mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
[CSSPGO] Overwrite branch weight annotated in previous pass.
Sample profile loader can be run in both LTO prelink and postlink. Currently the counts annoation in postilnk doesn't fully overwrite what's done in prelink. I'm adding a switch (`-overwrite-existing-weights=1`) to enable a full overwrite, which includes: 1. Clear old metadata for calls when their parent block has a zero count. This could be caused by prelink code duplication. 2. Clear indirect call metadata if somehow all the rest targets have a sum of zero count. 3. Overwrite branch weight for basic blocks. With a CS profile, I was seeing #1 and #2 help reduce code size by preventing post-sample ICP and CGSCC inliner working on obsolete metadata, which come from a partial global inlining in prelink. It's not expected to work well for non-CS case with a less-accurate post-inline count quality. It's worth calling out that some prelink optimizations can damage counts quality in an irreversible way. One example is the loop rotate optimization. Due to lack of exact loop entry count (profiling can only give loop iteration count and loop exit count), moving one iteration out of the loop body leaves the rest iteration count unknown. We had to turn off prelink loop rotate to achieve a better postlink counts quality. A even better postlink counts quality can be archived by turning off prelink CGSCC inlining which is not context-sensitive. Reviewed By: wenlei, wmi Differential Revision: https://reviews.llvm.org/D102537
This commit is contained in:
Hongtao Yu
parent
3f3a533213
commit
ba7bb5fc7d
@ -208,7 +208,6 @@ static cl::opt<bool> CallsitePrioritizedInline(
|
||||
cl::desc("Use call site prioritized inlining for sample profile loader."
|
||||
"Currently only CSSPGO is supported."));
|
||||
|
||||
|
||||
static cl::opt<std::string> ProfileInlineReplayFile(
|
||||
"sample-profile-inline-replay", cl::init(""), cl::value_desc("filename"),
|
||||
cl::desc(
|
||||
@ -222,6 +221,10 @@ static cl::opt<unsigned>
|
||||
cl::desc("Max number of promotions for a single indirect "
|
||||
"call callsite in sample profile loader"));
|
||||
|
||||
static cl::opt<bool> OverwriteExistingWeights(
|
||||
"overwrite-existing-weights", cl::Hidden, cl::init(false),
|
||||
cl::desc("Ignore existing branch weights on IR and always overwrite."));
|
||||
|
||||
namespace {
|
||||
|
||||
using BlockWeightMap = DenseMap<const BasicBlock *, uint64_t>;
|
||||
@ -1453,9 +1456,10 @@ void SampleProfileLoader::generateMDProfMetadata(Function &F) {
|
||||
auto T = FS->findCallTargetMapAt(CallSite);
|
||||
if (!T || T.get().empty())
|
||||
continue;
|
||||
// Prorate the callsite counts to reflect what is already done to the
|
||||
// callsite, such as ICP or calliste cloning.
|
||||
if (FunctionSamples::ProfileIsProbeBased) {
|
||||
// Prorate the callsite counts based on the pre-ICP distribution
|
||||
// factor to reflect what is already done to the callsite before
|
||||
// ICP, such as calliste cloning.
|
||||
if (Optional<PseudoProbe> Probe = extractProbe(I)) {
|
||||
if (Probe->Factor < 1)
|
||||
T = SampleRecord::adjustCallTargets(T.get(), Probe->Factor);
|
||||
@ -1476,16 +1480,29 @@ void SampleProfileLoader::generateMDProfMetadata(Function &F) {
|
||||
Sum += NameFS.second.getEntrySamples();
|
||||
}
|
||||
}
|
||||
if (!Sum)
|
||||
continue;
|
||||
updateIDTMetaData(I, SortedCallTargets, Sum);
|
||||
if (Sum)
|
||||
updateIDTMetaData(I, SortedCallTargets, Sum);
|
||||
else if (OverwriteExistingWeights)
|
||||
I.setMetadata(LLVMContext::MD_prof, nullptr);
|
||||
} else if (!isa<IntrinsicInst>(&I)) {
|
||||
I.setMetadata(LLVMContext::MD_prof,
|
||||
MDB.createBranchWeights(
|
||||
{static_cast<uint32_t>(BlockWeights[BB])}));
|
||||
}
|
||||
}
|
||||
} else if (OverwriteExistingWeights) {
|
||||
// Set profile metadata (possibly annotated by LTO prelink) to zero or
|
||||
// clear it for cold code.
|
||||
for (auto &I : BB->getInstList()) {
|
||||
if (isa<CallInst>(I) || isa<InvokeInst>(I)) {
|
||||
if (cast<CallBase>(I).isIndirectCall())
|
||||
I.setMetadata(LLVMContext::MD_prof, nullptr);
|
||||
else
|
||||
I.setMetadata(LLVMContext::MD_prof, MDB.createBranchWeights(0));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Instruction *TI = BB->getTerminator();
|
||||
if (TI->getNumSuccessors() == 1)
|
||||
continue;
|
||||
@ -1527,20 +1544,28 @@ void SampleProfileLoader::generateMDProfMetadata(Function &F) {
|
||||
uint64_t TempWeight;
|
||||
// Only set weights if there is at least one non-zero weight.
|
||||
// In any other case, let the analyzer set weights.
|
||||
// Do not set weights if the weights are present. In ThinLTO, the profile
|
||||
// annotation is done twice. If the first annotation already set the
|
||||
// weights, the second pass does not need to set it.
|
||||
if (MaxWeight > 0 && !TI->extractProfTotalWeight(TempWeight)) {
|
||||
// Do not set weights if the weights are present unless under
|
||||
// OverwriteExistingWeights. In ThinLTO, the profile annotation is done
|
||||
// twice. If the first annotation already set the weights, the second pass
|
||||
// does not need to set it. With OverwriteExistingWeights, Blocks with zero
|
||||
// weight should have their existing metadata (possibly annotated by LTO
|
||||
// prelink) cleared.
|
||||
if (MaxWeight > 0 &&
|
||||
(!TI->extractProfTotalWeight(TempWeight) || OverwriteExistingWeights)) {
|
||||
LLVM_DEBUG(dbgs() << "SUCCESS. Found non-zero weights.\n");
|
||||
TI->setMetadata(LLVMContext::MD_prof,
|
||||
MDB.createBranchWeights(Weights));
|
||||
TI->setMetadata(LLVMContext::MD_prof, MDB.createBranchWeights(Weights));
|
||||
ORE->emit([&]() {
|
||||
return OptimizationRemark(DEBUG_TYPE, "PopularDest", MaxDestInst)
|
||||
<< "most popular destination for conditional branches at "
|
||||
<< ore::NV("CondBranchesLoc", BranchLoc);
|
||||
});
|
||||
} else {
|
||||
LLVM_DEBUG(dbgs() << "SKIPPED. All branch weights are zero.\n");
|
||||
if (OverwriteExistingWeights) {
|
||||
TI->setMetadata(LLVMContext::MD_prof, nullptr);
|
||||
LLVM_DEBUG(dbgs() << "CLEARED. All branch weights are zero.\n");
|
||||
} else {
|
||||
LLVM_DEBUG(dbgs() << "SKIPPED. All branch weights are zero.\n");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/branch.prof | opt -analyze -branch-prob -enable-new-pm=0 | FileCheck %s
|
||||
; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/branch.prof | opt -passes='print<branch-prob>' -disable-output 2>&1 | FileCheck %s
|
||||
; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/branch.prof -overwrite-existing-weights=1 | opt -passes='print<branch-prob>' -disable-output 2>&1 | FileCheck %s --check-prefix=OVW
|
||||
|
||||
; Original C++ code for this test case:
|
||||
;
|
||||
@ -90,6 +91,8 @@ for.cond: ; preds = %for.inc, %if.then.2
|
||||
br i1 %cmp5, label %for.body, label %for.end, !dbg !50, !prof !80
|
||||
; CHECK: edge for.cond -> for.body probability is 0x73333333 / 0x80000000 = 90.00%
|
||||
; CHECK: edge for.cond -> for.end probability is 0x0ccccccd / 0x80000000 = 10.00%
|
||||
; OVW: edge for.cond -> for.body probability is 0x76b3f3be / 0x80000000 = 92.74%
|
||||
; OVW: edge for.cond -> for.end probability is 0x094c0c42 / 0x80000000 = 7.26%
|
||||
|
||||
for.body: ; preds = %for.cond
|
||||
call void @llvm.dbg.declare(metadata double* %x, metadata !51, metadata !17), !dbg !53
|
||||
|
||||
@ -0,0 +1,67 @@
|
||||
; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/pseudo-probe-profile.prof -pass-remarks=sample-profile -S | FileCheck %s
