[llvm] [SLP]Add debug counter support (PR #110734)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Oct 1 13:10:55 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-transforms
Author: Alexey Bataev (alexey-bataev)
<details>
<summary>Changes</summary>
---
Patch is 20.09 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/110734.diff
2 Files Affected:
- (modified) llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp (+7)
- (added) llvm/test/Transforms/SLPVectorizer/debug-counter.ll (+235)
``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 15e798bd6c98f9..b68dfbaa6c3075 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -79,6 +79,7 @@
#include "llvm/Support/Compiler.h"
#include "llvm/Support/DOTGraphTraits.h"
#include "llvm/Support/Debug.h"
+#include "llvm/Support/DebugCounter.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/GraphWriter.h"
#include "llvm/Support/InstructionCost.h"
@@ -109,6 +110,9 @@ using namespace slpvectorizer;
STATISTIC(NumVectorInstructions, "Number of vector instructions generated");
+DEBUG_COUNTER(VectorizedGraphs, "slp-vectorized",
+ "Controls which SLP graphs should be vectorized.");
+
static cl::opt<bool>
RunSLPVectorization("vectorize-slp", cl::init(true), cl::Hidden,
cl::desc("Run the SLP vectorization passes"));
@@ -11175,6 +11179,9 @@ bool BoUpSLP::isLoadCombineCandidate(ArrayRef<Value *> Stores) const {
}
bool BoUpSLP::isTreeTinyAndNotFullyVectorizable(bool ForReduction) const {
+ if (!DebugCounter::shouldExecute(VectorizedGraphs))
+ return true;
+
// No need to vectorize inserts of gathered values.
if (VectorizableTree.size() == 2 &&
isa<InsertElementInst>(VectorizableTree[0]->Scalars[0]) &&
diff --git a/llvm/test/Transforms/SLPVectorizer/debug-counter.ll b/llvm/test/Transforms/SLPVectorizer/debug-counter.ll
new file mode 100644
index 00000000000000..006b6ef33964e5
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/debug-counter.ll
@@ -0,0 +1,235 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
+; RUN: opt -S -passes=slp-vectorizer -debug-counter=slp-vectorized=0 -slp-threshold=-99999 < %s | FileCheck %s --check-prefix=COUNT0
+; RUN: opt -S -passes=slp-vectorizer -debug-counter=slp-vectorized=1 -slp-threshold=-99999 < %s | FileCheck %s --check-prefix=COUNT1
+; RUN: opt -S -passes=slp-vectorizer -debug-counter=slp-vectorized=2 -slp-threshold=-99999 < %s | FileCheck %s --check-prefix=COUNT2
+; RUN: opt -S -passes=slp-vectorizer -debug-counter=slp-vectorized=0-1 -slp-threshold=-99999 < %s | FileCheck %s --check-prefix=COUNT-1
+
+define void @blam(ptr %arg, double %load2, i1 %fcmp3) {
+; CHECK-LABEL: define void @blam
+; CHECK-SAME: (ptr [[ARG:%.*]], double [[LOAD2:%.*]], i1 [[FCMP3:%.*]]) {
+; CHECK-NEXT: bb:
+; CHECK-NEXT: [[GETELEMENTPTR13:%.*]] = getelementptr double, ptr [[ARG]], i64 3
+; CHECK-NEXT: [[TMP0:%.*]] = load <2 x double>, ptr [[ARG]], align 8
+; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x i1> poison, i1 [[FCMP3]], i32 0
+; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i1> [[TMP1]], <2 x i1> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP3:%.*]] = select <2 x i1> [[TMP2]], <2 x double> zeroinitializer, <2 x double> [[TMP0]]
+; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x double> [[TMP0]], double [[LOAD2]], i32 0
+; CHECK-NEXT: [[TMP5:%.*]] = fcmp olt <2 x double> [[TMP4]], zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = select <2 x i1> [[TMP5]], <2 x double> zeroinitializer, <2 x double> [[TMP0]]
+; CHECK-NEXT: [[TMP7:%.*]] = fcmp olt <2 x double> [[TMP3]], zeroinitializer
+; CHECK-NEXT: [[TMP8:%.*]] = select <2 x i1> [[TMP7]], <2 x double> <double 0.000000e+00, double 1.000000e+00>, <2 x double> <double 1.000000e+00, double 0.000000e+00>
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x double> [[TMP8]], <2 x double> poison, <2 x i32> <i32 1, i32 0>
+; CHECK-NEXT: [[TMP10:%.*]] = fcmp olt <2 x double> [[TMP9]], [[TMP6]]
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> <double poison, double 0.000000e+00>, <2 x i32> <i32 0, i32 3>
+; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> <double 0.000000e+00, double poison>, <2 x i32> <i32 2, i32 0>
+; CHECK-NEXT: [[TMP13:%.*]] = select <2 x i1> [[TMP10]], <2 x double> [[TMP11]], <2 x double> [[TMP12]]
+; CHECK-NEXT: [[TMP14:%.*]] = fcmp olt <2 x double> [[TMP13]], zeroinitializer
+; CHECK-NEXT: [[TMP15:%.*]] = select <2 x i1> [[TMP14]], <2 x double> zeroinitializer, <2 x double> <double 1.000000e+00, double 1.000000e+00>
+; CHECK-NEXT: [[TMP16:%.*]] = fcmp ogt <2 x double> [[TMP15]], zeroinitializer
+; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP18:%.*]] = select <2 x i1> [[TMP16]], <2 x double> zeroinitializer, <2 x double> [[TMP17]]
+; CHECK-NEXT: [[TMP19:%.*]] = fcmp olt <2 x double> [[TMP18]], zeroinitializer
+; CHECK-NEXT: [[TMP20:%.*]] = select <2 x i1> [[TMP19]], <2 x double> <double 1.000000e+00, double 1.000000e+00>, <2 x double> zeroinitializer
+; CHECK-NEXT: store <2 x double> [[TMP20]], ptr [[GETELEMENTPTR13]], align 8
+; CHECK-NEXT: ret void
+;
+; COUNT0-LABEL: define void @blam
+; COUNT0-SAME: (ptr [[ARG:%.*]], double [[LOAD2:%.*]], i1 [[FCMP3:%.*]]) {
+; COUNT0-NEXT: bb:
+; COUNT0-NEXT: [[GETELEMENTPTR:%.*]] = getelementptr double, ptr [[ARG]], i64 1
+; COUNT0-NEXT: [[LOAD:%.*]] = load double, ptr [[GETELEMENTPTR]], align 8
+; COUNT0-NEXT: [[FCMP:%.*]] = fcmp olt double [[LOAD]], 0.000000e+00
+; COUNT0-NEXT: [[SELECT3:%.*]] = select i1 [[FCMP]], double 0.000000e+00, double [[LOAD]]
+; COUNT0-NEXT: [[SELECT4:%.*]] = select i1 [[FCMP3]], double 0.000000e+00, double [[LOAD]]
+; COUNT0-NEXT: [[LOAD7:%.*]] = load double, ptr [[ARG]], align 8
+; COUNT0-NEXT: [[SELECT10:%.*]] = select i1 [[FCMP3]], double 0.000000e+00, double [[LOAD7]]
+; COUNT0-NEXT: [[GETELEMENTPTR13:%.*]] = getelementptr double, ptr [[ARG]], i64 3
