[llvm] r281787 - [InstCombine] canonicalize vector select with constant vector condition to shuffle
Sanjay Patel via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 16 15:16:18 PDT 2016
Author: spatel
Date: Fri Sep 16 17:16:18 2016
New Revision: 281787
URL: http://llvm.org/viewvc/llvm-project?rev=281787&view=rev
Log:
[InstCombine] canonicalize vector select with constant vector condition to shuffle
As discussed on llvm-dev ( http://lists.llvm.org/pipermail/llvm-dev/2016-August/104210.html ):
turn a vector select with constant condition operand into a shuffle as a canonicalization step.
Shuffles may be easier to reason about in conjunction with other shuffles and insert/extract.
Possible known (minor?) regressions from this change are filed as:
https://llvm.org/bugs/show_bug.cgi?id=28530
https://llvm.org/bugs/show_bug.cgi?id=28531
https://llvm.org/bugs/show_bug.cgi?id=30371
If something terrible happens to perf after this commit, feel free to revert until a backend
fix is in place.
Differential Revision: https://reviews.llvm.org/D24279
Modified:
llvm/trunk/lib/Transforms/InstCombine/InstCombineSelect.cpp
llvm/trunk/test/Transforms/InstCombine/blend_x86.ll
llvm/trunk/test/Transforms/InstCombine/logical-select.ll
llvm/trunk/test/Transforms/InstCombine/select.ll
llvm/trunk/test/Transforms/InstCombine/vec_demanded_elts.ll
Modified: llvm/trunk/lib/Transforms/InstCombine/InstCombineSelect.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/InstCombine/InstCombineSelect.cpp?rev=281787&r1=281786&r2=281787&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/InstCombine/InstCombineSelect.cpp (original)
+++ llvm/trunk/lib/Transforms/InstCombine/InstCombineSelect.cpp Fri Sep 16 17:16:18 2016
@@ -947,6 +947,42 @@ static Instruction *foldSelectExtConst(I
return new ZExtInst(Select, SI.getType());
}
+/// Try to transform a vector select with a constant condition vector into a
+/// shuffle for easier combining with other shuffles and insert/extract.
+static Instruction *canonicalizeSelectToShuffle(SelectInst &SI) {
+ Value *CondVal = SI.getCondition();
+ Constant *CondC;
+ if (!CondVal->getType()->isVectorTy() || !match(CondVal, m_Constant(CondC)))
+ return nullptr;
+
+ unsigned NumElts = CondVal->getType()->getVectorNumElements();
+ SmallVector<Constant *, 16> Mask;
+ Mask.reserve(NumElts);
+ Type *Int32Ty = Type::getInt32Ty(CondVal->getContext());
+ for (unsigned i = 0; i != NumElts; ++i) {
+ Constant *Elt = CondC->getAggregateElement(i);
+ if (!Elt)
+ return nullptr;
+
+ if (Elt->isOneValue()) {
+ // If the select condition element is true, choose from the 1st vector.
+ Mask.push_back(ConstantInt::get(Int32Ty, i));
+ } else if (Elt->isNullValue()) {
+ // If the select condition element is false, choose from the 2nd vector.
+ Mask.push_back(ConstantInt::get(Int32Ty, i + NumElts));
+ } else if (isa<UndefValue>(Elt)) {
+ // If the select condition element is undef, the shuffle mask is undef.
+ Mask.push_back(UndefValue::get(Int32Ty));
+ } else {
+ // Bail out on a constant expression.
