mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-23 01:30:19 +00:00
Use discriminator information in sample profiles.
Summary: When the sample profiles include discriminator information, use the discriminator values to distinguish instruction weights in different basic blocks. This modifies the BodySamples mapping to map <line, discriminator> pairs to weights. Instructions on the same line but different blocks, will use different discriminator values. This, in turn, means that the blocks may have different weights. Other changes in this patch: - Add tests for positive values of line offset, discriminator and samples. - Change data types from uint32_t to unsigned and int and do additional validation. Reviewers: chandlerc CC: llvm-commits Differential Revision: http://llvm-reviews.chandlerc.com/D2857 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@203508 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Diego Novillo
parent
e45534d027
commit
87393cfd6b
@ -64,12 +64,51 @@ static cl::opt<unsigned> SampleProfileMaxPropagateIterations(
|
||||
"sample block/edge weights through the CFG."));
|
||||
|
||||
namespace {
|
||||
/// \brief Represents the relative location of an instruction.
|
||||
///
|
||||
/// Instruction locations are specified by the line offset from the
|
||||
/// beginning of the function (marked by the line where the function
|
||||
/// header is) and the discriminator value within that line.
|
||||
///
|
||||
/// The discriminator value is useful to distinguish instructions
|
||||
/// that are on the same line but belong to different basic blocks
|
||||
/// (e.g., the two post-increment instructions in "if (p) x++; else y++;").
|
||||
struct InstructionLocation {
|
||||
InstructionLocation(int L, unsigned D) : LineOffset(L), Discriminator(D) {}
|
||||
int LineOffset;
|
||||
unsigned Discriminator;
|
||||
};
|
||||
}
|
||||
|
||||
typedef DenseMap<uint32_t, uint32_t> BodySampleMap;
|
||||
typedef DenseMap<BasicBlock *, uint32_t> BlockWeightMap;
|
||||
namespace llvm {
|
||||
template <> struct DenseMapInfo<InstructionLocation> {
|
||||
typedef DenseMapInfo<int> OffsetInfo;
|
||||
typedef DenseMapInfo<unsigned> DiscriminatorInfo;
|
||||
static inline InstructionLocation getEmptyKey() {
|
||||
return InstructionLocation(OffsetInfo::getEmptyKey(),
|
||||
DiscriminatorInfo::getEmptyKey());
|
||||
}
|
||||
static inline InstructionLocation getTombstoneKey() {
|
||||
return InstructionLocation(OffsetInfo::getTombstoneKey(),
|
||||
DiscriminatorInfo::getTombstoneKey());
|
||||
}
|
||||
static inline unsigned getHashValue(InstructionLocation Val) {
|
||||
return DenseMapInfo<std::pair<int, unsigned> >::getHashValue(
|
||||
std::pair<int, unsigned>(Val.LineOffset, Val.Discriminator));
|
||||
}
|
||||
static inline bool isEqual(InstructionLocation LHS, InstructionLocation RHS) {
|
||||
return LHS.LineOffset == RHS.LineOffset &&
|
||||
LHS.Discriminator == RHS.Discriminator;
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
namespace {
|
||||
typedef DenseMap<InstructionLocation, unsigned> BodySampleMap;
|
||||
typedef DenseMap<BasicBlock *, unsigned> BlockWeightMap;
|
||||
typedef DenseMap<BasicBlock *, BasicBlock *> EquivalenceClassMap;
|
||||
typedef std::pair<BasicBlock *, BasicBlock *> Edge;
|
||||
typedef DenseMap<Edge, uint32_t> EdgeWeightMap;
|
||||
typedef DenseMap<Edge, unsigned> EdgeWeightMap;
|
||||
typedef DenseMap<BasicBlock *, SmallVector<BasicBlock *, 8> > BlockEdgeMap;
|
||||
|
||||
/// \brief Representation of the runtime profile for a function.
|
||||
@ -81,17 +120,18 @@ class SampleFunctionProfile {
|
||||
public:
|
||||
SampleFunctionProfile()
|
||||
: TotalSamples(0), TotalHeadSamples(0), HeaderLineno(0), DT(0), PDT(0),
|
||||
LI(0) {}
|
||||
LI(0), Ctx(0) {}
|
||||
|
||||
unsigned getFunctionLoc(Function &F);
|
||||
bool emitAnnotations(Function &F, DominatorTree *DomTree,
|
||||
PostDominatorTree *PostDomTree, LoopInfo *Loops);
|
||||
uint32_t getInstWeight(Instruction &I);
|
||||
uint32_t getBlockWeight(BasicBlock *B);
|
||||
unsigned getInstWeight(Instruction &I);
|
||||
unsigned getBlockWeight(BasicBlock *B);
|
||||
void addTotalSamples(unsigned Num) { TotalSamples += Num; }
|
||||
void addHeadSamples(unsigned Num) { TotalHeadSamples += Num; }
|
||||
void addBodySamples(unsigned LineOffset, unsigned Num) {
|
||||
BodySamples[LineOffset] += Num;
|
||||
void addBodySamples(int LineOffset, unsigned Discriminator, unsigned Num) {
|
||||
assert(LineOffset >= 0);
|
||||
BodySamples[InstructionLocation(LineOffset, Discriminator)] += Num;
|
||||
}
|
||||
void print(raw_ostream &OS);
|
||||
void printEdgeWeight(raw_ostream &OS, Edge E);
|
||||
@ -103,7 +143,7 @@ public:
|
||||
SmallVector<BasicBlock *, 8> Descendants,
|
||||
DominatorTreeBase<BasicBlock> *DomTree);
|
||||
void propagateWeights(Function &F);
|
||||
uint32_t visitEdge(Edge E, unsigned *NumUnknownEdges, Edge *UnknownEdge);
|
||||
unsigned visitEdge(Edge E, unsigned *NumUnknownEdges, Edge *UnknownEdge);
|
||||
void buildEdges(Function &F);
|
||||
bool propagateThroughEdges(Function &F);
|
||||
bool empty() { return BodySamples.empty(); }
|
||||
@ -168,6 +208,9 @@ protected:
|
||||
|
||||
/// \brief Successors for each basic block in the CFG.
|
||||
BlockEdgeMap Successors;
|
||||
|
||||
/// \brief LLVM context holding the debug data we need.
|
||||
LLVMContext *Ctx;
|
||||
};
|
||||
|
||||
/// \brief Sample-based profile reader.
|
||||
@ -276,7 +319,8 @@ void SampleFunctionProfile::print(raw_ostream &OS) {
|
||||
for (BodySampleMap::const_iterator SI = BodySamples.begin(),
|
||||
SE = BodySamples.end();
|
||||
SI != SE; ++SI)
|
||||
OS << "\tline offset: " << SI->first
|
||||
OS << "\tline offset: " << SI->first.LineOffset
|
||||
<< ", discriminator: " << SI->first.Discriminator
|
||||
<< ", number of samples: " << SI->second << "\n";
|
||||
OS << "\n";
|
||||
}
|
||||
@ -364,10 +408,6 @@ void SampleModuleProfile::dump() {
|
||||
/// b- [OPTIONAL] Discriminator. This is used if the sampled program
|
||||
/// was compiled with DWARF discriminator support
|
||||
/// (http://wiki.dwarfstd.org/index.php?title=Path_Discriminators)
|
||||
/// This is currently only emitted by GCC and we just ignore it.
|
||||
///
|
||||
/// FIXME: Handle discriminators, since they are needed to distinguish
|
||||
/// multiple control flow within a single source LOC.
|
||||
///
|
||||
/// c- Number of samples. This is the number of samples collected by
|
||||
/// the profiler at this source location.
|
||||
@ -408,7 +448,7 @@ void SampleModuleProfile::loadText() {
|
||||
// mentioned more than once, and we are collecting flat profiles,
|
||||
// accumulate samples as we parse them.
|
||||
Regex HeadRE("^([^:]+):([0-9]+):([0-9]+)$");
|
||||
Regex LineSample("^([0-9]+)(\\.[0-9]+)?: ([0-9]+)(.*)$");
|
||||
Regex LineSample("^([0-9]+)\\.?([0-9]+)?: ([0-9]+)(.*)$");
|
||||
while (!LineIt.is_at_eof()) {
|
||||
// Read the header of each function. The function header should
|
||||
// have this format:
|
||||
@ -439,11 +479,10 @@ void SampleModuleProfile::loadText() {
|
||||
LineIt.line_number(),
|
||||
"Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found " + *LineIt);
|
||||
assert(Matches.size() == 5);
|
||||
unsigned LineOffset, NumSamples;
|
||||
unsigned LineOffset, NumSamples, Discriminator = 0;
|
||||
Matches[1].getAsInteger(10, LineOffset);
|
||||
|
||||
// FIXME: Handle discriminator information (in Matches[2]).
|
||||
|
||||
if (Matches[2] != "")
|
||||
Matches[2].getAsInteger(10, Discriminator);
|
||||
Matches[3].getAsInteger(10, NumSamples);
|
||||
|
||||
// FIXME: Handle called targets (in Matches[4]).
|
||||
@ -454,7 +493,7 @@ void SampleModuleProfile::loadText() {
|
||||
// avoid the confusion later on.
|
||||
if (NumSamples == 0)
|
||||
NumSamples = 1;
|
||||
FProfile.addBodySamples(LineOffset, NumSamples);
|
||||
FProfile.addBodySamples(LineOffset, Discriminator, NumSamples);
|
||||
++LineIt;
|
||||
}
|
||||
}
|
||||
@ -471,14 +510,19 @@ void SampleModuleProfile::loadText() {
|
||||
/// \param Inst Instruction to query.
|
||||
///
|
||||
/// \returns The profiled weight of I.
|
||||
uint32_t SampleFunctionProfile::getInstWeight(Instruction &Inst) {
|
||||
unsigned Lineno = Inst.getDebugLoc().getLine();
|
||||
unsigned SampleFunctionProfile::getInstWeight(Instruction &Inst) {
|
||||
DebugLoc DLoc = Inst.getDebugLoc();
|
||||
unsigned Lineno = DLoc.getLine();
|
||||
if (Lineno < HeaderLineno)
|
||||
return 0;
|
||||
unsigned LOffset = Lineno - HeaderLineno;
|
||||
uint32_t Weight = BodySamples.lookup(LOffset);
|
||||
DEBUG(dbgs() << " " << Lineno << ":" << Inst.getDebugLoc().getCol() << ":"
|
||||
<< Inst << " (line offset: " << LOffset
|
||||
|
||||
DILocation DIL(DLoc.getAsMDNode(*Ctx));
|
||||
int LOffset = Lineno - HeaderLineno;
|
||||
unsigned Discriminator = DIL.getDiscriminator();
|
||||
unsigned Weight =
|
||||
BodySamples.lookup(InstructionLocation(LOffset, Discriminator));
|
||||
DEBUG(dbgs() << " " << Lineno << "." << Discriminator << ":" << Inst
|
||||
<< " (line offset: " << LOffset << "." << Discriminator
|
||||
<< " - weight: " << Weight << ")\n");
|
||||
return Weight;
|
||||
}
|
||||
@ -492,7 +536,7 @@ uint32_t SampleFunctionProfile::getInstWeight(Instruction &Inst) {
|
||||
/// \param B The basic block to query.
|
||||
///
|
||||
/// \returns The computed weight of B.
|
||||
uint32_t SampleFunctionProfile::getBlockWeight(BasicBlock *B) {
|
||||
unsigned SampleFunctionProfile::getBlockWeight(BasicBlock *B) {
|
||||
// If we've computed B's weight before, return it.
|
||||
std::pair<BlockWeightMap::iterator, bool> Entry =
|
||||
BlockWeights.insert(std::make_pair(B, 0));
|
||||
@ -500,9 +544,9 @@ uint32_t SampleFunctionProfile::getBlockWeight(BasicBlock *B) {
|
||||
return Entry.first->second;
|
||||
|
||||
// Otherwise, compute and cache B's weight.
|
||||
uint32_t Weight = 0;
|
||||
unsigned Weight = 0;
|
||||
for (BasicBlock::iterator I = B->begin(), E = B->end(); I != E; ++I) {
|
||||
uint32_t InstWeight = getInstWeight(*I);
|
||||
unsigned InstWeight = getInstWeight(*I);
|
||||
if (InstWeight > Weight)
|
||||
Weight = InstWeight;
|
||||
}
|
||||
@ -520,7 +564,7 @@ bool SampleFunctionProfile::computeBlockWeights(Function &F) {
|
||||
bool Changed = false;
|
||||
DEBUG(dbgs() << "Block weights\n");
|
||||
for (Function::iterator B = F.begin(), E = F.end(); B != E; ++B) {
|
||||
uint32_t Weight = getBlockWeight(B);
|
||||
unsigned Weight = getBlockWeight(B);
|
||||
Changed |= (Weight > 0);
|
||||
DEBUG(printBlockWeight(dbgs(), B));
|
||||
}
|
||||
@ -572,8 +616,8 @@ void SampleFunctionProfile::findEquivalencesFor(
|
||||
// during the propagation phase. Right now, we just want to
|
||||
// make sure that BB1 has the largest weight of all the
|
||||
// members of its equivalence set.
|
||||
uint32_t &BB1Weight = BlockWeights[BB1];
|
||||
uint32_t &BB2Weight = BlockWeights[BB2];
|
||||
unsigned &BB1Weight = BlockWeights[BB1];
|
||||
unsigned &BB2Weight = BlockWeights[BB2];
|
||||
BB1Weight = std::max(BB1Weight, BB2Weight);
|
||||
}
|
||||
}
|
||||
@ -659,7 +703,7 @@ void SampleFunctionProfile::findEquivalenceClasses(Function &F) {
|
||||
/// \param UnknownEdge Set if E has not been visited before.
|
||||
///
|
||||
/// \returns E's weight, if known. Otherwise, return 0.
|
||||
uint32_t SampleFunctionProfile::visitEdge(Edge E, unsigned *NumUnknownEdges,
|
||||
unsigned SampleFunctionProfile::visitEdge(Edge E, unsigned *NumUnknownEdges,
|
||||
Edge *UnknownEdge) {
|
||||
if (!VisitedEdges.count(E)) {
|
||||
(*NumUnknownEdges)++;
|
||||
@ -693,7 +737,7 @@ bool SampleFunctionProfile::propagateThroughEdges(Function &F) {
|
||||
// only case we are interested in handling is when only a single
|
||||
// edge is unknown (see setEdgeOrBlockWeight).
|
||||
for (unsigned i = 0; i < 2; i++) {
|
||||
uint32_t TotalWeight = 0;
|
||||
unsigned TotalWeight = 0;
|
||||
unsigned NumUnknownEdges = 0;
|
||||
Edge UnknownEdge, SelfReferentialEdge;
|
||||
|
||||
@ -737,7 +781,7 @@ bool SampleFunctionProfile::propagateThroughEdges(Function &F) {
|
||||
// all edges will get a weight, or iteration will stop when
|
||||
// it reaches SampleProfileMaxPropagateIterations.
|
||||
if (NumUnknownEdges <= 1) {
|
||||
uint32_t &BBWeight = BlockWeights[BB];
|
||||
unsigned &BBWeight = BlockWeights[BB];
|
||||
if (NumUnknownEdges == 0) {
|
||||
// If we already know the weight of all edges, the weight of the
|
||||
// basic block can be computed. It should be no larger than the sum
|
||||
@ -764,7 +808,7 @@ bool SampleFunctionProfile::propagateThroughEdges(Function &F) {
|
||||
printEdgeWeight(dbgs(), UnknownEdge));
|
||||
}
|
||||
} else if (SelfReferentialEdge.first && VisitedBlocks.count(BB)) {
|
||||
uint32_t &BBWeight = BlockWeights[BB];
|
||||
unsigned &BBWeight = BlockWeights[BB];
|
||||
// We have a self-referential edge and the weight of BB is known.
|
||||
if (BBWeight >= TotalWeight)
|
||||
EdgeWeights[SelfReferentialEdge] = BBWeight - TotalWeight;
|
||||
@ -857,14 +901,13 @@ void SampleFunctionProfile::propagateWeights(Function &F) {
|
||||
continue;
|
||||
|
||||
DEBUG(dbgs() << "\nGetting weights for branch at line "
|
||||
<< TI->getDebugLoc().getLine() << ":"
|
||||
<< TI->getDebugLoc().getCol() << ".\n");
|
||||
SmallVector<uint32_t, 4> Weights;
|
||||
<< TI->getDebugLoc().getLine() << ".\n");
|
||||
SmallVector<unsigned, 4> Weights;
|
||||
bool AllWeightsZero = true;
|
||||
for (unsigned I = 0; I < TI->getNumSuccessors(); ++I) {
|
||||
BasicBlock *Succ = TI->getSuccessor(I);
|
||||
Edge E = std::make_pair(B, Succ);
|
||||
uint32_t Weight = EdgeWeights[E];
|
||||
unsigned Weight = EdgeWeights[E];
|
||||
DEBUG(dbgs() << "\t"; printEdgeWeight(dbgs(), E));
|
||||
Weights.push_back(Weight);
|
||||
if (Weight != 0)
|
||||
@ -970,6 +1013,7 @@ bool SampleFunctionProfile::emitAnnotations(Function &F, DominatorTree *DomTree,
|
||||
DT = DomTree;
|
||||
PDT = PostDomTree;
|
||||
LI = Loops;
|
||||
Ctx = &F.getParent()->getContext();
|
||||
|
||||
// Compute basic block weights.
|
||||
Changed |= computeBlockWeights(F);
|
||||
@ -991,6 +1035,7 @@ INITIALIZE_PASS_BEGIN(SampleProfileLoader, "sample-profile",
|
||||
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
|
||||
INITIALIZE_PASS_DEPENDENCY(PostDominatorTree)
|
||||
INITIALIZE_PASS_DEPENDENCY(LoopInfo)
|
||||
INITIALIZE_PASS_DEPENDENCY(AddDiscriminators)
|
||||
INITIALIZE_PASS_END(SampleProfileLoader, "sample-profile",
|
||||
"Sample Profile loader", false, false)
|
||||
|
||||
|
||||
@ -0,0 +1,2 @@
|
||||
empty:100:0
|
||||
1.-3: 10
|
||||
@ -0,0 +1,2 @@
|
||||
empty:100:0
|
||||
-1: 10
|
||||
2
test/Transforms/SampleProfile/Inputs/bad_samples.prof
Normal file
2
test/Transforms/SampleProfile/Inputs/bad_samples.prof
Normal file
@ -0,0 +1,2 @@
|
||||
empty:100:0
|
||||
1.3: -10
|
||||
@ -3,9 +3,8 @@ _Z3sumii:105580:5279
|
||||
1: 5279
|
||||
2: 5279
|
||||
main:225715:0
|
||||
2: 5553
|
||||
2.1: 5553
|
||||
3: 5391
|
||||
# This indicates that at line 3 of this function, the 'then' branch
|
||||
# of the conditional is taken (discriminator '1'). However, we still
|
||||
# do not handle this case, so we compute the wrong branch weights here.
|
||||
# of the conditional is taken (discriminator '1').
|
||||
3.1: 5752 _Z3sumii:5860
|
||||
|
||||
8
test/Transforms/SampleProfile/Inputs/discriminator.prof
Normal file
8
test/Transforms/SampleProfile/Inputs/discriminator.prof
Normal file
@ -0,0 +1,8 @@
|
||||
foo:1000:0
|
||||
1: 1
|
||||
2: 1
|
||||
2.1: 100
|
||||
3: 100
|
||||
3.1: 5
|
||||
4: 100
|
||||
5: 1
|
||||
@ -117,17 +117,17 @@ attributes #4 = { nounwind readonly }
|
||||
!16 = metadata !{i32 786468, null, null, metadata !"double", i32 0, i64 64, i64 64, i64 0, i32 0, i32 4} ; [ DW_TAG_base_type ] [double] [line 0, size 64, align 64, offset 0, enc DW_ATE_float]
|
||||
!17 = metadata !{i32 786688, metadata !4, metadata !"limit", metadata !5, i32 8, metadata !8, i32 0, i32 0} ; [ DW_TAG_auto_variable ] [limit] [line 8]
|
||||
!18 = metadata !{i32 786688, metadata !19, metadata !"s", metadata !5, i32 10, metadata !16, i32 0, i32 0} ; [ DW_TAG_auto_variable ] [s] [line 10]
|
||||
!19 = metadata !{i32 786443, metadata !1, metadata !20, i32 9, i32 0, i32 2} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!20 = metadata !{i32 786443, metadata !1, metadata !4, i32 9, i32 0, i32 1} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!19 = metadata !{i32 786443, metadata !1, metadata !20, i32 9, i32 0, i32 0, i32 2} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!20 = metadata !{i32 786443, metadata !1, metadata !4, i32 9, i32 0, i32 0, i32 1} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!21 = metadata !{i32 786688, metadata !22, metadata !"u", metadata !5, i32 11, metadata !8, i32 0, i32 0} ; [ DW_TAG_auto_variable ] [u] [line 11]
|
||||
!22 = metadata !{i32 786443, metadata !1, metadata !19, i32 11, i32 0, i32 3} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!22 = metadata !{i32 786443, metadata !1, metadata !19, i32 11, i32 0, i32 0, i32 3} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!23 = metadata !{i32 786688, metadata !24, metadata !"x", metadata !5, i32 12, metadata !16, i32 0, i32 0} ; [ DW_TAG_auto_variable ] [x] [line 12]
|
||||
