[llvm-branch-commits] [llvm] [BOLT] Function matching with function calls as anchors (PR #96596)
https://github.com/aaupov edited https://github.com/llvm/llvm-project/pull/96596 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Function matching with function calls as anchors (PR #96596)
@@ -415,11 +495,20 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
matchProfileToFunction(YamlBF, *BF);
+ uint64_t MatchedWithCallsAsAnchors = 0;
+ if (opts::MatchWithCallsAsAnchors)
+matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
aaupov wrote:
This new matching needs to be inside `inferStaleProfile` as we discussed,
conceptually sandwiched between strict and loose block hash matching.
Logistically it happen in this vicinity:
https://github.com/llvm/llvm-project/blob/e214ed9d7060f6caa0c1bb756edb62643f23aa5b/bolt/lib/Profile/StaleProfileMatching.cpp#L439-L440
https://github.com/llvm/llvm-project/pull/96596
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [flang] [Flang][OpenMP] Derived type explicit allocatable member mapping (PR #96266)
https://github.com/agozillon updated
https://github.com/llvm/llvm-project/pull/96266
>From 2e24a3b56c2be7203aa87b1d6bb886706e138496 Mon Sep 17 00:00:00 2001
From: agozillon
Date: Tue, 25 Jun 2024 17:40:04 -0500
Subject: [PATCH] removal of some leftover artifacts
Created using spr 1.3.4
---
flang/lib/Optimizer/Transforms/OMPMapInfoFinalization.cpp | 7 ---
1 file changed, 7 deletions(-)
diff --git a/flang/lib/Optimizer/Transforms/OMPMapInfoFinalization.cpp
b/flang/lib/Optimizer/Transforms/OMPMapInfoFinalization.cpp
index 8749daf757f52..c88b3cf4cc0b4 100644
--- a/flang/lib/Optimizer/Transforms/OMPMapInfoFinalization.cpp
+++ b/flang/lib/Optimizer/Transforms/OMPMapInfoFinalization.cpp
@@ -493,13 +493,6 @@ class OMPMapInfoFinalizationPass
mlir::isa_and_present(
op.getVarPtr().getDefiningOp())) {
builder.setInsertionPoint(op);
-
-// - contact benifit people
-// - update broken lit tests
-// -create commit and apply clang-format
-// -cherry pick pr onto PR stack and split the commit into relevant
-// components and rebase fixup into orignal corresponding PR. -push
-// upstream
genDescriptorMemberMaps(op, builder, getFirstTargetUser(op));
}
});
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] AMDGPU: Add subtarget feature for memory atomic fadd f64 (PR #96444)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96444
>From 7648917e1a8f14940f31add840201d3413abbbdb Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 17:07:53 +0200
Subject: [PATCH] AMDGPU: Add subtarget feature for memory atomic fadd f64
---
llvm/lib/Target/AMDGPU/AMDGPU.td | 21 ++---
llvm/lib/Target/AMDGPU/BUFInstructions.td | 10 ++
llvm/lib/Target/AMDGPU/FLATInstructions.td | 6 +++---
llvm/lib/Target/AMDGPU/GCNSubtarget.h | 10 +++---
llvm/lib/Target/AMDGPU/SIISelLowering.cpp | 2 +-
5 files changed, 31 insertions(+), 18 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 39a1d629a4aea..97dd45df91da2 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -788,6 +788,13 @@ def FeatureFlatAtomicFaddF32Inst
"Has flat_atomic_add_f32 instruction"
>;
+def FeatureFlatBufferGlobalAtomicFaddF64Inst
+ : SubtargetFeature<"flat-buffer-global-fadd-f64-inst",
+ "HasFlatBufferGlobalAtomicFaddF64Inst",
+ "true",
+ "Has flat, buffer, and global instructions for f64 atomic fadd"
+>;
+
def FeatureMemoryAtomicFaddF32DenormalSupport
: SubtargetFeature<"memory-atomic-fadd-f32-denormal-support",
"HasAtomicMemoryAtomicFaddF32DenormalSupport",
@@ -1390,7 +1397,8 @@ def FeatureISAVersion9_0_A : FeatureSet<
FeatureBackOffBarrier,
FeatureKernargPreload,
FeatureAtomicFMinFMaxF64GlobalInsts,
- FeatureAtomicFMinFMaxF64FlatInsts
+ FeatureAtomicFMinFMaxF64FlatInsts,
+ FeatureFlatBufferGlobalAtomicFaddF64Inst
])>;
def FeatureISAVersion9_0_C : FeatureSet<
@@ -1435,7 +1443,8 @@ def FeatureISAVersion9_4_Common : FeatureSet<
FeatureAtomicFMinFMaxF64GlobalInsts,
FeatureAtomicFMinFMaxF64FlatInsts,
FeatureAgentScopeFineGrainedRemoteMemoryAtomics,
- FeatureMemoryAtomicFaddF32DenormalSupport
+ FeatureMemoryAtomicFaddF32DenormalSupport,
+ FeatureFlatBufferGlobalAtomicFaddF64Inst
]>;
def FeatureISAVersion9_4_0 : FeatureSet<
@@ -1932,11 +1941,9 @@ def isGFX12Plus :
def HasFlatAddressSpace : Predicate<"Subtarget->hasFlatAddressSpace()">,
AssemblerPredicate<(all_of FeatureFlatAddressSpace)>;
-
-def HasBufferFlatGlobalAtomicsF64 : // FIXME: Rename to show it's only for fadd
- Predicate<"Subtarget->hasBufferFlatGlobalAtomicsF64()">,
- // FIXME: This is too coarse, and working around using pseudo's predicates
on real instruction.
- AssemblerPredicate<(any_of FeatureGFX90AInsts, FeatureGFX10Insts,
FeatureSouthernIslands, FeatureSeaIslands)>;
+def HasFlatBufferGlobalAtomicFaddF64Inst :
+ Predicate<"Subtarget->hasFlatBufferGlobalAtomicFaddF64Inst()">,
+ AssemblerPredicate<(any_of FeatureFlatBufferGlobalAtomicFaddF64Inst)>;
def HasAtomicFMinFMaxF32GlobalInsts :
Predicate<"Subtarget->hasAtomicFMinFMaxF32GlobalInsts()">,
diff --git a/llvm/lib/Target/AMDGPU/BUFInstructions.td
b/llvm/lib/Target/AMDGPU/BUFInstructions.td
index 3b8d94b744000..a904c8483dbf5 100644
--- a/llvm/lib/Target/AMDGPU/BUFInstructions.td
+++ b/llvm/lib/Target/AMDGPU/BUFInstructions.td
@@ -1312,14 +1312,16 @@ let SubtargetPredicate = isGFX90APlus in {
}
} // End SubtargetPredicate = isGFX90APlus
-let SubtargetPredicate = HasBufferFlatGlobalAtomicsF64 in {
+let SubtargetPredicate = HasFlatBufferGlobalAtomicFaddF64Inst in {
defm BUFFER_ATOMIC_ADD_F64 : MUBUF_Pseudo_Atomics<"buffer_atomic_add_f64",
VReg_64, f64>;
+} // End SubtargetPredicate = HasFlatBufferGlobalAtomicFaddF64Inst
+let SubtargetPredicate = HasAtomicFMinFMaxF64GlobalInsts in {
// Note the names can be buffer_atomic_fmin_x2/buffer_atomic_fmax_x2
// depending on some subtargets.
defm BUFFER_ATOMIC_MIN_F64 : MUBUF_Pseudo_Atomics<"buffer_atomic_min_f64",
VReg_64, f64>;
defm BUFFER_ATOMIC_MAX_F64 : MUBUF_Pseudo_Atomics<"buffer_atomic_max_f64",
VReg_64, f64>;
-} // End SubtargetPredicate = HasBufferFlatGlobalAtomicsF64
+}
def BUFFER_INV : MUBUF_Invalidate<"buffer_inv"> {
let SubtargetPredicate = isGFX940Plus;
@@ -1836,9 +1838,9 @@ let SubtargetPredicate =
HasAtomicBufferGlobalPkAddF16Insts in {
defm : SIBufferAtomicPat<"SIbuffer_atomic_fadd", v2f16,
"BUFFER_ATOMIC_PK_ADD_F16", ["ret"]>;
} // End SubtargetPredicate = HasAtomicBufferGlobalPkAddF16Insts
-let SubtargetPredicate = HasBufferFlatGlobalAtomicsF64 in {
+let SubtargetPredicate = HasFlatBufferGlobalAtomicFaddF64Inst in {
defm : SIBufferAtomicPat<"SIbuffer_atomic_fadd", f64,
"BUFFER_ATOMIC_ADD_F64">;
-} // End SubtargetPredicate = HasBufferFlatGlobalAtomicsF64
+} // End SubtargetPredicate = HasFlatBufferGlobalAtomicFaddF64Inst
let SubtargetPredicate = HasAtomicFMinFMaxF64GlobalInsts in {
defm : SIBufferAtomicPat<"SIbuffer_atomic_fmin", f64,
"BUFFER_ATOMIC_MIN_F64">;
diff --git a/llvm/lib/Target/AMDGPU/FLATInstructions.td
b/llvm/lib/Target/AMDGPU/FLATInstructions.td
index 98054dde398b3..89946a4719557 100644
---
[llvm-branch-commits] [llvm] AMDGPU: Add subtarget feature for global atomic fadd denormal support (PR #96443)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96443
>From 78edc216186854e3320ec5e16b78a26af19dee66 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 16:44:08 +0200
Subject: [PATCH 1/2] AMDGPU: Add subtarget feature for global atomic fadd
denormal support
Not sure what the behavior for gfx90a is. The SPG says it always flushes.
The instruction documentation says it does not.
