> +; AVX2-NEXT: testb $32, %al
> +; AVX2-NEXT: jne .LBB4_27
> +; AVX2-NEXT: .LBB4_28: # %else57
> +; AVX2-NEXT: testb $64, %al
> +; AVX2-NEXT: jne .LBB4_29
> +; AVX2-NEXT: .LBB4_30: # %else63
> +; AVX2-NEXT: testb $-128, %al
> +; AVX2-NEXT: je .LBB4_32
> +; AVX2-NEXT: .LBB4_31: # %cond.load65
> +; AVX2-NEXT: vpextrq $1, %xmm4, %rax
> +; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm5
> +; AVX2-NEXT: vpinsrd $3, (%rax), %xmm5, %xmm5
> +; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm2, %ymm2
> +; AVX2-NEXT: .LBB4_32: # %else69
> +; AVX2-NEXT: vpxor %xmm5, %xmm5, %xmm5
> +; AVX2-NEXT: vpcmpeqd %ymm5, %ymm0, %ymm0
> +; AVX2-NEXT: vmovmskps %ymm0, %eax
> +; AVX2-NEXT: testb $1, %al
> +; AVX2-NEXT: # implicit-def: $ymm0
> +; AVX2-NEXT: jne .LBB4_33
> +; AVX2-NEXT: # %bb.34: # %else76
> +; AVX2-NEXT: testb $2, %al
> +; AVX2-NEXT: jne .LBB4_35
> +; AVX2-NEXT: .LBB4_36: # %else82
> +; AVX2-NEXT: testb $4, %al
> +; AVX2-NEXT: jne .LBB4_37
> +; AVX2-NEXT: .LBB4_38: # %else88
> +; AVX2-NEXT: testb $8, %al
> +; AVX2-NEXT: jne .LBB4_39
> +; AVX2-NEXT: .LBB4_40: # %else94
> +; AVX2-NEXT: testb $16, %al
> +; AVX2-NEXT: jne .LBB4_41
> +; AVX2-NEXT: .LBB4_42: # %else100
> +; AVX2-NEXT: testb $32, %al
> +; AVX2-NEXT: jne .LBB4_43
> +; AVX2-NEXT: .LBB4_44: # %else106
> +; AVX2-NEXT: testb $64, %al
> +; AVX2-NEXT: je .LBB4_46
> +; AVX2-NEXT: .LBB4_45: # %cond.load108
> +; AVX2-NEXT: vmovq %xmm4, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm3
> +; AVX2-NEXT: vpinsrd $2, (%rcx), %xmm3, %xmm3
> +; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm0, %ymm0
> +; AVX2-NEXT: .LBB4_46: # %else112
> +; AVX2-NEXT: vpaddd %ymm2, %ymm1, %ymm1
> +; AVX2-NEXT: testb $-128, %al
> +; AVX2-NEXT: je .LBB4_48
> +; AVX2-NEXT: # %bb.47: # %cond.load114
> +; AVX2-NEXT: vpextrq $1, %xmm4, %rax
> +; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2
> +; AVX2-NEXT: vpinsrd $3, (%rax), %xmm2, %xmm2
> +; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm0, %ymm0
> +; AVX2-NEXT: .LBB4_48: # %else118
> +; AVX2-NEXT: vpaddd %ymm0, %ymm1, %ymm0
> +; AVX2-NEXT: retq
> +; AVX2-NEXT: .LBB4_5: # %cond.load4
> +; AVX2-NEXT: vmovq %xmm4, %rcx
> +; AVX2-NEXT: vpinsrd $2, (%rcx), %xmm1, %xmm5
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm5[0,1,2,3],ymm1[4,5,6,7]
> +; AVX2-NEXT: testb $8, %al
> +; AVX2-NEXT: je .LBB4_8
> +; AVX2-NEXT: .LBB4_7: # %cond.load7
> +; AVX2-NEXT: vpextrq $1, %xmm4, %rcx
> +; AVX2-NEXT: vpinsrd $3, (%rcx), %xmm1, %xmm5
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm5[0,1,2,3],ymm1[4,5,6,7]
> +; AVX2-NEXT: testb $16, %al
> +; AVX2-NEXT: je .LBB4_10
> +; AVX2-NEXT: .LBB4_9: # %cond.load10
> +; AVX2-NEXT: vmovq %xmm3, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm5
> +; AVX2-NEXT: vpinsrd $0, (%rcx), %xmm5, %xmm5
> +; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm1, %ymm1
> +; AVX2-NEXT: testb $32, %al
> +; AVX2-NEXT: je .LBB4_12
> +; AVX2-NEXT: .LBB4_11: # %cond.load13
> +; AVX2-NEXT: vpextrq $1, %xmm3, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm3