!24 = metadata !{i32 786443, metadata !1, metadata !22, i32 11, i32 0, i32 4} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!24 = metadata !{i32 786443, metadata !1, metadata !22, i32 11, i32 0, i32 0, i32 4} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!25 = metadata !{i32 2, metadata !"Dwarf Version", i32 4}
|
||||
!26 = metadata !{metadata !"clang version 3.4 (trunk 192896) (llvm/trunk 192895)"}
|
||||
!27 = metadata !{i32 4, i32 0, metadata !4, null}
|
||||
!28 = metadata !{i32 5, i32 0, metadata !29, null}
|
||||
!29 = metadata !{i32 786443, metadata !1, metadata !4, i32 5, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!29 = metadata !{i32 786443, metadata !1, metadata !4, i32 5, i32 0, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [./branch.cc]
|
||||
!30 = metadata !{i32 8, i32 0, metadata !4, null} ; [ DW_TAG_imported_declaration ]
|
||||
!31 = metadata !{metadata !32, metadata !32, i64 0}
|
||||
!32 = metadata !{metadata !"any pointer", metadata !33, i64 0}
|
||||
|
||||
@ -42,46 +42,47 @@ entry:
|
||||
br label %while.cond, !dbg !13
|
||||
|
||||
while.cond: ; preds = %if.end, %entry
|
||||
%0 = load i32* %i, align 4, !dbg !13
|
||||
%inc = add nsw i32 %0, 1, !dbg !13
|
||||
store i32 %inc, i32* %i, align 4, !dbg !13
|
||||
%cmp = icmp slt i32 %0, 400000000, !dbg !13
|
||||
br i1 %cmp, label %while.body, label %while.end, !dbg !13
|
||||
; CHECK: edge while.cond -> while.body probability is 11143 / 16696 = 66.7405%
|
||||
; CHECK: edge while.cond -> while.end probability is 5553 / 16696 = 33.2595%
|
||||
%0 = load i32* %i, align 4, !dbg !14
|
||||
%inc = add nsw i32 %0, 1, !dbg !14
|
||||
store i32 %inc, i32* %i, align 4, !dbg !14
|
||||
%cmp = icmp slt i32 %0, 400000000, !dbg !14
|
||||
br i1 %cmp, label %while.body, label %while.end, !dbg !14
|
||||
; CHECK: edge while.cond -> while.body probability is 5391 / 5392 = 99.9815% [HOT edge]
|
||||
; CHECK: edge while.cond -> while.end probability is 1 / 5392 = 0.018546%
|
||||
|
||||
while.body: ; preds = %while.cond
|
||||
%1 = load i32* %i, align 4, !dbg !14
|
||||
%cmp1 = icmp ne i32 %1, 100, !dbg !14
|
||||
br i1 %cmp1, label %if.then, label %if.else, !dbg !14
|
||||
; NOTE: These weights are wrong. We currently do not handle multiple
|
||||
; control flow paths in the same line. The edge while.body -> if.then
|
||||
; should be much heavier than the other one. Support for DWARF
|
||||
; discriminators will fix this.
|
||||
; CHECK: edge while.body -> if.then probability is 11143 / 22286 = 50%
|
||||
; CHECK: edge while.body -> if.else probability is 11143 / 22286 = 50%
|
||||
%1 = load i32* %i, align 4, !dbg !16
|
||||
%cmp1 = icmp ne i32 %1, 100, !dbg !16
|
||||
br i1 %cmp1, label %if.then, label %if.else, !dbg !16
|
||||
; Without discriminator information, the profiler used to think that
|
||||
; both branches out of while.body had the same weight. In reality,
|
||||
; the edge while.body->if.then is taken most of the time.
|
||||
;
|
||||
; CHECK: edge while.body -> if.then probability is 5752 / 5753 = 99.9826% [HOT edge]
|
||||
; CHECK: edge while.body -> if.else probability is 1 / 5753 = 0.0173822%
|
||||
|
||||
|
||||
if.then: ; preds = %while.body
|
||||
%2 = load i32* %i, align 4, !dbg !14
|
||||
%3 = load i32* %s, align 4, !dbg !14
|
||||
%call = call i32 @_Z3sumii(i32 %2, i32 %3), !dbg !14
|
||||
store i32 %call, i32* %s, align 4, !dbg !14
|
||||
br label %if.end, !dbg !14
|
||||
%2 = load i32* %i, align 4, !dbg !18
|
||||
%3 = load i32* %s, align 4, !dbg !18
|
||||
%call = call i32 @_Z3sumii(i32 %2, i32 %3), !dbg !18
|
||||
store i32 %call, i32* %s, align 4, !dbg !18
|
||||
br label %if.end, !dbg !18
|
||||
|
||||
if.else: ; preds = %while.body
|
||||
store i32 30, i32* %s, align 4, !dbg !14
|
||||
store i32 30, i32* %s, align 4, !dbg !20
|
||||
br label %if.end
|
||||
|
||||
if.end: ; preds = %if.else, %if.then
|
||||
br label %while.cond, !dbg !14
|
||||
br label %while.cond, !dbg !22
|
||||
|
||||
while.end: ; preds = %while.cond
|
||||
%4 = load i32* %s, align 4, !dbg !16
|
||||
%call2 = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([11 x i8]* @.str, i32 0, i32 0), i32 %4), !dbg !16
|
||||
ret i32 0, !dbg !17
|
||||
%4 = load i32* %s, align 4, !dbg !24
|
||||
%call2 = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([11 x i8]* @.str, i32 0, i32 0), i32 %4), !dbg !24
|
||||
ret i32 0, !dbg !25
|
||||
}
|
||||
|
||||
declare i32 @printf(i8*, ...)
