maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Revert "[LV] Move runtime pointer size check to LVP::plan()." 

This reverts commit 25fbe803d4.

This breaks a clang test which filters for the wrong remark type.
This commit is contained in:
Florian Hahn 2021-03-29 14:41:53 +01:00
parent da381cf7ce
commit 485c8ce733
No known key found for this signature in database
GPG Key ID: 61D7554B5CECDC0D
6 changed files with 60 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
View File

@ -177,6 +177,8 @@ private:
/// followed by a non-expert user.
class LoopVectorizationRequirements {
public:
LoopVectorizationRequirements(OptimizationRemarkEmitter &ORE) : ORE(ORE) {}
/// Track the 1st floating-point instruction that can not be reassociated.
void addExactFPMathInst(Instruction *I) {
if (I && !ExactFPMathInst)
@ -185,19 +187,19 @@ public:
void addRuntimePointerChecks(unsigned Num) { NumRuntimePointerChecks = Num; }
bool doesNotMeet(Function *F, Loop *L, const LoopVectorizeHints &Hints);
Instruction *getExactFPInst() { return ExactFPMathInst; }
bool canVectorizeFPMath(const LoopVectorizeHints &Hints) const {
return !ExactFPMathInst || Hints.allowReordering();
}
unsigned getNumRuntimePointerChecks() const {
return NumRuntimePointerChecks;
}
private:
unsigned NumRuntimePointerChecks = 0;
Instruction *ExactFPMathInst = nullptr;
/// Interface to emit optimization remarks.
OptimizationRemarkEmitter &ORE;
};
/// LoopVectorizationLegality checks if it is legal to vectorize a loop, and

33
llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
View File

@ -37,8 +37,11 @@ static cl::opt<bool>
EnableIfConversion("enable-if-conversion", cl::init(true), cl::Hidden,
cl::desc("Enable if-conversion during vectorization."));
// TODO: Move size-based thresholds out of legality checking, make cost based
// decisions instead of hard thresholds.
static cl::opt<unsigned> PragmaVectorizeMemoryCheckThreshold(
"pragma-vectorize-memory-check-threshold", cl::init(128), cl::Hidden,
cl::desc("The maximum allowed number of runtime memory checks with a "
"vectorize(enable) pragma."));
static cl::opt<unsigned> VectorizeSCEVCheckThreshold(
"vectorize-scev-check-threshold", cl::init(16), cl::Hidden,
cl::desc("The maximum number of SCEV checks allowed."));
@ -243,6 +246,32 @@ void LoopVectorizeHints::setHint(StringRef Name, Metadata *Arg) {
}
}
bool LoopVectorizationRequirements::doesNotMeet(
Function *F, Loop *L, const LoopVectorizeHints &Hints) {
const char *PassName = Hints.vectorizeAnalysisPassName();
bool Failed = false;
// Test if runtime memcheck thresholds are exceeded.
bool PragmaThresholdReached =
NumRuntimePointerChecks > PragmaVectorizeMemoryCheckThreshold;
bool ThresholdReached =
NumRuntimePointerChecks > VectorizerParams::RuntimeMemoryCheckThreshold;
if ((ThresholdReached && !Hints.allowReordering()) ||
PragmaThresholdReached) {
ORE.emit([&]() {
return OptimizationRemarkAnalysisAliasing(PassName, "CantReorderMemOps",
L->getStartLoc(),
L->getHeader())
<< "loop not vectorized: cannot prove it is safe to reorder "
"memory operations";
});
LLVM_DEBUG(dbgs() << "LV: Too many memory checks needed.\n");
Failed = true;
}
return Failed;
}
// Return true if the inner loop \p Lp is uniform with regard to the outer loop
// \p OuterLp (i.e., if the outer loop is vectorized, all the vector lanes
// executing the inner loop will execute the same iterations). This check is

16
llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
View File

@ -34,9 +34,6 @@ namespace llvm {
class LoopVectorizationLegality;
class LoopVectorizationCostModel;
class PredicatedScalarEvolution;
class LoopVectorizationRequirements;
class LoopVectorizeHints;
class OptimizationRemarkEmitter;
class VPRecipeBuilder;
/// VPlan-based builder utility analogous to IRBuilder.
@ -223,12 +220,6 @@ class LoopVectorizationPlanner {
PredicatedScalarEvolution &PSE;
const LoopVectorizeHints &Hints;
LoopVectorizationRequirements &Requirements;
OptimizationRemarkEmitter *ORE;
SmallVector<VPlanPtr, 4> VPlans;
/// A builder used to construct the current plan.
@ -246,12 +237,9 @@ public:
LoopVectorizationLegality *Legal,
LoopVectorizationCostModel &CM,
InterleavedAccessInfo &IAI,
PredicatedScalarEvolution &PSE,
const LoopVectorizeHints &Hints,
LoopVectorizationRequirements &Requirements,
OptimizationRemarkEmitter *ORE)
PredicatedScalarEvolution &PSE)
: OrigLoop(L), LI(LI), TLI(TLI), TTI(TTI), Legal(Legal), CM(CM), IAI(IAI),
PSE(PSE), Hints(Hints), Requirements(Requirements), ORE(ORE) {}
PSE(PSE) {}
/// Plan how to best vectorize, return the best VF and its cost, or None if
/// vectorization and interleaving should be avoided up front.