+; COUNT0-NEXT: [[GETELEMENTPTR21:%.*]] = getelementptr double, ptr [[ARG]], i64 4
+; COUNT0-NEXT: [[FCMP23:%.*]] = fcmp olt double [[SELECT10]], 0.000000e+00
+; COUNT0-NEXT: [[SELECT24:%.*]] = select i1 [[FCMP23]], double 0.000000e+00, double 1.000000e+00
+; COUNT0-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[LOAD2]], i32 1
+; COUNT0-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[SELECT4]], i32 0
+; COUNT0-NEXT: [[TMP2:%.*]] = fcmp olt <2 x double> [[TMP1]], zeroinitializer
+; COUNT0-NEXT: [[TMP3:%.*]] = insertelement <2 x double> <double 0.000000e+00, double poison>, double [[LOAD7]], i32 1
+; COUNT0-NEXT: [[TMP4:%.*]] = select <2 x i1> [[TMP2]], <2 x double> <double 1.000000e+00, double 0.000000e+00>, <2 x double> [[TMP3]]
+; COUNT0-NEXT: [[FCMP33:%.*]] = fcmp olt double [[SELECT24]], [[SELECT3]]
+; COUNT0-NEXT: [[SELECT34:%.*]] = select i1 [[FCMP33]], double 0.000000e+00, double [[LOAD2]]
+; COUNT0-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[TMP4]], i32 0
+; COUNT0-NEXT: [[TMP6:%.*]] = extractelement <2 x double> [[TMP4]], i32 1
+; COUNT0-NEXT: [[FCMP39:%.*]] = fcmp olt double [[TMP5]], [[TMP6]]
+; COUNT0-NEXT: [[SELECT40:%.*]] = select i1 [[FCMP39]], double [[LOAD2]], double 0.000000e+00
+; COUNT0-NEXT: [[FCMP62:%.*]] = fcmp olt double [[SELECT34]], 0.000000e+00
+; COUNT0-NEXT: [[SELECT639:%.*]] = select i1 [[FCMP62]], double 0.000000e+00, double 1.000000e+00
+; COUNT0-NEXT: [[FCMP76:%.*]] = fcmp olt double [[SELECT40]], 0.000000e+00
+; COUNT0-NEXT: [[SELECT77:%.*]] = select i1 [[FCMP76]], double 0.000000e+00, double 1.000000e+00
+; COUNT0-NEXT: [[FCMP90:%.*]] = fcmp ogt double [[SELECT639]], 0.000000e+00
+; COUNT0-NEXT: [[SELECT91:%.*]] = select i1 [[FCMP90]], double 0.000000e+00, double [[LOAD2]]
+; COUNT0-NEXT: [[FCMP92:%.*]] = fcmp ogt double [[SELECT77]], 0.000000e+00
+; COUNT0-NEXT: [[SELECT93:%.*]] = select i1 [[FCMP92]], double 0.000000e+00, double [[LOAD2]]
+; COUNT0-NEXT: [[FCMP108:%.*]] = fcmp olt double [[SELECT93]], 0.000000e+00
+; COUNT0-NEXT: [[SELECT109:%.*]] = select i1 [[FCMP108]], double 1.000000e+00, double 0.000000e+00
+; COUNT0-NEXT: [[FCMP110:%.*]] = fcmp olt double [[SELECT91]], 0.000000e+00
+; COUNT0-NEXT: [[SELECT111:%.*]] = select i1 [[FCMP110]], double 1.000000e+00, double 0.000000e+00
+; COUNT0-NEXT: store double [[SELECT111]], ptr [[GETELEMENTPTR21]], align 8
+; COUNT0-NEXT: store double [[SELECT109]], ptr [[GETELEMENTPTR13]], align 8
+; COUNT0-NEXT: ret void
+;
+; COUNT1-LABEL: define void @blam
+; COUNT1-SAME: (ptr [[ARG:%.*]], double [[LOAD2:%.*]], i1 [[FCMP3:%.*]]) {
+; COUNT1-NEXT: bb:
+; COUNT1-NEXT: [[GETELEMENTPTR:%.*]] = getelementptr double, ptr [[ARG]], i64 1
+; COUNT1-NEXT: [[LOAD:%.*]] = load double, ptr [[GETELEMENTPTR]], align 8
+; COUNT1-NEXT: [[SELECT4:%.*]] = select i1 [[FCMP3]], double 0.000000e+00, double [[LOAD]]