|
||||
declare i32 @printf(i8*, ...) #2
|
||||
|
||||
!llvm.dbg.cu = !{!0}
|
||||
!llvm.module.flags = !{!8, !9}
|
||||
@ -89,7 +90,7 @@ declare i32 @printf(i8*, ...)
|
||||
|
||||
!0 = metadata !{i32 786449, metadata !1, i32 4, metadata !"clang version 3.5 ", i1 false, metadata !"", i32 0, metadata !2, metadata !2, metadata !3, metadata !2, metadata !2, metadata !""} ; [ DW_TAG_compile_unit ] [./calls.cc] [DW_LANG_C_plus_plus]
|
||||
!1 = metadata !{metadata !"calls.cc", metadata !"."}
|
||||
!2 = metadata !{i32 0}
|
||||
!2 = metadata !{}
|
||||
!3 = metadata !{metadata !4, metadata !7}
|
||||
!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"sum", metadata !"sum", metadata !"", i32 3, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 false, i32 (i32, i32)* @_Z3sumii, null, null, metadata !2, i32 3} ; [ DW_TAG_subprogram ] [line 3] [def] [sum]
|
||||
!5 = metadata !{i32 786473, metadata !1} ; [ DW_TAG_file_type ] [./calls.cc]
|
||||
@ -101,7 +102,15 @@ declare i32 @printf(i8*, ...)
|
||||
!11 = metadata !{i32 4, i32 0, metadata !4, null}
|
||||
!12 = metadata !{i32 8, i32 0, metadata !7, null} ; [ DW_TAG_imported_declaration ]
|
||||
!13 = metadata !{i32 9, i32 0, metadata !7, null}
|
||||
!14 = metadata !{i32 10, i32 0, metadata !15, null}
|
||||
!15 = metadata !{i32 786443, metadata !1, metadata !7, i32 10, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [./calls.cc]
|
||||
!16 = metadata !{i32 11, i32 0, metadata !7, null}
|
||||
!17 = metadata !{i32 12, i32 0, metadata !7, null}
|
||||
!14 = metadata !{i32 9, i32 0, metadata !15, null}
|
||||
!15 = metadata !{i32 786443, metadata !1, metadata !7, i32 9, i32 0, i32 1, i32 1} ; [ DW_TAG_lexical_block ] [./calls.cc]
|
||||
!16 = metadata !{i32 10, i32 0, metadata !17, null}
|
||||
!17 = metadata !{i32 786443, metadata !1, metadata !7, i32 10, i32 0, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [./calls.cc]
|
||||
!18 = metadata !{i32 10, i32 0, metadata !19, null}
|
||||
!19 = metadata !{i32 786443, metadata !1, metadata !17, i32 10, i32 0, i32 1, i32 2} ; [ DW_TAG_lexical_block ] [./calls.cc]
|
||||
!20 = metadata !{i32 10, i32 0, metadata !21, null}
|
||||
!21 = metadata !{i32 786443, metadata !1, metadata !17, i32 10, i32 0, i32 2, i32 3} ; [ DW_TAG_lexical_block ] [./calls.cc]
|
||||
!22 = metadata !{i32 10, i32 0, metadata !23, null}
|
||||
!23 = metadata !{i32 786443, metadata !1, metadata !17, i32 10, i32 0, i32 3, i32 4} ; [ DW_TAG_lexical_block ] [./calls.cc]
|
||||
!24 = metadata !{i32 11, i32 0, metadata !7, null}
|
||||
!25 = metadata !{i32 12, i32 0, metadata !7, null}
|
||||
|
||||
90
test/Transforms/SampleProfile/discriminator.ll
Normal file
90
test/Transforms/SampleProfile/discriminator.ll
Normal file
@ -0,0 +1,90 @@
|
||||
; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/discriminator.prof | opt -analyze -branch-prob | FileCheck %s
|
||||
|
||||
; Original code
|
||||
;
|
||||
; 1 int foo(int i) {
|
||||
; 2 int x = 0;
|
||||
; 3 while (i < 100) {
|
||||
; 4 if (i < 5) x--;
|
||||
; 5 i++;
|
||||
; 6 }
|
||||
; 7 return x;
|
||||
; 8 }
|
||||
;
|
||||
; In this test, if the loop is executed 100 times, the decrement operation
|
||||
; at line 4 should only execute 5 times. This is reflected in the profile
|
||||
; data for line offset 3. In Inputs/discriminator.prof, we have:
|
||||
;
|
||||
; 3: 100
|
||||
; 3.1: 5
|
||||
;
|
||||
; This means that the predicate 'i < 5' (line 3) is executed 100 times,
|
||||
; but the then branch (line 3.1) is only executed 5 times.