50
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -197,11 +197,6 @@ static cl::opt<unsigned> TinyTripCountVectorThreshold(
"value are vectorized only if no scalar iteration overheads "
"are incurred."));
static cl::opt<unsigned> PragmaVectorizeMemoryCheckThreshold(
"pragma-vectorize-memory-check-threshold", cl::init(128), cl::Hidden,
cl::desc("The maximum allowed number of runtime memory checks with a "
"vectorize(enable) pragma."));
// Option prefer-predicate-over-epilogue indicates that an epilogue is undesired,
// that predication is preferred, and this lists all options. I.e., the
// vectorizer will try to fold the tail-loop (epilogue) into the vector body
@ -7779,30 +7774,7 @@ LoopVectorizationPlanner::plan(ElementCount UserVF, unsigned UserIC) {
return VectorizationFactor::Disabled();
// Select the optimal vectorization factor.
auto SelectedVF = CM.selectVectorizationFactor(MaxVF);
// Check if it is profitable to vectorize with runtime checks.
unsigned NumRuntimePointerChecks = Requirements.getNumRuntimePointerChecks();
if (SelectedVF.Width.getKnownMinValue() > 1 && NumRuntimePointerChecks) {
bool PragmaThresholdReached =
NumRuntimePointerChecks > PragmaVectorizeMemoryCheckThreshold;
bool ThresholdReached =
NumRuntimePointerChecks > VectorizerParams::RuntimeMemoryCheckThreshold;
if ((ThresholdReached && !Hints.allowReordering()) ||
PragmaThresholdReached) {
ORE->emit([&]() {
return OptimizationRemarkMissed(DEBUG_TYPE, "CantReorderMemOps",
OrigLoop->getStartLoc(),
OrigLoop->getHeader())
<< "loop not vectorized: cannot prove it is safe to reorder "
"memory operations";
});
LLVM_DEBUG(dbgs() << "LV: Too many memory checks needed.\n");
Hints.emitRemarkWithHints();
return VectorizationFactor::Disabled();
}
}
return SelectedVF;
return CM.selectVectorizationFactor(MaxVF);
}
void LoopVectorizationPlanner::setBestPlan(ElementCount VF, unsigned UF) {
@ -9419,8 +9391,7 @@ static bool processLoopInVPlanNativePath(
LoopVectorizationLegality *LVL, TargetTransformInfo *TTI,
TargetLibraryInfo *TLI, DemandedBits *DB, AssumptionCache *AC,
OptimizationRemarkEmitter *ORE, BlockFrequencyInfo *BFI,
ProfileSummaryInfo *PSI, LoopVectorizeHints &Hints,
LoopVectorizationRequirements &Requirements) {
ProfileSummaryInfo *PSI, LoopVectorizeHints &Hints) {
if (isa<SCEVCouldNotCompute>(PSE.getBackedgeTakenCount())) {
LLVM_DEBUG(dbgs() << "LV: cannot compute the outer-loop trip count\n");
@ -9438,8 +9409,7 @@ static bool processLoopInVPlanNativePath(
// Use the planner for outer loop vectorization.
// TODO: CM is not used at this point inside the planner. Turn CM into an
// optional argument if we don't need it in the future.
LoopVectorizationPlanner LVP(L, LI, TLI, TTI, LVL, CM, IAI, PSE, Hints,
Requirements, ORE);
LoopVectorizationPlanner LVP(L, LI, TLI, TTI, LVL, CM, IAI, PSE);
// Get user vectorization factor.
ElementCount UserVF = Hints.getWidth();
@ -9567,7 +9537,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
PredicatedScalarEvolution PSE(*SE, *L);
// Check if it is legal to vectorize the loop.
LoopVectorizationRequirements Requirements;
LoopVectorizationRequirements Requirements(*ORE);
LoopVectorizationLegality LVL(L, PSE, DT, TTI, TLI, AA, F, GetLAA, LI, ORE,
&Requirements, &Hints, DB, AC, BFI, PSI);
if (!LVL.canVectorize(EnableVPlanNativePath)) {
@ -9588,7 +9558,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
// pipeline.
if (!L->isInnermost())
return processLoopInVPlanNativePath(L, PSE, LI, DT, &LVL, TTI, TLI, DB, AC,
ORE, BFI, PSI, Hints, Requirements);
ORE, BFI, PSI, Hints);
assert(L->isInnermost() && "Inner loop expected.");
@ -9667,8 +9637,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
CM.collectValuesToIgnore();
// Use the planner for vectorization.
LoopVectorizationPlanner LVP(L, LI, TLI, TTI, &LVL, CM, IAI, PSE, Hints,
Requirements, ORE);
LoopVectorizationPlanner LVP(L, LI, TLI, TTI, &LVL, CM, IAI, PSE);
// Get user vectorization factor and interleave count.
ElementCount UserVF = Hints.getWidth();
@ -9689,6 +9658,13 @@ bool LoopVectorizePass::processLoop(Loop *L) {
// Identify the diagnostic messages that should be produced.
std::pair<StringRef, std::string> VecDiagMsg, IntDiagMsg;
bool VectorizeLoop = true, InterleaveLoop = true;
if (Requirements.doesNotMeet(F, L, Hints)) {
LLVM_DEBUG(dbgs() << "LV: Not vectorizing: loop did not meet vectorization "
"requirements.\n");
Hints.emitRemarkWithHints();
return false;
}
if (VF.Width.isScalar()) {
LLVM_DEBUG(dbgs() << "LV: Vectorization is possible but not beneficial.\n");
VecDiagMsg = std::make_pair(

