This is an archive of the discontinued LLVM Phabricator instance.

Show First 20 Lines • Show All 5,207 Lines • ▼ Show 20 Lines	case Instruction::InsertElement: {
if (!InsertIdx \|\| *InsertIdx == UndefMaskElem)		if (!InsertIdx \|\| *InsertIdx == UndefMaskElem)
continue;		continue;
Mask[*InsertIdx - Offset] = I;		Mask[*InsertIdx - Offset] = I;
}		}
} else {		} else {
std::iota(Mask.begin(), std::next(Mask.begin(), NumScalars), 0);		std::iota(Mask.begin(), std::next(Mask.begin(), NumScalars), 0);
}		}
if (!IsIdentity \|\| NumElts != NumScalars)		if (!IsIdentity \|\| NumElts != NumScalars)
V = Builder.CreateShuffleVector(V, UndefValue::get(V->getType()), Mask);		V = Builder.CreateShuffleVector(V, Mask);

if (NumElts != NumScalars) {		if (NumElts != NumScalars) {
SmallVector<int> InsertMask(NumElts);		SmallVector<int> InsertMask(NumElts);
std::iota(InsertMask.begin(), InsertMask.end(), 0);		std::iota(InsertMask.begin(), InsertMask.end(), 0);
for (unsigned I = 0; I < NumElts; I++) {		for (unsigned I = 0; I < NumElts; I++) {
if (Mask[I] != UndefMaskElem)		if (Mask[I] != UndefMaskElem)
InsertMask[Offset + I] = NumElts + I;		InsertMask[Offset + I] = NumElts + I;
}		}
▲ Show 20 Lines • Show All 3,335 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions-inseltpoison.ll

	Show All 23 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @llvm.sin.f32(float %vecext)			%1 = tail call fast float @llvm.sin.f32(float %vecext)
	%vecins = insertelement <4 x float> poison, float %1, i32 0			%vecins = insertelement <4 x float> poison, float %1, i32 0
	▲ Show 20 Lines • Show All 179 Lines • ▼ Show 20 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @expf(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @expf(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.exp.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.exp.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @expf(float %vecext)			%1 = tail call fast float @expf(float %vecext)
	%vecins = insertelement <4 x float> poison, float %1, i32 0			%vecins = insertelement <4 x float> poison, float %1, i32 0
	▲ Show 20 Lines • Show All 66 Lines • ▼ Show 20 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @logf(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @logf(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.log.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.log.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @logf(float %vecext)			%1 = tail call fast float @logf(float %vecext)
	%vecins = insertelement <4 x float> poison, float %1, i32 0			%vecins = insertelement <4 x float> poison, float %1, i32 0
	▲ Show 20 Lines • Show All 159 Lines • ▼ Show 20 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @sinf(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @sinf(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @sinf(float %vecext)			%1 = tail call fast float @sinf(float %vecext)
	%vecins = insertelement <4 x float> poison, float %1, i32 0			%vecins = insertelement <4 x float> poison, float %1, i32 0
	Show All 25 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @cosf(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @cosf(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @cosf(float %vecext)			%1 = tail call fast float @cosf(float %vecext)
	%vecins = insertelement <4 x float> poison, float %1, i32 0			%vecins = insertelement <4 x float> poison, float %1, i32 0
	▲ Show 20 Lines • Show All 474 Lines • ▼ Show 20 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @llvm.cos.f32(float %vecext)			%1 = tail call fast float @llvm.cos.f32(float %vecext)
	%vecins = insertelement <4 x float> poison, float %1, i32 0			%vecins = insertelement <4 x float> poison, float %1, i32 0
	▲ Show 20 Lines • Show All 46 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions.ll

	Show All 23 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @llvm.sin.f32(float %vecext)			%1 = tail call fast float @llvm.sin.f32(float %vecext)
	%vecins = insertelement <4 x float> undef, float %1, i32 0			%vecins = insertelement <4 x float> undef, float %1, i32 0
	▲ Show 20 Lines • Show All 179 Lines • ▼ Show 20 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @expf(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @expf(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.exp.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.exp.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @expf(float %vecext)			%1 = tail call fast float @expf(float %vecext)
	%vecins = insertelement <4 x float> undef, float %1, i32 0			%vecins = insertelement <4 x float> undef, float %1, i32 0
	▲ Show 20 Lines • Show All 66 Lines • ▼ Show 20 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @logf(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @logf(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.log.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.log.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @logf(float %vecext)			%1 = tail call fast float @logf(float %vecext)
	%vecins = insertelement <4 x float> undef, float %1, i32 0			%vecins = insertelement <4 x float> undef, float %1, i32 0
	▲ Show 20 Lines • Show All 159 Lines • ▼ Show 20 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @sinf(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @sinf(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @sinf(float %vecext)			%1 = tail call fast float @sinf(float %vecext)
	%vecins = insertelement <4 x float> undef, float %1, i32 0			%vecins = insertelement <4 x float> undef, float %1, i32 0
	Show All 25 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @cosf(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @cosf(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @cosf(float %vecext)			%1 = tail call fast float @cosf(float %vecext)
	%vecins = insertelement <4 x float> undef, float %1, i32 0			%vecins = insertelement <4 x float> undef, float %1, i32 0
	▲ Show 20 Lines • Show All 474 Lines • ▼ Show 20 Lines
	; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1			; NOACCELERATE-NEXT: [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
	; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT_1]])			; NOACCELERATE-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT_1]])
	; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1			; NOACCELERATE-NEXT: [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
	; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2			; NOACCELERATE-NEXT: [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
	; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3			; NOACCELERATE-NEXT: [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
	; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0			; NOACCELERATE-NEXT: [[TMP3:%.*]] = insertelement <2 x float> poison, float [[VECEXT_2]], i32 0
	; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1			; NOACCELERATE-NEXT: [[TMP4:%.*]] = insertelement <2 x float> [[TMP3]], float [[VECEXT_3]], i32 1
	; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP4]])			; NOACCELERATE-NEXT: [[TMP5:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP4]])
	; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; NOACCELERATE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; NOACCELERATE-NEXT: [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]			; NOACCELERATE-NEXT: ret <4 x float> [[VECINS_31]]
	;			;
	entry:			entry:
	%0 = load <4 x float>, <4 x float>* %a, align 16			%0 = load <4 x float>, <4 x float>* %a, align 16
	%vecext = extractelement <4 x float> %0, i32 0			%vecext = extractelement <4 x float> %0, i32 0
	%1 = tail call fast float @llvm.cos.f32(float %vecext)			%1 = tail call fast float @llvm.cos.f32(float %vecext)
	%vecins = insertelement <4 x float> undef, float %1, i32 0			%vecins = insertelement <4 x float> undef, float %1, i32 0
	▲ Show 20 Lines • Show All 46 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AArch64/gather-root.ll

	Show First 20 Lines • Show All 181 Lines • ▼ Show 20 Lines
	; MAX-COST-NEXT: [[P12:%.]] = load i8, i8 getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 7), align 1			; MAX-COST-NEXT: [[P12:%.]] = load i8, i8 getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 7), align 1
	; MAX-COST-NEXT: [[P13:%.*]] = icmp eq i8 [[P12]], 0			; MAX-COST-NEXT: [[P13:%.*]] = icmp eq i8 [[P12]], 0
	; MAX-COST-NEXT: [[P14:%.]] = load i8, i8 getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 8), align 8			; MAX-COST-NEXT: [[P14:%.]] = load i8, i8 getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 8), align 8
	; MAX-COST-NEXT: [[P15:%.*]] = icmp eq i8 [[P14]], 0			; MAX-COST-NEXT: [[P15:%.*]] = icmp eq i8 [[P14]], 0
	; MAX-COST-NEXT: br label [[FOR_BODY:%.*]]			; MAX-COST-NEXT: br label [[FOR_BODY:%.*]]
	; MAX-COST: for.body:			; MAX-COST: for.body:
	; MAX-COST-NEXT: [[P17:%.]] = phi i32 [ [[P34:%.]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]			; MAX-COST-NEXT: [[P17:%.]] = phi i32 [ [[P34:%.]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
	; MAX-COST-NEXT: [[TMP4:%.*]] = extractelement <2 x i1> [[TMP3]], i32 1			; MAX-COST-NEXT: [[TMP4:%.*]] = extractelement <2 x i1> [[TMP3]], i32 1
	; MAX-COST-NEXT: [[TMP5:%.*]] = shufflevector <2 x i1> [[TMP1]], <2 x i1> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; MAX-COST-NEXT: [[TMP5:%.*]] = shufflevector <2 x i1> [[TMP1]], <2 x i1> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; MAX-COST-NEXT: [[TMP6:%.*]] = shufflevector <4 x i1> poison, <4 x i1> [[TMP5]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>			; MAX-COST-NEXT: [[TMP6:%.*]] = shufflevector <4 x i1> poison, <4 x i1> [[TMP5]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
	; MAX-COST-NEXT: [[TMP7:%.*]] = shufflevector <2 x i1> [[TMP3]], <2 x i1> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; MAX-COST-NEXT: [[TMP7:%.*]] = shufflevector <2 x i1> [[TMP3]], <2 x i1> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; MAX-COST-NEXT: [[TMP8:%.*]] = shufflevector <4 x i1> [[TMP6]], <4 x i1> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; MAX-COST-NEXT: [[TMP8:%.*]] = shufflevector <4 x i1> [[TMP6]], <4 x i1> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; MAX-COST-NEXT: [[TMP9:%.*]] = select <4 x i1> [[TMP8]], <4 x i32> <i32 -720, i32 -720, i32 -720, i32 -720>, <4 x i32> <i32 -80, i32 -80, i32 -80, i32 -80>			; MAX-COST-NEXT: [[TMP9:%.*]] = select <4 x i1> [[TMP8]], <4 x i32> <i32 -720, i32 -720, i32 -720, i32 -720>, <4 x i32> <i32 -80, i32 -80, i32 -80, i32 -80>
	; MAX-COST-NEXT: [[TMP10:%.*]] = extractelement <2 x i1> [[TMP3]], i32 0			; MAX-COST-NEXT: [[TMP10:%.*]] = extractelement <2 x i1> [[TMP3]], i32 0
	; MAX-COST-NEXT: [[TMP11:%.*]] = extractelement <2 x i1> [[TMP1]], i32 1			; MAX-COST-NEXT: [[TMP11:%.*]] = extractelement <2 x i1> [[TMP1]], i32 1
	; MAX-COST-NEXT: [[TMP12:%.*]] = extractelement <2 x i1> [[TMP1]], i32 0			; MAX-COST-NEXT: [[TMP12:%.*]] = extractelement <2 x i1> [[TMP1]], i32 0
	; MAX-COST-NEXT: [[P27:%.*]] = select i1 [[P9]], i32 -720, i32 -80			; MAX-COST-NEXT: [[P27:%.*]] = select i1 [[P9]], i32 -720, i32 -80
	; MAX-COST-NEXT: [[P29:%.*]] = select i1 [[P11]], i32 -720, i32 -80			; MAX-COST-NEXT: [[P29:%.*]] = select i1 [[P11]], i32 -720, i32 -80
	; MAX-COST-NEXT: [[TMP13:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP9]])			; MAX-COST-NEXT: [[TMP13:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP9]])
	▲ Show 20 Lines • Show All 48 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AArch64/transpose-inseltpoison.ll

	Show First 20 Lines • Show All 152 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[TMP0_1:%.*]] = add i32 [[TMP3]], [[TMP1]]			; CHECK-NEXT: [[TMP0_1:%.*]] = add i32 [[TMP3]], [[TMP1]]
	; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[V0]], [[V1]]			; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[V0]], [[V1]]
	; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_0]], i32 0			; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_0]], i32 0
	; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_1]], i32 0			; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_1]], i32 0
	; CHECK-NEXT: [[TMP8:%.*]] = sub <2 x i32> [[TMP6]], [[TMP7]]			; CHECK-NEXT: [[TMP8:%.*]] = sub <2 x i32> [[TMP6]], [[TMP7]]
	; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <2 x i32> <i32 1, i32 0>			; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <2 x i32> <i32 1, i32 0>
	; CHECK-NEXT: [[TMP10:%.*]] = sub <2 x i32> [[TMP5]], [[TMP9]]			; CHECK-NEXT: [[TMP10:%.*]] = sub <2 x i32> [[TMP5]], [[TMP9]]
	; CHECK-NEXT: [[TMP2_11:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> undef, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP2_11:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> undef, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP10]], <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP10]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP2_32:%.*]] = shufflevector <4 x i32> [[TMP2_11]], <4 x i32> [[TMP11]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; CHECK-NEXT: [[TMP2_32:%.*]] = shufflevector <4 x i32> [[TMP2_11]], <4 x i32> [[TMP11]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; CHECK-NEXT: ret <4 x i32> [[TMP2_32]]			; CHECK-NEXT: ret <4 x i32> [[TMP2_32]]
	;			;
	%v0.0 = extractelement <2 x i32> %v0, i32 0			%v0.0 = extractelement <2 x i32> %v0, i32 0
	%v0.1 = extractelement <2 x i32> %v0, i32 1			%v0.1 = extractelement <2 x i32> %v0, i32 1
	%v1.0 = extractelement <2 x i32> %v1, i32 0			%v1.0 = extractelement <2 x i32> %v1, i32 0
	%v1.1 = extractelement <2 x i32> %v1, i32 1			%v1.1 = extractelement <2 x i32> %v1, i32 1
	%tmp0.0 = add i32 %v0.0, %v1.0			%tmp0.0 = add i32 %v0.0, %v1.0
	Show All 25 Lines
	; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> undef, <2 x i32> zeroinitializer			; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> undef, <2 x i32> zeroinitializer
	; CHECK-NEXT: [[TMP3:%.*]] = xor <2 x i32> [[V0]], [[V1]]			; CHECK-NEXT: [[TMP3:%.*]] = xor <2 x i32> [[V0]], [[V1]]
	; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> undef, <2 x i32> <i32 1, i32 1>			; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> undef, <2 x i32> <i32 1, i32 1>
	; CHECK-NEXT: [[TMP2_0:%.*]] = add i32 [[TMP0_0]], [[TMP0_1]]			; CHECK-NEXT: [[TMP2_0:%.*]] = add i32 [[TMP0_0]], [[TMP0_1]]
	; CHECK-NEXT: [[TMP2_1:%.*]] = add i32 [[TMP1_0]], [[TMP1_1]]			; CHECK-NEXT: [[TMP2_1:%.*]] = add i32 [[TMP1_0]], [[TMP1_1]]
	; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i32> [[TMP2]], [[TMP4]]			; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i32> [[TMP2]], [[TMP4]]
	; CHECK-NEXT: [[TMP3_0:%.*]] = insertelement <4 x i32> poison, i32 [[TMP2_0]], i32 0			; CHECK-NEXT: [[TMP3_0:%.*]] = insertelement <4 x i32> poison, i32 [[TMP2_0]], i32 0
	; CHECK-NEXT: [[TMP3_1:%.*]] = insertelement <4 x i32> [[TMP3_0]], i32 [[TMP2_1]], i32 1			; CHECK-NEXT: [[TMP3_1:%.*]] = insertelement <4 x i32> [[TMP3_0]], i32 [[TMP2_1]], i32 1
	; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP3_31:%.*]] = shufflevector <4 x i32> [[TMP3_1]], <4 x i32> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; CHECK-NEXT: [[TMP3_31:%.*]] = shufflevector <4 x i32> [[TMP3_1]], <4 x i32> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; CHECK-NEXT: ret <4 x i32> [[TMP3_31]]			; CHECK-NEXT: ret <4 x i32> [[TMP3_31]]
	;			;
	%v0.0 = extractelement <2 x i32> %v0, i32 0			%v0.0 = extractelement <2 x i32> %v0, i32 0
	%v0.1 = extractelement <2 x i32> %v0, i32 1			%v0.1 = extractelement <2 x i32> %v0, i32 1
	%v1.0 = extractelement <2 x i32> %v1, i32 0			%v1.0 = extractelement <2 x i32> %v1, i32 0
	%v1.1 = extractelement <2 x i32> %v1, i32 1			%v1.1 = extractelement <2 x i32> %v1, i32 1
	%tmp0.0 = add i32 %v0.0, %v1.0			%tmp0.0 = add i32 %v0.0, %v1.0
	▲ Show 20 Lines • Show All 82 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll

	Show First 20 Lines • Show All 152 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[TMP0_1:%.*]] = add i32 [[TMP3]], [[TMP1]]			; CHECK-NEXT: [[TMP0_1:%.*]] = add i32 [[TMP3]], [[TMP1]]
	; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[V0]], [[V1]]			; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[V0]], [[V1]]
	; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_0]], i32 0			; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_0]], i32 0
	; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_1]], i32 0			; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[TMP0_1]], i32 0
	; CHECK-NEXT: [[TMP8:%.*]] = sub <2 x i32> [[TMP6]], [[TMP7]]			; CHECK-NEXT: [[TMP8:%.*]] = sub <2 x i32> [[TMP6]], [[TMP7]]
	; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <2 x i32> <i32 1, i32 0>			; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <2 x i32> <i32 1, i32 0>
	; CHECK-NEXT: [[TMP10:%.*]] = sub <2 x i32> [[TMP5]], [[TMP9]]			; CHECK-NEXT: [[TMP10:%.*]] = sub <2 x i32> [[TMP5]], [[TMP9]]
	; CHECK-NEXT: [[TMP2_11:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> undef, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP2_11:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> undef, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP10]], <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP10]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP2_32:%.*]] = shufflevector <4 x i32> [[TMP2_11]], <4 x i32> [[TMP11]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; CHECK-NEXT: [[TMP2_32:%.*]] = shufflevector <4 x i32> [[TMP2_11]], <4 x i32> [[TMP11]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; CHECK-NEXT: ret <4 x i32> [[TMP2_32]]			; CHECK-NEXT: ret <4 x i32> [[TMP2_32]]
	;			;
	%v0.0 = extractelement <2 x i32> %v0, i32 0			%v0.0 = extractelement <2 x i32> %v0, i32 0
	%v0.1 = extractelement <2 x i32> %v0, i32 1			%v0.1 = extractelement <2 x i32> %v0, i32 1
	%v1.0 = extractelement <2 x i32> %v1, i32 0			%v1.0 = extractelement <2 x i32> %v1, i32 0
	%v1.1 = extractelement <2 x i32> %v1, i32 1			%v1.1 = extractelement <2 x i32> %v1, i32 1
	%tmp0.0 = add i32 %v0.0, %v1.0			%tmp0.0 = add i32 %v0.0, %v1.0
	Show All 25 Lines
	; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> undef, <2 x i32> zeroinitializer			; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> undef, <2 x i32> zeroinitializer
	; CHECK-NEXT: [[TMP3:%.*]] = xor <2 x i32> [[V0]], [[V1]]			; CHECK-NEXT: [[TMP3:%.*]] = xor <2 x i32> [[V0]], [[V1]]
	; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> undef, <2 x i32> <i32 1, i32 1>			; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> undef, <2 x i32> <i32 1, i32 1>
	; CHECK-NEXT: [[TMP2_0:%.*]] = add i32 [[TMP0_0]], [[TMP0_1]]			; CHECK-NEXT: [[TMP2_0:%.*]] = add i32 [[TMP0_0]], [[TMP0_1]]
	; CHECK-NEXT: [[TMP2_1:%.*]] = add i32 [[TMP1_0]], [[TMP1_1]]			; CHECK-NEXT: [[TMP2_1:%.*]] = add i32 [[TMP1_0]], [[TMP1_1]]
	; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i32> [[TMP2]], [[TMP4]]			; CHECK-NEXT: [[TMP5:%.*]] = add <2 x i32> [[TMP2]], [[TMP4]]
	; CHECK-NEXT: [[TMP3_0:%.*]] = insertelement <4 x i32> undef, i32 [[TMP2_0]], i32 0			; CHECK-NEXT: [[TMP3_0:%.*]] = insertelement <4 x i32> undef, i32 [[TMP2_0]], i32 0
	; CHECK-NEXT: [[TMP3_1:%.*]] = insertelement <4 x i32> [[TMP3_0]], i32 [[TMP2_1]], i32 1			; CHECK-NEXT: [[TMP3_1:%.*]] = insertelement <4 x i32> [[TMP3_0]], i32 [[TMP2_1]], i32 1
	; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP3_31:%.*]] = shufflevector <4 x i32> [[TMP3_1]], <4 x i32> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; CHECK-NEXT: [[TMP3_31:%.*]] = shufflevector <4 x i32> [[TMP3_1]], <4 x i32> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; CHECK-NEXT: ret <4 x i32> [[TMP3_31]]			; CHECK-NEXT: ret <4 x i32> [[TMP3_31]]
	;			;
	%v0.0 = extractelement <2 x i32> %v0, i32 0			%v0.0 = extractelement <2 x i32> %v0, i32 0
	%v0.1 = extractelement <2 x i32> %v0, i32 1			%v0.1 = extractelement <2 x i32> %v0, i32 1
	%v1.0 = extractelement <2 x i32> %v1, i32 0			%v1.0 = extractelement <2 x i32> %v1, i32 0
	%v1.1 = extractelement <2 x i32> %v1, i32 1			%v1.1 = extractelement <2 x i32> %v1, i32 1
	%tmp0.0 = add i32 %v0.0, %v1.0			%tmp0.0 = add i32 %v0.0, %v1.0
	▲ Show 20 Lines • Show All 82 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AArch64/vectorize-free-extracts-inserts.ll