+; COUNT1-NEXT: [[LOAD7:%.*]] = load double, ptr [[ARG]], align 8
+; COUNT1-NEXT: [[SELECT10:%.*]] = select i1 [[FCMP3]], double 0.000000e+00, double [[LOAD7]]
+; COUNT1-NEXT: [[FCMP11:%.*]] = fcmp olt double [[LOAD2]], 0.000000e+00
+; COUNT1-NEXT: [[SELECT128:%.*]] = select i1 [[FCMP11]], double 0.000000e+00, double [[LOAD7]]
+; COUNT1-NEXT: [[GETELEMENTPTR13:%.*]] = getelementptr double, ptr [[ARG]], i64 3
+; COUNT1-NEXT: [[GETELEMENTPTR21:%.*]] = getelementptr double, ptr [[ARG]], i64 4
+; COUNT1-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[SELECT10]], i32 0
+; COUNT1-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[LOAD]], i32 1
+; COUNT1-NEXT: [[TMP2:%.*]] = fcmp olt <2 x double> [[TMP1]], zeroinitializer
+; COUNT1-NEXT: [[TMP3:%.*]] = shufflevector <2 x double> [[TMP1]], <2 x double> <double 1.000000e+00, double poison>, <2 x i32> <i32 2, i32 1>
+; COUNT1-NEXT: [[TMP4:%.*]] = select <2 x i1> [[TMP2]], <2 x double> zeroinitializer, <2 x double> [[TMP3]]
+; COUNT1-NEXT: [[FCMP29:%.*]] = fcmp olt double [[SELECT4]], 0.000000e+00
+; COUNT1-NEXT: [[SELECT30:%.*]] = select i1 [[FCMP29]], double 1.000000e+00, double 0.000000e+00
+; COUNT1-NEXT: [[TMP5:%.*]] = extractelement <2 x double> [[TMP4]], i32 0
+; COUNT1-NEXT: [[TMP6:%.*]] = extractelement <2 x double> [[TMP4]], i32 1
+; COUNT1-NEXT: [[FCMP33:%.*]] = fcmp olt double [[TMP5]], [[TMP6]]
+; COUNT1-NEXT: [[SELECT34:%.*]] = select i1 [[FCMP33]], double 0.000000e+00, double [[LOAD2]]
+; COUNT1-NEXT: [[FCMP39:%.*]] = fcmp olt double [[SELECT30]], [[SELECT128]]
+; COUNT1-NEXT: [[SELECT40:%.*]] = select i1 [[FCMP39]], double [[LOAD2]], double 0.000000e+00
+; COUNT1-NEXT: [[FCMP62:%.*]] = fcmp olt double [[SELECT34]], 0.000000e+00
+; COUNT1-NEXT: [[SELECT639:%.*]] = select i1 [[FCMP62]], double 0.000000e+00, double 1.000000e+00
+; COUNT1-NEXT: [[FCMP76:%.*]] = fcmp olt double [[SELECT40]], 0.000000e+00
+; COUNT1-NEXT: [[SELECT77:%.*]] = select i1 [[FCMP76]], double 0.000000e+00, double 1.000000e+00
+; COUNT1-NEXT: [[FCMP90:%.*]] = fcmp ogt double [[SELECT639]], 0.000000e+00
+; COUNT1-NEXT: [[SELECT91:%.*]] = select i1 [[FCMP90]], double 0.000000e+00, double [[LOAD2]]
+; COUNT1-NEXT: [[FCMP92:%.*]] = fcmp ogt double [[SELECT77]], 0.000000e+00
+; COUNT1-NEXT: [[SELECT93:%.*]] = select i1 [[FCMP92]], double 0.000000e+00, double [[LOAD2]]
+; COUNT1-NEXT: [[FCMP108:%.*]] = fcmp olt double [[SELECT93]], 0.000000e+00
+; COUNT1-NEXT: [[SELECT109:%.*]] = select i1 [[FCMP108]], double 1.000000e+00, double 0.000000e+00
+; COUNT1-NEXT: [[FCMP110:%.*]] = fcmp olt double [[SELECT91]], 0.000000e+00
+; COUNT1-NEXT: [[SELECT111:%.*]] = select i1 [[FCMP110]], double 1.000000e+00, double 0.000000e+00
+; COUNT1-NEXT: store double [[SELECT111]], ptr [[GETELEMENTPTR21]], align 8
+; COUNT1-NEXT: store double [[SELECT109]], ptr [[GETELEMENTPTR13]], align 8
+; COUNT1-NEXT: ret void
+;
+; COUNT2-LABEL: define void @blam