4
llvm/test/LTO/X86/diagnostic-handler-remarks.ll
View File

@ -6,14 +6,14 @@
; Confirm that there are -pass-remarks.
; RUN: llvm-lto -use-new-pm=false \
; RUN: -pass-remarks=inline \
; RUN: -exported-symbol _func2 -pass-remarks-missed=loop-vectorize \
; RUN: -exported-symbol _func2 -pass-remarks-analysis=loop-vectorize \
; RUN: -exported-symbol _main -o %t.o %t.bc 2>&1 | \
; RUN: FileCheck %s -allow-empty -check-prefix=REMARKS
; RUN: llvm-nm %t.o | FileCheck %s -check-prefix NM
; RUN: llvm-lto -use-new-pm=false \
; RUN: -pass-remarks=inline -use-diagnostic-handler \
; RUN: -exported-symbol _func2 -pass-remarks-missed=loop-vectorize \
; RUN: -exported-symbol _func2 -pass-remarks-analysis=loop-vectorize \
; RUN: -exported-symbol _main -o %t.o %t.bc 2>&1 | \
; RUN: FileCheck %s -allow-empty -check-prefix=REMARKS_DH
; RUN: llvm-nm %t.o | FileCheck %s -check-prefix NM

14
llvm/test/Transforms/LoopVectorize/X86/runtime-limit.ll → llvm/test/Transforms/LoopVectorize/runtime-limit.ll
View File

@ -1,19 +1,17 @@
; RUN: opt < %s -loop-vectorize -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s -check-prefix=OVERRIDE
; RUN: opt < %s -loop-vectorize -pragma-vectorize-memory-check-threshold=6 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s
; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s -check-prefix=OVERRIDE
; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -pragma-vectorize-memory-check-threshold=6 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux"
; First loop produced diagnostic pass remark.
;CHECK: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 2)
;CHECK: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 1)
; Second loop produces diagnostic analysis remark.
;CHECK: remark: {{.*}}:0:0: loop not vectorized: cannot prove it is safe to reorder memory operations
; First loop produced diagnostic pass remark.
;OVERRIDE: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 2)
;OVERRIDE: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 1)
; Second loop produces diagnostic pass remark.
;OVERRIDE: remark: {{.*}}:0:0: loop not vectorized: cannot prove it is safe to reorder memory operations
;OVERRIDE: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 1)
; We are vectorizing with 6 runtime checks.
;CHECK-LABEL: func1x6(
@ -58,7 +56,7 @@ for.end: ; preds = %for.body
;CHECK: ret
; We vectorize with 12 checks if a vectorization hint is provided.
;OVERRIDE-LABEL: func2x6(
;OVERRIDE-NOT: <4 x i32>
;OVERRIDE: <4 x i32>
;OVERRIDE: ret
define i32 @func2x6(i32* nocapture %out, i32* nocapture %out2, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) {
entry: