Skip to content

[memprof] Simplify readMemprof (NFC) #119930

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Dec 14, 2024
Merged

[memprof] Simplify readMemprof (NFC) #119930

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9d32764
[memprof] Simplify readMemprof (NFC)
kazutakahirata Dec 13, 2024
4dba136
Address comments.
kazutakahirata Dec 14, 2024
a790e98
Address comments.
kazutakahirata Dec 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 16 additions & 13 deletions llvm/lib/Transforms/Instrumentation/MemProfiler.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -725,8 +725,7 @@ static uint64_t computeStackId(const memprof::Frame &Frame) {

// Helper to generate a single hash id for a given callstack, used for emitting
// matching statistics and useful for uniquing such statistics across modules.
static uint64_t
computeFullStackId(const std::vector<memprof::Frame> &CallStack) {
static uint64_t computeFullStackId(ArrayRef<Frame> CallStack) {
llvm::HashBuilder<llvm::TruncatedBLAKE3<8>, llvm::endianness::little>
HashBuilder;
for (auto &F : CallStack)
Expand Down Expand Up @@ -763,9 +762,8 @@ static AllocationType addCallStack(CallStackTrie &AllocTrie,
// non-zero.
static bool
stackFrameIncludesInlinedCallStack(ArrayRef<Frame> ProfileCallStack,
ArrayRef<uint64_t> InlinedCallStack,
unsigned StartIndex = 0) {
auto StackFrame = ProfileCallStack.begin() + StartIndex;
ArrayRef<uint64_t> InlinedCallStack) {
auto StackFrame = ProfileCallStack.begin();
auto InlCallStackIter = InlinedCallStack.begin();
for (; StackFrame != ProfileCallStack.end() &&
InlCallStackIter != InlinedCallStack.end();
Expand Down Expand Up @@ -969,9 +967,15 @@ readMemprof(Module &M, Function &F, IndexedInstrProfReader *MemProfReader,
// Build maps of the location hash to all profile data with that leaf location
// (allocation info and the callsites).
std::map<uint64_t, std::set<const AllocationInfo *>> LocHashToAllocInfo;
// For the callsites we need to record the index of the associated frame in
// the frame array (see comments below where the map entries are added).
std::map<uint64_t, std::set<std::pair<const std::vector<Frame> *, unsigned>>>
// A hash function for std::unordered_set<ArrayRef<Frame>> to work.
struct CallStackHash {
size_t operator()(ArrayRef<Frame> CS) const {
return computeFullStackId(CS);
}
};
// For the callsites we need to record slices of the frame array (see comments
// below where the map entries are added).
std::map<uint64_t, std::unordered_set<ArrayRef<Frame>, CallStackHash>>
LocHashToCallSites;
for (auto &AI : MemProfRec->AllocSites) {
NumOfMemProfAllocContextProfiles++;
Expand All @@ -989,7 +993,7 @@ readMemprof(Module &M, Function &F, IndexedInstrProfReader *MemProfReader,
unsigned Idx = 0;
for (auto &StackFrame : CS) {
uint64_t StackId = computeStackId(StackFrame);
LocHashToCallSites[StackId].insert(std::make_pair(&CS, Idx++));
LocHashToCallSites[StackId].insert(ArrayRef<Frame>(CS).drop_front(Idx++));
ProfileHasColumns |= StackFrame.Column;
// Once we find this function, we can stop recording.
if (StackFrame.Function == FuncGUID)
Expand Down Expand Up @@ -1029,8 +1033,7 @@ readMemprof(Module &M, Function &F, IndexedInstrProfReader *MemProfReader,
// and another callsite).
std::map<uint64_t, std::set<const AllocationInfo *>>::iterator
AllocInfoIter;
std::map<uint64_t, std::set<std::pair<const std::vector<Frame> *,
unsigned>>>::iterator CallSitesIter;
decltype(LocHashToCallSites)::iterator CallSitesIter;
for (const DILocation *DIL = I.getDebugLoc(); DIL != nullptr;
DIL = DIL->getInlinedAt()) {
// Use C++ linkage name if possible. Need to compile with
Expand Down Expand Up @@ -1121,8 +1124,8 @@ readMemprof(Module &M, Function &F, IndexedInstrProfReader *MemProfReader,
for (auto CallStackIdx : CallSitesIter->second) {
// If we found and thus matched all frames on the call, create and
// attach call stack metadata.
if (stackFrameIncludesInlinedCallStack(
*CallStackIdx.first, InlinedCallStack, CallStackIdx.second)) {
if (stackFrameIncludesInlinedCallStack(CallStackIdx,
InlinedCallStack)) {
NumOfMemProfMatchedCallSites++;
addCallsiteMetadata(I, InlinedCallStack, Ctx);
// Only need to find one with a matching call stack and add a single
Expand Down
Loading