+; COUNT2-SAME: (ptr [[ARG:%.*]], double [[LOAD2:%.*]], i1 [[FCMP3:%.*]]) {
+; COUNT2-NEXT: bb:
+; COUNT2-NEXT: [[GETELEMENTPTR:%.*]] = getelementptr double, ptr [[ARG]], i64 1
+; COUNT2-NEXT: [[LOAD:%.*]] = load double, ptr [[GETELEMENTPTR]], align 8
+; COUNT2-NEXT: [[FCMP:%.*]] = fcmp olt double [[LOAD]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT3:%.*]] = select i1 [[FCMP]], double 0.000000e+00, double [[LOAD]]
+; COUNT2-NEXT: [[SELECT4:%.*]] = select i1 [[FCMP3]], double 0.000000e+00, double [[LOAD]]
+; COUNT2-NEXT: [[LOAD7:%.*]] = load double, ptr [[ARG]], align 8
+; COUNT2-NEXT: [[SELECT10:%.*]] = select i1 [[FCMP3]], double 0.000000e+00, double [[LOAD7]]
+; COUNT2-NEXT: [[FCMP11:%.*]] = fcmp olt double [[LOAD2]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT128:%.*]] = select i1 [[FCMP11]], double 0.000000e+00, double [[LOAD7]]
+; COUNT2-NEXT: [[GETELEMENTPTR13:%.*]] = getelementptr double, ptr [[ARG]], i64 3
+; COUNT2-NEXT: [[GETELEMENTPTR21:%.*]] = getelementptr double, ptr [[ARG]], i64 4
+; COUNT2-NEXT: [[FCMP23:%.*]] = fcmp olt double [[SELECT10]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT24:%.*]] = select i1 [[FCMP23]], double 0.000000e+00, double 1.000000e+00
+; COUNT2-NEXT: [[FCMP29:%.*]] = fcmp olt double [[SELECT4]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT30:%.*]] = select i1 [[FCMP29]], double 1.000000e+00, double 0.000000e+00
+; COUNT2-NEXT: [[FCMP33:%.*]] = fcmp olt double [[SELECT24]], [[SELECT3]]
+; COUNT2-NEXT: [[SELECT34:%.*]] = select i1 [[FCMP33]], double 0.000000e+00, double [[LOAD2]]
+; COUNT2-NEXT: [[FCMP39:%.*]] = fcmp olt double [[SELECT30]], [[SELECT128]]
+; COUNT2-NEXT: [[SELECT40:%.*]] = select i1 [[FCMP39]], double [[LOAD2]], double 0.000000e+00
+; COUNT2-NEXT: [[FCMP62:%.*]] = fcmp olt double [[SELECT34]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT639:%.*]] = select i1 [[FCMP62]], double 0.000000e+00, double 1.000000e+00
+; COUNT2-NEXT: [[FCMP76:%.*]] = fcmp olt double [[SELECT40]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT77:%.*]] = select i1 [[FCMP76]], double 0.000000e+00, double 1.000000e+00
+; COUNT2-NEXT: [[FCMP90:%.*]] = fcmp ogt double [[SELECT639]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT91:%.*]] = select i1 [[FCMP90]], double 0.000000e+00, double [[LOAD2]]
+; COUNT2-NEXT: [[FCMP92:%.*]] = fcmp ogt double [[SELECT77]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT93:%.*]] = select i1 [[FCMP92]], double 0.000000e+00, double [[LOAD2]]
+; COUNT2-NEXT: [[FCMP108:%.*]] = fcmp olt double [[SELECT93]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT109:%.*]] = select i1 [[FCMP108]], double 1.000000e+00, double 0.000000e+00
+; COUNT2-NEXT: [[FCMP110:%.*]] = fcmp olt double [[SELECT91]], 0.000000e+00
+; COUNT2-NEXT: [[SELECT111:%.*]] = select i1 [[FCMP110]], double 1.000000e+00, double 0.000000e+00