|
||||
|
||||
define i32 @foo(i32 %i) #0 {
|
||||
; CHECK: Printing analysis 'Branch Probability Analysis' for function 'foo':
|
||||
entry:
|
||||
%i.addr = alloca i32, align 4
|
||||
%x = alloca i32, align 4
|
||||
store i32 %i, i32* %i.addr, align 4
|
||||
store i32 0, i32* %x, align 4, !dbg !10
|
||||
br label %while.cond, !dbg !11
|
||||
|
||||
while.cond: ; preds = %if.end, %entry
|
||||
%0 = load i32* %i.addr, align 4, !dbg !12
|
||||
%cmp = icmp slt i32 %0, 100, !dbg !12
|
||||
br i1 %cmp, label %while.body, label %while.end, !dbg !12
|
||||
; CHECK: edge while.cond -> while.body probability is 100 / 101 = 99.0099% [HOT edge]
|
||||
; CHECK: edge while.cond -> while.end probability is 1 / 101 = 0.990099%
|
||||
|
||||
while.body: ; preds = %while.cond
|
||||
%1 = load i32* %i.addr, align 4, !dbg !14
|
||||
%cmp1 = icmp slt i32 %1, 50, !dbg !14
|
||||
br i1 %cmp1, label %if.then, label %if.end, !dbg !14
|
||||
; CHECK: edge while.body -> if.then probability is 5 / 100 = 5%
|
||||
; CHECK: edge while.body -> if.end probability is 95 / 100 = 95% [HOT edge]
|
||||
|
||||
if.then: ; preds = %while.body
|
||||
%2 = load i32* %x, align 4, !dbg !17
|
||||
%dec = add nsw i32 %2, -1, !dbg !17
|
||||
store i32 %dec, i32* %x, align 4, !dbg !17
|
||||
br label %if.end, !dbg !17
|
||||
|
||||
if.end: ; preds = %if.then, %while.body
|
||||
%3 = load i32* %i.addr, align 4, !dbg !19
|
||||
%inc = add nsw i32 %3, 1, !dbg !19
|
||||
store i32 %inc, i32* %i.addr, align 4, !dbg !19
|
||||
br label %while.cond, !dbg !20
|
||||
|
||||
while.end: ; preds = %while.cond
|
||||
%4 = load i32* %x, align 4, !dbg !21
|
||||
ret i32 %4, !dbg !21
|
||||
}
|
||||
|
||||
|
||||
!llvm.dbg.cu = !{!0}
|
||||
!llvm.module.flags = !{!7, !8}
|
||||
!llvm.ident = !{!9}
|
||||
|
||||
!0 = metadata !{i32 786449, metadata !1, i32 12, metadata !"clang version 3.5 ", i1 false, metadata !"", i32 0, metadata !2, metadata !2, metadata !3, metadata !2, metadata !2, metadata !""} ; [ DW_TAG_compile_unit ] [discriminator.c] [DW_LANG_C99]
|
||||
!1 = metadata !{metadata !"discriminator.c", metadata !"."}
|
||||
!2 = metadata !{}
|
||||
!3 = metadata !{metadata !4}
|
||||
!4 = metadata !{i32 786478, metadata !1, metadata !5, metadata !"foo", metadata !"foo", metadata !"", i32 1, metadata !6, i1 false, i1 true, i32 0, i32 0, null, i32 256, i1 false, i32 (i32)* @foo, null, null, metadata !2, i32 1} ; [ DW_TAG_subprogram ] [line 1] [def] [foo]
|
||||
!5 = metadata !{i32 786473, metadata !1} ; [ DW_TAG_file_type ] [discriminator.c]
|
||||
!6 = metadata !{i32 786453, i32 0, null, metadata !"", i32 0, i64 0, i64 0, i64 0, i32 0, null, metadata !2, i32 0, null, null, null} ; [ DW_TAG_subroutine_type ] [line 0, size 0, align 0, offset 0] [from ]
|
||||
!7 = metadata !{i32 2, metadata !"Dwarf Version", i32 4}
|
||||
!8 = metadata !{i32 1, metadata !"Debug Info Version", i32 1}
|
||||
!9 = metadata !{metadata !"clang version 3.5 "}
|
||||
!10 = metadata !{i32 2, i32 0, metadata !4, null}
|
||||
!11 = metadata !{i32 3, i32 0, metadata !4, null}
|
||||
!12 = metadata !{i32 3, i32 0, metadata !13, null}
|
||||
!13 = metadata !{i32 786443, metadata !1, metadata !4, i32 3, i32 0, i32 1, i32 2} ; [ DW_TAG_lexical_block ] [discriminator.c]
|
||||
!14 = metadata !{i32 4, i32 0, metadata !15, null}
|
||||
!15 = metadata !{i32 786443, metadata !1, metadata !16, i32 4, i32 0, i32 0, i32 1} ; [ DW_TAG_lexical_block ] [discriminator.c]
|
||||
!16 = metadata !{i32 786443, metadata !1, metadata !4, i32 3, i32 0, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [discriminator.c]
|
||||
!17 = metadata !{i32 4, i32 0, metadata !18, null}
|
||||
!18 = metadata !{i32 786443, metadata !1, metadata !15, i32 4, i32 0, i32 1, i32 3} ; [ DW_TAG_lexical_block ] [discriminator.c]
|
||||
!19 = metadata !{i32 5, i32 0, metadata !16, null}
|
||||
!20 = metadata !{i32 6, i32 0, metadata !16, null}
|
||||
!21 = metadata !{i32 7, i32 0, metadata !4, null}
|
||||
@ -210,27 +210,27 @@ attributes #2 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "n
|
||||
!9 = metadata !{i32 1, metadata !"Debug Info Version", i32 1}
|
||||
!10 = metadata !{metadata !"clang version 3.5 "}
|
||||
!11 = metadata !{i32 4, i32 0, metadata !12, null}
|
||||
!12 = metadata !{i32 786443, metadata !1, metadata !4, i32 4, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!12 = metadata !{i32 786443, metadata !1, metadata !4, i32 4, i32 0, i32 0, i32 0} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!13 = metadata !{i32 5, i32 0, metadata !14, null}
|
||||
!14 = metadata !{i32 786443, metadata !1, metadata !12, i32 4, i32 0, i32 1} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!14 = metadata !{i32 786443, metadata !1, metadata !12, i32 4, i32 0, i32 0, i32 1} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!15 = metadata !{i32 7, i32 0, metadata !16, null}