	Show First 20 Lines • Show All 98 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[V1_LANE_3:%.*]] = extractelement <4 x double> [[V_1]], i32 3			; CHECK-NEXT: [[V1_LANE_3:%.*]] = extractelement <4 x double> [[V_1]], i32 3
	; CHECK-NEXT: [[V_2:%.]] = load <4 x double>, <4 x double> [[PTR_2:%.*]], align 16			; CHECK-NEXT: [[V_2:%.]] = load <4 x double>, <4 x double> [[PTR_2:%.*]], align 16
	; CHECK-NEXT: [[V2_LANE_2:%.*]] = extractelement <4 x double> [[V_2]], i32 2			; CHECK-NEXT: [[V2_LANE_2:%.*]] = extractelement <4 x double> [[V_2]], i32 2
	; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[V1_LANE_2]], i32 0			; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[V1_LANE_2]], i32 0
	; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[V1_LANE_3]], i32 1			; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[V1_LANE_3]], i32 1
	; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[V2_LANE_2]], i32 0			; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[V2_LANE_2]], i32 0
	; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[V2_LANE_2]], i32 1			; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[V2_LANE_2]], i32 1
	; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]			; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
	; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[A_INS_11:%.*]] = shufflevector <4 x double> undef, <4 x double> [[TMP5]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>			; CHECK-NEXT: [[A_INS_11:%.*]] = shufflevector <4 x double> undef, <4 x double> [[TMP5]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
	; CHECK-NEXT: call void @use(double [[V1_LANE_2]])			; CHECK-NEXT: call void @use(double [[V1_LANE_2]])
	; CHECK-NEXT: call void @use(double [[V1_LANE_3]])			; CHECK-NEXT: call void @use(double [[V1_LANE_3]])
	; CHECK-NEXT: store <4 x double> [[A_INS_11]], <4 x double>* [[PTR_1]], align 8			; CHECK-NEXT: store <4 x double> [[A_INS_11]], <4 x double>* [[PTR_1]], align 8
	; CHECK-NEXT: ret void			; CHECK-NEXT: ret void
	;			;
	bb:			bb:
	%v.1 = load <4 x double>, <4 x double>* %ptr.1, align 8			%v.1 = load <4 x double>, <4 x double>* %ptr.1, align 8
	▲ Show 20 Lines • Show All 64 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[V1_LANE_2:%.*]] = extractelement <4 x double> [[V_1]], i32 2			; CHECK-NEXT: [[V1_LANE_2:%.*]] = extractelement <4 x double> [[V_1]], i32 2
	; CHECK-NEXT: [[V_2:%.]] = load <4 x double>, <4 x double> [[PTR_2:%.*]], align 16			; CHECK-NEXT: [[V_2:%.]] = load <4 x double>, <4 x double> [[PTR_2:%.*]], align 16
	; CHECK-NEXT: [[V2_LANE_2:%.*]] = extractelement <4 x double> [[V_2]], i32 2			; CHECK-NEXT: [[V2_LANE_2:%.*]] = extractelement <4 x double> [[V_2]], i32 2
	; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[V1_LANE_1]], i32 0			; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[V1_LANE_1]], i32 0
	; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[V1_LANE_2]], i32 1			; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[V1_LANE_2]], i32 1
	; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[V2_LANE_2]], i32 0			; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[V2_LANE_2]], i32 0
	; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[V2_LANE_2]], i32 1			; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[V2_LANE_2]], i32 1
	; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]			; CHECK-NEXT: [[TMP4:%.*]] = fmul <2 x double> [[TMP1]], [[TMP3]]
	; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[A_INS_11:%.*]] = shufflevector <4 x double> undef, <4 x double> [[TMP5]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>			; CHECK-NEXT: [[A_INS_11:%.*]] = shufflevector <4 x double> undef, <4 x double> [[TMP5]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
	; CHECK-NEXT: call void @use(double [[V1_LANE_1]])			; CHECK-NEXT: call void @use(double [[V1_LANE_1]])
	; CHECK-NEXT: call void @use(double [[V1_LANE_2]])			; CHECK-NEXT: call void @use(double [[V1_LANE_2]])
	; CHECK-NEXT: store <4 x double> [[A_INS_11]], <4 x double>* [[PTR_1]], align 8			; CHECK-NEXT: store <4 x double> [[A_INS_11]], <4 x double>* [[PTR_1]], align 8
	; CHECK-NEXT: ret void			; CHECK-NEXT: ret void
	;			;
	bb:			bb:
	%v.1 = load <4 x double>, <4 x double>* %ptr.1, align 8			%v.1 = load <4 x double>, <4 x double>* %ptr.1, align 8
	Show All 34 Lines
	; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x double> poison, double [[V1_LANE_2]], i32 0			; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x double> poison, double [[V1_LANE_2]], i32 0
	; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x double> [[TMP0]], double [[V1_LANE_3]], i32 1			; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x double> [[TMP0]], double [[V1_LANE_3]], i32 1
	; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double [[V1_LANE_0]], i32 2			; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double [[V1_LANE_0]], i32 2
	; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double [[V1_LANE_1]], i32 3			; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double [[V1_LANE_1]], i32 3
	; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x double> poison, double [[V2_LANE_2]], i32 0			; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x double> poison, double [[V2_LANE_2]], i32 0
	; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x double> [[TMP4]], double [[V2_LANE_0]], i32 1			; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x double> [[TMP4]], double [[V2_LANE_0]], i32 1
	; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x double> [[TMP5]], <4 x double> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>			; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x double> [[TMP5]], <4 x double> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
	; CHECK-NEXT: [[TMP6:%.*]] = fmul <4 x double> [[TMP3]], [[SHUFFLE]]			; CHECK-NEXT: [[TMP6:%.*]] = fmul <4 x double> [[TMP3]], [[SHUFFLE]]
	; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x double> [[TMP6]], <4 x double> undef, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x double> [[TMP6]], <4 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[A_INS_31:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP7]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 4, i32 5, i32 6, i32 7, i32 8>			; CHECK-NEXT: [[A_INS_31:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP7]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 4, i32 5, i32 6, i32 7, i32 8>
	; CHECK-NEXT: call void @use(double [[V1_LANE_0]])			; CHECK-NEXT: call void @use(double [[V1_LANE_0]])
	; CHECK-NEXT: call void @use(double [[V1_LANE_1]])			; CHECK-NEXT: call void @use(double [[V1_LANE_1]])
	; CHECK-NEXT: call void @use(double [[V1_LANE_2]])			; CHECK-NEXT: call void @use(double [[V1_LANE_2]])
	; CHECK-NEXT: call void @use(double [[V1_LANE_3]])			; CHECK-NEXT: call void @use(double [[V1_LANE_3]])
	; CHECK-NEXT: store <9 x double> [[A_INS_31]], <9 x double>* [[PTR_1]], align 8			; CHECK-NEXT: store <9 x double> [[A_INS_31]], <9 x double>* [[PTR_1]], align 8
	; CHECK-NEXT: ret void			; CHECK-NEXT: ret void
	;			;
	▲ Show 20 Lines • Show All 108 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[TMP6:%.*]] = insertelement <8 x double> [[TMP5]], double [[V1_LANE_0]], i32 6			; CHECK-NEXT: [[TMP6:%.*]] = insertelement <8 x double> [[TMP5]], double [[V1_LANE_0]], i32 6
	; CHECK-NEXT: [[TMP7:%.*]] = insertelement <8 x double> [[TMP6]], double [[V1_LANE_1]], i32 7			; CHECK-NEXT: [[TMP7:%.*]] = insertelement <8 x double> [[TMP6]], double [[V1_LANE_1]], i32 7
	; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_0]], i32 0			; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_0]], i32 0
	; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_2]], i32 1			; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_2]], i32 1
	; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_1]], i32 2			; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_1]], i32 2
	; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 0, i32 1, i32 0, i32 1, i32 2>			; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 0, i32 1, i32 0, i32 1, i32 2>
	; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]			; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]
	; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_0]]			; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_0]]
	; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> undef, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>			; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
	; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>			; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
	; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8			; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8
	; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_6]], i32 0			; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_6]], i32 0
	; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_7]], i32 1			; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_7]], i32 1
	; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2			; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2
	; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x double> [[TMP15]], double [[V1_LANE_0]], i32 3			; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x double> [[TMP15]], double [[V1_LANE_0]], i32 3
	; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x double> [[TMP16]], double [[V1_LANE_1]], i32 4			; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x double> [[TMP16]], double [[V1_LANE_1]], i32 4
	; CHECK-NEXT: [[TMP18:%.*]] = insertelement <8 x double> [[TMP17]], double [[V1_LANE_2]], i32 5			; CHECK-NEXT: [[TMP18:%.*]] = insertelement <8 x double> [[TMP17]], double [[V1_LANE_2]], i32 5
	; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x double> [[TMP18]], double [[V1_LANE_3]], i32 6			; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x double> [[TMP18]], double [[V1_LANE_3]], i32 6
	; CHECK-NEXT: [[TMP20:%.*]] = insertelement <8 x double> [[TMP19]], double [[V1_LANE_4]], i32 7			; CHECK-NEXT: [[TMP20:%.*]] = insertelement <8 x double> [[TMP19]], double [[V1_LANE_4]], i32 7
	; CHECK-NEXT: [[TMP21:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_2]], i32 0			; CHECK-NEXT: [[TMP21:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_2]], i32 0
	; CHECK-NEXT: [[TMP22:%.*]] = insertelement <8 x double> [[TMP21]], double [[V2_LANE_1]], i32 1			; CHECK-NEXT: [[TMP22:%.*]] = insertelement <8 x double> [[TMP21]], double [[V2_LANE_1]], i32 1
	; CHECK-NEXT: [[TMP23:%.*]] = insertelement <8 x double> [[TMP22]], double [[V2_LANE_0]], i32 2			; CHECK-NEXT: [[TMP23:%.*]] = insertelement <8 x double> [[TMP22]], double [[V2_LANE_0]], i32 2
	; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <8 x double> [[TMP23]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 0, i32 1, i32 2, i32 0, i32 1>			; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <8 x double> [[TMP23]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 0, i32 1, i32 2, i32 0, i32 1>
	; CHECK-NEXT: [[TMP24:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE]]			; CHECK-NEXT: [[TMP24:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE]]
	; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_5]], [[V2_LANE_0]]			; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_5]], [[V2_LANE_0]]
	; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <8 x double> [[TMP24]], <8 x double> undef, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>			; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <8 x double> [[TMP24]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
	; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP25]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>			; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP25]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
	; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8			; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8
	; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]			; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]
	; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8			; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8
	; CHECK-NEXT: ret void			; CHECK-NEXT: ret void
	;			;
	bb:			bb:
	%v.1 = load <9 x double>, <9 x double>* %ptr.1, align 8			%v.1 = load <9 x double>, <9 x double>* %ptr.1, align 8
	▲ Show 20 Lines • Show All 85 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[TMP6:%.*]] = insertelement <8 x double> [[TMP5]], double [[V1_LANE_1]], i32 6			; CHECK-NEXT: [[TMP6:%.*]] = insertelement <8 x double> [[TMP5]], double [[V1_LANE_1]], i32 6
	; CHECK-NEXT: [[TMP7:%.*]] = insertelement <8 x double> [[TMP6]], double [[V1_LANE_0]], i32 7			; CHECK-NEXT: [[TMP7:%.*]] = insertelement <8 x double> [[TMP6]], double [[V1_LANE_0]], i32 7
	; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_1]], i32 0			; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_1]], i32 0
	; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_0]], i32 1			; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_0]], i32 1
	; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_2]], i32 2			; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_2]], i32 2
	; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>			; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>
	; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]			; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]
	; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_1]]			; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_1]]
	; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> undef, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>			; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
	; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>			; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
	; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8			; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8
	; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_6]], i32 0			; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_6]], i32 0
	; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_7]], i32 1			; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_7]], i32 1
	; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2			; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2
	; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x double> [[TMP15]], double [[V1_LANE_0]], i32 3			; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x double> [[TMP15]], double [[V1_LANE_0]], i32 3
	; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x double> [[TMP16]], double [[V1_LANE_1]], i32 4			; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x double> [[TMP16]], double [[V1_LANE_1]], i32 4
	; CHECK-NEXT: [[TMP18:%.*]] = insertelement <8 x double> [[TMP17]], double [[V1_LANE_2]], i32 5			; CHECK-NEXT: [[TMP18:%.*]] = insertelement <8 x double> [[TMP17]], double [[V1_LANE_2]], i32 5
	; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x double> [[TMP18]], double [[V1_LANE_3]], i32 6			; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x double> [[TMP18]], double [[V1_LANE_3]], i32 6
	; CHECK-NEXT: [[TMP20:%.*]] = insertelement <8 x double> [[TMP19]], double [[V1_LANE_4]], i32 7			; CHECK-NEXT: [[TMP20:%.*]] = insertelement <8 x double> [[TMP19]], double [[V1_LANE_4]], i32 7
	; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>			; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>
	; CHECK-NEXT: [[TMP21:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE]]			; CHECK-NEXT: [[TMP21:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE]]
	; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_5]], [[V2_LANE_0]]			; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_5]], [[V2_LANE_0]]
	; CHECK-NEXT: [[TMP22:%.*]] = shufflevector <8 x double> [[TMP21]], <8 x double> undef, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>			; CHECK-NEXT: [[TMP22:%.*]] = shufflevector <8 x double> [[TMP21]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
	; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP22]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>			; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP22]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
	; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8			; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8
	; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]			; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]
	; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8			; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8
	; CHECK-NEXT: ret void			; CHECK-NEXT: ret void
	;			;
	bb:			bb:
	%v.1 = load <9 x double>, <9 x double>* %ptr.1, align 8			%v.1 = load <9 x double>, <9 x double>* %ptr.1, align 8
	▲ Show 20 Lines • Show All 85 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[TMP6:%.*]] = insertelement <8 x double> [[TMP5]], double [[V1_LANE_1]], i32 6			; CHECK-NEXT: [[TMP6:%.*]] = insertelement <8 x double> [[TMP5]], double [[V1_LANE_1]], i32 6
	; CHECK-NEXT: [[TMP7:%.*]] = insertelement <8 x double> [[TMP6]], double [[V1_LANE_0]], i32 7			; CHECK-NEXT: [[TMP7:%.*]] = insertelement <8 x double> [[TMP6]], double [[V1_LANE_0]], i32 7
	; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_0]], i32 0			; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_0]], i32 0
	; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_2]], i32 1			; CHECK-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP8]], double [[V2_LANE_2]], i32 1
	; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_1]], i32 2			; CHECK-NEXT: [[TMP10:%.*]] = insertelement <8 x double> [[TMP9]], double [[V2_LANE_1]], i32 2
	; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>			; CHECK-NEXT: [[SHUFFLE2:%.*]] = shufflevector <8 x double> [[TMP10]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 1, i32 2, i32 0, i32 1, i32 2>
	; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]			; CHECK-NEXT: [[TMP11:%.*]] = fmul <8 x double> [[TMP7]], [[SHUFFLE2]]
	; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_0]]			; CHECK-NEXT: [[A_LANE_8:%.*]] = fmul double [[V1_LANE_2]], [[V2_LANE_0]]
	; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> undef, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>			; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x double> [[TMP11]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
	; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>			; CHECK-NEXT: [[A_INS_73:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP12]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
	; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8			; CHECK-NEXT: [[A_INS_8:%.*]] = insertelement <9 x double> [[A_INS_73]], double [[A_LANE_8]], i32 8
	; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_7]], i32 0			; CHECK-NEXT: [[TMP13:%.*]] = insertelement <8 x double> poison, double [[V1_LANE_7]], i32 0
	; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_6]], i32 1			; CHECK-NEXT: [[TMP14:%.*]] = insertelement <8 x double> [[TMP13]], double [[V1_LANE_6]], i32 1
	; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2			; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP14]], double [[V1_LANE_8]], i32 2
	; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x double> [[TMP15]], double [[V1_LANE_1]], i32 3			; CHECK-NEXT: [[TMP16:%.*]] = insertelement <8 x double> [[TMP15]], double [[V1_LANE_1]], i32 3
	; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x double> [[TMP16]], double [[V1_LANE_0]], i32 4			; CHECK-NEXT: [[TMP17:%.*]] = insertelement <8 x double> [[TMP16]], double [[V1_LANE_0]], i32 4
	; CHECK-NEXT: [[TMP18:%.*]] = insertelement <8 x double> [[TMP17]], double [[V1_LANE_3]], i32 5			; CHECK-NEXT: [[TMP18:%.*]] = insertelement <8 x double> [[TMP17]], double [[V1_LANE_3]], i32 5
	; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x double> [[TMP18]], double [[V1_LANE_2]], i32 6			; CHECK-NEXT: [[TMP19:%.*]] = insertelement <8 x double> [[TMP18]], double [[V1_LANE_2]], i32 6
	; CHECK-NEXT: [[TMP20:%.*]] = insertelement <8 x double> [[TMP19]], double [[V1_LANE_5]], i32 7			; CHECK-NEXT: [[TMP20:%.*]] = insertelement <8 x double> [[TMP19]], double [[V1_LANE_5]], i32 7
	; CHECK-NEXT: [[TMP21:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_2]], i32 0			; CHECK-NEXT: [[TMP21:%.*]] = insertelement <8 x double> poison, double [[V2_LANE_2]], i32 0
	; CHECK-NEXT: [[TMP22:%.*]] = insertelement <8 x double> [[TMP21]], double [[V2_LANE_1]], i32 1			; CHECK-NEXT: [[TMP22:%.*]] = insertelement <8 x double> [[TMP21]], double [[V2_LANE_1]], i32 1
	; CHECK-NEXT: [[TMP23:%.*]] = insertelement <8 x double> [[TMP22]], double [[V2_LANE_0]], i32 2			; CHECK-NEXT: [[TMP23:%.*]] = insertelement <8 x double> [[TMP22]], double [[V2_LANE_0]], i32 2
	; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <8 x double> [[TMP23]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 0, i32 2, i32 0, i32 1, i32 2>			; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <8 x double> [[TMP23]], <8 x double> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 0, i32 2, i32 0, i32 1, i32 2>
	; CHECK-NEXT: [[TMP24:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE]]			; CHECK-NEXT: [[TMP24:%.*]] = fmul <8 x double> [[TMP20]], [[SHUFFLE]]
	; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_4]], [[V2_LANE_2]]			; CHECK-NEXT: [[B_LANE_8:%.*]] = fmul double [[V1_LANE_4]], [[V2_LANE_2]]
	; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <8 x double> [[TMP24]], <8 x double> undef, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>			; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <8 x double> [[TMP24]], <8 x double> poison, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef>
	; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP25]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>			; CHECK-NEXT: [[B_INS_71:%.*]] = shufflevector <9 x double> undef, <9 x double> [[TMP25]], <9 x i32> <i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 8>
	; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8			; CHECK-NEXT: [[B_INS_8:%.*]] = insertelement <9 x double> [[B_INS_71]], double [[B_LANE_8]], i32 8
	; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]			; CHECK-NEXT: [[RES:%.*]] = fsub <9 x double> [[A_INS_8]], [[B_INS_8]]
	; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8			; CHECK-NEXT: store <9 x double> [[RES]], <9 x double>* [[PTR_1]], align 8
	; CHECK-NEXT: ret void			; CHECK-NEXT: ret void
	;			;
	bb:			bb:
	%v.1 = load <9 x double>, <9 x double>* %ptr.1, align 8			%v.1 = load <9 x double>, <9 x double>* %ptr.1, align 8
	▲ Show 20 Lines • Show All 59 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AMDGPU/add_sub_sat-inseltpoison.ll

	Show First 20 Lines • Show All 242 Lines • ▼ Show 20 Lines
	; GFX8-LABEL: @uadd_sat_v3i16(			; GFX8-LABEL: @uadd_sat_v3i16(
	; GFX8-NEXT: bb:			; GFX8-NEXT: bb:
	; GFX8-NEXT: [[ARG0_2:%.]] = extractelement <3 x i16> [[ARG0:%.]], i64 2			; GFX8-NEXT: [[ARG0_2:%.]] = extractelement <3 x i16> [[ARG0:%.]], i64 2
	; GFX8-NEXT: [[ARG1_2:%.]] = extractelement <3 x i16> [[ARG1:%.]], i64 2			; GFX8-NEXT: [[ARG1_2:%.]] = extractelement <3 x i16> [[ARG1:%.]], i64 2
	; GFX8-NEXT: [[TMP0:%.*]] = shufflevector <3 x i16> [[ARG0]], <3 x i16> undef, <2 x i32> <i32 0, i32 1>			; GFX8-NEXT: [[TMP0:%.*]] = shufflevector <3 x i16> [[ARG0]], <3 x i16> undef, <2 x i32> <i32 0, i32 1>
	; GFX8-NEXT: [[TMP1:%.*]] = shufflevector <3 x i16> [[ARG1]], <3 x i16> undef, <2 x i32> <i32 0, i32 1>			; GFX8-NEXT: [[TMP1:%.*]] = shufflevector <3 x i16> [[ARG1]], <3 x i16> undef, <2 x i32> <i32 0, i32 1>
	; GFX8-NEXT: [[TMP2:%.*]] = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> [[TMP0]], <2 x i16> [[TMP1]])			; GFX8-NEXT: [[TMP2:%.*]] = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> [[TMP0]], <2 x i16> [[TMP1]])
	; GFX8-NEXT: [[ADD_2:%.*]] = call i16 @llvm.uadd.sat.i16(i16 [[ARG0_2]], i16 [[ARG1_2]])			; GFX8-NEXT: [[ADD_2:%.*]] = call i16 @llvm.uadd.sat.i16(i16 [[ARG0_2]], i16 [[ARG1_2]])
	; GFX8-NEXT: [[INS_11:%.*]] = shufflevector <2 x i16> [[TMP2]], <2 x i16> undef, <3 x i32> <i32 0, i32 1, i32 undef>			; GFX8-NEXT: [[INS_11:%.*]] = shufflevector <2 x i16> [[TMP2]], <2 x i16> poison, <3 x i32> <i32 0, i32 1, i32 undef>
	; GFX8-NEXT: [[INS_2:%.*]] = insertelement <3 x i16> [[INS_11]], i16 [[ADD_2]], i64 2			; GFX8-NEXT: [[INS_2:%.*]] = insertelement <3 x i16> [[INS_11]], i16 [[ADD_2]], i64 2
	; GFX8-NEXT: ret <3 x i16> [[INS_2]]			; GFX8-NEXT: ret <3 x i16> [[INS_2]]
	;			;
	bb:			bb:
	%arg0.0 = extractelement <3 x i16> %arg0, i64 0			%arg0.0 = extractelement <3 x i16> %arg0, i64 0
	%arg0.1 = extractelement <3 x i16> %arg0, i64 1			%arg0.1 = extractelement <3 x i16> %arg0, i64 1
	%arg0.2 = extractelement <3 x i16> %arg0, i64 2			%arg0.2 = extractelement <3 x i16> %arg0, i64 2
	%arg1.0 = extractelement <3 x i16> %arg1, i64 0			%arg1.0 = extractelement <3 x i16> %arg1, i64 0
	▲ Show 20 Lines • Show All 74 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AMDGPU/add_sub_sat.ll