> +; AVX2-NEXT: vpinsrd $1, (%rcx), %xmm3, %xmm3
> +; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm1, %ymm1
> +; AVX2-NEXT: testb $64, %al
> +; AVX2-NEXT: je .LBB4_14
> +; AVX2-NEXT: .LBB4_13: # %cond.load16
> +; AVX2-NEXT: vmovq %xmm4, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm3
> +; AVX2-NEXT: vpinsrd $2, (%rcx), %xmm3, %xmm3
> +; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm1, %ymm1
> +; AVX2-NEXT: testb $-128, %al
> +; AVX2-NEXT: jne .LBB4_15
> +; AVX2-NEXT: jmp .LBB4_16
> +; AVX2-NEXT: .LBB4_21: # %cond.load35
> +; AVX2-NEXT: vmovq %xmm4, %rcx
> +; AVX2-NEXT: vpinsrd $2, (%rcx), %xmm2, %xmm5
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm5[0,1,2,3],ymm2[4,5,6,7]
> +; AVX2-NEXT: testb $8, %al
> +; AVX2-NEXT: je .LBB4_24
> +; AVX2-NEXT: .LBB4_23: # %cond.load41
> +; AVX2-NEXT: vpextrq $1, %xmm4, %rcx
> +; AVX2-NEXT: vpinsrd $3, (%rcx), %xmm2, %xmm5
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm2 = ymm5[0,1,2,3],ymm2[4,5,6,7]
> +; AVX2-NEXT: testb $16, %al
> +; AVX2-NEXT: je .LBB4_26
> +; AVX2-NEXT: .LBB4_25: # %cond.load47
> +; AVX2-NEXT: vmovq %xmm3, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm5
> +; AVX2-NEXT: vpinsrd $0, (%rcx), %xmm5, %xmm5
> +; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm2, %ymm2
> +; AVX2-NEXT: testb $32, %al
> +; AVX2-NEXT: je .LBB4_28
> +; AVX2-NEXT: .LBB4_27: # %cond.load53
> +; AVX2-NEXT: vpextrq $1, %xmm3, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm5
> +; AVX2-NEXT: vpinsrd $1, (%rcx), %xmm5, %xmm5
> +; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm2, %ymm2
> +; AVX2-NEXT: testb $64, %al
> +; AVX2-NEXT: je .LBB4_30
> +; AVX2-NEXT: .LBB4_29: # %cond.load59
> +; AVX2-NEXT: vmovq %xmm4, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm5
> +; AVX2-NEXT: vpinsrd $2, (%rcx), %xmm5, %xmm5
> +; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm2, %ymm2
> +; AVX2-NEXT: testb $-128, %al
> +; AVX2-NEXT: jne .LBB4_31
> +; AVX2-NEXT: jmp .LBB4_32
> +; AVX2-NEXT: .LBB4_33: # %cond.load72
> +; AVX2-NEXT: vmovq %xmm3, %rcx
> +; AVX2-NEXT: vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
> +; AVX2-NEXT: testb $2, %al
> +; AVX2-NEXT: je .LBB4_36
> +; AVX2-NEXT: .LBB4_35: # %cond.load78
> +; AVX2-NEXT: vpextrq $1, %xmm3, %rcx
> +; AVX2-NEXT: vpinsrd $1, (%rcx), %xmm0, %xmm5
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm5[0,1,2,3],ymm0[4,5,6,7]
> +; AVX2-NEXT: testb $4, %al
> +; AVX2-NEXT: je .LBB4_38
> +; AVX2-NEXT: .LBB4_37: # %cond.load84
> +; AVX2-NEXT: vmovq %xmm4, %rcx
> +; AVX2-NEXT: vpinsrd $2, (%rcx), %xmm0, %xmm5
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm5[0,1,2,3],ymm0[4,5,6,7]
> +; AVX2-NEXT: testb $8, %al
> +; AVX2-NEXT: je .LBB4_40
> +; AVX2-NEXT: .LBB4_39: # %cond.load90
> +; AVX2-NEXT: vpextrq $1, %xmm4, %rcx
> +; AVX2-NEXT: vpinsrd $3, (%rcx), %xmm0, %xmm5
> +; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm5[0,1,2,3],ymm0[4,5,6,7]
> +; AVX2-NEXT: testb $16, %al
> +; AVX2-NEXT: je .LBB4_42