+; COUNT2-NEXT: store double [[SELECT111]], ptr [[GETELEMENTPTR21]], align 8
+; COUNT2-NEXT: store double [[SELECT109]], ptr [[GETELEMENTPTR13]], align 8
+; COUNT2-NEXT: ret void
+;
+; COUNT-1-LABEL: define void @blam
+; COUNT-1-SAME: (ptr [[ARG:%.*]], double [[LOAD2:%.*]], i1 [[FCMP3:%.*]]) {
+; COUNT-1-NEXT: bb:
+; COUNT-1-NEXT: [[GETELEMENTPTR:%.*]] = getelementptr double, ptr [[ARG]], i64 1
+; COUNT-1-NEXT: [[LOAD:%.*]] = load double, ptr [[GETELEMENTPTR]], align 8
+; COUNT-1-NEXT: [[SELECT4:%.*]] = select i1 [[FCMP3]], double 0.000000e+00, double [[LOAD]]
+; COUNT-1-NEXT: [[LOAD7:%.*]] = load double, ptr [[ARG]], align 8
+; COUNT-1-NEXT: [[SELECT10:%.*]] = select i1 [[FCMP3]], double 0.000000e+00, double [[LOAD7]]
+; COUNT-1-NEXT: [[GETELEMENTPTR13:%.*]] = getelementptr double, ptr [[ARG]], i64 3
+; COUNT-1-NEXT: [[GETELEMENTPTR21:%.*]] = getelementptr double, ptr [[ARG]], i64 4
+; COUNT-1-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[SELECT10]], i32 0
+; COUNT-1-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[LOAD]], i32 1
+; COUNT-1-NEXT: [[TMP2:%.*]] = fcmp olt <2 x double> [[TMP1]], zeroinitializer
+; COUNT-1-NEXT: [[TMP3:%.*]] = shufflevector <2 x double> [[TMP1]], <2 x double> <double 1.000000e+00, double poison>, <2 x i32> <i32 2, i32 1>
+; COUNT-1-NEXT: [[TMP4:%.*]] = select <2 x i1> [[TMP2]], <2 x double> zeroinitializer, <2 x double> [[TMP3]]
+; COUNT-1-NEXT: [[TMP5:%.*]] = insertelement <2 x double> poison, double [[LOAD2]], i32 1
+; COUNT-1-NEXT: [[TMP6:%.*]] = insertelement <2 x double> [[TMP5]], double [[SELECT4]], i32 0
+; COUNT-1-NEXT: [[TMP7:%.*]] = fcmp olt <2 x double> [[TMP6]], zeroinitializer
+; COUNT-1-NEXT: [[TMP8:%.*]] = insertelement <2 x double> <double 0.000000e+00, double poison>, double [[LOAD7]], i32 1
+; COUNT-1-NEXT: [[TMP9:%.*]] = select <2 x i1> [[TMP7]], <2 x double> <double 1.000000e+00, double 0.000000e+00>, <2 x double> [[TMP8]]
+; COUNT-1-NEXT: [[TMP10:%.*]] = extractelement <2 x double> [[TMP4]], i32 0
+; COUNT-1-NEXT: [[TMP11:%.*]] = extractelement <2 x double> [[TMP4]], i32 1
+; COUNT-1-NEXT: [[FCMP33:%.*]] = fcmp olt double [[TMP10]], [[TMP11]]
+; COUNT-1-NEXT: [[SELECT34:%.*]] = select i1 [[FCMP33]], double 0.000000e+00, double [[LOAD2]]
+; COUNT-1-NEXT: [[TMP12:%.*]] = extractelement <2 x double> [[TMP9]], i32 0
+; COUNT-1-NEXT: [[TMP13:%.*]] = extractelement <2 x double> [[TMP9]], i32 1
+; COUNT-1-NEXT: [[FCMP39:%.*]] = fcmp olt double [[TMP12]], [[TMP13]]
+; COUNT-1-NEXT: [[SELECT40:%.*]] = select i1 [[FCMP39]], double [[LOAD2]], double 0.000000e+00
+; COUNT-1-NEXT: [[FCMP62:%.*]] = fcmp olt double [[SELECT34]], 0.000000e+00
+; COUNT-1-NEXT: [[SELECT639:%.*]] = select i1 [[FCMP62]], double 0.000000e+00, double 1.000000e+00
+; COUNT-1-NEXT: [[FCMP76:%.*]] = fcmp olt double [[SELECT40]], 0.000000e+00
+; COUNT-1-NEXT: [[SELECT77:%.*]] = select i1 [[FCMP76]], double 0.000000e+00, double 1.000000e+00