	Show First 20 Lines • Show All 242 Lines • ▼ Show 20 Lines
	; GFX8-LABEL: @uadd_sat_v3i16(			; GFX8-LABEL: @uadd_sat_v3i16(
	; GFX8-NEXT: bb:			; GFX8-NEXT: bb:
	; GFX8-NEXT: [[ARG0_2:%.]] = extractelement <3 x i16> [[ARG0:%.]], i64 2			; GFX8-NEXT: [[ARG0_2:%.]] = extractelement <3 x i16> [[ARG0:%.]], i64 2
	; GFX8-NEXT: [[ARG1_2:%.]] = extractelement <3 x i16> [[ARG1:%.]], i64 2			; GFX8-NEXT: [[ARG1_2:%.]] = extractelement <3 x i16> [[ARG1:%.]], i64 2
	; GFX8-NEXT: [[TMP0:%.*]] = shufflevector <3 x i16> [[ARG0]], <3 x i16> undef, <2 x i32> <i32 0, i32 1>			; GFX8-NEXT: [[TMP0:%.*]] = shufflevector <3 x i16> [[ARG0]], <3 x i16> undef, <2 x i32> <i32 0, i32 1>
	; GFX8-NEXT: [[TMP1:%.*]] = shufflevector <3 x i16> [[ARG1]], <3 x i16> undef, <2 x i32> <i32 0, i32 1>			; GFX8-NEXT: [[TMP1:%.*]] = shufflevector <3 x i16> [[ARG1]], <3 x i16> undef, <2 x i32> <i32 0, i32 1>
	; GFX8-NEXT: [[TMP2:%.*]] = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> [[TMP0]], <2 x i16> [[TMP1]])			; GFX8-NEXT: [[TMP2:%.*]] = call <2 x i16> @llvm.uadd.sat.v2i16(<2 x i16> [[TMP0]], <2 x i16> [[TMP1]])
	; GFX8-NEXT: [[ADD_2:%.*]] = call i16 @llvm.uadd.sat.i16(i16 [[ARG0_2]], i16 [[ARG1_2]])			; GFX8-NEXT: [[ADD_2:%.*]] = call i16 @llvm.uadd.sat.i16(i16 [[ARG0_2]], i16 [[ARG1_2]])
	; GFX8-NEXT: [[INS_11:%.*]] = shufflevector <2 x i16> [[TMP2]], <2 x i16> undef, <3 x i32> <i32 0, i32 1, i32 undef>			; GFX8-NEXT: [[INS_11:%.*]] = shufflevector <2 x i16> [[TMP2]], <2 x i16> poison, <3 x i32> <i32 0, i32 1, i32 undef>
	; GFX8-NEXT: [[INS_2:%.*]] = insertelement <3 x i16> [[INS_11]], i16 [[ADD_2]], i64 2			; GFX8-NEXT: [[INS_2:%.*]] = insertelement <3 x i16> [[INS_11]], i16 [[ADD_2]], i64 2
	; GFX8-NEXT: ret <3 x i16> [[INS_2]]			; GFX8-NEXT: ret <3 x i16> [[INS_2]]
	;			;
	bb:			bb:
	%arg0.0 = extractelement <3 x i16> %arg0, i64 0			%arg0.0 = extractelement <3 x i16> %arg0, i64 0
	%arg0.1 = extractelement <3 x i16> %arg0, i64 1			%arg0.1 = extractelement <3 x i16> %arg0, i64 1
	%arg0.2 = extractelement <3 x i16> %arg0, i64 2			%arg0.2 = extractelement <3 x i16> %arg0, i64 2
	%arg1.0 = extractelement <3 x i16> %arg1, i64 0			%arg1.0 = extractelement <3 x i16> %arg1, i64 0
	▲ Show 20 Lines • Show All 74 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/PR35865-inseltpoison.ll

	; NOTE: Assertions have been autogenerated by utils/update_test_checks.py			; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
	; RUN: opt -slp-vectorizer < %s -S -o - -mtriple=x86_64-apple-macosx10.10.0 -mcpu=core2 \| FileCheck %s			; RUN: opt -slp-vectorizer < %s -S -o - -mtriple=x86_64-apple-macosx10.10.0 -mcpu=core2 \| FileCheck %s

	define void @_Z10fooConvertPDv4_xS0_S0_PKS_() {			define void @_Z10fooConvertPDv4_xS0_S0_PKS_() {
	; CHECK-LABEL: @_Z10fooConvertPDv4_xS0_S0_PKS_(			; CHECK-LABEL: @_Z10fooConvertPDv4_xS0_S0_PKS_(
	; CHECK-NEXT: entry:			; CHECK-NEXT: entry:
	; CHECK-NEXT: [[TMP0:%.*]] = extractelement <16 x half> undef, i32 4			; CHECK-NEXT: [[TMP0:%.*]] = extractelement <16 x half> undef, i32 4
	; CHECK-NEXT: [[TMP1:%.*]] = extractelement <16 x half> undef, i32 5			; CHECK-NEXT: [[TMP1:%.*]] = extractelement <16 x half> undef, i32 5
	; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x half> poison, half [[TMP0]], i32 0			; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x half> poison, half [[TMP0]], i32 0
	; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x half> [[TMP2]], half [[TMP1]], i32 1			; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x half> [[TMP2]], half [[TMP1]], i32 1
	; CHECK-NEXT: [[TMP4:%.*]] = fpext <2 x half> [[TMP3]] to <2 x float>			; CHECK-NEXT: [[TMP4:%.*]] = fpext <2 x half> [[TMP3]] to <2 x float>
	; CHECK-NEXT: [[TMP5:%.*]] = bitcast <2 x float> [[TMP4]] to <2 x i32>			; CHECK-NEXT: [[TMP5:%.*]] = bitcast <2 x float> [[TMP4]] to <2 x i32>
	; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[VECINS_I_5_I1:%.*]] = shufflevector <8 x i32> poison, <8 x i32> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>			; CHECK-NEXT: [[VECINS_I_5_I1:%.*]] = shufflevector <8 x i32> poison, <8 x i32> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
	; CHECK-NEXT: ret void			; CHECK-NEXT: ret void
	;			;
	entry:			entry:
	%0 = extractelement <16 x half> undef, i32 4			%0 = extractelement <16 x half> undef, i32 4
	%conv.i.4.i = fpext half %0 to float			%conv.i.4.i = fpext half %0 to float
	%1 = bitcast float %conv.i.4.i to i32			%1 = bitcast float %conv.i.4.i to i32
	%vecins.i.4.i = insertelement <8 x i32> poison, i32 %1, i32 4			%vecins.i.4.i = insertelement <8 x i32> poison, i32 %1, i32 4
	%2 = extractelement <16 x half> undef, i32 5			%2 = extractelement <16 x half> undef, i32 5
	%conv.i.5.i = fpext half %2 to float			%conv.i.5.i = fpext half %2 to float
	%3 = bitcast float %conv.i.5.i to i32			%3 = bitcast float %conv.i.5.i to i32
	%vecins.i.5.i = insertelement <8 x i32> %vecins.i.4.i, i32 %3, i32 5			%vecins.i.5.i = insertelement <8 x i32> %vecins.i.4.i, i32 %3, i32 5
	ret void			ret void
	}			}

llvm/test/Transforms/SLPVectorizer/X86/PR35865.ll

	; NOTE: Assertions have been autogenerated by utils/update_test_checks.py			; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
	; RUN: opt -slp-vectorizer < %s -S -o - -mtriple=x86_64-apple-macosx10.10.0 -mcpu=core2 \| FileCheck %s			; RUN: opt -slp-vectorizer < %s -S -o - -mtriple=x86_64-apple-macosx10.10.0 -mcpu=core2 \| FileCheck %s

	define void @_Z10fooConvertPDv4_xS0_S0_PKS_() {			define void @_Z10fooConvertPDv4_xS0_S0_PKS_() {
	; CHECK-LABEL: @_Z10fooConvertPDv4_xS0_S0_PKS_(			; CHECK-LABEL: @_Z10fooConvertPDv4_xS0_S0_PKS_(
	; CHECK-NEXT: entry:			; CHECK-NEXT: entry:
	; CHECK-NEXT: [[TMP0:%.*]] = extractelement <16 x half> undef, i32 4			; CHECK-NEXT: [[TMP0:%.*]] = extractelement <16 x half> undef, i32 4
	; CHECK-NEXT: [[TMP1:%.*]] = extractelement <16 x half> undef, i32 5			; CHECK-NEXT: [[TMP1:%.*]] = extractelement <16 x half> undef, i32 5
	; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x half> poison, half [[TMP0]], i32 0			; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x half> poison, half [[TMP0]], i32 0
	; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x half> [[TMP2]], half [[TMP1]], i32 1			; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x half> [[TMP2]], half [[TMP1]], i32 1
	; CHECK-NEXT: [[TMP4:%.*]] = fpext <2 x half> [[TMP3]] to <2 x float>			; CHECK-NEXT: [[TMP4:%.*]] = fpext <2 x half> [[TMP3]] to <2 x float>
	; CHECK-NEXT: [[TMP5:%.*]] = bitcast <2 x float> [[TMP4]] to <2 x i32>			; CHECK-NEXT: [[TMP5:%.*]] = bitcast <2 x float> [[TMP4]] to <2 x i32>
	; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[VECINS_I_5_I1:%.*]] = shufflevector <8 x i32> undef, <8 x i32> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>			; CHECK-NEXT: [[VECINS_I_5_I1:%.*]] = shufflevector <8 x i32> undef, <8 x i32> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
	; CHECK-NEXT: ret void			; CHECK-NEXT: ret void
	;			;
	entry:			entry:
	%0 = extractelement <16 x half> undef, i32 4			%0 = extractelement <16 x half> undef, i32 4
	%conv.i.4.i = fpext half %0 to float			%conv.i.4.i = fpext half %0 to float
	%1 = bitcast float %conv.i.4.i to i32			%1 = bitcast float %conv.i.4.i to i32
	%vecins.i.4.i = insertelement <8 x i32> undef, i32 %1, i32 4			%vecins.i.4.i = insertelement <8 x i32> undef, i32 %1, i32 4
	%2 = extractelement <16 x half> undef, i32 5			%2 = extractelement <16 x half> undef, i32 5
	%conv.i.5.i = fpext half %2 to float			%conv.i.5.i = fpext half %2 to float
	%3 = bitcast float %conv.i.5.i to i32			%3 = bitcast float %conv.i.5.i to i32
	%vecins.i.5.i = insertelement <8 x i32> %vecins.i.4.i, i32 %3, i32 5			%vecins.i.5.i = insertelement <8 x i32> %vecins.i.4.i, i32 %3, i32 5
	ret void			ret void
	}			}

llvm/test/Transforms/SLPVectorizer/X86/alternate-calls-inseltpoison.ll

	Show All 18 Lines
	; SSE-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>			; SSE-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>
	; SSE-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP1]])			; SSE-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP1]])
	; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>			; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>
	; SSE-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP3]])			; SSE-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP3]])
	; SSE-NEXT: [[R0:%.*]] = insertelement <8 x float> poison, float [[AB0]], i32 0			; SSE-NEXT: [[R0:%.*]] = insertelement <8 x float> poison, float [[AB0]], i32 0
	; SSE-NEXT: [[R1:%.*]] = insertelement <8 x float> [[R0]], float [[AB1]], i32 1			; SSE-NEXT: [[R1:%.*]] = insertelement <8 x float> [[R0]], float [[AB1]], i32 1
	; SSE-NEXT: [[R2:%.*]] = insertelement <8 x float> [[R1]], float [[AB2]], i32 2			; SSE-NEXT: [[R2:%.*]] = insertelement <8 x float> [[R1]], float [[AB2]], i32 2
	; SSE-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R2]], float [[AB3]], i32 3			; SSE-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R2]], float [[AB3]], i32 3
	; SSE-NEXT: [[TMP5:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SSE-NEXT: [[TMP5:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SSE-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>			; SSE-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>
	; SSE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SSE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SSE-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; SSE-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; SSE-NEXT: ret <8 x float> [[R71]]			; SSE-NEXT: ret <8 x float> [[R71]]
	;			;
	; SLM-LABEL: @ceil_floor(			; SLM-LABEL: @ceil_floor(
	; SLM-NEXT: [[A0:%.]] = extractelement <8 x float> [[A:%.]], i32 0			; SLM-NEXT: [[A0:%.]] = extractelement <8 x float> [[A:%.]], i32 0
	; SLM-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i32 3			; SLM-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i32 3
	; SLM-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])			; SLM-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])
	; SLM-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 1, i32 2>			; SLM-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 1, i32 2>
	; SLM-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP1]])			; SLM-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP1]])
	; SLM-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])			; SLM-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])
	; SLM-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>			; SLM-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>
	; SLM-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP3]])			; SLM-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP3]])
	; SLM-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>			; SLM-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>
	; SLM-NEXT: [[TMP6:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP5]])			; SLM-NEXT: [[TMP6:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP5]])
	; SLM-NEXT: [[R0:%.*]] = insertelement <8 x float> poison, float [[AB0]], i32 0			; SLM-NEXT: [[R0:%.*]] = insertelement <8 x float> poison, float [[AB0]], i32 0
	; SLM-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R23:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[R23:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R23]], float [[AB3]], i32 3			; SLM-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R23]], float [[AB3]], i32 3
	; SLM-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>			; SLM-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>
	; SLM-NEXT: [[TMP9:%.*]] = shufflevector <2 x float> [[TMP6]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP9:%.*]] = shufflevector <2 x float> [[TMP6]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; SLM-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; SLM-NEXT: ret <8 x float> [[R71]]			; SLM-NEXT: ret <8 x float> [[R71]]
	;			;
	; AVX-LABEL: @ceil_floor(			; AVX-LABEL: @ceil_floor(
	; AVX-NEXT: [[A0:%.]] = extractelement <8 x float> [[A:%.]], i32 0			; AVX-NEXT: [[A0:%.]] = extractelement <8 x float> [[A:%.]], i32 0
	; AVX-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i32 3			; AVX-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i32 3
	; AVX-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])			; AVX-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])
	; AVX-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 1, i32 2>			; AVX-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 1, i32 2>
	; AVX-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP1]])			; AVX-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP1]])
	; AVX-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])			; AVX-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])
	; AVX-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>			; AVX-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>
	; AVX-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP3]])			; AVX-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP3]])
	; AVX-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>			; AVX-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>
	; AVX-NEXT: [[TMP6:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP5]])			; AVX-NEXT: [[TMP6:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP5]])
	; AVX-NEXT: [[R0:%.*]] = insertelement <8 x float> poison, float [[AB0]], i32 0			; AVX-NEXT: [[R0:%.*]] = insertelement <8 x float> poison, float [[AB0]], i32 0
	; AVX-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[R23:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[R23:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R23]], float [[AB3]], i32 3			; AVX-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R23]], float [[AB3]], i32 3
	; AVX-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>			; AVX-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP9:%.*]] = shufflevector <2 x float> [[TMP6]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP9:%.*]] = shufflevector <2 x float> [[TMP6]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; AVX-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; AVX-NEXT: ret <8 x float> [[R71]]			; AVX-NEXT: ret <8 x float> [[R71]]
	;			;
	%a0 = extractelement <8 x float> %a, i32 0			%a0 = extractelement <8 x float> %a, i32 0
	%a1 = extractelement <8 x float> %a, i32 1			%a1 = extractelement <8 x float> %a, i32 1
	%a2 = extractelement <8 x float> %a, i32 2			%a2 = extractelement <8 x float> %a, i32 2
	%a3 = extractelement <8 x float> %a, i32 3			%a3 = extractelement <8 x float> %a, i32 3
	%a4 = extractelement <8 x float> %a, i32 4			%a4 = extractelement <8 x float> %a, i32 4
	Show All 24 Lines

llvm/test/Transforms/SLPVectorizer/X86/alternate-calls.ll

	Show All 18 Lines
	; SSE-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>			; SSE-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>
	; SSE-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP1]])			; SSE-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP1]])
	; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>			; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>
	; SSE-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP3]])			; SSE-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP3]])
	; SSE-NEXT: [[R0:%.*]] = insertelement <8 x float> undef, float [[AB0]], i32 0			; SSE-NEXT: [[R0:%.*]] = insertelement <8 x float> undef, float [[AB0]], i32 0
	; SSE-NEXT: [[R1:%.*]] = insertelement <8 x float> [[R0]], float [[AB1]], i32 1			; SSE-NEXT: [[R1:%.*]] = insertelement <8 x float> [[R0]], float [[AB1]], i32 1
	; SSE-NEXT: [[R2:%.*]] = insertelement <8 x float> [[R1]], float [[AB2]], i32 2			; SSE-NEXT: [[R2:%.*]] = insertelement <8 x float> [[R1]], float [[AB2]], i32 2
	; SSE-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R2]], float [[AB3]], i32 3			; SSE-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R2]], float [[AB3]], i32 3
	; SSE-NEXT: [[TMP5:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SSE-NEXT: [[TMP5:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SSE-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>			; SSE-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>
	; SSE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SSE-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SSE-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; SSE-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; SSE-NEXT: ret <8 x float> [[R71]]			; SSE-NEXT: ret <8 x float> [[R71]]
	;			;
	; SLM-LABEL: @ceil_floor(			; SLM-LABEL: @ceil_floor(
	; SLM-NEXT: [[A0:%.]] = extractelement <8 x float> [[A:%.]], i32 0			; SLM-NEXT: [[A0:%.]] = extractelement <8 x float> [[A:%.]], i32 0
	; SLM-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i32 3			; SLM-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i32 3
	; SLM-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])			; SLM-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])
	; SLM-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 1, i32 2>			; SLM-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 1, i32 2>
	; SLM-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP1]])			; SLM-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP1]])
	; SLM-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])			; SLM-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])
	; SLM-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>			; SLM-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>
	; SLM-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP3]])			; SLM-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP3]])
	; SLM-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>			; SLM-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>
	; SLM-NEXT: [[TMP6:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP5]])			; SLM-NEXT: [[TMP6:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP5]])
	; SLM-NEXT: [[R0:%.*]] = insertelement <8 x float> undef, float [[AB0]], i32 0			; SLM-NEXT: [[R0:%.*]] = insertelement <8 x float> undef, float [[AB0]], i32 0
	; SLM-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R23:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[R23:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R23]], float [[AB3]], i32 3			; SLM-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R23]], float [[AB3]], i32 3
	; SLM-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>			; SLM-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>
	; SLM-NEXT: [[TMP9:%.*]] = shufflevector <2 x float> [[TMP6]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP9:%.*]] = shufflevector <2 x float> [[TMP6]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; SLM-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; SLM-NEXT: ret <8 x float> [[R71]]			; SLM-NEXT: ret <8 x float> [[R71]]
	;			;
	; AVX-LABEL: @ceil_floor(			; AVX-LABEL: @ceil_floor(
	; AVX-NEXT: [[A0:%.]] = extractelement <8 x float> [[A:%.]], i32 0			; AVX-NEXT: [[A0:%.]] = extractelement <8 x float> [[A:%.]], i32 0
	; AVX-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i32 3			; AVX-NEXT: [[A3:%.*]] = extractelement <8 x float> [[A]], i32 3
	; AVX-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])			; AVX-NEXT: [[AB0:%.*]] = call float @llvm.ceil.f32(float [[A0]])
	; AVX-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 1, i32 2>			; AVX-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 1, i32 2>
	; AVX-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP1]])			; AVX-NEXT: [[TMP2:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP1]])
	; AVX-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])			; AVX-NEXT: [[AB3:%.*]] = call float @llvm.ceil.f32(float [[A3]])
	; AVX-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>			; AVX-NEXT: [[TMP3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 4, i32 5>
	; AVX-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP3]])			; AVX-NEXT: [[TMP4:%.*]] = call <2 x float> @llvm.ceil.v2f32(<2 x float> [[TMP3]])
	; AVX-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>			; AVX-NEXT: [[TMP5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <2 x i32> <i32 6, i32 7>
	; AVX-NEXT: [[TMP6:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP5]])			; AVX-NEXT: [[TMP6:%.*]] = call <2 x float> @llvm.floor.v2f32(<2 x float> [[TMP5]])
	; AVX-NEXT: [[R0:%.*]] = insertelement <8 x float> undef, float [[AB0]], i32 0			; AVX-NEXT: [[R0:%.*]] = insertelement <8 x float> undef, float [[AB0]], i32 0
	; AVX-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP7:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[R23:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[R23:%.*]] = shufflevector <8 x float> [[R0]], <8 x float> [[TMP7]], <8 x i32> <i32 0, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R23]], float [[AB3]], i32 3			; AVX-NEXT: [[R3:%.*]] = insertelement <8 x float> [[R23]], float [[AB3]], i32 3
	; AVX-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>			; AVX-NEXT: [[R52:%.*]] = shufflevector <8 x float> [[R3]], <8 x float> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP9:%.*]] = shufflevector <2 x float> [[TMP6]], <2 x float> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP9:%.*]] = shufflevector <2 x float> [[TMP6]], <2 x float> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; AVX-NEXT: [[R71:%.*]] = shufflevector <8 x float> [[R52]], <8 x float> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; AVX-NEXT: ret <8 x float> [[R71]]			; AVX-NEXT: ret <8 x float> [[R71]]
	;			;
	%a0 = extractelement <8 x float> %a, i32 0			%a0 = extractelement <8 x float> %a, i32 0
	%a1 = extractelement <8 x float> %a, i32 1			%a1 = extractelement <8 x float> %a, i32 1
	%a2 = extractelement <8 x float> %a, i32 2			%a2 = extractelement <8 x float> %a, i32 2
	%a3 = extractelement <8 x float> %a, i32 3			%a3 = extractelement <8 x float> %a, i32 3
	%a4 = extractelement <8 x float> %a, i32 4			%a4 = extractelement <8 x float> %a, i32 4
	Show All 24 Lines