|
||||
; RUN: opt < %s -passes=sample-profile -sample-profile-file=%S/Inputs/pseudo-probe-profile.prof -pass-remarks=sample-profile -overwrite-existing-weights=1 -S | FileCheck %s -check-prefix=OVW
|
||||
|
||||
define dso_local i32 @foo(i32 %x, void (i32)* %f) #0 !dbg !4 !prof !10 {
|
||||
entry:
|
||||
%retval = alloca i32, align 4
|
||||
%x.addr = alloca i32, align 4
|
||||
store i32 %x, i32* %x.addr, align 4
|
||||
%0 = load i32, i32* %x.addr, align 4
|
||||
%cmp = icmp eq i32 %0, 0
|
||||
call void @llvm.pseudoprobe(i64 6699318081062747564, i64 1, i32 0, i64 -1)
|
||||
br i1 %cmp, label %if.then, label %if.else, !prof !11
|
||||
|
||||
if.then:
|
||||
call void @llvm.pseudoprobe(i64 6699318081062747564, i64 2, i32 0, i64 -1)
|
||||
; CHECK: call {{.*}}, !dbg ![[#]], !prof ![[#PROF:]]
|
||||
; OVW: call {{.*}}, !dbg ![[#]], !prof ![[#PROF:]]
|
||||
call void %f(i32 1), !dbg !13, !prof !16
|
||||
store i32 1, i32* %retval, align 4
|
||||
br label %return
|
||||
|
||||
if.else:
|
||||
call void @llvm.pseudoprobe(i64 6699318081062747564, i64 2, i32 0, i64 0)
|
||||
; CHECK: call {{.*}}, !dbg ![[#]], !prof ![[#PROF]]
|
||||
;; The block should have a 0 weight. Check the profile metadata is dropped.
|
||||
; OVW-NOT: call {{.*}}, !dbg ![[#]], !prof
|
||||
call void %f(i32 2), !dbg !15, !prof !16
|
||||
store i32 2, i32* %retval, align 4
|
||||
br label %return
|
||||
|
||||
return:
|
||||
call void @llvm.pseudoprobe(i64 6699318081062747564, i64 4, i32 0, i64 -1)
|
||||
%1 = load i32, i32* %retval, align 4
|
||||
ret i32 %1
|
||||
}
|
||||
|
||||
; CHECK: ![[#PROF]] = !{!"VP", i32 0, i64 7, i64 9191153033785521275, i64 5, i64 -1069303473483922844, i64 2}
|
||||
; OVW: ![[#PROF]] = !{!"VP", i32 0, i64 7, i64 9191153033785521275, i64 5, i64 -1069303473483922844, i64 2}
|
||||
|
||||
declare void @llvm.pseudoprobe(i64, i64, i32, i64) #0
|
||||
|
||||
attributes #0 = {"use-sample-profile"}
|
||||
|
||||
!llvm.module.flags = !{!0, !1}
|
||||
!llvm.pseudo_probe_desc = !{!2}
|
||||
|
||||
!0 = !{i32 7, !"Dwarf Version", i32 4}
|
||||
!1 = !{i32 2, !"Debug Info Version", i32 3}
|
||||
!2 = !{i64 6699318081062747564, i64 563022570642068, !"foo", null}
|
||||
!4 = distinct !DISubprogram(name: "foo", scope: !5, file: !5, line: 9, type: !6, scopeLine: 9, spFlags: DISPFlagDefinition, unit: !9)
|
||||
!5 = !DIFile(filename: "test.cpp", directory: "test")
|
||||
!6 = !DISubroutineType(types: !7)
|
||||
!7 = !{!8, !8}
|
||||
!8 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
|
||||
!9 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus_14, file: !5, isOptimized: false, runtimeVersion: 0, emissionKind: NoDebug)
|
||||
!10 = !{!"function_entry_count", i64 14}
|
||||
!11 = !{!"branch_weights", i32 100, i32 0}
|
||||
;; A discriminator of 186646575 which is 0x6f80057 in hexdecimal, stands for an indirect call probe
|
||||
;; with an index of 5 and probe factor of 1.0.
|
||||
!12 = !DILexicalBlockFile(scope: !4, file: !5, discriminator: 186646575)
|
||||
!13 = distinct !DILocation(line: 10, column: 11, scope: !12)
|
||||
;; A discriminator of 134217775 which is 0x6f80057 in hexdecimal, stands for an indirect call probe
|
||||
;; with an index of 5 and probe factor of 0.
|
||||
!14 = !DILexicalBlockFile(scope: !4, file: !5, discriminator: 134217775)
|
||||
!15 = distinct !DILocation(line: 10, column: 11, scope: !14)
|
||||
!16 = !{!"VP", i32 0, i64 7, i64 9191153033785521275, i64 5, i64 -1069303473483922844, i64 2}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user