+ return nullptr;
+ }
+ }
+
+ return new ShuffleVectorInst(SI.getTrueValue(), SI.getFalseValue(),
+ ConstantVector::get(Mask));
+}
+
Instruction *InstCombiner::visitSelectInst(SelectInst &SI) {
Value *CondVal = SI.getCondition();
Value *TrueVal = SI.getTrueValue();
@@ -957,6 +993,9 @@ Instruction *InstCombiner::visitSelectIn
SimplifySelectInst(CondVal, TrueVal, FalseVal, DL, &TLI, &DT, &AC))
return replaceInstUsesWith(SI, V);
+ if (Instruction *I = canonicalizeSelectToShuffle(SI))
+ return I;
+
if (SelType->getScalarType()->isIntegerTy(1) &&
TrueVal->getType() == CondVal->getType()) {
if (match(TrueVal, m_One())) {
Modified: llvm/trunk/test/Transforms/InstCombine/blend_x86.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/blend_x86.ll?rev=281787&r1=281786&r2=281787&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/blend_x86.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/blend_x86.ll Fri Sep 16 17:16:18 2016
@@ -1,9 +1,10 @@
; RUN: opt < %s -instcombine -mtriple=x86_64-apple-macosx -mcpu=core-avx2 -S | FileCheck %s
define <2 x double> @constant_blendvpd(<2 x double> %xy, <2 x double> %ab) {
-; CHECK-LABEL: @constant_blendvpd
-; CHECK-NEXT: %1 = select <2 x i1> <i1 true, i1 false>, <2 x double> %ab, <2 x double> %xy
-; CHECK-NEXT: ret <2 x double> %1
+; CHECK-LABEL: @constant_blendvpd(
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <2 x double> %ab, <2 x double> %xy, <2 x i32> <i32 0, i32 3>
+; CHECK-NEXT: ret <2 x double> [[TMP1]]
+;
%1 = tail call <2 x double> @llvm.x86.sse41.blendvpd(<2 x double> %xy, <2 x double> %ab, <2 x double> <double 0xFFFFFFFFE0000000, double 0.000000e+00>)
ret <2 x double> %1
}
@@ -23,9 +24,10 @@ define <2 x double> @constant_blendvpd_d
}
define <4 x float> @constant_blendvps(<4 x float> %xyzw, <4 x float> %abcd) {
-; CHECK-LABEL: @constant_blendvps
-; CHECK-NEXT: %1 = select <4 x i1> <i1 false, i1 false, i1 false, i1 true>, <4 x float> %abcd, <4 x float> %xyzw
-; CHECK-NEXT: ret <4 x float> %1
+; CHECK-LABEL: @constant_blendvps(
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x float> %abcd, <4 x float> %xyzw, <4 x i32> <i32 4, i32 5, i32 6, i32 3>
+; CHECK-NEXT: ret <4 x float> [[TMP1]]
+;
%1 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %xyzw, <4 x float> %abcd, <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0xFFFFFFFFE0000000>)
ret <4 x float> %1
}
@@ -45,9 +47,10 @@ define <4 x float> @constant_blendvps_du
}
define <16 x i8> @constant_pblendvb(<16 x i8> %xyzw, <16 x i8> %abcd) {
-; CHECK-LABEL: @constant_pblendvb
-; CHECK-NEXT: %1 = select <16 x i1> <i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false>, <16 x i8> %abcd, <16 x i8> %xyzw
-; CHECK-NEXT: ret <16 x i8> %1
+; CHECK-LABEL: @constant_pblendvb(
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <16 x i8> %abcd, <16 x i8> %xyzw, <16 x i32> <i32 16, i32 17, i32 2, i32 19, i32 4, i32 5, i32 6, i32 23, i32 24, i32 25, i32 10, i32 27, i32 12, i32 13, i32 14, i32 31>
+; CHECK-NEXT: ret <16 x i8> [[TMP1]]
+;
%1 = tail call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> %xyzw, <16 x i8> %abcd, <16 x i8> <i8 0, i8 0, i8 255, i8 0, i8 255, i8 255, i8 255, i8 0, i8 0, i8 0, i8 255, i8 0, i8 255, i8 255, i8 255, i8 0>)
ret <16 x i8> %1
}
@@ -67,9 +70,10 @@ define <16 x i8> @constant_pblendvb_dup(
}
define <4 x double> @constant_blendvpd_avx(<4 x double> %xy, <4 x double> %ab) {
-; CHECK-LABEL: @constant_blendvpd_avx
-; CHECK-NEXT: %1 = select <4 x i1> <i1 true, i1 false, i1 true, i1 false>, <4 x double> %ab, <4 x double> %xy
-; CHECK-NEXT: ret <4 x double> %1
+; CHECK-LABEL: @constant_blendvpd_avx(
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x double> %ab, <4 x double> %xy, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT: ret <4 x double> [[TMP1]]
+;
%1 = tail call <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double> %xy, <4 x double> %ab, <4 x double> <double 0xFFFFFFFFE0000000, double 0.000000e+00, double 0xFFFFFFFFE0000000, double 0.000000e+00>)