llvm/test/Transforms/SLPVectorizer/X86/alternate-cast-inseltpoison.ll

	Show First 20 Lines • Show All 165 Lines • ▼ Show 20 Lines
	; SSE-NEXT: [[B1:%.*]] = extractelement <8 x i16> [[B]], i32 1			; SSE-NEXT: [[B1:%.*]] = extractelement <8 x i16> [[B]], i32 1
	; SSE-NEXT: [[B2:%.*]] = extractelement <8 x i16> [[B]], i32 2			; SSE-NEXT: [[B2:%.*]] = extractelement <8 x i16> [[B]], i32 2
	; SSE-NEXT: [[B3:%.*]] = extractelement <8 x i16> [[B]], i32 3			; SSE-NEXT: [[B3:%.*]] = extractelement <8 x i16> [[B]], i32 3
	; SSE-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>			; SSE-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>
	; SSE-NEXT: [[AB4:%.*]] = sitofp i16 [[B0]] to float			; SSE-NEXT: [[AB4:%.*]] = sitofp i16 [[B0]] to float
	; SSE-NEXT: [[AB5:%.*]] = sitofp i16 [[B1]] to float			; SSE-NEXT: [[AB5:%.*]] = sitofp i16 [[B1]] to float
	; SSE-NEXT: [[AB6:%.*]] = sitofp i16 [[B2]] to float			; SSE-NEXT: [[AB6:%.*]] = sitofp i16 [[B2]] to float
	; SSE-NEXT: [[AB7:%.*]] = sitofp i16 [[B3]] to float			; SSE-NEXT: [[AB7:%.*]] = sitofp i16 [[B3]] to float
	; SSE-NEXT: [[R31:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>			; SSE-NEXT: [[R31:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
	; SSE-NEXT: [[R4:%.*]] = insertelement <8 x float> [[R31]], float [[AB4]], i32 4			; SSE-NEXT: [[R4:%.*]] = insertelement <8 x float> [[R31]], float [[AB4]], i32 4
	; SSE-NEXT: [[R5:%.*]] = insertelement <8 x float> [[R4]], float [[AB5]], i32 5			; SSE-NEXT: [[R5:%.*]] = insertelement <8 x float> [[R4]], float [[AB5]], i32 5
	; SSE-NEXT: [[R6:%.*]] = insertelement <8 x float> [[R5]], float [[AB6]], i32 6			; SSE-NEXT: [[R6:%.*]] = insertelement <8 x float> [[R5]], float [[AB6]], i32 6
	; SSE-NEXT: [[R7:%.*]] = insertelement <8 x float> [[R6]], float [[AB7]], i32 7			; SSE-NEXT: [[R7:%.*]] = insertelement <8 x float> [[R6]], float [[AB7]], i32 7
	; SSE-NEXT: ret <8 x float> [[R7]]			; SSE-NEXT: ret <8 x float> [[R7]]
	;			;
	; SLM-LABEL: @sitofp_4i32_8i16(			; SLM-LABEL: @sitofp_4i32_8i16(
	; SLM-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>			; SLM-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>
	▲ Show 20 Lines • Show All 52 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[C1:%.*]] = extractelement <16 x i8> [[C]], i32 1			; CHECK-NEXT: [[C1:%.*]] = extractelement <16 x i8> [[C]], i32 1
	; CHECK-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>			; CHECK-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>
	; CHECK-NEXT: [[TMP2:%.*]] = uitofp <4 x i32> [[A]] to <4 x float>			; CHECK-NEXT: [[TMP2:%.*]] = uitofp <4 x i32> [[A]] to <4 x float>
	; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> [[TMP2]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>			; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> [[TMP2]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
	; CHECK-NEXT: [[AB4:%.*]] = sitofp i16 [[B0]] to float			; CHECK-NEXT: [[AB4:%.*]] = sitofp i16 [[B0]] to float
	; CHECK-NEXT: [[AB5:%.*]] = uitofp i16 [[B1]] to float			; CHECK-NEXT: [[AB5:%.*]] = uitofp i16 [[B1]] to float
	; CHECK-NEXT: [[AB6:%.*]] = sitofp i8 [[C0]] to float			; CHECK-NEXT: [[AB6:%.*]] = sitofp i8 [[C0]] to float
	; CHECK-NEXT: [[AB7:%.*]] = uitofp i8 [[C1]] to float			; CHECK-NEXT: [[AB7:%.*]] = uitofp i8 [[C1]] to float
	; CHECK-NEXT: [[R31:%.*]] = shufflevector <4 x float> [[TMP3]], <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[R31:%.*]] = shufflevector <4 x float> [[TMP3]], <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[R4:%.*]] = insertelement <8 x float> [[R31]], float [[AB4]], i32 4			; CHECK-NEXT: [[R4:%.*]] = insertelement <8 x float> [[R31]], float [[AB4]], i32 4
	; CHECK-NEXT: [[R5:%.*]] = insertelement <8 x float> [[R4]], float [[AB5]], i32 5			; CHECK-NEXT: [[R5:%.*]] = insertelement <8 x float> [[R4]], float [[AB5]], i32 5
	; CHECK-NEXT: [[R6:%.*]] = insertelement <8 x float> [[R5]], float [[AB6]], i32 6			; CHECK-NEXT: [[R6:%.*]] = insertelement <8 x float> [[R5]], float [[AB6]], i32 6
	; CHECK-NEXT: [[R7:%.*]] = insertelement <8 x float> [[R6]], float [[AB7]], i32 7			; CHECK-NEXT: [[R7:%.*]] = insertelement <8 x float> [[R6]], float [[AB7]], i32 7
	; CHECK-NEXT: ret <8 x float> [[R7]]			; CHECK-NEXT: ret <8 x float> [[R7]]
	;			;
	%a0 = extractelement <4 x i32> %a, i32 0			%a0 = extractelement <4 x i32> %a, i32 0
	%a1 = extractelement <4 x i32> %a, i32 1			%a1 = extractelement <4 x i32> %a, i32 1
	Show All 24 Lines

llvm/test/Transforms/SLPVectorizer/X86/alternate-cast.ll

	Show First 20 Lines • Show All 165 Lines • ▼ Show 20 Lines
	; SSE-NEXT: [[B1:%.*]] = extractelement <8 x i16> [[B]], i32 1			; SSE-NEXT: [[B1:%.*]] = extractelement <8 x i16> [[B]], i32 1
	; SSE-NEXT: [[B2:%.*]] = extractelement <8 x i16> [[B]], i32 2			; SSE-NEXT: [[B2:%.*]] = extractelement <8 x i16> [[B]], i32 2
	; SSE-NEXT: [[B3:%.*]] = extractelement <8 x i16> [[B]], i32 3			; SSE-NEXT: [[B3:%.*]] = extractelement <8 x i16> [[B]], i32 3
	; SSE-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>			; SSE-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>
	; SSE-NEXT: [[AB4:%.*]] = sitofp i16 [[B0]] to float			; SSE-NEXT: [[AB4:%.*]] = sitofp i16 [[B0]] to float
	; SSE-NEXT: [[AB5:%.*]] = sitofp i16 [[B1]] to float			; SSE-NEXT: [[AB5:%.*]] = sitofp i16 [[B1]] to float
	; SSE-NEXT: [[AB6:%.*]] = sitofp i16 [[B2]] to float			; SSE-NEXT: [[AB6:%.*]] = sitofp i16 [[B2]] to float
	; SSE-NEXT: [[AB7:%.*]] = sitofp i16 [[B3]] to float			; SSE-NEXT: [[AB7:%.*]] = sitofp i16 [[B3]] to float
	; SSE-NEXT: [[R31:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>			; SSE-NEXT: [[R31:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
	; SSE-NEXT: [[R4:%.*]] = insertelement <8 x float> [[R31]], float [[AB4]], i32 4			; SSE-NEXT: [[R4:%.*]] = insertelement <8 x float> [[R31]], float [[AB4]], i32 4
	; SSE-NEXT: [[R5:%.*]] = insertelement <8 x float> [[R4]], float [[AB5]], i32 5			; SSE-NEXT: [[R5:%.*]] = insertelement <8 x float> [[R4]], float [[AB5]], i32 5
	; SSE-NEXT: [[R6:%.*]] = insertelement <8 x float> [[R5]], float [[AB6]], i32 6			; SSE-NEXT: [[R6:%.*]] = insertelement <8 x float> [[R5]], float [[AB6]], i32 6
	; SSE-NEXT: [[R7:%.*]] = insertelement <8 x float> [[R6]], float [[AB7]], i32 7			; SSE-NEXT: [[R7:%.*]] = insertelement <8 x float> [[R6]], float [[AB7]], i32 7
	; SSE-NEXT: ret <8 x float> [[R7]]			; SSE-NEXT: ret <8 x float> [[R7]]
	;			;
	; SLM-LABEL: @sitofp_4i32_8i16(			; SLM-LABEL: @sitofp_4i32_8i16(
	; SLM-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>			; SLM-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>
	▲ Show 20 Lines • Show All 52 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[C1:%.*]] = extractelement <16 x i8> [[C]], i32 1			; CHECK-NEXT: [[C1:%.*]] = extractelement <16 x i8> [[C]], i32 1
	; CHECK-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>			; CHECK-NEXT: [[TMP1:%.]] = sitofp <4 x i32> [[A:%.]] to <4 x float>
	; CHECK-NEXT: [[TMP2:%.*]] = uitofp <4 x i32> [[A]] to <4 x float>			; CHECK-NEXT: [[TMP2:%.*]] = uitofp <4 x i32> [[A]] to <4 x float>
	; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> [[TMP2]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>			; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> [[TMP2]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
	; CHECK-NEXT: [[AB4:%.*]] = sitofp i16 [[B0]] to float			; CHECK-NEXT: [[AB4:%.*]] = sitofp i16 [[B0]] to float
	; CHECK-NEXT: [[AB5:%.*]] = uitofp i16 [[B1]] to float			; CHECK-NEXT: [[AB5:%.*]] = uitofp i16 [[B1]] to float
	; CHECK-NEXT: [[AB6:%.*]] = sitofp i8 [[C0]] to float			; CHECK-NEXT: [[AB6:%.*]] = sitofp i8 [[C0]] to float
	; CHECK-NEXT: [[AB7:%.*]] = uitofp i8 [[C1]] to float			; CHECK-NEXT: [[AB7:%.*]] = uitofp i8 [[C1]] to float
	; CHECK-NEXT: [[R31:%.*]] = shufflevector <4 x float> [[TMP3]], <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[R31:%.*]] = shufflevector <4 x float> [[TMP3]], <4 x float> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[R4:%.*]] = insertelement <8 x float> [[R31]], float [[AB4]], i32 4			; CHECK-NEXT: [[R4:%.*]] = insertelement <8 x float> [[R31]], float [[AB4]], i32 4
	; CHECK-NEXT: [[R5:%.*]] = insertelement <8 x float> [[R4]], float [[AB5]], i32 5			; CHECK-NEXT: [[R5:%.*]] = insertelement <8 x float> [[R4]], float [[AB5]], i32 5
	; CHECK-NEXT: [[R6:%.*]] = insertelement <8 x float> [[R5]], float [[AB6]], i32 6			; CHECK-NEXT: [[R6:%.*]] = insertelement <8 x float> [[R5]], float [[AB6]], i32 6
	; CHECK-NEXT: [[R7:%.*]] = insertelement <8 x float> [[R6]], float [[AB7]], i32 7			; CHECK-NEXT: [[R7:%.*]] = insertelement <8 x float> [[R6]], float [[AB7]], i32 7
	; CHECK-NEXT: ret <8 x float> [[R7]]			; CHECK-NEXT: ret <8 x float> [[R7]]
	;			;
	%a0 = extractelement <4 x i32> %a, i32 0			%a0 = extractelement <4 x i32> %a, i32 0
	%a1 = extractelement <4 x i32> %a, i32 1			%a1 = extractelement <4 x i32> %a, i32 1
	Show All 24 Lines

llvm/test/Transforms/SLPVectorizer/X86/alternate-fp-inseltpoison.ll

	Show First 20 Lines • Show All 95 Lines • ▼ Show 20 Lines
	; SSE-NEXT: ret <4 x float> [[TMP1]]			; SSE-NEXT: ret <4 x float> [[TMP1]]
	;			;
	; SLM-LABEL: @fmul_fdiv_v4f32_const(			; SLM-LABEL: @fmul_fdiv_v4f32_const(
	; SLM-NEXT: [[A2:%.]] = extractelement <4 x float> [[A:%.]], i32 2			; SLM-NEXT: [[A2:%.]] = extractelement <4 x float> [[A:%.]], i32 2
	; SLM-NEXT: [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3			; SLM-NEXT: [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
	; SLM-NEXT: [[TMP1:%.*]] = shufflevector <4 x float> [[A]], <4 x float> undef, <2 x i32> <i32 0, i32 1>			; SLM-NEXT: [[TMP1:%.*]] = shufflevector <4 x float> [[A]], <4 x float> undef, <2 x i32> <i32 0, i32 1>
	; SLM-NEXT: [[TMP2:%.*]] = fmul <2 x float> [[TMP1]], <float 2.000000e+00, float 1.000000e+00>			; SLM-NEXT: [[TMP2:%.*]] = fmul <2 x float> [[TMP1]], <float 2.000000e+00, float 1.000000e+00>
	; SLM-NEXT: [[AB3:%.*]] = fmul float [[A3]], 2.000000e+00			; SLM-NEXT: [[AB3:%.*]] = fmul float [[A3]], 2.000000e+00
	; SLM-NEXT: [[R11:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; SLM-NEXT: [[R11:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; SLM-NEXT: [[R2:%.*]] = insertelement <4 x float> [[R11]], float [[A2]], i32 2			; SLM-NEXT: [[R2:%.*]] = insertelement <4 x float> [[R11]], float [[A2]], i32 2
	; SLM-NEXT: [[R3:%.*]] = insertelement <4 x float> [[R2]], float [[AB3]], i32 3			; SLM-NEXT: [[R3:%.*]] = insertelement <4 x float> [[R2]], float [[AB3]], i32 3
	; SLM-NEXT: ret <4 x float> [[R3]]			; SLM-NEXT: ret <4 x float> [[R3]]
	;			;
	; AVX-LABEL: @fmul_fdiv_v4f32_const(			; AVX-LABEL: @fmul_fdiv_v4f32_const(
	; AVX-NEXT: [[TMP1:%.]] = fmul <4 x float> [[A:%.]], <float 2.000000e+00, float 1.000000e+00, float 1.000000e+00, float 2.000000e+00>			; AVX-NEXT: [[TMP1:%.]] = fmul <4 x float> [[A:%.]], <float 2.000000e+00, float 1.000000e+00, float 1.000000e+00, float 2.000000e+00>
	; AVX-NEXT: ret <4 x float> [[TMP1]]			; AVX-NEXT: ret <4 x float> [[TMP1]]
	;			;
	Show All 18 Lines

llvm/test/Transforms/SLPVectorizer/X86/alternate-fp.ll

	Show First 20 Lines • Show All 95 Lines • ▼ Show 20 Lines
	; SSE-NEXT: ret <4 x float> [[TMP1]]			; SSE-NEXT: ret <4 x float> [[TMP1]]
	;			;
	; SLM-LABEL: @fmul_fdiv_v4f32_const(			; SLM-LABEL: @fmul_fdiv_v4f32_const(
	; SLM-NEXT: [[A2:%.]] = extractelement <4 x float> [[A:%.]], i32 2			; SLM-NEXT: [[A2:%.]] = extractelement <4 x float> [[A:%.]], i32 2
	; SLM-NEXT: [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3			; SLM-NEXT: [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
	; SLM-NEXT: [[TMP1:%.*]] = shufflevector <4 x float> [[A]], <4 x float> undef, <2 x i32> <i32 0, i32 1>			; SLM-NEXT: [[TMP1:%.*]] = shufflevector <4 x float> [[A]], <4 x float> undef, <2 x i32> <i32 0, i32 1>
	; SLM-NEXT: [[TMP2:%.*]] = fmul <2 x float> [[TMP1]], <float 2.000000e+00, float 1.000000e+00>			; SLM-NEXT: [[TMP2:%.*]] = fmul <2 x float> [[TMP1]], <float 2.000000e+00, float 1.000000e+00>
	; SLM-NEXT: [[AB3:%.*]] = fmul float [[A3]], 2.000000e+00			; SLM-NEXT: [[AB3:%.*]] = fmul float [[A3]], 2.000000e+00
	; SLM-NEXT: [[R11:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; SLM-NEXT: [[R11:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; SLM-NEXT: [[R2:%.*]] = insertelement <4 x float> [[R11]], float [[A2]], i32 2			; SLM-NEXT: [[R2:%.*]] = insertelement <4 x float> [[R11]], float [[A2]], i32 2
	; SLM-NEXT: [[R3:%.*]] = insertelement <4 x float> [[R2]], float [[AB3]], i32 3			; SLM-NEXT: [[R3:%.*]] = insertelement <4 x float> [[R2]], float [[AB3]], i32 3
	; SLM-NEXT: ret <4 x float> [[R3]]			; SLM-NEXT: ret <4 x float> [[R3]]
	;			;
	; AVX-LABEL: @fmul_fdiv_v4f32_const(			; AVX-LABEL: @fmul_fdiv_v4f32_const(
	; AVX-NEXT: [[TMP1:%.]] = fmul <4 x float> [[A:%.]], <float 2.000000e+00, float 1.000000e+00, float 1.000000e+00, float 2.000000e+00>			; AVX-NEXT: [[TMP1:%.]] = fmul <4 x float> [[A:%.]], <float 2.000000e+00, float 1.000000e+00, float 1.000000e+00, float 2.000000e+00>
	; AVX-NEXT: ret <4 x float> [[TMP1]]			; AVX-NEXT: ret <4 x float> [[TMP1]]
	;			;
	Show All 18 Lines

llvm/test/Transforms/SLPVectorizer/X86/alternate-int-inseltpoison.ll

Show First 20 Lines • Show All 99 Lines • ▼ Show 20 Lines	;
ret <4 x i32> %r3		ret <4 x i32> %r3
}		}