> +; AVX2-NEXT: .LBB4_41: # %cond.load96
> +; AVX2-NEXT: vmovq %xmm3, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm5
> +; AVX2-NEXT: vpinsrd $0, (%rcx), %xmm5, %xmm5
> +; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm0, %ymm0
> +; AVX2-NEXT: testb $32, %al
> +; AVX2-NEXT: je .LBB4_44
> +; AVX2-NEXT: .LBB4_43: # %cond.load102
> +; AVX2-NEXT: vpextrq $1, %xmm3, %rcx
> +; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm3
> +; AVX2-NEXT: vpinsrd $1, (%rcx), %xmm3, %xmm3
> +; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm0, %ymm0
> +; AVX2-NEXT: testb $64, %al
> +; AVX2-NEXT: jne .LBB4_45
> +; AVX2-NEXT: jmp .LBB4_46
> +;
> +; AVX512-LABEL: gather_v8i32_v8i32:
> +; AVX512: # %bb.0:
> +; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
> +; AVX512-NEXT: vptestnmd %zmm0, %zmm0, %k1
> +; AVX512-NEXT: kshiftlw $8, %k1, %k0
> +; AVX512-NEXT: kshiftrw $8, %k0, %k2
> +; AVX512-NEXT: vpbroadcastd {{.*#+}} zmm0 =
> [3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3]
> +; AVX512-NEXT: vpgatherdd c(,%zmm0,4), %zmm1 {%k2}
> +; AVX512-NEXT: vpbroadcastq $28, %zmm0
> +; AVX512-NEXT: vpgatherqd c(,%zmm0), %ymm2 {%k1}
> +; AVX512-NEXT: vpaddd %ymm2, %ymm2, %ymm0
> +; AVX512-NEXT: vpaddd %ymm0, %ymm1, %ymm0
> +; AVX512-NEXT: retq
> + %1 = insertelement <8 x %struct.a*> undef, %struct.a* @c, i32 0
> + %2 = shufflevector <8 x %struct.a*> %1, <8 x %struct.a*> undef, <8 x
> i32> zeroinitializer
> + %3 = getelementptr %struct.a, <8 x %struct.a*> %2, <8 x i32>
> zeroinitializer, i32 0, i32 3
> + %4 = icmp eq <8 x i32> %trigger, zeroinitializer
> + %5 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> %3,
> i32 4, <8 x i1> %4, <8 x i32> undef)
> + %6 = getelementptr %struct.a, <8 x %struct.a*> %2, <8 x i32>
> zeroinitializer, i32 3
> + %7 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> %6,
> i32 4, <8 x i1> %4, <8 x i32> undef)
> + %8 = add <8 x i32> %5, %7
> + %9 = getelementptr %struct.a, <8 x %struct.a*> %2, i32 0, <8 x i32>
> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
> + %10 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> %9,
> i32 4, <8 x i1> %4, <8 x i32> undef)
> + %11 = add <8 x i32> %8, %10
> + ret <8 x i32> %11
> +}
> +
> declare <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*>,
> i32, <2 x i1>, <2 x double>)
> declare <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*>,
> i32, <4 x i1>, <4 x double>)
>
> @@ -1023,3 +1756,5 @@ declare <4 x float>
> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*>, i32, <4 x i1
> declare <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*>, i32,
> <8 x i1>, <8 x float>)
>
> declare <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*>, i32, <16
> x i1>, <16 x i8>)
> +
> +declare <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*>, i32, <8 x
> i1>, <8 x i32>)
>
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at lists.llvm.org
> https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191218/729f8390/attachment.html>
More information about the llvm-commits
mailing list