+; COUNT-1-NEXT: [[FCMP90:%.*]] = fcmp ogt double [[SELECT639]], 0.000000e+00
+; COUNT-1-NEXT: [[SELECT91:%.*]] = select i1 [[FCMP90]], double 0.000000e+00, double [[LOAD2]]
+; COUNT-1-NEXT: [[FCMP92:%.*]] = fcmp ogt double [[SELECT77]], 0.000000e+00
+; COUNT-1-NEXT: [[SELECT93:%.*]] = select i1 [[FCMP92]], double 0.000000e+00, double [[LOAD2]]
+; COUNT-1-NEXT: [[FCMP108:%.*]] = fcmp olt double [[SELECT93]], 0.000000e+00
+; COUNT-1-NEXT: [[SELECT109:%.*]] = select i1 [[FCMP108]], double 1.000000e+00, double 0.000000e+00
+; COUNT-1-NEXT: [[FCMP110:%.*]] = fcmp olt double [[SELECT91]], 0.000000e+00
+; COUNT-1-NEXT: [[SELECT111:%.*]] = select i1 [[FCMP110]], double 1.000000e+00, double 0.000000e+00
+; COUNT-1-NEXT: store double [[SELECT111]], ptr [[GETELEMENTPTR21]], align 8
+; COUNT-1-NEXT: store double [[SELECT109]], ptr [[GETELEMENTPTR13]], align 8
+; COUNT-1-NEXT: ret void
+;
+bb:
+ %getelementptr = getelementptr double, ptr %arg, i64 1
+ %load = load double, ptr %getelementptr, align 8
+ %fcmp = fcmp olt double %load, 0.000000e+00
+ %select3 = select i1 %fcmp, double 0.000000e+00, double %load
+ %select4 = select i1 %fcmp3, double 0.000000e+00, double %load
+ %load7 = load double, ptr %arg, align 8
+ %select10 = select i1 %fcmp3, double 0.000000e+00, double %load7
+ %fcmp11 = fcmp olt double %load2, 0.000000e+00
+ %select128 = select i1 %fcmp11, double 0.000000e+00, double %load7
+ %getelementptr13 = getelementptr double, ptr %arg, i64 3
+ %getelementptr21 = getelementptr double, ptr %arg, i64 4
+ %fcmp23 = fcmp olt double %select10, 0.000000e+00
+ %select24 = select i1 %fcmp23, double 0.000000e+00, double 1.000000e+00
+ %fcmp29 = fcmp olt double %select4, 0.000000e+00
+ %select30 = select i1 %fcmp29, double 1.000000e+00, double 0.000000e+00
+ %fcmp33 = fcmp olt double %select24, %select3
+ %select34 = select i1 %fcmp33, double 0.000000e+00, double %load2
+ %fcmp39 = fcmp olt double %select30, %select128
+ %select40 = select i1 %fcmp39, double %load2, double 0.000000e+00
+ %fcmp62 = fcmp olt double %select34, 0.000000e+00
+ %select639 = select i1 %fcmp62, double 0.000000e+00, double 1.000000e+00
+ %fcmp76 = fcmp olt double %select40, 0.000000e+00
+ %select77 = select i1 %fcmp76, double 0.000000e+00, double 1.000000e+00
+ %fcmp90 = fcmp ogt double %select639, 0.000000e+00
+ %select91 = select i1 %fcmp90, double 0.000000e+00, double %load2
+ %fcmp92 = fcmp ogt double %select77, 0.000000e+00
+ %select93 = select i1 %fcmp92, double 0.000000e+00, double %load2
+ %fcmp108 = fcmp olt double %select93, 0.000000e+00
+ %select109 = select i1 %fcmp108, double 1.000000e+00, double 0.000000e+00
+ %fcmp110 = fcmp olt double %select91, 0.000000e+00
+ %select111 = select i1 %fcmp110, double 1.000000e+00, double 0.000000e+00
+ store double %select111, ptr %g...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/110734
More information about the llvm-commits
mailing list