define <8 x i32> @ashr_shl_v8i32(<8 x i32> %a, <8 x i32> %b) {		define <8 x i32> @ashr_shl_v8i32(<8 x i32> %a, <8 x i32> %b) {
; SSE-LABEL: @ashr_shl_v8i32(		; SSE-LABEL: @ashr_shl_v8i32(
; SSE-NEXT: [[TMP1:%.]] = ashr <8 x i32> [[A:%.]], [[B:%.*]]		; SSE-NEXT: [[TMP1:%.]] = ashr <8 x i32> [[A:%.]], [[B:%.*]]
; SSE-NEXT: [[TMP2:%.*]] = shl <8 x i32> [[A]], [[B]]		; SSE-NEXT: [[TMP2:%.*]] = shl <8 x i32> [[A]], [[B]]
; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>		; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; SSE-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>		; SSE-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE-NEXT: [[R72:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[TMP4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>		; SSE-NEXT: [[R72:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[TMP4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; SSE-NEXT: ret <8 x i32> [[R72]]		; SSE-NEXT: ret <8 x i32> [[R72]]
;		;
; SLM-LABEL: @ashr_shl_v8i32(		; SLM-LABEL: @ashr_shl_v8i32(
; SLM-NEXT: [[TMP1:%.]] = ashr <8 x i32> [[A:%.]], [[B:%.*]]		; SLM-NEXT: [[TMP1:%.]] = ashr <8 x i32> [[A:%.]], [[B:%.*]]
; SLM-NEXT: [[TMP2:%.*]] = shl <8 x i32> [[A]], [[B]]		; SLM-NEXT: [[TMP2:%.*]] = shl <8 x i32> [[A]], [[B]]
; SLM-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[TMP2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>		; SLM-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[TMP2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
; SLM-NEXT: ret <8 x i32> [[TMP3]]		; SLM-NEXT: ret <8 x i32> [[TMP3]]
▲ Show 20 Lines • Show All 134 Lines • ▼ Show 20 Lines
; SSE-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[A]], [[B]]		; SSE-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[A]], [[B]]
; SSE-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>		; SSE-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>
; SSE-NEXT: [[R0:%.*]] = insertelement <8 x i32> poison, i32 [[AB0]], i32 0		; SSE-NEXT: [[R0:%.*]] = insertelement <8 x i32> poison, i32 [[AB0]], i32 0
; SSE-NEXT: [[R1:%.*]] = insertelement <8 x i32> [[R0]], i32 [[AB1]], i32 1		; SSE-NEXT: [[R1:%.*]] = insertelement <8 x i32> [[R0]], i32 [[AB1]], i32 1
; SSE-NEXT: [[R2:%.*]] = insertelement <8 x i32> [[R1]], i32 [[AB2]], i32 2		; SSE-NEXT: [[R2:%.*]] = insertelement <8 x i32> [[R1]], i32 [[AB2]], i32 2
; SSE-NEXT: [[R3:%.*]] = insertelement <8 x i32> [[R2]], i32 [[AB3]], i32 3		; SSE-NEXT: [[R3:%.*]] = insertelement <8 x i32> [[R2]], i32 [[AB3]], i32 3
; SSE-NEXT: [[R4:%.*]] = insertelement <8 x i32> [[R3]], i32 [[AB4]], i32 4		; SSE-NEXT: [[R4:%.*]] = insertelement <8 x i32> [[R3]], i32 [[AB4]], i32 4
; SSE-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R4]], i32 [[AB5]], i32 5		; SSE-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R4]], i32 [[AB5]], i32 5
; SSE-NEXT: [[TMP3:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; SSE-NEXT: [[TMP3:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>		; SSE-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; SSE-NEXT: ret <8 x i32> [[R71]]		; SSE-NEXT: ret <8 x i32> [[R71]]
;		;
; SLM-LABEL: @ashr_lshr_shl_v8i32(		; SLM-LABEL: @ashr_lshr_shl_v8i32(
; SLM-NEXT: [[TMP1:%.]] = shufflevector <8 x i32> [[A:%.]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>		; SLM-NEXT: [[TMP1:%.]] = shufflevector <8 x i32> [[A:%.]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; SLM-NEXT: [[TMP2:%.]] = shufflevector <8 x i32> [[B:%.]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>		; SLM-NEXT: [[TMP2:%.]] = shufflevector <8 x i32> [[B:%.]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; SLM-NEXT: [[TMP3:%.*]] = ashr <4 x i32> [[TMP1]], [[TMP2]]		; SLM-NEXT: [[TMP3:%.*]] = ashr <4 x i32> [[TMP1]], [[TMP2]]
; SLM-NEXT: [[TMP4:%.*]] = lshr <4 x i32> [[TMP1]], [[TMP2]]		; SLM-NEXT: [[TMP4:%.*]] = lshr <4 x i32> [[TMP1]], [[TMP2]]
▲ Show 20 Lines • Show All 184 Lines • ▼ Show 20 Lines
; AVX2-NEXT: [[A5:%.*]] = extractelement <8 x i32> [[A]], i32 5		; AVX2-NEXT: [[A5:%.*]] = extractelement <8 x i32> [[A]], i32 5
; AVX2-NEXT: [[AB1:%.*]] = sdiv i32 [[A1]], 4		; AVX2-NEXT: [[AB1:%.*]] = sdiv i32 [[A1]], 4
; AVX2-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>		; AVX2-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>
; AVX2-NEXT: [[TMP2:%.*]] = sdiv <2 x i32> [[TMP1]], <i32 8, i32 16>		; AVX2-NEXT: [[TMP2:%.*]] = sdiv <2 x i32> [[TMP1]], <i32 8, i32 16>
; AVX2-NEXT: [[AB5:%.*]] = sdiv i32 [[A5]], 4		; AVX2-NEXT: [[AB5:%.*]] = sdiv i32 [[A5]], 4
; AVX2-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>		; AVX2-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>
; AVX2-NEXT: [[TMP4:%.*]] = sdiv <2 x i32> [[TMP3]], <i32 8, i32 16>		; AVX2-NEXT: [[TMP4:%.*]] = sdiv <2 x i32> [[TMP3]], <i32 8, i32 16>
; AVX2-NEXT: [[R1:%.*]] = insertelement <8 x i32> poison, i32 [[AB1]], i32 1		; AVX2-NEXT: [[R1:%.*]] = insertelement <8 x i32> poison, i32 [[AB1]], i32 1
; AVX2-NEXT: [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX2-NEXT: [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: [[R32:%.*]] = shufflevector <8 x i32> [[R1]], <8 x i32> [[TMP5]], <8 x i32> <i32 undef, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX2-NEXT: [[R32:%.*]] = shufflevector <8 x i32> [[R1]], <8 x i32> [[TMP5]], <8 x i32> <i32 undef, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R32]], i32 [[AB5]], i32 5		; AVX2-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R32]], i32 [[AB5]], i32 5
; AVX2-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX2-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP6]], <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 5, i32 8, i32 9>		; AVX2-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP6]], <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 5, i32 8, i32 9>
; AVX2-NEXT: ret <8 x i32> [[R71]]		; AVX2-NEXT: ret <8 x i32> [[R71]]
;		;
; AVX512-LABEL: @sdiv_v8i32_undefs(		; AVX512-LABEL: @sdiv_v8i32_undefs(
; AVX512-NEXT: [[A1:%.]] = extractelement <8 x i32> [[A:%.]], i32 1		; AVX512-NEXT: [[A1:%.]] = extractelement <8 x i32> [[A:%.]], i32 1
; AVX512-NEXT: [[A5:%.*]] = extractelement <8 x i32> [[A]], i32 5		; AVX512-NEXT: [[A5:%.*]] = extractelement <8 x i32> [[A]], i32 5
; AVX512-NEXT: [[AB1:%.*]] = sdiv i32 [[A1]], 4		; AVX512-NEXT: [[AB1:%.*]] = sdiv i32 [[A1]], 4
; AVX512-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>		; AVX512-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>
; AVX512-NEXT: [[TMP2:%.*]] = sdiv <2 x i32> [[TMP1]], <i32 8, i32 16>		; AVX512-NEXT: [[TMP2:%.*]] = sdiv <2 x i32> [[TMP1]], <i32 8, i32 16>
; AVX512-NEXT: [[AB5:%.*]] = sdiv i32 [[A5]], 4		; AVX512-NEXT: [[AB5:%.*]] = sdiv i32 [[A5]], 4
; AVX512-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>		; AVX512-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>
; AVX512-NEXT: [[TMP4:%.*]] = sdiv <2 x i32> [[TMP3]], <i32 8, i32 16>		; AVX512-NEXT: [[TMP4:%.*]] = sdiv <2 x i32> [[TMP3]], <i32 8, i32 16>
; AVX512-NEXT: [[R1:%.*]] = insertelement <8 x i32> poison, i32 [[AB1]], i32 1		; AVX512-NEXT: [[R1:%.*]] = insertelement <8 x i32> poison, i32 [[AB1]], i32 1
; AVX512-NEXT: [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX512-NEXT: [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX512-NEXT: [[R32:%.*]] = shufflevector <8 x i32> [[R1]], <8 x i32> [[TMP5]], <8 x i32> <i32 undef, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX512-NEXT: [[R32:%.*]] = shufflevector <8 x i32> [[R1]], <8 x i32> [[TMP5]], <8 x i32> <i32 undef, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX512-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R32]], i32 [[AB5]], i32 5		; AVX512-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R32]], i32 [[AB5]], i32 5
; AVX512-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX512-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX512-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP6]], <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 5, i32 8, i32 9>		; AVX512-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP6]], <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 5, i32 8, i32 9>
; AVX512-NEXT: ret <8 x i32> [[R71]]		; AVX512-NEXT: ret <8 x i32> [[R71]]
;		;
%a0 = extractelement <8 x i32> %a, i32 0		%a0 = extractelement <8 x i32> %a, i32 0
%a1 = extractelement <8 x i32> %a, i32 1		%a1 = extractelement <8 x i32> %a, i32 1
%a2 = extractelement <8 x i32> %a, i32 2		%a2 = extractelement <8 x i32> %a, i32 2
%a3 = extractelement <8 x i32> %a, i32 3		%a3 = extractelement <8 x i32> %a, i32 3
%a4 = extractelement <8 x i32> %a, i32 4		%a4 = extractelement <8 x i32> %a, i32 4
▲ Show 20 Lines • Show All 57 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll

Show First 20 Lines • Show All 99 Lines • ▼ Show 20 Lines	;
ret <4 x i32> %r3		ret <4 x i32> %r3
}		}

define <8 x i32> @ashr_shl_v8i32(<8 x i32> %a, <8 x i32> %b) {		define <8 x i32> @ashr_shl_v8i32(<8 x i32> %a, <8 x i32> %b) {
; SSE-LABEL: @ashr_shl_v8i32(		; SSE-LABEL: @ashr_shl_v8i32(
; SSE-NEXT: [[TMP1:%.]] = ashr <8 x i32> [[A:%.]], [[B:%.*]]		; SSE-NEXT: [[TMP1:%.]] = ashr <8 x i32> [[A:%.]], [[B:%.*]]
; SSE-NEXT: [[TMP2:%.*]] = shl <8 x i32> [[A]], [[B]]		; SSE-NEXT: [[TMP2:%.*]] = shl <8 x i32> [[A]], [[B]]
; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>		; SSE-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; SSE-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>		; SSE-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE-NEXT: [[R72:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[TMP4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>		; SSE-NEXT: [[R72:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[TMP4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
; SSE-NEXT: ret <8 x i32> [[R72]]		; SSE-NEXT: ret <8 x i32> [[R72]]
;		;
; SLM-LABEL: @ashr_shl_v8i32(		; SLM-LABEL: @ashr_shl_v8i32(
; SLM-NEXT: [[TMP1:%.]] = ashr <8 x i32> [[A:%.]], [[B:%.*]]		; SLM-NEXT: [[TMP1:%.]] = ashr <8 x i32> [[A:%.]], [[B:%.*]]
; SLM-NEXT: [[TMP2:%.*]] = shl <8 x i32> [[A]], [[B]]		; SLM-NEXT: [[TMP2:%.*]] = shl <8 x i32> [[A]], [[B]]
; SLM-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[TMP2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>		; SLM-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> [[TMP2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
; SLM-NEXT: ret <8 x i32> [[TMP3]]		; SLM-NEXT: ret <8 x i32> [[TMP3]]
▲ Show 20 Lines • Show All 134 Lines • ▼ Show 20 Lines
; SSE-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[A]], [[B]]		; SSE-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[A]], [[B]]
; SSE-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>		; SSE-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP1]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>
; SSE-NEXT: [[R0:%.*]] = insertelement <8 x i32> undef, i32 [[AB0]], i32 0		; SSE-NEXT: [[R0:%.*]] = insertelement <8 x i32> undef, i32 [[AB0]], i32 0
; SSE-NEXT: [[R1:%.*]] = insertelement <8 x i32> [[R0]], i32 [[AB1]], i32 1		; SSE-NEXT: [[R1:%.*]] = insertelement <8 x i32> [[R0]], i32 [[AB1]], i32 1
; SSE-NEXT: [[R2:%.*]] = insertelement <8 x i32> [[R1]], i32 [[AB2]], i32 2		; SSE-NEXT: [[R2:%.*]] = insertelement <8 x i32> [[R1]], i32 [[AB2]], i32 2
; SSE-NEXT: [[R3:%.*]] = insertelement <8 x i32> [[R2]], i32 [[AB3]], i32 3		; SSE-NEXT: [[R3:%.*]] = insertelement <8 x i32> [[R2]], i32 [[AB3]], i32 3
; SSE-NEXT: [[R4:%.*]] = insertelement <8 x i32> [[R3]], i32 [[AB4]], i32 4		; SSE-NEXT: [[R4:%.*]] = insertelement <8 x i32> [[R3]], i32 [[AB4]], i32 4
; SSE-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R4]], i32 [[AB5]], i32 5		; SSE-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R4]], i32 [[AB5]], i32 5
; SSE-NEXT: [[TMP3:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; SSE-NEXT: [[TMP3:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; SSE-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>		; SSE-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; SSE-NEXT: ret <8 x i32> [[R71]]		; SSE-NEXT: ret <8 x i32> [[R71]]
;		;
; SLM-LABEL: @ashr_lshr_shl_v8i32(		; SLM-LABEL: @ashr_lshr_shl_v8i32(
; SLM-NEXT: [[TMP1:%.]] = shufflevector <8 x i32> [[A:%.]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>		; SLM-NEXT: [[TMP1:%.]] = shufflevector <8 x i32> [[A:%.]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; SLM-NEXT: [[TMP2:%.]] = shufflevector <8 x i32> [[B:%.]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>		; SLM-NEXT: [[TMP2:%.]] = shufflevector <8 x i32> [[B:%.]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; SLM-NEXT: [[TMP3:%.*]] = ashr <4 x i32> [[TMP1]], [[TMP2]]		; SLM-NEXT: [[TMP3:%.*]] = ashr <4 x i32> [[TMP1]], [[TMP2]]
; SLM-NEXT: [[TMP4:%.*]] = lshr <4 x i32> [[TMP1]], [[TMP2]]		; SLM-NEXT: [[TMP4:%.*]] = lshr <4 x i32> [[TMP1]], [[TMP2]]
▲ Show 20 Lines • Show All 184 Lines • ▼ Show 20 Lines
; AVX2-NEXT: [[A5:%.*]] = extractelement <8 x i32> [[A]], i32 5		; AVX2-NEXT: [[A5:%.*]] = extractelement <8 x i32> [[A]], i32 5
; AVX2-NEXT: [[AB1:%.*]] = sdiv i32 [[A1]], 4		; AVX2-NEXT: [[AB1:%.*]] = sdiv i32 [[A1]], 4
; AVX2-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>		; AVX2-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>
; AVX2-NEXT: [[TMP2:%.*]] = sdiv <2 x i32> [[TMP1]], <i32 8, i32 16>		; AVX2-NEXT: [[TMP2:%.*]] = sdiv <2 x i32> [[TMP1]], <i32 8, i32 16>
; AVX2-NEXT: [[AB5:%.*]] = sdiv i32 [[A5]], 4		; AVX2-NEXT: [[AB5:%.*]] = sdiv i32 [[A5]], 4
; AVX2-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>		; AVX2-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>
; AVX2-NEXT: [[TMP4:%.*]] = sdiv <2 x i32> [[TMP3]], <i32 8, i32 16>		; AVX2-NEXT: [[TMP4:%.*]] = sdiv <2 x i32> [[TMP3]], <i32 8, i32 16>
; AVX2-NEXT: [[R1:%.*]] = insertelement <8 x i32> <i32 poison, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>, i32 [[AB1]], i32 1		; AVX2-NEXT: [[R1:%.*]] = insertelement <8 x i32> <i32 poison, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>, i32 [[AB1]], i32 1
; AVX2-NEXT: [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX2-NEXT: [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: [[R32:%.*]] = shufflevector <8 x i32> [[R1]], <8 x i32> [[TMP5]], <8 x i32> <i32 undef, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX2-NEXT: [[R32:%.*]] = shufflevector <8 x i32> [[R1]], <8 x i32> [[TMP5]], <8 x i32> <i32 undef, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R32]], i32 [[AB5]], i32 5		; AVX2-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R32]], i32 [[AB5]], i32 5
; AVX2-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX2-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX2-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP6]], <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 5, i32 8, i32 9>		; AVX2-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP6]], <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 5, i32 8, i32 9>
; AVX2-NEXT: ret <8 x i32> [[R71]]		; AVX2-NEXT: ret <8 x i32> [[R71]]
;		;
; AVX512-LABEL: @sdiv_v8i32_undefs(		; AVX512-LABEL: @sdiv_v8i32_undefs(
; AVX512-NEXT: [[A1:%.]] = extractelement <8 x i32> [[A:%.]], i32 1		; AVX512-NEXT: [[A1:%.]] = extractelement <8 x i32> [[A:%.]], i32 1
; AVX512-NEXT: [[A5:%.*]] = extractelement <8 x i32> [[A]], i32 5		; AVX512-NEXT: [[A5:%.*]] = extractelement <8 x i32> [[A]], i32 5
; AVX512-NEXT: [[AB1:%.*]] = sdiv i32 [[A1]], 4		; AVX512-NEXT: [[AB1:%.*]] = sdiv i32 [[A1]], 4
; AVX512-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>		; AVX512-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 2, i32 3>
; AVX512-NEXT: [[TMP2:%.*]] = sdiv <2 x i32> [[TMP1]], <i32 8, i32 16>		; AVX512-NEXT: [[TMP2:%.*]] = sdiv <2 x i32> [[TMP1]], <i32 8, i32 16>
; AVX512-NEXT: [[AB5:%.*]] = sdiv i32 [[A5]], 4		; AVX512-NEXT: [[AB5:%.*]] = sdiv i32 [[A5]], 4
; AVX512-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>		; AVX512-NEXT: [[TMP3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <2 x i32> <i32 6, i32 7>
; AVX512-NEXT: [[TMP4:%.*]] = sdiv <2 x i32> [[TMP3]], <i32 8, i32 16>		; AVX512-NEXT: [[TMP4:%.*]] = sdiv <2 x i32> [[TMP3]], <i32 8, i32 16>
; AVX512-NEXT: [[R1:%.*]] = insertelement <8 x i32> <i32 poison, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>, i32 [[AB1]], i32 1		; AVX512-NEXT: [[R1:%.*]] = insertelement <8 x i32> <i32 poison, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>, i32 [[AB1]], i32 1
; AVX512-NEXT: [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX512-NEXT: [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX512-NEXT: [[R32:%.*]] = shufflevector <8 x i32> [[R1]], <8 x i32> [[TMP5]], <8 x i32> <i32 undef, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX512-NEXT: [[R32:%.*]] = shufflevector <8 x i32> [[R1]], <8 x i32> [[TMP5]], <8 x i32> <i32 undef, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX512-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R32]], i32 [[AB5]], i32 5		; AVX512-NEXT: [[R5:%.*]] = insertelement <8 x i32> [[R32]], i32 [[AB5]], i32 5
; AVX512-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>		; AVX512-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; AVX512-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP6]], <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 5, i32 8, i32 9>		; AVX512-NEXT: [[R71:%.*]] = shufflevector <8 x i32> [[R5]], <8 x i32> [[TMP6]], <8 x i32> <i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 5, i32 8, i32 9>
; AVX512-NEXT: ret <8 x i32> [[R71]]		; AVX512-NEXT: ret <8 x i32> [[R71]]
;		;
%a0 = extractelement <8 x i32> %a, i32 0		%a0 = extractelement <8 x i32> %a, i32 0
%a1 = extractelement <8 x i32> %a, i32 1		%a1 = extractelement <8 x i32> %a, i32 1
%a2 = extractelement <8 x i32> %a, i32 2		%a2 = extractelement <8 x i32> %a, i32 2
%a3 = extractelement <8 x i32> %a, i32 3		%a3 = extractelement <8 x i32> %a, i32 3
%a4 = extractelement <8 x i32> %a, i32 4		%a4 = extractelement <8 x i32> %a, i32 4
▲ Show 20 Lines • Show All 57 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/arith-fp-inseltpoison.ll

	Show First 20 Lines • Show All 637 Lines • ▼ Show 20 Lines
	; SLM-NEXT: [[TMP13:%.*]] = insertelement <2 x double> poison, double [[B4]], i32 0			; SLM-NEXT: [[TMP13:%.*]] = insertelement <2 x double> poison, double [[B4]], i32 0
	; SLM-NEXT: [[TMP14:%.*]] = insertelement <2 x double> [[TMP13]], double [[B5]], i32 1			; SLM-NEXT: [[TMP14:%.*]] = insertelement <2 x double> [[TMP13]], double [[B5]], i32 1
	; SLM-NEXT: [[TMP15:%.*]] = fdiv <2 x double> [[TMP12]], [[TMP14]]			; SLM-NEXT: [[TMP15:%.*]] = fdiv <2 x double> [[TMP12]], [[TMP14]]
	; SLM-NEXT: [[TMP16:%.*]] = insertelement <2 x double> poison, double [[A6]], i32 0			; SLM-NEXT: [[TMP16:%.*]] = insertelement <2 x double> poison, double [[A6]], i32 0
	; SLM-NEXT: [[TMP17:%.*]] = insertelement <2 x double> [[TMP16]], double [[A7]], i32 1			; SLM-NEXT: [[TMP17:%.*]] = insertelement <2 x double> [[TMP16]], double [[A7]], i32 1
	; SLM-NEXT: [[TMP18:%.*]] = insertelement <2 x double> poison, double [[B6]], i32 0			; SLM-NEXT: [[TMP18:%.*]] = insertelement <2 x double> poison, double [[B6]], i32 0
	; SLM-NEXT: [[TMP19:%.*]] = insertelement <2 x double> [[TMP18]], double [[B7]], i32 1			; SLM-NEXT: [[TMP19:%.*]] = insertelement <2 x double> [[TMP18]], double [[B7]], i32 1
	; SLM-NEXT: [[TMP20:%.*]] = fdiv <2 x double> [[TMP17]], [[TMP19]]			; SLM-NEXT: [[TMP20:%.*]] = fdiv <2 x double> [[TMP17]], [[TMP19]]
	; SLM-NEXT: [[TMP21:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP21:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R11:%.*]] = shufflevector <8 x double> poison, <8 x double> [[TMP21]], <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>			; SLM-NEXT: [[R11:%.*]] = shufflevector <8 x double> poison, <8 x double> [[TMP21]], <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
	; SLM-NEXT: [[TMP22:%.*]] = shufflevector <2 x double> [[TMP10]], <2 x double> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP22:%.*]] = shufflevector <2 x double> [[TMP10]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R32:%.*]] = shufflevector <8 x double> [[R11]], <8 x double> [[TMP22]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>			; SLM-NEXT: [[R32:%.*]] = shufflevector <8 x double> [[R11]], <8 x double> [[TMP22]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
	; SLM-NEXT: [[TMP23:%.*]] = shufflevector <2 x double> [[TMP15]], <2 x double> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP23:%.*]] = shufflevector <2 x double> [[TMP15]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R53:%.*]] = shufflevector <8 x double> [[R32]], <8 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>			; SLM-NEXT: [[R53:%.*]] = shufflevector <8 x double> [[R32]], <8 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
	; SLM-NEXT: [[TMP24:%.*]] = shufflevector <2 x double> [[TMP20]], <2 x double> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP24:%.*]] = shufflevector <2 x double> [[TMP20]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R74:%.*]] = shufflevector <8 x double> [[R53]], <8 x double> [[TMP24]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; SLM-NEXT: [[R74:%.*]] = shufflevector <8 x double> [[R53]], <8 x double> [[TMP24]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; SLM-NEXT: ret <8 x double> [[R74]]			; SLM-NEXT: ret <8 x double> [[R74]]
	;			;
	; AVX-LABEL: @buildvector_div_8f64(			; AVX-LABEL: @buildvector_div_8f64(
	; AVX-NEXT: [[TMP1:%.]] = fdiv <8 x double> [[A:%.]], [[B:%.*]]			; AVX-NEXT: [[TMP1:%.]] = fdiv <8 x double> [[A:%.]], [[B:%.*]]
	; AVX-NEXT: ret <8 x double> [[TMP1]]			; AVX-NEXT: ret <8 x double> [[TMP1]]
	;			;
	; AVX512-LABEL: @buildvector_div_8f64(			; AVX512-LABEL: @buildvector_div_8f64(
	▲ Show 20 Lines • Show All 325 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/arith-fp.ll