|
||||
!16 = metadata !{i32 786443, metadata !1, metadata !17, i32 7, i32 0, i32 3} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!17 = metadata !{i32 786443, metadata !1, metadata !12, i32 6, i32 0, i32 2} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!16 = metadata !{i32 786443, metadata !1, metadata !17, i32 7, i32 0, i32 0, i32 3} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!17 = metadata !{i32 786443, metadata !1, metadata !12, i32 6, i32 0, i32 0, i32 2} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!18 = metadata !{i32 8, i32 0, metadata !19, null} ; [ DW_TAG_imported_declaration ]
|
||||
!19 = metadata !{i32 786443, metadata !1, metadata !20, i32 8, i32 0, i32 5} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!20 = metadata !{i32 786443, metadata !1, metadata !16, i32 7, i32 0, i32 4} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!19 = metadata !{i32 786443, metadata !1, metadata !20, i32 8, i32 0, i32 0, i32 5} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!20 = metadata !{i32 786443, metadata !1, metadata !16, i32 7, i32 0, i32 0, i32 4} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!21 = metadata !{i32 9, i32 0, metadata !19, null}
|
||||
!22 = metadata !{i32 10, i32 0, metadata !23, null}
|
||||
!23 = metadata !{i32 786443, metadata !1, metadata !20, i32 10, i32 0, i32 6} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!23 = metadata !{i32 786443, metadata !1, metadata !20, i32 10, i32 0, i32 0, i32 6} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!24 = metadata !{i32 11, i32 0, metadata !25, null}
|
||||
!25 = metadata !{i32 786443, metadata !1, metadata !23, i32 10, i32 0, i32 7} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!25 = metadata !{i32 786443, metadata !1, metadata !23, i32 10, i32 0, i32 0, i32 7} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!26 = metadata !{i32 12, i32 0, metadata !25, null}
|
||||
!27 = metadata !{i32 13, i32 0, metadata !25, null}
|
||||
!28 = metadata !{i32 14, i32 0, metadata !29, null}
|
||||
!29 = metadata !{i32 786443, metadata !1, metadata !30, i32 14, i32 0, i32 9} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!30 = metadata !{i32 786443, metadata !1, metadata !23, i32 13, i32 0, i32 8} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!29 = metadata !{i32 786443, metadata !1, metadata !30, i32 14, i32 0, i32 0, i32 9} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!30 = metadata !{i32 786443, metadata !1, metadata !23, i32 13, i32 0, i32 0, i32 8} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!31 = metadata !{i32 15, i32 0, metadata !32, null}
|
||||
!32 = metadata !{i32 786443, metadata !1, metadata !29, i32 14, i32 0, i32 10} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!32 = metadata !{i32 786443, metadata !1, metadata !29, i32 14, i32 0, i32 0, i32 10} ; [ DW_TAG_lexical_block ] [propagate.cc]
|
||||
!33 = metadata !{i32 16, i32 0, metadata !32, null}
|
||||
!34 = metadata !{i32 17, i32 0, metadata !32, null}
|
||||
!35 = metadata !{i32 19, i32 0, metadata !20, null}
|
||||
|
||||
@ -2,6 +2,9 @@
|
||||
; RUN: not opt < %s -sample-profile -sample-profile-file=missing.prof 2>&1 | FileCheck -check-prefix=MISSING-FILE %s
|
||||
; RUN: not opt < %s -sample-profile -sample-profile-file=%S/Inputs/bad_fn_header.prof 2>&1 | FileCheck -check-prefix=BAD-FN-HEADER %s
|
||||
; RUN: not opt < %s -sample-profile -sample-profile-file=%S/Inputs/bad_sample_line.prof 2>&1 | FileCheck -check-prefix=BAD-SAMPLE-LINE %s
|
||||
; RUN: not opt < %s -sample-profile -sample-profile-file=%S/Inputs/bad_line_values.prof 2>&1 | FileCheck -check-prefix=BAD-LINE-VALUES %s
|
||||
; RUN: not opt < %s -sample-profile -sample-profile-file=%S/Inputs/bad_discriminator_value.prof 2>&1 | FileCheck -check-prefix=BAD-DISCRIMINATOR-VALUE %s
|
||||
; RUN: not opt < %s -sample-profile -sample-profile-file=%S/Inputs/bad_samples.prof 2>&1 | FileCheck -check-prefix=BAD-SAMPLES %s
|
||||
|
||||
define void @empty() {
|
||||
entry:
|
||||
@ -11,3 +14,6 @@ entry:
|
||||
; MISSING-FILE: LLVM ERROR: Could not open file missing.prof:
|
||||
; BAD-FN-HEADER: LLVM ERROR: {{.*}}bad_fn_header.prof:1: Expected 'mangled_name:NUM:NUM', found empty:100:BAD
|
||||
; BAD-SAMPLE-LINE: LLVM ERROR: {{.*}}bad_sample_line.prof:3: Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found 1: BAD
|
||||
; BAD-LINE-VALUES: LLVM ERROR: {{.*}}bad_line_values.prof:2: Expected 'mangled_name:NUM:NUM', found -1: 10
|
||||
; BAD-DISCRIMINATOR-VALUE: LLVM ERROR: {{.*}}bad_discriminator_value.prof:2: Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found 1.-3: 10
|
||||
; BAD-SAMPLES: LLVM ERROR: {{.*}}bad_samples.prof:2: Expected 'NUM[.NUM]: NUM[ mangled_name:NUM]*', found 1.3: -10
|
||||
|
||||
Loading…
Reference in New Issue
Block a user