ret <4 x double> %1
}
@@ -89,9 +93,10 @@ define <4 x double> @constant_blendvpd_a
}
define <8 x float> @constant_blendvps_avx(<8 x float> %xyzw, <8 x float> %abcd) {
-; CHECK-LABEL: @constant_blendvps_avx
-; CHECK-NEXT: %1 = select <8 x i1> <i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true>, <8 x float> %abcd, <8 x float> %xyzw
-; CHECK-NEXT: ret <8 x float> %1
+; CHECK-LABEL: @constant_blendvps_avx(
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x float> %abcd, <8 x float> %xyzw, <8 x i32> <i32 8, i32 9, i32 10, i32 3, i32 12, i32 13, i32 14, i32 7>
+; CHECK-NEXT: ret <8 x float> [[TMP1]]
+;
%1 = tail call <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float> %xyzw, <8 x float> %abcd, <8 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0xFFFFFFFFE0000000, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0xFFFFFFFFE0000000>)
ret <8 x float> %1
}
@@ -111,9 +116,10 @@ define <8 x float> @constant_blendvps_av
}
define <32 x i8> @constant_pblendvb_avx2(<32 x i8> %xyzw, <32 x i8> %abcd) {
-; CHECK-LABEL: @constant_pblendvb_avx2
-; CHECK-NEXT: %1 = select <32 x i1> <i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false>, <32 x i8> %abcd, <32 x i8> %xyzw
-; CHECK-NEXT: ret <32 x i8> %1
+; CHECK-LABEL: @constant_pblendvb_avx2(
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <32 x i8> %abcd, <32 x i8> %xyzw, <32 x i32> <i32 32, i32 33, i32 2, i32 35, i32 4, i32 5, i32 6, i32 39, i32 40, i32 41, i32 10, i32 43, i32 12, i32 13, i32 14, i32 47, i32 48, i32 49, i32 18, i32 51, i32 20, i32 21, i32 22, i32 55, i32 56, i32 57, i32 26, i32 59, i32 28, i32 29, i32 30, i32 63>
+; CHECK-NEXT: ret <32 x i8> [[TMP1]]
+;
%1 = tail call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> %xyzw, <32 x i8> %abcd,
<32 x i8> <i8 0, i8 0, i8 255, i8 0, i8 255, i8 255, i8 255, i8 0,
i8 0, i8 0, i8 255, i8 0, i8 255, i8 255, i8 255, i8 0,
Modified: llvm/trunk/test/Transforms/InstCombine/logical-select.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/logical-select.ll?rev=281787&r1=281786&r2=281787&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/logical-select.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/logical-select.ll Fri Sep 16 17:16:18 2016
@@ -366,11 +366,11 @@ define i4 @vec_of_casted_bools(i4 %a, i4
ret i4 %or
}
-; Inverted 'and' constants mean this is a select.
+; Inverted 'and' constants mean this is a select which is canonicalized to a shuffle.
define <4 x i32> @vec_sel_consts(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: @vec_sel_consts(
-; CHECK-NEXT: [[TMP1:%.*]] = select <4 x i1> <i1 true, i1 false, i1 false, i1 true>, <4 x i32> %a, <4 x i32> %b
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 5, i32 6, i32 3>
; CHECK-NEXT: ret <4 x i32> [[TMP1]]
;
%and1 = and <4 x i32> %a, <i32 -1, i32 0, i32 0, i32 -1>
@@ -379,11 +379,9 @@ define <4 x i32> @vec_sel_consts(<4 x i3
ret <4 x i32> %or
}
-; The select condition constant is always derived from the first operand of the 'or'.
-
define <3 x i129> @vec_sel_consts_weird(<3 x i129> %a, <3 x i129> %b) {
; CHECK-LABEL: @vec_sel_consts_weird(
-; CHECK-NEXT: [[TMP1:%.*]] = select <3 x i1> <i1 false, i1 true, i1 false>, <3 x i129> %b, <3 x i129> %a
+; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <3 x i129> %b, <3 x i129> %a, <3 x i32> <i32 3, i32 1, i32 5>
; CHECK-NEXT: ret <3 x i129> [[TMP1]]
;
%and1 = and <3 x i129> %a, <i129 -1, i129 0, i129 -1>
Modified: llvm/trunk/test/Transforms/InstCombine/select.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/select.ll?rev=281787&r1=281786&r2=281787&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/select.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/select.ll Fri Sep 16 17:16:18 2016
@@ -1765,3 +1765,36 @@ define <2 x i32> @select_icmp_slt0_xor_v
ret <2 x i32> %x.xor
}
+; Make sure that undef elements of the select condition are translated into undef elements of the shuffle mask.
+
+define <4 x i32> @canonicalize_to_shuffle(<4 x i32> %a, <4 x i32> %b) {
+; CHECK-LABEL: @canonicalize_to_shuffle(
+; CHECK-NEXT: [[SEL:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 undef, i32 6, i32 undef>
+; CHECK-NEXT: ret <4 x i32> [[SEL]]
+;
+ %sel = select <4 x i1> <i1 true, i1 undef, i1 false, i1 undef>, <4 x i32> %a, <4 x i32> %b
+ ret <4 x i32> %sel
+}
+
+; Don't die or try if the condition mask is a constant expression or contains a constant expression.
+
+ at g = global i32 0
+
+define <4 x i32> @cannot_canonicalize_to_shuffle1(<4 x i32> %a, <4 x i32> %b) {
+; CHECK-LABEL: @cannot_canonicalize_to_shuffle1(
+; CHECK-NEXT: [[SEL:%.*]] = select <4 x i1> bitcast (i4 ptrtoint (i32* @g to i4) to <4 x i1>), <4 x i32> %a, <4 x i32> %b
+; CHECK-NEXT: ret <4 x i32> [[SEL]]
+;
+ %sel = select <4 x i1> bitcast (i4 ptrtoint (i32* @g to i4) to <4 x i1>), <4 x i32> %a, <4 x i32> %b
+ ret <4 x i32> %sel
+}
+
+define <4 x i32> @cannot_canonicalize_to_shuffle2(<4 x i32> %a, <4 x i32> %b) {
+; CHECK-LABEL: @cannot_canonicalize_to_shuffle2(
+; CHECK-NEXT: [[SEL:%.*]] = select <4 x i1> <i1 true, i1 undef, i1 false, i1 icmp sle (i16 ptrtoint (i32* @g to i16), i16 4)>, <4 x i32> %a, <4 x i32> %b
+; CHECK-NEXT: ret <4 x i32> [[SEL]]
+;
+ %sel = select <4 x i1> <i1 true, i1 undef, i1 false, i1 icmp sle (i16 ptrtoint (i32* @g to i16), i16 4)>, <4 x i32> %a, <4 x i32> %b
+ ret <4 x i32> %sel
+}
+
Modified: llvm/trunk/test/Transforms/InstCombine/vec_demanded_elts.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/vec_demanded_elts.ll?rev=281787&r1=281786&r2=281787&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/vec_demanded_elts.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/vec_demanded_elts.ll Fri Sep 16 17:16:18 2016
@@ -216,7 +216,7 @@ define <4 x float> @test_select(float %f
; CHECK-LABEL: @test_select(
; CHECK-NEXT: [[A0:%.*]] = insertelement <4 x float> undef, float %f, i32 0
; CHECK-NEXT: [[A3:%.*]] = insertelement <4 x float> [[A0]], float 3.000000e+00, i32 3
-; CHECK-NEXT: [[RET:%.*]] = select <4 x i1> <i1 true, i1 false, i1 false, i1 true>, <4 x float> [[A3]], <4 x float> <float undef, float 4.000000e+00, float 5.000000e+00, float undef>
+; CHECK-NEXT: [[RET:%.*]] = shufflevector <4 x float> [[A3]], <4 x float> <float undef, float 4.000000e+00, float 5.000000e+00, float undef>, <4 x i32> <i32 0, i32 5, i32 6, i32 3>
; CHECK-NEXT: ret <4 x float> [[RET]]
;
%a0 = insertelement <4 x float> undef, float %f, i32 0
@@ -231,10 +231,12 @@ define <4 x float> @test_select(float %f
ret <4 x float> %ret
}
-; Check that instcombine doesn't wrongly fold the select statement into a ret <2 x i64> %v
+; Check that instcombine doesn't wrongly fold away the select completely.
+; TODO: Should this be an insertelement rather than a shuffle?
+
define <2 x i64> @PR24922(<2 x i64> %v) {
; CHECK-LABEL: @PR24922(
-; CHECK-NEXT: [[RESULT:%.*]] = select <2 x i1> <i1 false, i1 true>, <2 x i64> %v, <2 x i64> <i64 0, i64 undef>
+; CHECK-NEXT: [[RESULT:%.*]] = shufflevector <2 x i64> %v, <2 x i64> <i64 0, i64 undef>, <2 x i32> <i32 2, i32 1>
; CHECK-NEXT: ret <2 x i64> [[RESULT]]
;
%result = select <2 x i1> <i1 icmp eq (i64 extractelement (<2 x i64> bitcast (<4 x i32> <i32 15, i32 15, i32 15, i32 15> to <2 x i64>), i64 0), i64 0), i1 true>, <2 x i64> %v, <2 x i64> zeroinitializer
More information about the llvm-commits
mailing list