	Show First 20 Lines • Show All 637 Lines • ▼ Show 20 Lines
	; SLM-NEXT: [[TMP13:%.*]] = insertelement <2 x double> poison, double [[B4]], i32 0			; SLM-NEXT: [[TMP13:%.*]] = insertelement <2 x double> poison, double [[B4]], i32 0
	; SLM-NEXT: [[TMP14:%.*]] = insertelement <2 x double> [[TMP13]], double [[B5]], i32 1			; SLM-NEXT: [[TMP14:%.*]] = insertelement <2 x double> [[TMP13]], double [[B5]], i32 1
	; SLM-NEXT: [[TMP15:%.*]] = fdiv <2 x double> [[TMP12]], [[TMP14]]			; SLM-NEXT: [[TMP15:%.*]] = fdiv <2 x double> [[TMP12]], [[TMP14]]
	; SLM-NEXT: [[TMP16:%.*]] = insertelement <2 x double> poison, double [[A6]], i32 0			; SLM-NEXT: [[TMP16:%.*]] = insertelement <2 x double> poison, double [[A6]], i32 0
	; SLM-NEXT: [[TMP17:%.*]] = insertelement <2 x double> [[TMP16]], double [[A7]], i32 1			; SLM-NEXT: [[TMP17:%.*]] = insertelement <2 x double> [[TMP16]], double [[A7]], i32 1
	; SLM-NEXT: [[TMP18:%.*]] = insertelement <2 x double> poison, double [[B6]], i32 0			; SLM-NEXT: [[TMP18:%.*]] = insertelement <2 x double> poison, double [[B6]], i32 0
	; SLM-NEXT: [[TMP19:%.*]] = insertelement <2 x double> [[TMP18]], double [[B7]], i32 1			; SLM-NEXT: [[TMP19:%.*]] = insertelement <2 x double> [[TMP18]], double [[B7]], i32 1
	; SLM-NEXT: [[TMP20:%.*]] = fdiv <2 x double> [[TMP17]], [[TMP19]]			; SLM-NEXT: [[TMP20:%.*]] = fdiv <2 x double> [[TMP17]], [[TMP19]]
	; SLM-NEXT: [[TMP21:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP21:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R11:%.*]] = shufflevector <8 x double> undef, <8 x double> [[TMP21]], <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>			; SLM-NEXT: [[R11:%.*]] = shufflevector <8 x double> undef, <8 x double> [[TMP21]], <8 x i32> <i32 8, i32 9, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
	; SLM-NEXT: [[TMP22:%.*]] = shufflevector <2 x double> [[TMP10]], <2 x double> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP22:%.*]] = shufflevector <2 x double> [[TMP10]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R32:%.*]] = shufflevector <8 x double> [[R11]], <8 x double> [[TMP22]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>			; SLM-NEXT: [[R32:%.*]] = shufflevector <8 x double> [[R11]], <8 x double> [[TMP22]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
	; SLM-NEXT: [[TMP23:%.*]] = shufflevector <2 x double> [[TMP15]], <2 x double> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP23:%.*]] = shufflevector <2 x double> [[TMP15]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R53:%.*]] = shufflevector <8 x double> [[R32]], <8 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>			; SLM-NEXT: [[R53:%.*]] = shufflevector <8 x double> [[R32]], <8 x double> [[TMP23]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
	; SLM-NEXT: [[TMP24:%.*]] = shufflevector <2 x double> [[TMP20]], <2 x double> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; SLM-NEXT: [[TMP24:%.*]] = shufflevector <2 x double> [[TMP20]], <2 x double> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; SLM-NEXT: [[R74:%.*]] = shufflevector <8 x double> [[R53]], <8 x double> [[TMP24]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; SLM-NEXT: [[R74:%.*]] = shufflevector <8 x double> [[R53]], <8 x double> [[TMP24]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; SLM-NEXT: ret <8 x double> [[R74]]			; SLM-NEXT: ret <8 x double> [[R74]]
	;			;
	; AVX-LABEL: @buildvector_div_8f64(			; AVX-LABEL: @buildvector_div_8f64(
	; AVX-NEXT: [[TMP1:%.]] = fdiv <8 x double> [[A:%.]], [[B:%.*]]			; AVX-NEXT: [[TMP1:%.]] = fdiv <8 x double> [[A:%.]], [[B:%.*]]
	; AVX-NEXT: ret <8 x double> [[TMP1]]			; AVX-NEXT: ret <8 x double> [[TMP1]]
	;			;
	; AVX512-LABEL: @buildvector_div_8f64(			; AVX512-LABEL: @buildvector_div_8f64(
	▲ Show 20 Lines • Show All 325 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/cmp_commute-inseltpoison.ll

	Show First 20 Lines • Show All 266 Lines • ▼ Show 20 Lines
	; AVX-NEXT: [[TMP1:%.]] = bitcast float [[P1]] to <2 x float>*			; AVX-NEXT: [[TMP1:%.]] = bitcast float [[P1]] to <2 x float>*
	; AVX-NEXT: [[TMP2:%.]] = load <2 x float>, <2 x float> [[TMP1]], align 4			; AVX-NEXT: [[TMP2:%.]] = load <2 x float>, <2 x float> [[TMP1]], align 4
	; AVX-NEXT: [[B3:%.]] = load float, float [[P3]], align 4			; AVX-NEXT: [[B3:%.]] = load float, float [[P3]], align 4
	; AVX-NEXT: [[C0:%.*]] = fcmp ord float [[A0]], [[B0]]			; AVX-NEXT: [[C0:%.*]] = fcmp ord float [[A0]], [[B0]]
	; AVX-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[A]], <4 x float> undef, <2 x i32> <i32 1, i32 2>			; AVX-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[A]], <4 x float> undef, <2 x i32> <i32 1, i32 2>
	; AVX-NEXT: [[TMP4:%.*]] = fcmp uno <2 x float> [[TMP2]], [[TMP3]]			; AVX-NEXT: [[TMP4:%.*]] = fcmp uno <2 x float> [[TMP2]], [[TMP3]]
	; AVX-NEXT: [[C3:%.*]] = fcmp ord float [[A3]], [[B3]]			; AVX-NEXT: [[C3:%.*]] = fcmp ord float [[A3]], [[B3]]
	; AVX-NEXT: [[D0:%.*]] = insertelement <4 x i1> poison, i1 [[C0]], i32 0			; AVX-NEXT: [[D0:%.*]] = insertelement <4 x i1> poison, i1 [[C0]], i32 0
	; AVX-NEXT: [[TMP5:%.*]] = shufflevector <2 x i1> [[TMP4]], <2 x i1> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; AVX-NEXT: [[TMP5:%.*]] = shufflevector <2 x i1> [[TMP4]], <2 x i1> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; AVX-NEXT: [[D21:%.*]] = shufflevector <4 x i1> [[D0]], <4 x i1> [[TMP5]], <4 x i32> <i32 0, i32 4, i32 5, i32 undef>			; AVX-NEXT: [[D21:%.*]] = shufflevector <4 x i1> [[D0]], <4 x i1> [[TMP5]], <4 x i32> <i32 0, i32 4, i32 5, i32 undef>
	; AVX-NEXT: [[D3:%.*]] = insertelement <4 x i1> [[D21]], i1 [[C3]], i32 3			; AVX-NEXT: [[D3:%.*]] = insertelement <4 x i1> [[D21]], i1 [[C3]], i32 3
	; AVX-NEXT: [[R:%.*]] = sext <4 x i1> [[D3]] to <4 x i32>			; AVX-NEXT: [[R:%.*]] = sext <4 x i1> [[D3]] to <4 x i32>
	; AVX-NEXT: ret <4 x i32> [[R]]			; AVX-NEXT: ret <4 x i32> [[R]]
	;			;
	%a0 = extractelement <4 x float> %a, i32 0			%a0 = extractelement <4 x float> %a, i32 0
	%a1 = extractelement <4 x float> %a, i32 1			%a1 = extractelement <4 x float> %a, i32 1
	%a2 = extractelement <4 x float> %a, i32 2			%a2 = extractelement <4 x float> %a, i32 2
	Show All 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/cmp_commute.ll

	Show First 20 Lines • Show All 266 Lines • ▼ Show 20 Lines
	; AVX-NEXT: [[TMP1:%.]] = bitcast float [[P1]] to <2 x float>*			; AVX-NEXT: [[TMP1:%.]] = bitcast float [[P1]] to <2 x float>*
	; AVX-NEXT: [[TMP2:%.]] = load <2 x float>, <2 x float> [[TMP1]], align 4			; AVX-NEXT: [[TMP2:%.]] = load <2 x float>, <2 x float> [[TMP1]], align 4
	; AVX-NEXT: [[B3:%.]] = load float, float [[P3]], align 4			; AVX-NEXT: [[B3:%.]] = load float, float [[P3]], align 4
	; AVX-NEXT: [[C0:%.*]] = fcmp ord float [[A0]], [[B0]]			; AVX-NEXT: [[C0:%.*]] = fcmp ord float [[A0]], [[B0]]
	; AVX-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[A]], <4 x float> undef, <2 x i32> <i32 1, i32 2>			; AVX-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[A]], <4 x float> undef, <2 x i32> <i32 1, i32 2>
	; AVX-NEXT: [[TMP4:%.*]] = fcmp uno <2 x float> [[TMP2]], [[TMP3]]			; AVX-NEXT: [[TMP4:%.*]] = fcmp uno <2 x float> [[TMP2]], [[TMP3]]
	; AVX-NEXT: [[C3:%.*]] = fcmp ord float [[A3]], [[B3]]			; AVX-NEXT: [[C3:%.*]] = fcmp ord float [[A3]], [[B3]]
	; AVX-NEXT: [[D0:%.*]] = insertelement <4 x i1> undef, i1 [[C0]], i32 0			; AVX-NEXT: [[D0:%.*]] = insertelement <4 x i1> undef, i1 [[C0]], i32 0
	; AVX-NEXT: [[TMP5:%.*]] = shufflevector <2 x i1> [[TMP4]], <2 x i1> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; AVX-NEXT: [[TMP5:%.*]] = shufflevector <2 x i1> [[TMP4]], <2 x i1> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; AVX-NEXT: [[D21:%.*]] = shufflevector <4 x i1> [[D0]], <4 x i1> [[TMP5]], <4 x i32> <i32 0, i32 4, i32 5, i32 undef>			; AVX-NEXT: [[D21:%.*]] = shufflevector <4 x i1> [[D0]], <4 x i1> [[TMP5]], <4 x i32> <i32 0, i32 4, i32 5, i32 undef>
	; AVX-NEXT: [[D3:%.*]] = insertelement <4 x i1> [[D21]], i1 [[C3]], i32 3			; AVX-NEXT: [[D3:%.*]] = insertelement <4 x i1> [[D21]], i1 [[C3]], i32 3
	; AVX-NEXT: [[R:%.*]] = sext <4 x i1> [[D3]] to <4 x i32>			; AVX-NEXT: [[R:%.*]] = sext <4 x i1> [[D3]] to <4 x i32>
	; AVX-NEXT: ret <4 x i32> [[R]]			; AVX-NEXT: ret <4 x i32> [[R]]
	;			;
	%a0 = extractelement <4 x float> %a, i32 0			%a0 = extractelement <4 x float> %a, i32 0
	%a1 = extractelement <4 x float> %a, i32 1			%a1 = extractelement <4 x float> %a, i32 1
	%a2 = extractelement <4 x float> %a, i32 2			%a2 = extractelement <4 x float> %a, i32 2
	Show All 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll

	Show First 20 Lines • Show All 295 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x float> poison, float [[B0]], i32 0			; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x float> poison, float [[B0]], i32 0
	; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x float> [[TMP9]], float [[B1]], i32 1			; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x float> [[TMP9]], float [[B1]], i32 1
	; CHECK-NEXT: [[TMP11:%.*]] = select <2 x i1> [[TMP3]], <2 x float> [[TMP8]], <2 x float> [[TMP10]]			; CHECK-NEXT: [[TMP11:%.*]] = select <2 x i1> [[TMP3]], <2 x float> [[TMP8]], <2 x float> [[TMP10]]
	; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x float> poison, float [[A2]], i32 0			; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x float> poison, float [[A2]], i32 0
	; CHECK-NEXT: [[TMP13:%.*]] = insertelement <2 x float> [[TMP12]], float [[A3]], i32 1			; CHECK-NEXT: [[TMP13:%.*]] = insertelement <2 x float> [[TMP12]], float [[A3]], i32 1
	; CHECK-NEXT: [[TMP14:%.*]] = insertelement <2 x float> poison, float [[B2]], i32 0			; CHECK-NEXT: [[TMP14:%.*]] = insertelement <2 x float> poison, float [[B2]], i32 0
	; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP14]], float [[B3]], i32 1			; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP14]], float [[B3]], i32 1
	; CHECK-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP6]], <2 x float> [[TMP13]], <2 x float> [[TMP15]]			; CHECK-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP6]], <2 x float> [[TMP13]], <2 x float> [[TMP15]]
	; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[RB2:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP17]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>			; CHECK-NEXT: [[RB2:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP17]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
	; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[RD1:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP18]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; CHECK-NEXT: [[RD1:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP18]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; CHECK-NEXT: ret <4 x float> [[RD1]]			; CHECK-NEXT: ret <4 x float> [[RD1]]
	;			;
	%c0 = extractelement <4 x i32> %c, i32 0			%c0 = extractelement <4 x i32> %c, i32 0
	%c1 = extractelement <4 x i32> %c, i32 1			%c1 = extractelement <4 x i32> %c, i32 1
	%c2 = extractelement <4 x i32> %c, i32 2			%c2 = extractelement <4 x i32> %c, i32 2
	%c3 = extractelement <4 x i32> %c, i32 3			%c3 = extractelement <4 x i32> %c, i32 3
	%a0 = extractelement <4 x float> %a, i32 0			%a0 = extractelement <4 x float> %a, i32 0
	▲ Show 20 Lines • Show All 321 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll

Show All 37 Lines	;
%rd = insertelement <4 x float> %rc, float %s3, i32 3		%rd = insertelement <4 x float> %rc, float %s3, i32 3
ret <4 x float> %rd		ret <4 x float> %rd
}		}

define <8 x float> @simple_select2(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {		define <8 x float> @simple_select2(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
; CHECK-LABEL: @simple_select2(		; CHECK-LABEL: @simple_select2(
; CHECK-NEXT: [[TMP1:%.]] = icmp ne <4 x i32> [[C:%.]], zeroinitializer		; CHECK-NEXT: [[TMP1:%.]] = icmp ne <4 x i32> [[C:%.]], zeroinitializer
; CHECK-NEXT: [[TMP2:%.]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.]], <4 x float> [[B:%.*]]		; CHECK-NEXT: [[TMP2:%.]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.]], <4 x float> [[B:%.*]]
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[TMP2]], <4 x float> undef, <8 x i32> <i32 0, i32 undef, i32 1, i32 undef, i32 2, i32 undef, i32 undef, i32 3>		; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[TMP2]], <4 x float> poison, <8 x i32> <i32 0, i32 undef, i32 1, i32 undef, i32 2, i32 undef, i32 undef, i32 3>
; CHECK-NEXT: [[RD1:%.*]] = shufflevector <8 x float> undef, <8 x float> [[TMP3]], <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 12, i32 5, i32 6, i32 15>		; CHECK-NEXT: [[RD1:%.*]] = shufflevector <8 x float> undef, <8 x float> [[TMP3]], <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 12, i32 5, i32 6, i32 15>
; CHECK-NEXT: ret <8 x float> [[RD1]]		; CHECK-NEXT: ret <8 x float> [[RD1]]
;		;
%c0 = extractelement <4 x i32> %c, i32 0		%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1		%c1 = extractelement <4 x i32> %c, i32 1
%c2 = extractelement <4 x i32> %c, i32 2		%c2 = extractelement <4 x i32> %c, i32 2
%c3 = extractelement <4 x i32> %c, i32 3		%c3 = extractelement <4 x i32> %c, i32 3
%a0 = extractelement <4 x float> %a, i32 0		%a0 = extractelement <4 x float> %a, i32 0
▲ Show 20 Lines • Show All 276 Lines • ▼ Show 20 Lines
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x float> poison, float [[B0]], i32 0		; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x float> poison, float [[B0]], i32 0
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x float> [[TMP9]], float [[B1]], i32 1		; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x float> [[TMP9]], float [[B1]], i32 1
; CHECK-NEXT: [[TMP11:%.*]] = select <2 x i1> [[TMP3]], <2 x float> [[TMP8]], <2 x float> [[TMP10]]		; CHECK-NEXT: [[TMP11:%.*]] = select <2 x i1> [[TMP3]], <2 x float> [[TMP8]], <2 x float> [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x float> poison, float [[A2]], i32 0		; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x float> poison, float [[A2]], i32 0
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <2 x float> [[TMP12]], float [[A3]], i32 1		; CHECK-NEXT: [[TMP13:%.*]] = insertelement <2 x float> [[TMP12]], float [[A3]], i32 1
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <2 x float> poison, float [[B2]], i32 0		; CHECK-NEXT: [[TMP14:%.*]] = insertelement <2 x float> poison, float [[B2]], i32 0
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP14]], float [[B3]], i32 1		; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP14]], float [[B3]], i32 1
; CHECK-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP6]], <2 x float> [[TMP13]], <2 x float> [[TMP15]]		; CHECK-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP6]], <2 x float> [[TMP13]], <2 x float> [[TMP15]]
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>		; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[RB2:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP17]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>		; CHECK-NEXT: [[RB2:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP17]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>		; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x float> [[TMP16]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[RD1:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP18]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>		; CHECK-NEXT: [[RD1:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP18]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: ret <4 x float> [[RD1]]		; CHECK-NEXT: ret <4 x float> [[RD1]]
;		;
%c0 = extractelement <4 x i32> %c, i32 0		%c0 = extractelement <4 x i32> %c, i32 0
%c1 = extractelement <4 x i32> %c, i32 1		%c1 = extractelement <4 x i32> %c, i32 1
%c2 = extractelement <4 x i32> %c, i32 2		%c2 = extractelement <4 x i32> %c, i32 2
%c3 = extractelement <4 x i32> %c, i32 3		%c3 = extractelement <4 x i32> %c, i32 3
%a0 = extractelement <4 x float> %a, i32 0		%a0 = extractelement <4 x float> %a, i32 0
▲ Show 20 Lines • Show All 321 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/load-merge-inseltpoison.ll

	Show First 20 Lines • Show All 51 Lines • ▼ Show 20 Lines
	define <4 x float> @PR16739_byref(<4 x float>* nocapture readonly dereferenceable(16) %x) {			define <4 x float> @PR16739_byref(<4 x float>* nocapture readonly dereferenceable(16) %x) {
	; CHECK-LABEL: @PR16739_byref(			; CHECK-LABEL: @PR16739_byref(
	; CHECK-NEXT: [[GEP0:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X:%.*]], i64 0, i64 0			; CHECK-NEXT: [[GEP0:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X:%.*]], i64 0, i64 0
	; CHECK-NEXT: [[GEP1:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X]], i64 0, i64 1			; CHECK-NEXT: [[GEP1:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X]], i64 0, i64 1
	; CHECK-NEXT: [[GEP2:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X]], i64 0, i64 2			; CHECK-NEXT: [[GEP2:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X]], i64 0, i64 2
	; CHECK-NEXT: [[TMP1:%.]] = bitcast float [[GEP0]] to <2 x float>*			; CHECK-NEXT: [[TMP1:%.]] = bitcast float [[GEP0]] to <2 x float>*
	; CHECK-NEXT: [[TMP2:%.]] = load <2 x float>, <2 x float> [[TMP1]], align 4			; CHECK-NEXT: [[TMP2:%.]] = load <2 x float>, <2 x float> [[TMP1]], align 4
	; CHECK-NEXT: [[X2:%.]] = load float, float [[GEP2]], align 4			; CHECK-NEXT: [[X2:%.]] = load float, float [[GEP2]], align 4
	; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[I11:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP3]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>			; CHECK-NEXT: [[I11:%.*]] = shufflevector <4 x float> poison, <4 x float> [[TMP3]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
	; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x float> [[I11]], float [[X2]], i32 2			; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x float> [[I11]], float [[X2]], i32 2
	; CHECK-NEXT: [[I3:%.*]] = insertelement <4 x float> [[I2]], float [[X2]], i32 3			; CHECK-NEXT: [[I3:%.*]] = insertelement <4 x float> [[I2]], float [[X2]], i32 3
	; CHECK-NEXT: ret <4 x float> [[I3]]			; CHECK-NEXT: ret <4 x float> [[I3]]
	;			;
	%gep0 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 0			%gep0 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 0
	%gep1 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 1			%gep1 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 1
	%gep2 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 2			%gep2 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 2
	▲ Show 20 Lines • Show All 132 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll

	Show First 20 Lines • Show All 51 Lines • ▼ Show 20 Lines
	define <4 x float> @PR16739_byref(<4 x float>* nocapture readonly dereferenceable(16) %x) {			define <4 x float> @PR16739_byref(<4 x float>* nocapture readonly dereferenceable(16) %x) {
	; CHECK-LABEL: @PR16739_byref(			; CHECK-LABEL: @PR16739_byref(
	; CHECK-NEXT: [[GEP0:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X:%.*]], i64 0, i64 0			; CHECK-NEXT: [[GEP0:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X:%.*]], i64 0, i64 0
	; CHECK-NEXT: [[GEP1:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X]], i64 0, i64 1			; CHECK-NEXT: [[GEP1:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X]], i64 0, i64 1
	; CHECK-NEXT: [[GEP2:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X]], i64 0, i64 2			; CHECK-NEXT: [[GEP2:%.]] = getelementptr inbounds <4 x float>, <4 x float> [[X]], i64 0, i64 2
	; CHECK-NEXT: [[TMP1:%.]] = bitcast float [[GEP0]] to <2 x float>*			; CHECK-NEXT: [[TMP1:%.]] = bitcast float [[GEP0]] to <2 x float>*
	; CHECK-NEXT: [[TMP2:%.]] = load <2 x float>, <2 x float> [[TMP1]], align 4			; CHECK-NEXT: [[TMP2:%.]] = load <2 x float>, <2 x float> [[TMP1]], align 4
	; CHECK-NEXT: [[X2:%.]] = load float, float [[GEP2]], align 4			; CHECK-NEXT: [[X2:%.]] = load float, float [[GEP2]], align 4
	; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[I11:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP3]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>			; CHECK-NEXT: [[I11:%.*]] = shufflevector <4 x float> undef, <4 x float> [[TMP3]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
	; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x float> [[I11]], float [[X2]], i32 2			; CHECK-NEXT: [[I2:%.*]] = insertelement <4 x float> [[I11]], float [[X2]], i32 2
	; CHECK-NEXT: [[I3:%.*]] = insertelement <4 x float> [[I2]], float [[X2]], i32 3			; CHECK-NEXT: [[I3:%.*]] = insertelement <4 x float> [[I2]], float [[X2]], i32 3
	; CHECK-NEXT: ret <4 x float> [[I3]]			; CHECK-NEXT: ret <4 x float> [[I3]]
	;			;
	%gep0 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 0			%gep0 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 0
	%gep1 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 1			%gep1 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 1
	%gep2 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 2			%gep2 = getelementptr inbounds <4 x float>, <4 x float>* %x, i64 0, i64 2
	▲ Show 20 Lines • Show All 132 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/phi.ll

	Show First 20 Lines • Show All 160 Lines • ▼ Show 20 Lines
	; CHECK-NEXT: [[TMP10:%.]] = load float, float [[ARRAYIDX14]], align 4			; CHECK-NEXT: [[TMP10:%.]] = load float, float [[ARRAYIDX14]], align 4
	; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 3			; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 3
	; CHECK-NEXT: [[ARRAYIDX19:%.]] = getelementptr inbounds float, float [[A]], i64 [[INDVARS_IV_NEXT]]			; CHECK-NEXT: [[ARRAYIDX19:%.]] = getelementptr inbounds float, float [[A]], i64 [[INDVARS_IV_NEXT]]
	; CHECK-NEXT: [[TMP11:%.]] = bitcast float [[ARRAYIDX19]] to <2 x float>*			; CHECK-NEXT: [[TMP11:%.]] = bitcast float [[ARRAYIDX19]] to <2 x float>*
	; CHECK-NEXT: [[TMP12]] = load <2 x float>, <2 x float>* [[TMP11]], align 4			; CHECK-NEXT: [[TMP12]] = load <2 x float>, <2 x float>* [[TMP11]], align 4
	; CHECK-NEXT: [[TMP13:%.*]] = extractelement <2 x float> [[TMP7]], i32 1			; CHECK-NEXT: [[TMP13:%.*]] = extractelement <2 x float> [[TMP7]], i32 1
	; CHECK-NEXT: [[TMP14:%.*]] = insertelement <4 x float> poison, float [[TMP13]], i32 0			; CHECK-NEXT: [[TMP14:%.*]] = insertelement <4 x float> poison, float [[TMP13]], i32 0
	; CHECK-NEXT: [[TMP15:%.*]] = insertelement <4 x float> [[TMP14]], float [[TMP10]], i32 1			; CHECK-NEXT: [[TMP15:%.*]] = insertelement <4 x float> [[TMP14]], float [[TMP10]], i32 1
	; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <2 x float> [[TMP12]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <2 x float> [[TMP12]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <4 x float> [[TMP15]], <4 x float> [[TMP16]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <4 x float> [[TMP15]], <4 x float> [[TMP16]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; CHECK-NEXT: [[TMP18:%.*]] = fmul <4 x float> [[TMP17]], <float 8.000000e+00, float 9.000000e+00, float 1.000000e+01, float 1.100000e+01>			; CHECK-NEXT: [[TMP18:%.*]] = fmul <4 x float> [[TMP17]], <float 8.000000e+00, float 9.000000e+00, float 1.000000e+01, float 1.100000e+01>
	; CHECK-NEXT: [[TMP19]] = fadd <4 x float> [[TMP6]], [[TMP18]]			; CHECK-NEXT: [[TMP19]] = fadd <4 x float> [[TMP6]], [[TMP18]]
	; CHECK-NEXT: [[TMP20:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32			; CHECK-NEXT: [[TMP20:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
	; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP20]], 121			; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP20]], 121
	; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]			; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]]
	; CHECK: for.end:			; CHECK: for.end:
	; CHECK-NEXT: [[TMP21:%.*]] = extractelement <4 x float> [[TMP19]], i32 0			; CHECK-NEXT: [[TMP21:%.*]] = extractelement <4 x float> [[TMP19]], i32 0
	▲ Show 20 Lines • Show All 163 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/pr47629-inseltpoison.ll

	Show First 20 Lines • Show All 529 Lines • ▼ Show 20 Lines
	; AVX-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10			; AVX-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10
	; AVX-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0			; AVX-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0
	; AVX-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer			; AVX-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer
	; AVX-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>			; AVX-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>
	; AVX-NEXT: [[TMP7:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 17, i64 8>			; AVX-NEXT: [[TMP7:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 17, i64 8>
	; AVX-NEXT: [[TMP8:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 5, i64 20>			; AVX-NEXT: [[TMP8:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 5, i64 20>
	; AVX-NEXT: [[TMP9:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0			; AVX-NEXT: [[TMP9:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0
	; AVX-NEXT: [[TMP10:%.]] = insertelement <8 x float> [[TMP9]], float* [[TMP3]], i32 1			; AVX-NEXT: [[TMP10:%.]] = insertelement <8 x float> [[TMP9]], float* [[TMP3]], i32 1
	; AVX-NEXT: [[TMP11:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP11:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP12:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> [[TMP11]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP12:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> [[TMP11]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP13:%.]] = shufflevector <2 x float> [[TMP7]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP13:%.]] = shufflevector <2 x float> [[TMP7]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP14:%.]] = shufflevector <8 x float> [[TMP12]], <8 x float*> [[TMP13]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>			; AVX-NEXT: [[TMP14:%.]] = shufflevector <8 x float> [[TMP12]], <8 x float*> [[TMP13]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP15:%.]] = shufflevector <2 x float> [[TMP8]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP15:%.]] = shufflevector <2 x float> [[TMP8]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP16:%.]] = shufflevector <8 x float> [[TMP14]], <8 x float*> [[TMP15]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; AVX-NEXT: [[TMP16:%.]] = shufflevector <8 x float> [[TMP14]], <8 x float*> [[TMP15]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; AVX-NEXT: [[TMP17:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP16]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX-NEXT: [[TMP17:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP16]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX-NEXT: [[TMP18:%.]] = shufflevector <8 x float> [[TMP9]], <8 x float*> poison, <8 x i32> zeroinitializer			; AVX-NEXT: [[TMP18:%.]] = shufflevector <8 x float> [[TMP9]], <8 x float*> poison, <8 x i32> zeroinitializer
	; AVX-NEXT: [[TMP19:%.]] = getelementptr float, <8 x float> [[TMP18]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>			; AVX-NEXT: [[TMP19:%.]] = getelementptr float, <8 x float> [[TMP18]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
	; AVX-NEXT: [[TMP20:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP19]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX-NEXT: [[TMP20:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP19]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX-NEXT: [[TMP21:%.*]] = fdiv <8 x float> [[TMP17]], [[TMP20]]			; AVX-NEXT: [[TMP21:%.*]] = fdiv <8 x float> [[TMP17]], [[TMP20]]
	; AVX-NEXT: [[TMP22:%.]] = bitcast float [[TMP0:%.]] to <8 x float>			; AVX-NEXT: [[TMP22:%.]] = bitcast float [[TMP0:%.]] to <8 x float>
	; AVX-NEXT: store <8 x float> [[TMP21]], <8 x float>* [[TMP22]], align 4, !tbaa [[TBAA0]]			; AVX-NEXT: store <8 x float> [[TMP21]], <8 x float>* [[TMP22]], align 4, !tbaa [[TBAA0]]
	; AVX-NEXT: ret void			; AVX-NEXT: ret void
	;			;
	; AVX2-LABEL: @gather_load_div(			; AVX2-LABEL: @gather_load_div(
	; AVX2-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10			; AVX2-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10
	; AVX2-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0			; AVX2-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0
	; AVX2-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer			; AVX2-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer
	; AVX2-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>			; AVX2-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>
	; AVX2-NEXT: [[TMP7:%.]] = insertelement <4 x float> poison, float* [[TMP1]], i32 0			; AVX2-NEXT: [[TMP7:%.]] = insertelement <4 x float> poison, float* [[TMP1]], i32 0
	; AVX2-NEXT: [[TMP8:%.]] = shufflevector <4 x float> [[TMP7]], <4 x float*> poison, <4 x i32> zeroinitializer			; AVX2-NEXT: [[TMP8:%.]] = shufflevector <4 x float> [[TMP7]], <4 x float*> poison, <4 x i32> zeroinitializer
	; AVX2-NEXT: [[TMP9:%.]] = getelementptr float, <4 x float> [[TMP8]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>			; AVX2-NEXT: [[TMP9:%.]] = getelementptr float, <4 x float> [[TMP8]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>
	; AVX2-NEXT: [[TMP10:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0			; AVX2-NEXT: [[TMP10:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0
	; AVX2-NEXT: [[TMP11:%.]] = insertelement <8 x float> [[TMP10]], float* [[TMP3]], i32 1			; AVX2-NEXT: [[TMP11:%.]] = insertelement <8 x float> [[TMP10]], float* [[TMP3]], i32 1
	; AVX2-NEXT: [[TMP12:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX2-NEXT: [[TMP12:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX2-NEXT: [[TMP13:%.]] = shufflevector <8 x float> [[TMP11]], <8 x float*> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX2-NEXT: [[TMP13:%.]] = shufflevector <8 x float> [[TMP11]], <8 x float*> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX2-NEXT: [[TMP14:%.]] = shufflevector <4 x float> [[TMP9]], <4 x float*> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX2-NEXT: [[TMP14:%.]] = shufflevector <4 x float> [[TMP9]], <4 x float*> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX2-NEXT: [[TMP15:%.]] = shufflevector <8 x float> [[TMP13]], <8 x float*> [[TMP14]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>			; AVX2-NEXT: [[TMP15:%.]] = shufflevector <8 x float> [[TMP13]], <8 x float*> [[TMP14]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
	; AVX2-NEXT: [[TMP16:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP15]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX2-NEXT: [[TMP16:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP15]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX2-NEXT: [[TMP17:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> poison, <8 x i32> zeroinitializer			; AVX2-NEXT: [[TMP17:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> poison, <8 x i32> zeroinitializer
	; AVX2-NEXT: [[TMP18:%.]] = getelementptr float, <8 x float> [[TMP17]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>			; AVX2-NEXT: [[TMP18:%.]] = getelementptr float, <8 x float> [[TMP17]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
	; AVX2-NEXT: [[TMP19:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP18]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX2-NEXT: [[TMP19:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP18]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX2-NEXT: [[TMP20:%.*]] = fdiv <8 x float> [[TMP16]], [[TMP19]]			; AVX2-NEXT: [[TMP20:%.*]] = fdiv <8 x float> [[TMP16]], [[TMP19]]
	; AVX2-NEXT: [[TMP21:%.]] = bitcast float [[TMP0:%.]] to <8 x float>			; AVX2-NEXT: [[TMP21:%.]] = bitcast float [[TMP0:%.]] to <8 x float>
	; AVX2-NEXT: store <8 x float> [[TMP20]], <8 x float>* [[TMP21]], align 4, !tbaa [[TBAA0]]			; AVX2-NEXT: store <8 x float> [[TMP20]], <8 x float>* [[TMP21]], align 4, !tbaa [[TBAA0]]
	; AVX2-NEXT: ret void			; AVX2-NEXT: ret void
	;			;
	; AVX512-LABEL: @gather_load_div(			; AVX512-LABEL: @gather_load_div(
	; AVX512-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10			; AVX512-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10
	; AVX512-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0			; AVX512-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0
	; AVX512-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer			; AVX512-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer
	; AVX512-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>			; AVX512-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>
	; AVX512-NEXT: [[TMP7:%.]] = insertelement <4 x float> poison, float* [[TMP1]], i32 0			; AVX512-NEXT: [[TMP7:%.]] = insertelement <4 x float> poison, float* [[TMP1]], i32 0
	; AVX512-NEXT: [[TMP8:%.]] = shufflevector <4 x float> [[TMP7]], <4 x float*> poison, <4 x i32> zeroinitializer			; AVX512-NEXT: [[TMP8:%.]] = shufflevector <4 x float> [[TMP7]], <4 x float*> poison, <4 x i32> zeroinitializer
	; AVX512-NEXT: [[TMP9:%.]] = getelementptr float, <4 x float> [[TMP8]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>			; AVX512-NEXT: [[TMP9:%.]] = getelementptr float, <4 x float> [[TMP8]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>
	; AVX512-NEXT: [[TMP10:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0			; AVX512-NEXT: [[TMP10:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0
	; AVX512-NEXT: [[TMP11:%.]] = insertelement <8 x float> [[TMP10]], float* [[TMP3]], i32 1			; AVX512-NEXT: [[TMP11:%.]] = insertelement <8 x float> [[TMP10]], float* [[TMP3]], i32 1
	; AVX512-NEXT: [[TMP12:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX512-NEXT: [[TMP12:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX512-NEXT: [[TMP13:%.]] = shufflevector <8 x float> [[TMP11]], <8 x float*> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX512-NEXT: [[TMP13:%.]] = shufflevector <8 x float> [[TMP11]], <8 x float*> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX512-NEXT: [[TMP14:%.]] = shufflevector <4 x float> [[TMP9]], <4 x float*> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX512-NEXT: [[TMP14:%.]] = shufflevector <4 x float> [[TMP9]], <4 x float*> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX512-NEXT: [[TMP15:%.]] = shufflevector <8 x float> [[TMP13]], <8 x float*> [[TMP14]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>			; AVX512-NEXT: [[TMP15:%.]] = shufflevector <8 x float> [[TMP13]], <8 x float*> [[TMP14]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
	; AVX512-NEXT: [[TMP16:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP15]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX512-NEXT: [[TMP16:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP15]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX512-NEXT: [[TMP17:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> poison, <8 x i32> zeroinitializer			; AVX512-NEXT: [[TMP17:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> poison, <8 x i32> zeroinitializer
	; AVX512-NEXT: [[TMP18:%.]] = getelementptr float, <8 x float> [[TMP17]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>			; AVX512-NEXT: [[TMP18:%.]] = getelementptr float, <8 x float> [[TMP17]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
	; AVX512-NEXT: [[TMP19:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP18]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX512-NEXT: [[TMP19:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP18]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX512-NEXT: [[TMP20:%.*]] = fdiv <8 x float> [[TMP16]], [[TMP19]]			; AVX512-NEXT: [[TMP20:%.*]] = fdiv <8 x float> [[TMP16]], [[TMP19]]
	; AVX512-NEXT: [[TMP21:%.]] = bitcast float [[TMP0:%.]] to <8 x float>			; AVX512-NEXT: [[TMP21:%.]] = bitcast float [[TMP0:%.]] to <8 x float>
	; AVX512-NEXT: store <8 x float> [[TMP20]], <8 x float>* [[TMP21]], align 4, !tbaa [[TBAA0]]			; AVX512-NEXT: store <8 x float> [[TMP20]], <8 x float>* [[TMP21]], align 4, !tbaa [[TBAA0]]
	▲ Show 20 Lines • Show All 63 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/pr47629.ll

	Show First 20 Lines • Show All 529 Lines • ▼ Show 20 Lines
	; AVX-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10			; AVX-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10
	; AVX-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0			; AVX-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0
	; AVX-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer			; AVX-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer
	; AVX-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>			; AVX-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>
	; AVX-NEXT: [[TMP7:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 17, i64 8>			; AVX-NEXT: [[TMP7:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 17, i64 8>
	; AVX-NEXT: [[TMP8:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 5, i64 20>			; AVX-NEXT: [[TMP8:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 5, i64 20>
	; AVX-NEXT: [[TMP9:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0			; AVX-NEXT: [[TMP9:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0
	; AVX-NEXT: [[TMP10:%.]] = insertelement <8 x float> [[TMP9]], float* [[TMP3]], i32 1			; AVX-NEXT: [[TMP10:%.]] = insertelement <8 x float> [[TMP9]], float* [[TMP3]], i32 1
	; AVX-NEXT: [[TMP11:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP11:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP12:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> [[TMP11]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP12:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> [[TMP11]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP13:%.]] = shufflevector <2 x float> [[TMP7]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP13:%.]] = shufflevector <2 x float> [[TMP7]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP14:%.]] = shufflevector <8 x float> [[TMP12]], <8 x float*> [[TMP13]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>			; AVX-NEXT: [[TMP14:%.]] = shufflevector <8 x float> [[TMP12]], <8 x float*> [[TMP13]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP15:%.]] = shufflevector <2 x float> [[TMP8]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX-NEXT: [[TMP15:%.]] = shufflevector <2 x float> [[TMP8]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX-NEXT: [[TMP16:%.]] = shufflevector <8 x float> [[TMP14]], <8 x float*> [[TMP15]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>			; AVX-NEXT: [[TMP16:%.]] = shufflevector <8 x float> [[TMP14]], <8 x float*> [[TMP15]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
	; AVX-NEXT: [[TMP17:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP16]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX-NEXT: [[TMP17:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP16]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX-NEXT: [[TMP18:%.]] = shufflevector <8 x float> [[TMP9]], <8 x float*> poison, <8 x i32> zeroinitializer			; AVX-NEXT: [[TMP18:%.]] = shufflevector <8 x float> [[TMP9]], <8 x float*> poison, <8 x i32> zeroinitializer
	; AVX-NEXT: [[TMP19:%.]] = getelementptr float, <8 x float> [[TMP18]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>			; AVX-NEXT: [[TMP19:%.]] = getelementptr float, <8 x float> [[TMP18]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
	; AVX-NEXT: [[TMP20:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP19]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX-NEXT: [[TMP20:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP19]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX-NEXT: [[TMP21:%.*]] = fdiv <8 x float> [[TMP17]], [[TMP20]]			; AVX-NEXT: [[TMP21:%.*]] = fdiv <8 x float> [[TMP17]], [[TMP20]]
	; AVX-NEXT: [[TMP22:%.]] = bitcast float [[TMP0:%.]] to <8 x float>			; AVX-NEXT: [[TMP22:%.]] = bitcast float [[TMP0:%.]] to <8 x float>
	; AVX-NEXT: store <8 x float> [[TMP21]], <8 x float>* [[TMP22]], align 4, !tbaa [[TBAA0]]			; AVX-NEXT: store <8 x float> [[TMP21]], <8 x float>* [[TMP22]], align 4, !tbaa [[TBAA0]]
	; AVX-NEXT: ret void			; AVX-NEXT: ret void
	;			;
	; AVX2-LABEL: @gather_load_div(			; AVX2-LABEL: @gather_load_div(
	; AVX2-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10			; AVX2-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10
	; AVX2-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0			; AVX2-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0
	; AVX2-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer			; AVX2-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer
	; AVX2-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>			; AVX2-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>
	; AVX2-NEXT: [[TMP7:%.]] = insertelement <4 x float> poison, float* [[TMP1]], i32 0			; AVX2-NEXT: [[TMP7:%.]] = insertelement <4 x float> poison, float* [[TMP1]], i32 0
	; AVX2-NEXT: [[TMP8:%.]] = shufflevector <4 x float> [[TMP7]], <4 x float*> poison, <4 x i32> zeroinitializer			; AVX2-NEXT: [[TMP8:%.]] = shufflevector <4 x float> [[TMP7]], <4 x float*> poison, <4 x i32> zeroinitializer
	; AVX2-NEXT: [[TMP9:%.]] = getelementptr float, <4 x float> [[TMP8]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>			; AVX2-NEXT: [[TMP9:%.]] = getelementptr float, <4 x float> [[TMP8]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>
	; AVX2-NEXT: [[TMP10:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0			; AVX2-NEXT: [[TMP10:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0
	; AVX2-NEXT: [[TMP11:%.]] = insertelement <8 x float> [[TMP10]], float* [[TMP3]], i32 1			; AVX2-NEXT: [[TMP11:%.]] = insertelement <8 x float> [[TMP10]], float* [[TMP3]], i32 1
	; AVX2-NEXT: [[TMP12:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX2-NEXT: [[TMP12:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX2-NEXT: [[TMP13:%.]] = shufflevector <8 x float> [[TMP11]], <8 x float*> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX2-NEXT: [[TMP13:%.]] = shufflevector <8 x float> [[TMP11]], <8 x float*> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX2-NEXT: [[TMP14:%.]] = shufflevector <4 x float> [[TMP9]], <4 x float*> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX2-NEXT: [[TMP14:%.]] = shufflevector <4 x float> [[TMP9]], <4 x float*> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX2-NEXT: [[TMP15:%.]] = shufflevector <8 x float> [[TMP13]], <8 x float*> [[TMP14]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>			; AVX2-NEXT: [[TMP15:%.]] = shufflevector <8 x float> [[TMP13]], <8 x float*> [[TMP14]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
	; AVX2-NEXT: [[TMP16:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP15]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX2-NEXT: [[TMP16:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP15]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX2-NEXT: [[TMP17:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> poison, <8 x i32> zeroinitializer			; AVX2-NEXT: [[TMP17:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> poison, <8 x i32> zeroinitializer
	; AVX2-NEXT: [[TMP18:%.]] = getelementptr float, <8 x float> [[TMP17]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>			; AVX2-NEXT: [[TMP18:%.]] = getelementptr float, <8 x float> [[TMP17]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
	; AVX2-NEXT: [[TMP19:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP18]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX2-NEXT: [[TMP19:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP18]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX2-NEXT: [[TMP20:%.*]] = fdiv <8 x float> [[TMP16]], [[TMP19]]			; AVX2-NEXT: [[TMP20:%.*]] = fdiv <8 x float> [[TMP16]], [[TMP19]]
	; AVX2-NEXT: [[TMP21:%.]] = bitcast float [[TMP0:%.]] to <8 x float>			; AVX2-NEXT: [[TMP21:%.]] = bitcast float [[TMP0:%.]] to <8 x float>
	; AVX2-NEXT: store <8 x float> [[TMP20]], <8 x float>* [[TMP21]], align 4, !tbaa [[TBAA0]]			; AVX2-NEXT: store <8 x float> [[TMP20]], <8 x float>* [[TMP21]], align 4, !tbaa [[TBAA0]]
	; AVX2-NEXT: ret void			; AVX2-NEXT: ret void
	;			;
	; AVX512-LABEL: @gather_load_div(			; AVX512-LABEL: @gather_load_div(
	; AVX512-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10			; AVX512-NEXT: [[TMP3:%.]] = getelementptr inbounds float, float [[TMP1:%.*]], i64 10
	; AVX512-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0			; AVX512-NEXT: [[TMP4:%.]] = insertelement <2 x float> poison, float* [[TMP1]], i32 0
	; AVX512-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer			; AVX512-NEXT: [[TMP5:%.]] = shufflevector <2 x float> [[TMP4]], <2 x float*> poison, <2 x i32> zeroinitializer
	; AVX512-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>			; AVX512-NEXT: [[TMP6:%.]] = getelementptr float, <2 x float> [[TMP5]], <2 x i64> <i64 3, i64 14>
	; AVX512-NEXT: [[TMP7:%.]] = insertelement <4 x float> poison, float* [[TMP1]], i32 0			; AVX512-NEXT: [[TMP7:%.]] = insertelement <4 x float> poison, float* [[TMP1]], i32 0
	; AVX512-NEXT: [[TMP8:%.]] = shufflevector <4 x float> [[TMP7]], <4 x float*> poison, <4 x i32> zeroinitializer			; AVX512-NEXT: [[TMP8:%.]] = shufflevector <4 x float> [[TMP7]], <4 x float*> poison, <4 x i32> zeroinitializer
	; AVX512-NEXT: [[TMP9:%.]] = getelementptr float, <4 x float> [[TMP8]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>			; AVX512-NEXT: [[TMP9:%.]] = getelementptr float, <4 x float> [[TMP8]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>
	; AVX512-NEXT: [[TMP10:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0			; AVX512-NEXT: [[TMP10:%.]] = insertelement <8 x float> poison, float* [[TMP1]], i32 0
	; AVX512-NEXT: [[TMP11:%.]] = insertelement <8 x float> [[TMP10]], float* [[TMP3]], i32 1			; AVX512-NEXT: [[TMP11:%.]] = insertelement <8 x float> [[TMP10]], float* [[TMP3]], i32 1
	; AVX512-NEXT: [[TMP12:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX512-NEXT: [[TMP12:%.]] = shufflevector <2 x float> [[TMP6]], <2 x float*> poison, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX512-NEXT: [[TMP13:%.]] = shufflevector <8 x float> [[TMP11]], <8 x float*> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX512-NEXT: [[TMP13:%.]] = shufflevector <8 x float> [[TMP11]], <8 x float*> [[TMP12]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX512-NEXT: [[TMP14:%.]] = shufflevector <4 x float> [[TMP9]], <4 x float*> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>			; AVX512-NEXT: [[TMP14:%.]] = shufflevector <4 x float> [[TMP9]], <4 x float*> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
	; AVX512-NEXT: [[TMP15:%.]] = shufflevector <8 x float> [[TMP13]], <8 x float*> [[TMP14]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>			; AVX512-NEXT: [[TMP15:%.]] = shufflevector <8 x float> [[TMP13]], <8 x float*> [[TMP14]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
	; AVX512-NEXT: [[TMP16:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP15]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX512-NEXT: [[TMP16:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP15]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX512-NEXT: [[TMP17:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> poison, <8 x i32> zeroinitializer			; AVX512-NEXT: [[TMP17:%.]] = shufflevector <8 x float> [[TMP10]], <8 x float*> poison, <8 x i32> zeroinitializer
	; AVX512-NEXT: [[TMP18:%.]] = getelementptr float, <8 x float> [[TMP17]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>			; AVX512-NEXT: [[TMP18:%.]] = getelementptr float, <8 x float> [[TMP17]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
	; AVX512-NEXT: [[TMP19:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP18]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]			; AVX512-NEXT: [[TMP19:%.]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float> [[TMP18]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), !tbaa [[TBAA0]]
	; AVX512-NEXT: [[TMP20:%.*]] = fdiv <8 x float> [[TMP16]], [[TMP19]]			; AVX512-NEXT: [[TMP20:%.*]] = fdiv <8 x float> [[TMP16]], [[TMP19]]
	; AVX512-NEXT: [[TMP21:%.]] = bitcast float [[TMP0:%.]] to <8 x float>			; AVX512-NEXT: [[TMP21:%.]] = bitcast float [[TMP0:%.]] to <8 x float>
	; AVX512-NEXT: store <8 x float> [[TMP20]], <8 x float>* [[TMP21]], align 4, !tbaa [[TBAA0]]			; AVX512-NEXT: store <8 x float> [[TMP20]], <8 x float>* [[TMP21]], align 4, !tbaa [[TBAA0]]
	▲ Show 20 Lines • Show All 63 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/pr49081.ll

	; NOTE: Assertions have been autogenerated by utils/update_test_checks.py			; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
	; RUN: opt -slp-vectorizer -instcombine -S < %s \| FileCheck %s			; RUN: opt -slp-vectorizer -instcombine -S < %s \| FileCheck %s
	; These conversions should be vectorized by reviews.llvm.org/D57059			; These conversions should be vectorized by reviews.llvm.org/D57059

	define dso_local <4 x float> @foo(<4 x i32> %0) {			define dso_local <4 x float> @foo(<4 x i32> %0) {
	; CHECK-LABEL: @foo(			; CHECK-LABEL: @foo(
	; CHECK-NEXT: [[TMP2:%.]] = extractelement <4 x i32> [[TMP0:%.]], i32 1			; CHECK-NEXT: [[TMP2:%.]] = extractelement <4 x i32> [[TMP0:%.]], i32 1
	; CHECK-NEXT: [[TMP3:%.*]] = sitofp i32 [[TMP2]] to float			; CHECK-NEXT: [[TMP3:%.*]] = sitofp i32 [[TMP2]] to float
	; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0			; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
	; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x float> [[TMP4]], <4 x float> poison, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x float> [[TMP4]], <4 x float> poison, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> undef, <2 x i32> <i32 2, i32 3>			; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> undef, <2 x i32> <i32 2, i32 3>
	; CHECK-NEXT: [[TMP7:%.*]] = sitofp <2 x i32> [[TMP6]] to <2 x float>			; CHECK-NEXT: [[TMP7:%.*]] = sitofp <2 x i32> [[TMP6]] to <2 x float>
	; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP7]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP7]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <4 x float> [[TMP5]], <4 x float> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <4 x float> [[TMP5]], <4 x float> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; CHECK-NEXT: ret <4 x float> [[TMP9]]			; CHECK-NEXT: ret <4 x float> [[TMP9]]
	;			;
	%2 = extractelement <4 x i32> %0, i32 1			%2 = extractelement <4 x i32> %0, i32 1
	%3 = sitofp i32 %2 to float			%3 = sitofp i32 %2 to float
	%4 = insertelement <4 x float> undef, float %3, i32 0			%4 = insertelement <4 x float> undef, float %3, i32 0
	%5 = insertelement <4 x float> %4, float %3, i32 1			%5 = insertelement <4 x float> %4, float %3, i32 1
	%6 = extractelement <4 x i32> %0, i32 2			%6 = extractelement <4 x i32> %0, i32 2
	%7 = sitofp i32 %6 to float			%7 = sitofp i32 %6 to float
	%8 = insertelement <4 x float> %5, float %7, i32 2			%8 = insertelement <4 x float> %5, float %7, i32 2
	%9 = extractelement <4 x i32> %0, i32 3			%9 = extractelement <4 x i32> %0, i32 3
	%10 = sitofp i32 %9 to float			%10 = sitofp i32 %9 to float
	%11 = insertelement <4 x float> %8, float %10, i32 3			%11 = insertelement <4 x float> %8, float %10, i32 3
	ret <4 x float> %11			ret <4 x float> %11
	}			}

llvm/test/Transforms/SLPVectorizer/X86/resched.ll

	Show All 34 Lines
	; CHECK-NEXT: [[ARRAYIDX_I_I7_11_I_I:%.]] = getelementptr inbounds %"struct.std::array", %"struct.std::array" undef, i64 0, i32 0, i64 11			; CHECK-NEXT: [[ARRAYIDX_I_I7_11_I_I:%.]] = getelementptr inbounds %"struct.std::array", %"struct.std::array" undef, i64 0, i32 0, i64 11
	; CHECK-NEXT: [[ARRAYIDX_I_I7_12_I_I:%.]] = getelementptr inbounds %"struct.std::array", %"struct.std::array" undef, i64 0, i32 0, i64 12			; CHECK-NEXT: [[ARRAYIDX_I_I7_12_I_I:%.]] = getelementptr inbounds %"struct.std::array", %"struct.std::array" undef, i64 0, i32 0, i64 12
	; CHECK-NEXT: [[ARRAYIDX_I_I7_13_I_I:%.]] = getelementptr inbounds %"struct.std::array", %"struct.std::array" undef, i64 0, i32 0, i64 13			; CHECK-NEXT: [[ARRAYIDX_I_I7_13_I_I:%.]] = getelementptr inbounds %"struct.std::array", %"struct.std::array" undef, i64 0, i32 0, i64 13
	; CHECK-NEXT: [[ARRAYIDX_I_I7_14_I_I:%.]] = getelementptr inbounds %"struct.std::array", %"struct.std::array" undef, i64 0, i32 0, i64 14			; CHECK-NEXT: [[ARRAYIDX_I_I7_14_I_I:%.]] = getelementptr inbounds %"struct.std::array", %"struct.std::array" undef, i64 0, i32 0, i64 14
	; CHECK-NEXT: [[TMP10:%.*]] = lshr <4 x i32> [[TMP7]], <i32 12, i32 13, i32 14, i32 15>			; CHECK-NEXT: [[TMP10:%.*]] = lshr <4 x i32> [[TMP7]], <i32 12, i32 13, i32 14, i32 15>
	; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i32> [[TMP10]], i32 3			; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i32> [[TMP10]], i32 3
	; CHECK-NEXT: [[TMP12:%.*]] = insertelement <16 x i32> poison, i32 [[SUB_I]], i32 0			; CHECK-NEXT: [[TMP12:%.*]] = insertelement <16 x i32> poison, i32 [[SUB_I]], i32 0
	; CHECK-NEXT: [[TMP13:%.*]] = insertelement <16 x i32> [[TMP12]], i32 [[SHR_I_I]], i32 1			; CHECK-NEXT: [[TMP13:%.*]] = insertelement <16 x i32> [[TMP12]], i32 [[SHR_I_I]], i32 1
	; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> undef, <16 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> poison, <16 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <16 x i32> [[TMP13]], <16 x i32> [[TMP14]], <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>			; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <16 x i32> [[TMP13]], <16 x i32> [[TMP14]], <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
	; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <4 x i32> [[TMP8]], <4 x i32> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <4 x i32> [[TMP8]], <4 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <16 x i32> [[TMP15]], <16 x i32> [[TMP16]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>			; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <16 x i32> [[TMP15]], <16 x i32> [[TMP16]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
	; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <4 x i32> [[TMP9]], <4 x i32> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <4 x i32> [[TMP9]], <4 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <16 x i32> [[TMP17]], <16 x i32> [[TMP18]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>			; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <16 x i32> [[TMP17]], <16 x i32> [[TMP18]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
	; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <4 x i32> [[TMP10]], <4 x i32> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>			; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <4 x i32> [[TMP10]], <4 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
	; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <16 x i32> [[TMP19]], <16 x i32> [[TMP20]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>			; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <16 x i32> [[TMP19]], <16 x i32> [[TMP20]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
	; CHECK-NEXT: [[TMP22:%.*]] = trunc <16 x i32> [[TMP21]] to <16 x i8>			; CHECK-NEXT: [[TMP22:%.*]] = trunc <16 x i32> [[TMP21]] to <16 x i8>
	; CHECK-NEXT: [[TMP23:%.*]] = extractelement <4 x i32> [[TMP10]], i32 2			; CHECK-NEXT: [[TMP23:%.*]] = extractelement <4 x i32> [[TMP10]], i32 2
	; CHECK-NEXT: [[TMP24:%.*]] = extractelement <4 x i32> [[TMP10]], i32 1			; CHECK-NEXT: [[TMP24:%.*]] = extractelement <4 x i32> [[TMP10]], i32 1
	; CHECK-NEXT: [[TMP25:%.*]] = extractelement <4 x i32> [[TMP10]], i32 0			; CHECK-NEXT: [[TMP25:%.*]] = extractelement <4 x i32> [[TMP10]], i32 0
	; CHECK-NEXT: [[TMP26:%.*]] = extractelement <4 x i32> [[TMP9]], i32 3			; CHECK-NEXT: [[TMP26:%.*]] = extractelement <4 x i32> [[TMP9]], i32 3
	; CHECK-NEXT: [[TMP27:%.*]] = extractelement <4 x i32> [[TMP9]], i32 2			; CHECK-NEXT: [[TMP27:%.*]] = extractelement <4 x i32> [[TMP9]], i32 2
	; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i32> [[TMP9]], i32 1			; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i32> [[TMP9]], i32 1
	▲ Show 20 Lines • Show All 105 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/sext-inseltpoison.ll

	Show First 20 Lines • Show All 411 Lines • ▼ Show 20 Lines
	; SSE2-NEXT: [[P2:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 2			; SSE2-NEXT: [[P2:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 2
	; SSE2-NEXT: [[P3:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 3			; SSE2-NEXT: [[P3:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 3
	; SSE2-NEXT: [[TMP1:%.]] = bitcast i16 [[P0]] to <2 x i16>*			; SSE2-NEXT: [[TMP1:%.]] = bitcast i16 [[P0]] to <2 x i16>*
	; SSE2-NEXT: [[TMP2:%.]] = load <2 x i16>, <2 x i16> [[TMP1]], align 1			; SSE2-NEXT: [[TMP2:%.]] = load <2 x i16>, <2 x i16> [[TMP1]], align 1
	; SSE2-NEXT: [[TMP3:%.]] = bitcast i16 [[P2]] to <2 x i16>*			; SSE2-NEXT: [[TMP3:%.]] = bitcast i16 [[P2]] to <2 x i16>*
	; SSE2-NEXT: [[TMP4:%.]] = load <2 x i16>, <2 x i16> [[TMP3]], align 1			; SSE2-NEXT: [[TMP4:%.]] = load <2 x i16>, <2 x i16> [[TMP3]], align 1
	; SSE2-NEXT: [[TMP5:%.*]] = sext <2 x i16> [[TMP2]] to <2 x i64>			; SSE2-NEXT: [[TMP5:%.*]] = sext <2 x i16> [[TMP2]] to <2 x i64>
	; SSE2-NEXT: [[TMP6:%.*]] = sext <2 x i16> [[TMP4]] to <2 x i64>			; SSE2-NEXT: [[TMP6:%.*]] = sext <2 x i16> [[TMP4]] to <2 x i64>
	; SSE2-NEXT: [[TMP7:%.*]] = shufflevector <2 x i64> [[TMP5]], <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; SSE2-NEXT: [[TMP7:%.*]] = shufflevector <2 x i64> [[TMP5]], <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; SSE2-NEXT: [[V12:%.*]] = shufflevector <4 x i64> poison, <4 x i64> [[TMP7]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>			; SSE2-NEXT: [[V12:%.*]] = shufflevector <4 x i64> poison, <4 x i64> [[TMP7]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
	; SSE2-NEXT: [[TMP8:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; SSE2-NEXT: [[TMP8:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; SSE2-NEXT: [[V31:%.*]] = shufflevector <4 x i64> [[V12]], <4 x i64> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; SSE2-NEXT: [[V31:%.*]] = shufflevector <4 x i64> [[V12]], <4 x i64> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; SSE2-NEXT: ret <4 x i64> [[V31]]			; SSE2-NEXT: ret <4 x i64> [[V31]]
	;			;
	; SLM-LABEL: @loadext_4i16_to_4i64(			; SLM-LABEL: @loadext_4i16_to_4i64(
	; SLM-NEXT: [[P1:%.]] = getelementptr inbounds i16, i16 [[P0:%.*]], i64 1			; SLM-NEXT: [[P1:%.]] = getelementptr inbounds i16, i16 [[P0:%.*]], i64 1
	; SLM-NEXT: [[P2:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 2			; SLM-NEXT: [[P2:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 2
	; SLM-NEXT: [[P3:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 3			; SLM-NEXT: [[P3:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 3
	; SLM-NEXT: [[TMP1:%.]] = bitcast i16 [[P0]] to <4 x i16>*			; SLM-NEXT: [[TMP1:%.]] = bitcast i16 [[P0]] to <4 x i16>*
	▲ Show 20 Lines • Show All 157 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/sext.ll

	Show First 20 Lines • Show All 411 Lines • ▼ Show 20 Lines
	; SSE2-NEXT: [[P2:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 2			; SSE2-NEXT: [[P2:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 2
	; SSE2-NEXT: [[P3:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 3			; SSE2-NEXT: [[P3:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 3
	; SSE2-NEXT: [[TMP1:%.]] = bitcast i16 [[P0]] to <2 x i16>*			; SSE2-NEXT: [[TMP1:%.]] = bitcast i16 [[P0]] to <2 x i16>*
	; SSE2-NEXT: [[TMP2:%.]] = load <2 x i16>, <2 x i16> [[TMP1]], align 1			; SSE2-NEXT: [[TMP2:%.]] = load <2 x i16>, <2 x i16> [[TMP1]], align 1
	; SSE2-NEXT: [[TMP3:%.]] = bitcast i16 [[P2]] to <2 x i16>*			; SSE2-NEXT: [[TMP3:%.]] = bitcast i16 [[P2]] to <2 x i16>*
	; SSE2-NEXT: [[TMP4:%.]] = load <2 x i16>, <2 x i16> [[TMP3]], align 1			; SSE2-NEXT: [[TMP4:%.]] = load <2 x i16>, <2 x i16> [[TMP3]], align 1
	; SSE2-NEXT: [[TMP5:%.*]] = sext <2 x i16> [[TMP2]] to <2 x i64>			; SSE2-NEXT: [[TMP5:%.*]] = sext <2 x i16> [[TMP2]] to <2 x i64>
	; SSE2-NEXT: [[TMP6:%.*]] = sext <2 x i16> [[TMP4]] to <2 x i64>			; SSE2-NEXT: [[TMP6:%.*]] = sext <2 x i16> [[TMP4]] to <2 x i64>
	; SSE2-NEXT: [[TMP7:%.*]] = shufflevector <2 x i64> [[TMP5]], <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; SSE2-NEXT: [[TMP7:%.*]] = shufflevector <2 x i64> [[TMP5]], <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; SSE2-NEXT: [[V12:%.*]] = shufflevector <4 x i64> undef, <4 x i64> [[TMP7]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>			; SSE2-NEXT: [[V12:%.*]] = shufflevector <4 x i64> undef, <4 x i64> [[TMP7]], <4 x i32> <i32 4, i32 5, i32 2, i32 3>
	; SSE2-NEXT: [[TMP8:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>			; SSE2-NEXT: [[TMP8:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
	; SSE2-NEXT: [[V31:%.*]] = shufflevector <4 x i64> [[V12]], <4 x i64> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>			; SSE2-NEXT: [[V31:%.*]] = shufflevector <4 x i64> [[V12]], <4 x i64> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
	; SSE2-NEXT: ret <4 x i64> [[V31]]			; SSE2-NEXT: ret <4 x i64> [[V31]]
	;			;
	; SLM-LABEL: @loadext_4i16_to_4i64(			; SLM-LABEL: @loadext_4i16_to_4i64(
	; SLM-NEXT: [[P1:%.]] = getelementptr inbounds i16, i16 [[P0:%.*]], i64 1			; SLM-NEXT: [[P1:%.]] = getelementptr inbounds i16, i16 [[P0:%.*]], i64 1
	; SLM-NEXT: [[P2:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 2			; SLM-NEXT: [[P2:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 2
	; SLM-NEXT: [[P3:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 3			; SLM-NEXT: [[P3:%.]] = getelementptr inbounds i16, i16 [[P0]], i64 3
	; SLM-NEXT: [[TMP1:%.]] = bitcast i16 [[P0]] to <4 x i16>*			; SLM-NEXT: [[TMP1:%.]] = bitcast i16 [[P0]] to <4 x i16>*
	▲ Show 20 Lines • Show All 157 Lines • Show Last 20 Lines

This is an archive of the discontinued LLVM Phabricator instance.

[SLP]Remove unnecessary UndefValue in CreateShuffle.ClosedPublic

Details

Diff Detail

Event Timeline

Revision Contents

Diff 351421

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions.ll

llvm/test/Transforms/SLPVectorizer/AArch64/gather-root.ll

llvm/test/Transforms/SLPVectorizer/AArch64/transpose-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll

llvm/test/Transforms/SLPVectorizer/AArch64/vectorize-free-extracts-inserts.ll

llvm/test/Transforms/SLPVectorizer/AMDGPU/add_sub_sat-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/AMDGPU/add_sub_sat.ll

llvm/test/Transforms/SLPVectorizer/X86/PR35865-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/PR35865.ll

llvm/test/Transforms/SLPVectorizer/X86/alternate-calls-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/alternate-calls.ll

llvm/test/Transforms/SLPVectorizer/X86/alternate-cast-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/alternate-cast.ll

llvm/test/Transforms/SLPVectorizer/X86/alternate-fp-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/alternate-fp.ll

llvm/test/Transforms/SLPVectorizer/X86/alternate-int-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/alternate-int.ll

llvm/test/Transforms/SLPVectorizer/X86/arith-fp-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/arith-fp.ll

llvm/test/Transforms/SLPVectorizer/X86/cmp_commute-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/cmp_commute.ll

llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll

llvm/test/Transforms/SLPVectorizer/X86/load-merge-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/load-merge.ll

llvm/test/Transforms/SLPVectorizer/X86/phi.ll

llvm/test/Transforms/SLPVectorizer/X86/pr47629-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/pr47629.ll

llvm/test/Transforms/SLPVectorizer/X86/pr49081.ll

llvm/test/Transforms/SLPVectorizer/X86/resched.ll

llvm/test/Transforms/SLPVectorizer/X86/sext-inseltpoison.ll

llvm/test/Transforms/SLPVectorizer/X86/sext.ll

[SLP]Remove unnecessary UndefValue in CreateShuffle.
ClosedPublic