---
llvm/lib/Target/AMDGPU/AMDGPU.td | 14 --
llvm/lib/Target/AMDGPU/GCNSubtarget.h | 7 +++
2 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 56ec5e9c4cfc2..6b212e1b2af03 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -788,6 +788,13 @@ def FeatureFlatAtomicFaddF32Inst
"Has flat_atomic_add_f32 instruction"
>;
+def FeatureMemoryAtomicFaddF32DenormalSupport
+ : SubtargetFeature<"memory-atomic-fadd-f32-denormal-support",
+ "HasAtomicMemoryAtomicFaddF32DenormalSupport",
+ "true",
+ "global/flat/buffer atomic fadd for float supports denormal handling"
+>;
+
def FeatureAgentScopeFineGrainedRemoteMemoryAtomics
: SubtargetFeature<"agent-scope-fine-grained-remote-memory-atomics",
"HasAgentScopeFineGrainedRemoteMemoryAtomics",
@@ -1427,7 +1434,8 @@ def FeatureISAVersion9_4_Common : FeatureSet<
FeatureKernargPreload,
FeatureAtomicFMinFMaxF64GlobalInsts,
FeatureAtomicFMinFMaxF64FlatInsts,
- FeatureAgentScopeFineGrainedRemoteMemoryAtomics
+ FeatureAgentScopeFineGrainedRemoteMemoryAtomics,
+ FeatureMemoryAtomicFaddF32DenormalSupport
]>;
def FeatureISAVersion9_4_0 : FeatureSet<
@@ -1631,7 +1639,9 @@ def FeatureISAVersion12 : FeatureSet<
FeatureScalarDwordx3Loads,
FeatureDPPSrc1SGPR,
FeatureMaxHardClauseLength32,
- Feature1_5xVGPRs]>;
+ Feature1_5xVGPRs,
+ FeatureMemoryAtomicFaddF32DenormalSupport]>;
+ ]>;
def FeatureISAVersion12_Generic: FeatureSet<
!listconcat(FeatureISAVersion12.Features,
diff --git a/llvm/lib/Target/AMDGPU/GCNSubtarget.h
b/llvm/lib/Target/AMDGPU/GCNSubtarget.h
index 9e2a316a9ed28..db0b2b67a0388 100644
--- a/llvm/lib/Target/AMDGPU/GCNSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/GCNSubtarget.h
@@ -167,6 +167,7 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool HasAtomicFlatPkAdd16Insts = false;
bool HasAtomicFaddRtnInsts = false;
bool HasAtomicFaddNoRtnInsts = false;
+ bool HasAtomicMemoryAtomicFaddF32DenormalSupport = false;
bool HasAtomicBufferGlobalPkAddF16NoRtnInsts = false;
bool HasAtomicBufferGlobalPkAddF16Insts = false;
bool HasAtomicCSubNoRtnInsts = false;
@@ -872,6 +873,12 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool hasFlatAtomicFaddF32Inst() const { return HasFlatAtomicFaddF32Inst; }
+ /// \return true if the target's flat, global, and buffer atomic fadd for
+ /// float supports denormal handling.
+ bool hasMemoryAtomicFaddF32DenormalSupport() const {
+return HasAtomicMemoryAtomicFaddF32DenormalSupport;
+ }
+
/// \return true if atomic operations targeting fine-grained memory work
/// correctly at device scope, in allocations in host or peer PCIe device
/// memory.
>From 47017c26844bc49a9842b2c40056392184119943 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Mon, 24 Jun 2024 12:10:37 +0200
Subject: [PATCH 2/2] Add to gfx11.
RDNA 3 manual says "Floating-point addition handles NAN/INF/denorm"
thought I'm not sure I trust it.
---
llvm/lib/Target/AMDGPU/AMDGPU.td | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 6b212e1b2af03..39a1d629a4aea 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -1547,7 +1547,8 @@ def FeatureISAVersion11_Common : FeatureSet<
FeatureFlatAtomicFaddF32Inst,
FeatureImageInsts,
FeaturePackedTID,
- FeatureVcmpxPermlaneHazard]>;
+ FeatureVcmpxPermlaneHazard,
+ FeatureMemoryAtomicFaddF32DenormalSupport]>;
// There are few workarounds that need to be
// added to all targets. This pessimizes codegen
@@ -1640,7 +1641,7 @@ def FeatureISAVersion12 : FeatureSet<
FeatureDPPSrc1SGPR,
FeatureMaxHardClauseLength32,
Feature1_5xVGPRs,
- FeatureMemoryAtomicFaddF32DenormalSupport]>;
+ FeatureMemoryAtomicFaddF32DenormalSupport
]>;
def FeatureISAVersion12_Generic: FeatureSet<
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [Flang][OpenMP] Derived type explicit allocatable member mapping (PR #96266)
https://github.com/agozillon updated https://github.com/llvm/llvm-project/pull/96266 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [Flang][OpenMP] Derived type explicit allocatable member mapping (PR #96266)
https://github.com/agozillon updated https://github.com/llvm/llvm-project/pull/96266 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [OpenMP][MLIR] Descriptor explicit member map lowering changes (PR #96265)
https://github.com/agozillon updated https://github.com/llvm/llvm-project/pull/96265 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [OpenMP][MLIR] Descriptor explicit member map lowering changes (PR #96265)
https://github.com/agozillon updated https://github.com/llvm/llvm-project/pull/96265 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/shawbyoung edited https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/shawbyoung edited https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/shawbyoung edited https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
aaupov wrote: Please expand the summary of the PR as well. https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/95884
>From 34652b2eebc62218c50a23509ce99937385c30e6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:42:00 -0700
Subject: [PATCH 1/7] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 73 --
1 file changed, 56 insertions(+), 17 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 66cabc236f4b2..c9f6d88f0b13a 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -424,36 +424,75 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
// Uses name similarity to match functions that were not matched by name.
uint64_t MatchedWithDemangledName = 0;
- if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
-
-std::unordered_map NameToBinaryFunction;
-NameToBinaryFunction.reserve(BC.getBinaryFunctions().size());
-for (auto &[_, BF] : BC.getBinaryFunctions()) {
+ if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
+auto DemangleName = [&](const char* String) {
int Status = 0;
- char *DemangledName = abi::__cxa_demangle(BF.getOneName().str().c_str(),
+ char *DemangledName = abi::__cxa_demangle(String,
nullptr, nullptr, );
- if (Status == 0)
-NameToBinaryFunction[std::string(DemangledName)] =
+ return Status == 0 ? new std::string(DemangledName) : nullptr;
+};
+
+auto DeriveNameSpace = [&](std::string DemangledName) {
+ size_t LParen = std::string(DemangledName).find("(");
+ std::string FunctionName = std::string(DemangledName).substr(0, LParen);
+ size_t ScopeResolutionOperator = std::string(FunctionName).rfind("::");
+ return ScopeResolutionOperator == std::string::npos ? std::string("") :
std::string(DemangledName).substr(0, ScopeResolutionOperator);
+};
+
+std::unordered_map>
NamespaceToBFs;
+NamespaceToBFs.reserve(BC.getBinaryFunctions().size());
+
+for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
+ std::string* DemangledName =
DemangleName(BF->getOneName().str().c_str());
+ if (!DemangledName)
+continue;
+ std::string Namespace = DeriveNameSpace(*DemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
+NamespaceToBFs[Namespace] = {BF};
+ else
+It->second.push_back(BF);
}
for (auto YamlBF : YamlBP.Functions) {
if (YamlBF.Used)
continue;
- int Status = 0;
- char *DemangledName =
- abi::__cxa_demangle(YamlBF.Name.c_str(), nullptr, nullptr, );
- if (Status != 0)
+ std::string* YamlBFDemangledName = DemangleName(YamlBF.Name.c_str());
+ if (!YamlBFDemangledName)
continue;
- auto It = NameToBinaryFunction.find(DemangledName);
- if (It == NameToBinaryFunction.end())
+ std::string Namespace = DeriveNameSpace(*YamlBFDemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
continue;
- BinaryFunction *BF = It->second;
- matchProfileToFunction(YamlBF, *BF);
- ++MatchedWithDemangledName;
+ std::vector BFs = It->second;
+
+ unsigned MinEditDistance = UINT_MAX;
+ BinaryFunction *ClosestNameBF = nullptr;
+
+ for (BinaryFunction *BF : BFs) {
+if (ProfiledFunctions.count(BF))
+ continue;
+std::string *BFDemangledName =
DemangleName(BF->getOneName().str().c_str());
+if (!BFDemangledName)
+ continue;
+unsigned BFEditDistance =
StringRef(*BFDemangledName).edit_distance(*YamlBFDemangledName);
+if (BFEditDistance < MinEditDistance) {
+ MinEditDistance = BFEditDistance;
+ ClosestNameBF = BF;
+}
+ }
+
+ if (ClosestNameBF &&
+MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
+matchProfileToFunction(YamlBF, *ClosestNameBF);
+++MatchedWithDemangledName;
+ }
}
}
+ outs() << MatchedWithDemangledName << ": functions matched by name
similarity\n";
+
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 2d23bbd6b9ce4f0786ae8ceb39b1b008b4ca9c4d Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:45:27 -0700
Subject: [PATCH 2/7] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 2 --
1 file changed, 2 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index c9f6d88f0b13a..cf4a5393df8f4 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -491,8 +491,6 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/95884
>From 34652b2eebc62218c50a23509ce99937385c30e6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:42:00 -0700
Subject: [PATCH 1/7] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 73 --
1 file changed, 56 insertions(+), 17 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 66cabc236f4b2..c9f6d88f0b13a 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -424,36 +424,75 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
// Uses name similarity to match functions that were not matched by name.
uint64_t MatchedWithDemangledName = 0;
- if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
-
-std::unordered_map NameToBinaryFunction;
-NameToBinaryFunction.reserve(BC.getBinaryFunctions().size());
-for (auto &[_, BF] : BC.getBinaryFunctions()) {
+ if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
+auto DemangleName = [&](const char* String) {
int Status = 0;
- char *DemangledName = abi::__cxa_demangle(BF.getOneName().str().c_str(),
+ char *DemangledName = abi::__cxa_demangle(String,
nullptr, nullptr, );
- if (Status == 0)
-NameToBinaryFunction[std::string(DemangledName)] =
+ return Status == 0 ? new std::string(DemangledName) : nullptr;
+};
+
+auto DeriveNameSpace = [&](std::string DemangledName) {
+ size_t LParen = std::string(DemangledName).find("(");
+ std::string FunctionName = std::string(DemangledName).substr(0, LParen);
+ size_t ScopeResolutionOperator = std::string(FunctionName).rfind("::");
+ return ScopeResolutionOperator == std::string::npos ? std::string("") :
std::string(DemangledName).substr(0, ScopeResolutionOperator);
+};
+
+std::unordered_map>
NamespaceToBFs;
+NamespaceToBFs.reserve(BC.getBinaryFunctions().size());
+
+for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
+ std::string* DemangledName =
DemangleName(BF->getOneName().str().c_str());
+ if (!DemangledName)
+continue;
+ std::string Namespace = DeriveNameSpace(*DemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
+NamespaceToBFs[Namespace] = {BF};
+ else
+It->second.push_back(BF);
}
for (auto YamlBF : YamlBP.Functions) {
if (YamlBF.Used)
continue;
- int Status = 0;
- char *DemangledName =
- abi::__cxa_demangle(YamlBF.Name.c_str(), nullptr, nullptr, );
- if (Status != 0)
+ std::string* YamlBFDemangledName = DemangleName(YamlBF.Name.c_str());
+ if (!YamlBFDemangledName)
continue;
- auto It = NameToBinaryFunction.find(DemangledName);
- if (It == NameToBinaryFunction.end())
+ std::string Namespace = DeriveNameSpace(*YamlBFDemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
continue;
- BinaryFunction *BF = It->second;
- matchProfileToFunction(YamlBF, *BF);
- ++MatchedWithDemangledName;
+ std::vector BFs = It->second;
+
+ unsigned MinEditDistance = UINT_MAX;
+ BinaryFunction *ClosestNameBF = nullptr;
+
+ for (BinaryFunction *BF : BFs) {
+if (ProfiledFunctions.count(BF))
+ continue;
+std::string *BFDemangledName =
DemangleName(BF->getOneName().str().c_str());
+if (!BFDemangledName)
+ continue;
+unsigned BFEditDistance =
StringRef(*BFDemangledName).edit_distance(*YamlBFDemangledName);
+if (BFEditDistance < MinEditDistance) {
+ MinEditDistance = BFEditDistance;
+ ClosestNameBF = BF;
+}
+ }
+
+ if (ClosestNameBF &&
+MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
+matchProfileToFunction(YamlBF, *ClosestNameBF);
+++MatchedWithDemangledName;
+ }
}
}
+ outs() << MatchedWithDemangledName << ": functions matched by name
similarity\n";
+
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 2d23bbd6b9ce4f0786ae8ceb39b1b008b4ca9c4d Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:45:27 -0700
Subject: [PATCH 2/7] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 2 --
1 file changed, 2 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index c9f6d88f0b13a..cf4a5393df8f4 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -491,8 +491,6 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
shawbyoung wrote: > Thank you for checking the runtime, and it's quite high. We'll need extra > filtering by block count to keep runtime low - please add it as we discussed. >if (BF->size() != YamlBF.NumBasicBlocks) > continue; Functions are filtered by block size here @aaupov https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
@@ -415,11 +422,87 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
matchProfileToFunction(YamlBF, *BF);
+ // Uses name similarity to match functions that were not matched by name.
+ uint64_t MatchedWithNameSimilarity = 0;
+
+ if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
+auto DemangleName = [&](std::string ) {
+ StringRef RestoredName = NameResolver::restore(FunctionName);
+ return demangle(RestoredName);
+};
+
+auto DeriveNameSpace = [&](ItaniumPartialDemangler
,
aaupov wrote:
You can have ItaniumPartialDemangler defined above, and it will be captured by
DeriveNameSpace lambda, so no need to pass it explicitly.
https://github.com/llvm/llvm-project/pull/95884
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/aaupov edited https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
@@ -23,6 +26,10 @@ extern cl::opt Verbosity;
extern cl::OptionCategory BoltOptCategory;
extern cl::opt InferStaleProfile;
+cl::opt NameSimilarityFunctionMatchingThreshold(
+"name-similarity-function-matching-threshold", cl::desc("edit distance."),
aaupov wrote:
Please expand the description
https://github.com/llvm/llvm-project/pull/95884
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/aaupov requested changes to this pull request. Thank you for checking the runtime, and it's quite high. We'll need extra filtering by block count to keep runtime low - please add it as we discussed. https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] b07dae1 - Revert "[flang] Add basic -mtune support (#95043)"
Author: Tarun Prabhu
Date: 2024-06-25T12:56:50-06:00
New Revision: b07dae1f1b758e9f55667dac4db38c78bd609656
URL:
https://github.com/llvm/llvm-project/commit/b07dae1f1b758e9f55667dac4db38c78bd609656
DIFF:
https://github.com/llvm/llvm-project/commit/b07dae1f1b758e9f55667dac4db38c78bd609656.diff
LOG: Revert "[flang] Add basic -mtune support (#95043)"
This reverts commit a790279bf2a8be2f9c42bf80f55a63933e398d0e.
Added:
Modified:
clang/include/clang/Driver/Options.td
clang/lib/Driver/ToolChains/Flang.cpp
flang/include/flang/Frontend/TargetOptions.h
flang/include/flang/Lower/Bridge.h
flang/include/flang/Optimizer/CodeGen/CGPasses.td
flang/include/flang/Optimizer/CodeGen/Target.h
flang/include/flang/Optimizer/Dialect/Support/FIRContext.h
flang/include/flang/Optimizer/Transforms/Passes.td
flang/lib/Frontend/CompilerInvocation.cpp
flang/lib/Frontend/FrontendActions.cpp
flang/lib/Lower/Bridge.cpp
flang/lib/Optimizer/CodeGen/CodeGen.cpp
flang/lib/Optimizer/CodeGen/Target.cpp
flang/lib/Optimizer/CodeGen/TargetRewrite.cpp
flang/lib/Optimizer/CodeGen/TypeConverter.cpp
flang/lib/Optimizer/Dialect/Support/FIRContext.cpp
flang/tools/bbc/bbc.cpp
flang/tools/tco/tco.cpp
flang/unittests/Optimizer/FIRContextTest.cpp
mlir/include/mlir/Dialect/LLVMIR/LLVMOps.td
mlir/lib/Target/LLVMIR/ModuleImport.cpp
mlir/lib/Target/LLVMIR/ModuleTranslation.cpp
Removed:
flang/test/Driver/tune-cpu-fir.f90
flang/test/Lower/tune-cpu-llvm.f90
mlir/test/Target/LLVMIR/Import/tune-cpu.ll
mlir/test/Target/LLVMIR/tune-cpu.mlir
diff --git a/clang/include/clang/Driver/Options.td
b/clang/include/clang/Driver/Options.td
index b85daa3fccc46..dd55838dcf384 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -5421,7 +5421,6 @@ def module_file_info : Flag<["-"], "module-file-info">,
Flags<[]>,
HelpText<"Provide information about a particular module file">;
def mthumb : Flag<["-"], "mthumb">, Group;
def mtune_EQ : Joined<["-"], "mtune=">, Group,
- Visibility<[ClangOption, FlangOption]>,
HelpText<"Only supported on AArch64, PowerPC, RISC-V, SPARC, SystemZ, and
X86">;
def multi__module : Flag<["-"], "multi_module">;
def multiply__defined__unused : Separate<["-"], "multiply_defined_unused">;
@@ -6738,6 +6737,9 @@ def emit_hlfir : Flag<["-"], "emit-hlfir">,
Group,
let Visibility = [CC1Option, CC1AsOption] in {
+def tune_cpu : Separate<["-"], "tune-cpu">,
+ HelpText<"Tune for a specific cpu type">,
+ MarshallingInfoString>;
def target_abi : Separate<["-"], "target-abi">,
HelpText<"Target a particular ABI type">,
MarshallingInfoString>;
@@ -6764,9 +6766,6 @@ def darwin_target_variant_triple : Separate<["-"],
"darwin-target-variant-triple
let Visibility = [CC1Option, CC1AsOption, FC1Option] in {
-def tune_cpu : Separate<["-"], "tune-cpu">,
- HelpText<"Tune for a specific cpu type">,
- MarshallingInfoString>;
def target_cpu : Separate<["-"], "target-cpu">,
HelpText<"Target a specific cpu type">,
MarshallingInfoString>;
diff --git a/clang/lib/Driver/ToolChains/Flang.cpp
b/clang/lib/Driver/ToolChains/Flang.cpp
index 98fe7cace058f..42b45dba2bd31 100644
--- a/clang/lib/Driver/ToolChains/Flang.cpp
+++ b/clang/lib/Driver/ToolChains/Flang.cpp
@@ -15,7 +15,6 @@
#include "llvm/Frontend/Debug/Options.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/Path.h"
-#include "llvm/TargetParser/Host.h"
#include "llvm/TargetParser/RISCVISAInfo.h"
#include "llvm/TargetParser/RISCVTargetParser.h"
@@ -412,13 +411,6 @@ void Flang::addTargetOptions(const ArgList ,
}
// TODO: Add target specific flags, ABI, mtune option etc.
- if (const Arg *A = Args.getLastArg(options::OPT_mtune_EQ)) {
-CmdArgs.push_back("-tune-cpu");
-if (A->getValue() == StringRef{"native"})
- CmdArgs.push_back(Args.MakeArgString(llvm::sys::getHostCPUName()));
-else
- CmdArgs.push_back(A->getValue());
- }
}
void Flang::addOffloadOptions(Compilation , const InputInfoList ,
@@ -810,7 +802,7 @@ void Flang::ConstructJob(Compilation , const JobAction
,
case CodeGenOptions::FramePointerKind::None:
FPKeepKindStr = "-mframe-pointer=none";
break;
- case CodeGenOptions::FramePointerKind::Reserved:
+ case CodeGenOptions::FramePointerKind::Reserved:
FPKeepKindStr = "-mframe-pointer=reserved";
break;
case CodeGenOptions::FramePointerKind::NonLeaf:
diff --git a/flang/include/flang/Frontend/TargetOptions.h
b/flang/include/flang/Frontend/TargetOptions.h
index fa72c77a028a1..ef5d270a2185d 100644
--- a/flang/include/flang/Frontend/TargetOptions.h
+++ b/flang/include/flang/Frontend/TargetOptions.h
@@ -32,9 +32,6 @@ class TargetOptions {
/// If given, the name of the target CPU to generate code for.
std::string cpu;
- /// If given, the name of the target
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/95884
>From 34652b2eebc62218c50a23509ce99937385c30e6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:42:00 -0700
Subject: [PATCH 1/7] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 73 --
1 file changed, 56 insertions(+), 17 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 66cabc236f4b2..c9f6d88f0b13a 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -424,36 +424,75 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
// Uses name similarity to match functions that were not matched by name.
uint64_t MatchedWithDemangledName = 0;
- if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
-
-std::unordered_map NameToBinaryFunction;
-NameToBinaryFunction.reserve(BC.getBinaryFunctions().size());
-for (auto &[_, BF] : BC.getBinaryFunctions()) {
+ if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
+auto DemangleName = [&](const char* String) {
int Status = 0;
- char *DemangledName = abi::__cxa_demangle(BF.getOneName().str().c_str(),
+ char *DemangledName = abi::__cxa_demangle(String,
nullptr, nullptr, );
- if (Status == 0)
-NameToBinaryFunction[std::string(DemangledName)] =
+ return Status == 0 ? new std::string(DemangledName) : nullptr;
+};
+
+auto DeriveNameSpace = [&](std::string DemangledName) {
+ size_t LParen = std::string(DemangledName).find("(");
+ std::string FunctionName = std::string(DemangledName).substr(0, LParen);
+ size_t ScopeResolutionOperator = std::string(FunctionName).rfind("::");
+ return ScopeResolutionOperator == std::string::npos ? std::string("") :
std::string(DemangledName).substr(0, ScopeResolutionOperator);
+};
+
+std::unordered_map>
NamespaceToBFs;
+NamespaceToBFs.reserve(BC.getBinaryFunctions().size());
+
+for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
+ std::string* DemangledName =
DemangleName(BF->getOneName().str().c_str());
+ if (!DemangledName)
+continue;
+ std::string Namespace = DeriveNameSpace(*DemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
+NamespaceToBFs[Namespace] = {BF};
+ else
+It->second.push_back(BF);
}
for (auto YamlBF : YamlBP.Functions) {
if (YamlBF.Used)
continue;
- int Status = 0;
- char *DemangledName =
- abi::__cxa_demangle(YamlBF.Name.c_str(), nullptr, nullptr, );
- if (Status != 0)
+ std::string* YamlBFDemangledName = DemangleName(YamlBF.Name.c_str());
+ if (!YamlBFDemangledName)
continue;
- auto It = NameToBinaryFunction.find(DemangledName);
- if (It == NameToBinaryFunction.end())
+ std::string Namespace = DeriveNameSpace(*YamlBFDemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
continue;
- BinaryFunction *BF = It->second;
- matchProfileToFunction(YamlBF, *BF);
- ++MatchedWithDemangledName;
+ std::vector BFs = It->second;
+
+ unsigned MinEditDistance = UINT_MAX;
+ BinaryFunction *ClosestNameBF = nullptr;
+
+ for (BinaryFunction *BF : BFs) {
+if (ProfiledFunctions.count(BF))
+ continue;
+std::string *BFDemangledName =
DemangleName(BF->getOneName().str().c_str());
+if (!BFDemangledName)
+ continue;
+unsigned BFEditDistance =
StringRef(*BFDemangledName).edit_distance(*YamlBFDemangledName);
+if (BFEditDistance < MinEditDistance) {
+ MinEditDistance = BFEditDistance;
+ ClosestNameBF = BF;
+}
+ }
+
+ if (ClosestNameBF &&
+MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
+matchProfileToFunction(YamlBF, *ClosestNameBF);
+++MatchedWithDemangledName;
+ }
}
}
+ outs() << MatchedWithDemangledName << ": functions matched by name
similarity\n";
+
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 2d23bbd6b9ce4f0786ae8ceb39b1b008b4ca9c4d Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:45:27 -0700
Subject: [PATCH 2/7] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 2 --
1 file changed, 2 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index c9f6d88f0b13a..cf4a5393df8f4 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -491,8 +491,6 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/95884
>From 34652b2eebc62218c50a23509ce99937385c30e6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:42:00 -0700
Subject: [PATCH 1/7] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 73 --
1 file changed, 56 insertions(+), 17 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 66cabc236f4b2..c9f6d88f0b13a 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -424,36 +424,75 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
// Uses name similarity to match functions that were not matched by name.
uint64_t MatchedWithDemangledName = 0;
- if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
-
-std::unordered_map NameToBinaryFunction;
-NameToBinaryFunction.reserve(BC.getBinaryFunctions().size());
-for (auto &[_, BF] : BC.getBinaryFunctions()) {
+ if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
+auto DemangleName = [&](const char* String) {
int Status = 0;
- char *DemangledName = abi::__cxa_demangle(BF.getOneName().str().c_str(),
+ char *DemangledName = abi::__cxa_demangle(String,
nullptr, nullptr, );
- if (Status == 0)
-NameToBinaryFunction[std::string(DemangledName)] =
+ return Status == 0 ? new std::string(DemangledName) : nullptr;
+};
+
+auto DeriveNameSpace = [&](std::string DemangledName) {
+ size_t LParen = std::string(DemangledName).find("(");
+ std::string FunctionName = std::string(DemangledName).substr(0, LParen);
+ size_t ScopeResolutionOperator = std::string(FunctionName).rfind("::");
+ return ScopeResolutionOperator == std::string::npos ? std::string("") :
std::string(DemangledName).substr(0, ScopeResolutionOperator);
+};
+
+std::unordered_map>
NamespaceToBFs;
+NamespaceToBFs.reserve(BC.getBinaryFunctions().size());
+
+for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
+ std::string* DemangledName =
DemangleName(BF->getOneName().str().c_str());
+ if (!DemangledName)
+continue;
+ std::string Namespace = DeriveNameSpace(*DemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
+NamespaceToBFs[Namespace] = {BF};
+ else
+It->second.push_back(BF);
}
for (auto YamlBF : YamlBP.Functions) {
if (YamlBF.Used)
continue;
- int Status = 0;
- char *DemangledName =
- abi::__cxa_demangle(YamlBF.Name.c_str(), nullptr, nullptr, );
- if (Status != 0)
+ std::string* YamlBFDemangledName = DemangleName(YamlBF.Name.c_str());
+ if (!YamlBFDemangledName)
continue;
- auto It = NameToBinaryFunction.find(DemangledName);
- if (It == NameToBinaryFunction.end())
+ std::string Namespace = DeriveNameSpace(*YamlBFDemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
continue;
- BinaryFunction *BF = It->second;
- matchProfileToFunction(YamlBF, *BF);
- ++MatchedWithDemangledName;
+ std::vector BFs = It->second;
+
+ unsigned MinEditDistance = UINT_MAX;
+ BinaryFunction *ClosestNameBF = nullptr;
+
+ for (BinaryFunction *BF : BFs) {
+if (ProfiledFunctions.count(BF))
+ continue;
+std::string *BFDemangledName =
DemangleName(BF->getOneName().str().c_str());
+if (!BFDemangledName)
+ continue;
+unsigned BFEditDistance =
StringRef(*BFDemangledName).edit_distance(*YamlBFDemangledName);
+if (BFEditDistance < MinEditDistance) {
+ MinEditDistance = BFEditDistance;
+ ClosestNameBF = BF;
+}
+ }
+
+ if (ClosestNameBF &&
+MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
+matchProfileToFunction(YamlBF, *ClosestNameBF);
+++MatchedWithDemangledName;
+ }
}
}
+ outs() << MatchedWithDemangledName << ": functions matched by name
similarity\n";
+
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 2d23bbd6b9ce4f0786ae8ceb39b1b008b4ca9c4d Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Thu, 20 Jun 2024 23:45:27 -0700
Subject: [PATCH 2/7] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 2 --
1 file changed, 2 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index c9f6d88f0b13a..cf4a5393df8f4 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -491,8 +491,6 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
[llvm-branch-commits] [llvm] [BOLT] Function matching with function calls as anchors (PR #96596)
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96596
>From 05d59574d6260b98a469921eb2fccf5398bfafb6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 24 Jun 2024 23:00:59 -0700
Subject: [PATCH 1/4] Added call to matchWithCallsAsAnchors
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 3 +++
1 file changed, 3 insertions(+)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index aafffac3d4b1c..1a0e5d239d252 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -479,6 +479,9 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
matchProfileToFunction(YamlBF, *BF);
+ uint64_t MatchedWithCallsAsAnchors = 0;
+ matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
+
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 77ef0008f4f5987719555e6cc3e32da812ae0f31 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 24 Jun 2024 23:11:43 -0700
Subject: [PATCH 2/4] Changed CallHashToBF representation
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 15 ++-
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 1a0e5d239d252..91b01a99c7485 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -29,6 +29,10 @@ static llvm::cl::opt
cl::desc("ignore hash while reading function profile"),
cl::Hidden, cl::cat(BoltOptCategory));
+llvm::cl::opt MatchWithCallsAsAnchors("match-with-calls-as-anchors",
+ cl::desc("Matches with calls as anchors"),
+ cl::Hidden, cl::cat(BoltOptCategory));
+
llvm::cl::opt ProfileUseDFS("profile-use-dfs",
cl::desc("use DFS order for YAML profile"),
cl::Hidden, cl::cat(BoltOptCategory));
@@ -353,7 +357,7 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
llvm_unreachable("Unhandled HashFunction");
};
- std::unordered_map CallHashToBF;
+ std::unordered_map CallHashToBF;
for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
if (ProfiledFunctions.count(BF))
@@ -375,12 +379,12 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
for (const std::string : FunctionNames)
HashString.append(FunctionName);
}
-CallHashToBF.emplace(ComputeCallHash(HashString), BF);
+CallHashToBF[ComputeCallHash(HashString)] = BF;
}
std::unordered_map ProfiledFunctionIdToName;
- for (const yaml::bolt::BinaryFunctionProfile YamlBF : YamlBP.Functions)
+ for (const yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
ProfiledFunctionIdToName[YamlBF.Id] = YamlBF.Name;
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions) {
@@ -401,7 +405,7 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
auto It = CallHashToBF.find(Hash);
if (It == CallHashToBF.end())
continue;
-matchProfileToFunction(YamlBF, It->second);
+matchProfileToFunction(YamlBF, *It->second);
++MatchedWithCallsAsAnchors;
}
}
@@ -480,7 +484,8 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
matchProfileToFunction(YamlBF, *BF);
uint64_t MatchedWithCallsAsAnchors = 0;
- matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
+ if (opts::MatchWithCallsAsAnchors)
+matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
>From ea7cb68ab9e8e158412c2e752986968968a60d93 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Tue, 25 Jun 2024 09:28:39 -0700
Subject: [PATCH 3/4] Changed BF called FunctionNames to multiset
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 91b01a99c7485..3b3d73f7af023 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -365,7 +365,7 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
std::string HashString;
for (const auto : BF->blocks()) {
- std::set FunctionNames;
+ std::multiset FunctionNames;
for (const MCInst : BB) {
// Skip non-call instructions.
if (!BC.MIB->isCall(Instr))
@@ -397,9 +397,8 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
std::string = ProfiledFunctionIdToName[CallSite.DestId];
FunctionNames.insert(FunctionName);
}
- for (const std::string : FunctionNames) {
+ for
[llvm-branch-commits] [llvm] [SPARC][IAS] Rework ASI/Prefetch tag matching in prep for `ParseForAllFeatures` (PR #96020)
https://github.com/s-barannikov approved this pull request. https://github.com/llvm/llvm-project/pull/96020 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Clang format includes (PR #96599)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96599 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Clang format includes (PR #96599)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96599 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Clang format includes (PR #96599)
https://github.com/thurstond approved this pull request. https://github.com/llvm/llvm-project/pull/96599 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [SPARC][IAS] Rework ASI/Prefetch tag matching in prep for `ParseForAllFeatures` (PR #96020)
https://github.com/koachan edited https://github.com/llvm/llvm-project/pull/96020 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [SPARC][IAS] Rework ASI/Prefetch tag matching in prep for `ParseForAllFeatures` (PR #96020)
https://github.com/koachan updated
https://github.com/llvm/llvm-project/pull/96020
>From d09920c3b70d2893fd67cd2fb1c0c58a4da13fa2 Mon Sep 17 00:00:00 2001
From: Koakuma
Date: Tue, 25 Jun 2024 23:52:44 +0700
Subject: [PATCH] Apply changes from review comments
Created using spr 1.3.5
---
.../Target/Sparc/AsmParser/SparcAsmParser.cpp | 58 +--
1 file changed, 27 insertions(+), 31 deletions(-)
diff --git a/llvm/lib/Target/Sparc/AsmParser/SparcAsmParser.cpp
b/llvm/lib/Target/Sparc/AsmParser/SparcAsmParser.cpp
index 1d29ff6d7daa3..af634a7da71c8 100644
--- a/llvm/lib/Target/Sparc/AsmParser/SparcAsmParser.cpp
+++ b/llvm/lib/Target/Sparc/AsmParser/SparcAsmParser.cpp
@@ -107,14 +107,14 @@ class SparcAsmParser : public MCTargetAsmParser {
ParseStatus parseBranchModifiers(OperandVector );
- ParseStatus parseExpression(OperandVector , int64_t );
+ ParseStatus parseExpression(int64_t );
// Helper function for dealing with %lo / %hi in PIC mode.
const SparcMCExpr *adjustPICRelocation(SparcMCExpr::VariantKind VK,
const MCExpr *subExpr);
// Helper function to see if current token can start an expression.
- bool isPossibleExpression(AsmToken );
+ bool isPossibleExpression(const AsmToken );
// returns true if Tok is matched to a register and returns register in
RegNo.
MCRegister matchRegisterName(const AsmToken , unsigned );
@@ -1093,7 +1093,7 @@ ParseStatus SparcAsmParser::parseASITag(OperandVector
) {
if (getLexer().getKind() != AsmToken::Hash) {
// If the ASI tag provided is not a named tag, then it
// must be a constant expression.
-ParseStatus ParseExprStatus = parseExpression(Operands, ASIVal);
+ParseStatus ParseExprStatus = parseExpression(ASIVal);
if (!ParseExprStatus.isSuccess())
return ParseExprStatus;
@@ -1128,35 +1128,32 @@ ParseStatus
SparcAsmParser::parsePrefetchTag(OperandVector ) {
SMLoc E = Parser.getTok().getEndLoc();
int64_t PrefetchVal = 0;
- switch (getLexer().getKind()) {
- case AsmToken::LParen:
- case AsmToken::Integer:
- case AsmToken::Identifier:
- case AsmToken::Plus:
- case AsmToken::Minus:
- case AsmToken::Tilde:
-if (getParser().parseAbsoluteExpression(PrefetchVal) ||
-!isUInt<5>(PrefetchVal))
- return Error(S, "invalid prefetch number, must be between 0 and 31");
-break;
- case AsmToken::Hash: {
-SMLoc TagStart = getLexer().peekTok(false).getLoc();
-Parser.Lex(); // Eat the '#'.
-const StringRef PrefetchName = Parser.getTok().getString();
-const SparcPrefetchTag::PrefetchTag *PrefetchTag =
-SparcPrefetchTag::lookupPrefetchTagByName(PrefetchName);
-Parser.Lex(); // Eat the identifier token.
+ if (getLexer().getKind() != AsmToken::Hash) {
+// If the prefetch tag provided is not a named tag, then it
+// must be a constant expression.
+ParseStatus ParseExprStatus = parseExpression(PrefetchVal);
+if (!ParseExprStatus.isSuccess())
+ return ParseExprStatus;
-if (!PrefetchTag)
- return Error(TagStart, "unknown prefetch tag");
+if (!isUInt<8>(PrefetchVal))
+ return Error(S, "invalid prefetch number, must be between 0 and 31");
-PrefetchVal = PrefetchTag->Encoding;
-break;
- }
- default:
-return ParseStatus::NoMatch;
+Operands.push_back(SparcOperand::CreatePrefetchTag(PrefetchVal, S, E));
+return ParseStatus::Success;
}
+ SMLoc TagStart = getLexer().peekTok(false).getLoc();
+ Parser.Lex(); // Eat the '#'.
+ const StringRef PrefetchName = Parser.getTok().getString();
+ const SparcPrefetchTag::PrefetchTag *PrefetchTag =
+ SparcPrefetchTag::lookupPrefetchTagByName(PrefetchName);
+ Parser.Lex(); // Eat the identifier token.
+
+ if (!PrefetchTag)
+return Error(TagStart, "unknown prefetch tag");
+
+ PrefetchVal = PrefetchTag->Encoding;
+
Operands.push_back(SparcOperand::CreatePrefetchTag(PrefetchVal, S, E));
return ParseStatus::Success;
}
@@ -1372,8 +1369,7 @@ ParseStatus
SparcAsmParser::parseBranchModifiers(OperandVector ) {
return ParseStatus::Success;
}
-ParseStatus SparcAsmParser::parseExpression(OperandVector ,
-int64_t ) {
+ParseStatus SparcAsmParser::parseExpression(int64_t ) {
AsmToken Tok = getLexer().getTok();
if (!isPossibleExpression(Tok))
@@ -1612,7 +1608,7 @@ bool SparcAsmParser::matchSparcAsmModifiers(const MCExpr
*,
return true;
}
-bool SparcAsmParser::isPossibleExpression(AsmToken ) {
+bool SparcAsmParser::isPossibleExpression(const AsmToken ) {
switch (Token.getKind()) {
case AsmToken::LParen:
case AsmToken::Integer:
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
https://github.com/shawbyoung ready_for_review https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Function matching with function calls as anchors (PR #96596)
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96596
>From 05d59574d6260b98a469921eb2fccf5398bfafb6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 24 Jun 2024 23:00:59 -0700
Subject: [PATCH 1/3] Added call to matchWithCallsAsAnchors
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 3 +++
1 file changed, 3 insertions(+)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index aafffac3d4b1c..1a0e5d239d252 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -479,6 +479,9 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
matchProfileToFunction(YamlBF, *BF);
+ uint64_t MatchedWithCallsAsAnchors = 0;
+ matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
+
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 77ef0008f4f5987719555e6cc3e32da812ae0f31 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 24 Jun 2024 23:11:43 -0700
Subject: [PATCH 2/3] Changed CallHashToBF representation
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 15 ++-
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 1a0e5d239d252..91b01a99c7485 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -29,6 +29,10 @@ static llvm::cl::opt
cl::desc("ignore hash while reading function profile"),
cl::Hidden, cl::cat(BoltOptCategory));
+llvm::cl::opt MatchWithCallsAsAnchors("match-with-calls-as-anchors",
+ cl::desc("Matches with calls as anchors"),
+ cl::Hidden, cl::cat(BoltOptCategory));
+
llvm::cl::opt ProfileUseDFS("profile-use-dfs",
cl::desc("use DFS order for YAML profile"),
cl::Hidden, cl::cat(BoltOptCategory));
@@ -353,7 +357,7 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
llvm_unreachable("Unhandled HashFunction");
};
- std::unordered_map CallHashToBF;
+ std::unordered_map CallHashToBF;
for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
if (ProfiledFunctions.count(BF))
@@ -375,12 +379,12 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
for (const std::string : FunctionNames)
HashString.append(FunctionName);
}
-CallHashToBF.emplace(ComputeCallHash(HashString), BF);
+CallHashToBF[ComputeCallHash(HashString)] = BF;
}
std::unordered_map ProfiledFunctionIdToName;
- for (const yaml::bolt::BinaryFunctionProfile YamlBF : YamlBP.Functions)
+ for (const yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
ProfiledFunctionIdToName[YamlBF.Id] = YamlBF.Name;
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions) {
@@ -401,7 +405,7 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
auto It = CallHashToBF.find(Hash);
if (It == CallHashToBF.end())
continue;
-matchProfileToFunction(YamlBF, It->second);
+matchProfileToFunction(YamlBF, *It->second);
++MatchedWithCallsAsAnchors;
}
}
@@ -480,7 +484,8 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
matchProfileToFunction(YamlBF, *BF);
uint64_t MatchedWithCallsAsAnchors = 0;
- matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
+ if (opts::MatchWithCallsAsAnchors)
+matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
>From ea7cb68ab9e8e158412c2e752986968968a60d93 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Tue, 25 Jun 2024 09:28:39 -0700
Subject: [PATCH 3/3] Changed BF called FunctionNames to multiset
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 91b01a99c7485..3b3d73f7af023 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -365,7 +365,7 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
std::string HashString;
for (const auto : BF->blocks()) {
- std::set FunctionNames;
+ std::multiset FunctionNames;
for (const MCInst : BB) {
// Skip non-call instructions.
if (!BC.MIB->isCall(Instr))
@@ -397,9 +397,8 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
std::string = ProfiledFunctionIdToName[CallSite.DestId];
FunctionNames.insert(FunctionName);
}
- for (const std::string : FunctionNames) {
+ for
[llvm-branch-commits] [runtimes] Allow building against an installed LLVM tree (PR #86209)
https://github.com/ldionne approved this pull request. LGTM but I think @petrhosek should also have a look. https://github.com/llvm/llvm-project/pull/86209 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
https://github.com/fmayer approved this pull request. https://github.com/llvm/llvm-project/pull/96600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
fmayer wrote: nit: and stack depot? "and stacks" is confusing a bit. https://github.com/llvm/llvm-project/pull/96600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [libcxx] [clang] Finish implementation of P0522 (PR #96023)
@@ -18,5 +18,9 @@
#include
#include
-// expected-error@+1 {{template template argument has different template
parameters than its corresponding template template parameter}}
-static_assert(!std::__is_specialization_v,
std::array>);
+#if defined(__clang__) && __clang_major__ >= 19
+// expected-error@array:* {{could not match _Size against
'type-parameter-0-0'}}
+#else
+// expected-error@#SA {{template template argument has different template
parameters than its corresponding template template parameter}}
+#endif
ldionne wrote:
Yeah, I really don't think the exact error message is important to test.
https://github.com/llvm/llvm-project/pull/96023
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] release/18.x: [SystemZ] Bugfix in getDemandedSrcElements(). (#88623) (PR #95463)
https://github.com/uweigand approved this pull request. https://github.com/llvm/llvm-project/pull/95463 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] release/18.x: [SystemZ] Bugfix in getDemandedSrcElements(). (#88623) (PR #95463)
uweigand wrote: It is not a regression, but a codegen wrong-code bug that can trigger based on random source code changes. Given that fact, and the fact the fix is very simple and "obviously correct", I do think this would be good to backport. https://github.com/llvm/llvm-project/pull/95463 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [LAA] Use SCEVUse to add extra NUW flags to pointer bounds. (WIP) (PR #91962)
https://github.com/fhahn updated https://github.com/llvm/llvm-project/pull/91962
>From 9a8305b0041586627b3c3c8a1dc954306767cadc Mon Sep 17 00:00:00 2001
From: Florian Hahn
Date: Wed, 1 May 2024 11:03:42 +0100
Subject: [PATCH 1/3] [SCEV,LAA] Add tests to make sure scoped SCEVs don't
impact other SCEVs.
---
.../LoopAccessAnalysis/scoped-scevs.ll| 182 ++
1 file changed, 182 insertions(+)
create mode 100644 llvm/test/Analysis/LoopAccessAnalysis/scoped-scevs.ll
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/scoped-scevs.ll
b/llvm/test/Analysis/LoopAccessAnalysis/scoped-scevs.ll
new file mode 100644
index 0..323ba2a739cf8
--- /dev/null
+++ b/llvm/test/Analysis/LoopAccessAnalysis/scoped-scevs.ll
@@ -0,0 +1,182 @@
+; NOTE: Assertions have been autogenerated by
utils/update_analyze_test_checks.py UTC_ARGS: --version 4
+; RUN: opt -passes='print,print'
-disable-output %s 2>&1 | FileCheck --check-prefixes=LAA,AFTER %s
+; RUN: opt
-passes='print,print,print'
-disable-output %s 2>&1 | FileCheck --check-prefixes=BEFORE,LAA,AFTER %s
+
+target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
+
+declare void @use(ptr)
+
+; Check that scoped expressions created by LAA do not interfere with non-scoped
+; SCEVs with the same operands. The tests first run print to
+; populate the SCEV cache. They contain a GEP computing A+405, which is the end
+; of the accessed range, before and/or after the loop. No nuw flags should be
+; added to them in the second print output.
+
+define ptr @test_ptr_range_end_computed_before_and_after_loop(ptr %A) {
+; BEFORE-LABEL: 'test_ptr_range_end_computed_before_and_after_loop'
+; BEFORE-NEXT: Classifying expressions for:
@test_ptr_range_end_computed_before_and_after_loop
+; BEFORE:%x = getelementptr inbounds i8, ptr %A, i64 405
+; BEFORE-NEXT:--> (405 + %A) U: full-set S: full-set
+; BEFORE:%y = getelementptr inbounds i8, ptr %A, i64 405
+; BEFORE-NEXT:--> (405 + %A) U: full-set S: full-set
+;
+; LAA-LABEL: 'test_ptr_range_end_computed_before_and_after_loop'
+; LAA-NEXT:loop:
+; LAA-NEXT: Memory dependences are safe with run-time checks
+; LAA-NEXT: Dependences:
+; LAA-NEXT: Run-time memory checks:
+; LAA-NEXT: Check 0:
+; LAA-NEXT:Comparing group ([[GRP1:0x[0-9a-f]+]]):
+; LAA-NEXT: %gep.A.400 = getelementptr inbounds i32, ptr %A.1, i64 %iv
+; LAA-NEXT:Against group ([[GRP2:0x[0-9a-f]+]]):
+; LAA-NEXT: %gep.A = getelementptr inbounds i8, ptr %A, i64 %iv
+; LAA-NEXT: Grouped accesses:
+; LAA-NEXT:Group [[GRP1]]:
+; LAA-NEXT: (Low: (1 + %A) High: (405 + %A))
+; LAA-NEXT:Member: {(1 + %A),+,4}<%loop>
+; LAA-NEXT:Group [[GRP2]]:
+; LAA-NEXT: (Low: %A High: (101 + %A))
+; LAA-NEXT:Member: {%A,+,1}<%loop>
+; LAA-EMPTY:
+; LAA-NEXT: Non vectorizable stores to invariant address were not found
in loop.
+; LAA-NEXT: SCEV assumptions:
+; LAA-EMPTY:
+; LAA-NEXT: Expressions re-written:
+;
+; AFTER-LABEL: 'test_ptr_range_end_computed_before_and_after_loop'
+; AFTER-NEXT: Classifying expressions for:
@test_ptr_range_end_computed_before_and_after_loop
+; AFTER:%x = getelementptr inbounds i8, ptr %A, i64 405
+; AFTER-NEXT:--> (405 + %A) U: full-set S: full-set
+; AFTER:%y = getelementptr inbounds i8, ptr %A, i64 405
+; AFTER-NEXT:--> (405 + %A) U: full-set S: full-set
+entry:
+ %A.1 = getelementptr inbounds i8, ptr %A, i64 1
+ %x = getelementptr inbounds i8, ptr %A, i64 405
+ call void @use(ptr %x)
+ br label %loop
+
+loop:
+ %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
+ %gep.A.400 = getelementptr inbounds i32, ptr %A.1, i64 %iv
+ %gep.A = getelementptr inbounds i8, ptr %A, i64 %iv
+ %l = load i8, ptr %gep.A, align 1
+ %ext = zext i8 %l to i32
+ store i32 %ext, ptr %gep.A.400, align 4
+ %iv.next = add nuw nsw i64 %iv, 1
+ %ec = icmp eq i64 %iv, 100
+ br i1 %ec, label %exit, label %loop
+
+exit:
+ %y = getelementptr inbounds i8, ptr %A, i64 405
+ ret ptr %y
+}
+
+define void @test_ptr_range_end_computed_before_loop(ptr %A) {
+; BEFORE-LABEL: 'test_ptr_range_end_computed_before_loop'
+; BEFORE-NEXT: Classifying expressions for:
@test_ptr_range_end_computed_before_loop
+; BEFORE-NEXT:%A.1 = getelementptr inbounds i8, ptr %A, i64 1
+; BEFORE-NEXT:--> (1 + %A) U: full-set S: full-set
+; BEFORE-NEXT:%x = getelementptr inbounds i8, ptr %A, i64 405
+;
+; LAA-LABEL: 'test_ptr_range_end_computed_before_loop'
+; LAA-NEXT:loop:
+; LAA-NEXT: Memory dependences are safe with run-time checks
+; LAA-NEXT: Dependences:
+; LAA-NEXT: Run-time memory checks:
+; LAA-NEXT: Check 0:
+; LAA-NEXT:Comparing group ([[GRP3:0x[0-9a-f]+]]):
+; LAA-NEXT: %gep.A.400 = getelementptr inbounds i32, ptr %A.1, i64 %iv
+; LAA-NEXT:Against group ([[GRP4:0x[0-9a-f]+]]):
+; LAA-NEXT: %gep.A = getelementptr inbounds i8, ptr
[llvm-branch-commits] [llvm] AMDGPU: Add a subtarget feature for fine-grained remote memory support (PR #96442)
@@ -788,6 +788,14 @@ def FeatureFlatAtomicFaddF32Inst "Has flat_atomic_add_f32 instruction" >; +def FeatureAgentScopeFineGrainedRemoteMemoryAtomics + : SubtargetFeature<"agent-scope-fine-grained-remote-memory-atomics", + "HasAgentScopeFineGrainedRemoteMemoryAtomics", + "true", + "Agent (device) scoped atomic operations not directly supported by " arsenm wrote: I dropped the last PCIe reference since XGMI should also work https://github.com/llvm/llvm-project/pull/96442 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] AMDGPU: Add subtarget feature for memory atomic fadd f64 (PR #96444)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96444
>From e948fe9cd65450f109ff02a7f1a033afeb04 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 17:07:53 +0200
Subject: [PATCH] AMDGPU: Add subtarget feature for memory atomic fadd f64
---
llvm/lib/Target/AMDGPU/AMDGPU.td | 21 ++---
llvm/lib/Target/AMDGPU/BUFInstructions.td | 10 ++
llvm/lib/Target/AMDGPU/FLATInstructions.td | 6 +++---
llvm/lib/Target/AMDGPU/GCNSubtarget.h | 10 +++---
llvm/lib/Target/AMDGPU/SIISelLowering.cpp | 2 +-
5 files changed, 31 insertions(+), 18 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 3d0d18e59a8c3..c6d2645e48b2b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -788,6 +788,13 @@ def FeatureFlatAtomicFaddF32Inst
"Has flat_atomic_add_f32 instruction"
>;
+def FeatureFlatBufferGlobalAtomicFaddF64Inst
+ : SubtargetFeature<"flat-buffer-global-fadd-f64-inst",
+ "HasFlatBufferGlobalAtomicFaddF64Inst",
+ "true",
+ "Has flat, buffer, and global instructions for f64 atomic fadd"
+>;
+
def FeatureMemoryAtomicFaddF32DenormalSupport
: SubtargetFeature<"memory-atomic-fadd-f32-denormal-support",
"HasAtomicMemoryAtomicFaddF32DenormalSupport",
@@ -1390,7 +1397,8 @@ def FeatureISAVersion9_0_A : FeatureSet<
FeatureBackOffBarrier,
FeatureKernargPreload,
FeatureAtomicFMinFMaxF64GlobalInsts,
- FeatureAtomicFMinFMaxF64FlatInsts
+ FeatureAtomicFMinFMaxF64FlatInsts,
+ FeatureFlatBufferGlobalAtomicFaddF64Inst
])>;
def FeatureISAVersion9_0_C : FeatureSet<
@@ -1435,7 +1443,8 @@ def FeatureISAVersion9_4_Common : FeatureSet<
FeatureAtomicFMinFMaxF64GlobalInsts,
FeatureAtomicFMinFMaxF64FlatInsts,
FeatureAgentScopeFineGrainedRemoteMemoryAtomics,
- FeatureMemoryAtomicFaddF32DenormalSupport
+ FeatureMemoryAtomicFaddF32DenormalSupport,
+ FeatureFlatBufferGlobalAtomicFaddF64Inst
]>;
def FeatureISAVersion9_4_0 : FeatureSet<
@@ -1930,11 +1939,9 @@ def isGFX12Plus :
def HasFlatAddressSpace : Predicate<"Subtarget->hasFlatAddressSpace()">,
AssemblerPredicate<(all_of FeatureFlatAddressSpace)>;
-
-def HasBufferFlatGlobalAtomicsF64 : // FIXME: Rename to show it's only for fadd
- Predicate<"Subtarget->hasBufferFlatGlobalAtomicsF64()">,
- // FIXME: This is too coarse, and working around using pseudo's predicates
on real instruction.
- AssemblerPredicate<(any_of FeatureGFX90AInsts, FeatureGFX10Insts,
FeatureSouthernIslands, FeatureSeaIslands)>;
+def HasFlatBufferGlobalAtomicFaddF64Inst :
+ Predicate<"Subtarget->hasFlatBufferGlobalAtomicFaddF64Inst()">,
+ AssemblerPredicate<(any_of FeatureFlatBufferGlobalAtomicFaddF64Inst)>;
def HasAtomicFMinFMaxF32GlobalInsts :
Predicate<"Subtarget->hasAtomicFMinFMaxF32GlobalInsts()">,
diff --git a/llvm/lib/Target/AMDGPU/BUFInstructions.td
b/llvm/lib/Target/AMDGPU/BUFInstructions.td
index 3b8d94b744000..a904c8483dbf5 100644
--- a/llvm/lib/Target/AMDGPU/BUFInstructions.td
+++ b/llvm/lib/Target/AMDGPU/BUFInstructions.td
@@ -1312,14 +1312,16 @@ let SubtargetPredicate = isGFX90APlus in {
}
} // End SubtargetPredicate = isGFX90APlus
-let SubtargetPredicate = HasBufferFlatGlobalAtomicsF64 in {
+let SubtargetPredicate = HasFlatBufferGlobalAtomicFaddF64Inst in {
defm BUFFER_ATOMIC_ADD_F64 : MUBUF_Pseudo_Atomics<"buffer_atomic_add_f64",
VReg_64, f64>;
+} // End SubtargetPredicate = HasFlatBufferGlobalAtomicFaddF64Inst
+let SubtargetPredicate = HasAtomicFMinFMaxF64GlobalInsts in {
// Note the names can be buffer_atomic_fmin_x2/buffer_atomic_fmax_x2
// depending on some subtargets.
defm BUFFER_ATOMIC_MIN_F64 : MUBUF_Pseudo_Atomics<"buffer_atomic_min_f64",
VReg_64, f64>;
defm BUFFER_ATOMIC_MAX_F64 : MUBUF_Pseudo_Atomics<"buffer_atomic_max_f64",
VReg_64, f64>;
-} // End SubtargetPredicate = HasBufferFlatGlobalAtomicsF64
+}
def BUFFER_INV : MUBUF_Invalidate<"buffer_inv"> {
let SubtargetPredicate = isGFX940Plus;
@@ -1836,9 +1838,9 @@ let SubtargetPredicate =
HasAtomicBufferGlobalPkAddF16Insts in {
defm : SIBufferAtomicPat<"SIbuffer_atomic_fadd", v2f16,
"BUFFER_ATOMIC_PK_ADD_F16", ["ret"]>;
} // End SubtargetPredicate = HasAtomicBufferGlobalPkAddF16Insts
-let SubtargetPredicate = HasBufferFlatGlobalAtomicsF64 in {
+let SubtargetPredicate = HasFlatBufferGlobalAtomicFaddF64Inst in {
defm : SIBufferAtomicPat<"SIbuffer_atomic_fadd", f64,
"BUFFER_ATOMIC_ADD_F64">;
-} // End SubtargetPredicate = HasBufferFlatGlobalAtomicsF64
+} // End SubtargetPredicate = HasFlatBufferGlobalAtomicFaddF64Inst
let SubtargetPredicate = HasAtomicFMinFMaxF64GlobalInsts in {
defm : SIBufferAtomicPat<"SIbuffer_atomic_fmin", f64,
"BUFFER_ATOMIC_MIN_F64">;
diff --git a/llvm/lib/Target/AMDGPU/FLATInstructions.td
b/llvm/lib/Target/AMDGPU/FLATInstructions.td
index 98054dde398b3..89946a4719557 100644
---
[llvm-branch-commits] [llvm] AMDGPU: Add subtarget feature for global atomic fadd denormal support (PR #96443)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96443
>From 975c64c4becd802f9d0038fa79f46e4e94623691 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 16:44:08 +0200
Subject: [PATCH 1/2] AMDGPU: Add subtarget feature for global atomic fadd
denormal support
Not sure what the behavior for gfx90a is. The SPG says it always flushes.
The instruction documentation says it does not.
---
llvm/lib/Target/AMDGPU/AMDGPU.td | 13 +++--
llvm/lib/Target/AMDGPU/GCNSubtarget.h | 7 +++
2 files changed, 18 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 4d2faacaa915b..9e8c36af97cf2 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -788,6 +788,13 @@ def FeatureFlatAtomicFaddF32Inst
"Has flat_atomic_add_f32 instruction"
>;
+def FeatureMemoryAtomicFaddF32DenormalSupport
+ : SubtargetFeature<"memory-atomic-fadd-f32-denormal-support",
+ "HasAtomicMemoryAtomicFaddF32DenormalSupport",
+ "true",
+ "global/flat/buffer atomic fadd for float supports denormal handling"
+>;
+
def FeatureAgentScopeFineGrainedRemoteMemoryAtomics
: SubtargetFeature<"agent-scope-fine-grained-remote-memory-atomics",
"HasAgentScopeFineGrainedRemoteMemoryAtomics",
@@ -1427,7 +1434,8 @@ def FeatureISAVersion9_4_Common : FeatureSet<
FeatureKernargPreload,
FeatureAtomicFMinFMaxF64GlobalInsts,
FeatureAtomicFMinFMaxF64FlatInsts,
- FeatureAgentScopeFineGrainedRemoteMemoryAtomics
+ FeatureAgentScopeFineGrainedRemoteMemoryAtomics,
+ FeatureMemoryAtomicFaddF32DenormalSupport
]>;
def FeatureISAVersion9_4_0 : FeatureSet<
@@ -1630,7 +1638,8 @@ def FeatureISAVersion12 : FeatureSet<
FeatureVGPRSingleUseHintInsts,
FeatureScalarDwordx3Loads,
FeatureDPPSrc1SGPR,
- FeatureMaxHardClauseLength32]>;
+ FeatureMaxHardClauseLength32,
+ FeatureMemoryAtomicFaddF32DenormalSupport]>;
def FeatureISAVersion12_Generic: FeatureSet<
!listconcat(FeatureISAVersion12.Features,
diff --git a/llvm/lib/Target/AMDGPU/GCNSubtarget.h
b/llvm/lib/Target/AMDGPU/GCNSubtarget.h
index c40efbdcf7f0b..674d84422538f 100644
--- a/llvm/lib/Target/AMDGPU/GCNSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/GCNSubtarget.h
@@ -167,6 +167,7 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool HasAtomicFlatPkAdd16Insts = false;
bool HasAtomicFaddRtnInsts = false;
bool HasAtomicFaddNoRtnInsts = false;
+ bool HasAtomicMemoryAtomicFaddF32DenormalSupport = false;
bool HasAtomicBufferGlobalPkAddF16NoRtnInsts = false;
bool HasAtomicBufferGlobalPkAddF16Insts = false;
bool HasAtomicCSubNoRtnInsts = false;
@@ -872,6 +873,12 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool hasFlatAtomicFaddF32Inst() const { return HasFlatAtomicFaddF32Inst; }
+ /// \return true if the target's flat, global, and buffer atomic fadd for
+ /// float supports denormal handling.
+ bool hasMemoryAtomicFaddF32DenormalSupport() const {
+return HasAtomicMemoryAtomicFaddF32DenormalSupport;
+ }
+
/// \return true if atomic operations targeting fine-grained memory work
/// correctly at device scope, in allocations in host or peer PCIe device
/// memory.
>From 3ec4e64a5cb5a3fe7904fa608c20a774bdc11b2b Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Mon, 24 Jun 2024 12:10:37 +0200
Subject: [PATCH 2/2] Add to gfx11.
RDNA 3 manual says "Floating-point addition handles NAN/INF/denorm"
thought I'm not sure I trust it.
---
llvm/lib/Target/AMDGPU/AMDGPU.td | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 9e8c36af97cf2..3d0d18e59a8c3 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -1547,7 +1547,8 @@ def FeatureISAVersion11_Common : FeatureSet<
FeatureFlatAtomicFaddF32Inst,
FeatureImageInsts,
FeaturePackedTID,
- FeatureVcmpxPermlaneHazard]>;
+ FeatureVcmpxPermlaneHazard,
+ FeatureMemoryAtomicFaddF32DenormalSupport]>;
// There are few workarounds that need to be
// added to all targets. This pessimizes codegen
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] AMDGPU: Add a subtarget feature for fine-grained remote memory support (PR #96442)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96442
>From 1a441c05eb510f3310604594b2687ddf90e884fe Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Sun, 23 Jun 2024 22:02:36 +0200
Subject: [PATCH] AMDGPU: Add a subtarget feature for fine-grained remote
memory support
Atomic access to fine-grained remote memory does not work on all
subtargets. Add a feature for targets where this is expected to work.
---
llvm/lib/Target/AMDGPU/AMDGPU.td | 16 ++--
llvm/lib/Target/AMDGPU/GCNSubtarget.h | 8
2 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 5bc0fe8bba608..4d2faacaa915b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -788,6 +788,16 @@ def FeatureFlatAtomicFaddF32Inst
"Has flat_atomic_add_f32 instruction"
>;
+def FeatureAgentScopeFineGrainedRemoteMemoryAtomics
+ : SubtargetFeature<"agent-scope-fine-grained-remote-memory-atomics",
+ "HasAgentScopeFineGrainedRemoteMemoryAtomics",
+ "true",
+ "Agent (device) scoped atomic operations, excluding those directly "
+ "supported by PCIe (i.e. integer atomic add, exchange, and "
+ "compare-and-swap), are functional for allocations in host or peer "
+ "device memory."
+>;
+
def FeatureDefaultComponentZero : SubtargetFeature<"default-component-zero",
"HasDefaultComponentZero",
"true",
@@ -1207,7 +1217,8 @@ def FeatureGFX12 : GCNSubtargetFeatureGeneration<"GFX12",
FeatureUnalignedBufferAccess, FeatureUnalignedDSAccess,
FeatureTrue16BitInsts, FeatureDefaultComponentBroadcast,
FeatureMaxHardClauseLength32,
- FeatureAtomicFMinFMaxF32GlobalInsts, FeatureAtomicFMinFMaxF32FlatInsts
+ FeatureAtomicFMinFMaxF32GlobalInsts, FeatureAtomicFMinFMaxF32FlatInsts,
+ FeatureAgentScopeFineGrainedRemoteMemoryAtomics
]
>;
@@ -1415,7 +1426,8 @@ def FeatureISAVersion9_4_Common : FeatureSet<
FeatureBackOffBarrier,
FeatureKernargPreload,
FeatureAtomicFMinFMaxF64GlobalInsts,
- FeatureAtomicFMinFMaxF64FlatInsts
+ FeatureAtomicFMinFMaxF64FlatInsts,
+ FeatureAgentScopeFineGrainedRemoteMemoryAtomics
]>;
def FeatureISAVersion9_4_0 : FeatureSet<
diff --git a/llvm/lib/Target/AMDGPU/GCNSubtarget.h
b/llvm/lib/Target/AMDGPU/GCNSubtarget.h
index 966708db4f37c..c40efbdcf7f0b 100644
--- a/llvm/lib/Target/AMDGPU/GCNSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/GCNSubtarget.h
@@ -174,6 +174,7 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool HasAtomicBufferPkAddBF16Inst = false;
bool HasFlatAtomicFaddF32Inst = false;
bool HasDefaultComponentZero = false;
+ bool HasAgentScopeFineGrainedRemoteMemoryAtomics = false;
bool HasDefaultComponentBroadcast = false;
/// The maximum number of instructions that may be placed within an S_CLAUSE,
/// which is one greater than the maximum argument to S_CLAUSE. A value of 0
@@ -871,6 +872,13 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool hasFlatAtomicFaddF32Inst() const { return HasFlatAtomicFaddF32Inst; }
+ /// \return true if atomic operations targeting fine-grained memory work
+ /// correctly at device scope, in allocations in host or peer PCIe device
+ /// memory.
+ bool supportsAgentScopeFineGrainedRemoteMemoryAtomics() const {
+return HasAgentScopeFineGrainedRemoteMemoryAtomics;
+ }
+
bool hasDefaultComponentZero() const { return HasDefaultComponentZero; }
bool hasDefaultComponentBroadcast() const {
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
https://github.com/dvyukov approved this pull request. Note that tsan simply disables itself after multithreaded fork, so it produces false sense to operation with die_after_fork=0. And it still can deadlock on mutex/atomic operations and maybe more. https://github.com/llvm/llvm-project/pull/96600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Test `__tsan_test_only_on_fork` only on Mac (PR #96597)
https://github.com/dvyukov approved this pull request. https://github.com/llvm/llvm-project/pull/96597 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [sanitizer] Rename DEFINE_REAL_PTHREAD_FUNCTIONS (PR #96527)
https://github.com/dvyukov approved this pull request. https://github.com/llvm/llvm-project/pull/96527 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Clang format includes (PR #96599)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96599 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Clang format includes (PR #96599)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96599 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Better name for locking functions (PR #96598)
https://github.com/vitalybuka edited https://github.com/llvm/llvm-project/pull/96598 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
llvmbot wrote:
@llvm/pr-subscribers-compiler-rt-sanitizer
Author: Vitaly Buka (vitalybuka)
Changes
We do that for other Sanitizers, and we
should do the same for TSAN.
There are know deadlocks reports here.
---
Full diff: https://github.com/llvm/llvm-project/pull/96600.diff
2 Files Affected:
- (modified) compiler-rt/lib/tsan/rtl/tsan_mman.cpp (+10)
- (modified) compiler-rt/test/sanitizer_common/TestCases/Posix/fork_threaded.c
(-3)
``diff
diff --git a/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
b/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
index 1e579c6a020e9..e129e9af272f5 100644
--- a/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
+++ b/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
@@ -17,6 +17,7 @@
#include "sanitizer_common/sanitizer_common.h"
#include "sanitizer_common/sanitizer_errno.h"
#include "sanitizer_common/sanitizer_placement_new.h"
+#include "sanitizer_common/sanitizer_stackdepot.h"
#include "tsan_flags.h"
#include "tsan_interface.h"
#include "tsan_report.h"
@@ -119,9 +120,18 @@ ScopedGlobalProcessor::~ScopedGlobalProcessor() {
void AllocatorLockBeforeFork() SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
global_proc()->internal_alloc_mtx.Lock();
InternalAllocatorLock();
+#if !SANITIZER_APPLE
+ // OS X allocates from hooks, see 6a3958247a.
+ allocator()->ForceLock();
+ StackDepotLockBeforeFork();
+#endif
}
void AllocatorUnlockAfterFork(bool child) SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
+#if !SANITIZER_APPLE
+ StackDepotUnlockAfterFork(child);
+ allocator()->ForceUnlock();
+#endif
InternalAllocatorUnlock();
global_proc()->internal_alloc_mtx.Unlock();
}
diff --git a/compiler-rt/test/sanitizer_common/TestCases/Posix/fork_threaded.c
b/compiler-rt/test/sanitizer_common/TestCases/Posix/fork_threaded.c
index 13240234a1c79..27b67db0c0a38 100644
--- a/compiler-rt/test/sanitizer_common/TestCases/Posix/fork_threaded.c
+++ b/compiler-rt/test/sanitizer_common/TestCases/Posix/fork_threaded.c
@@ -6,9 +6,6 @@
// FIXME: It probably hangs on this platform.
// UNSUPPORTED: ppc
-// FIXME: TSAN does not lock allocator.
-// UNSUPPORTED: tsan
-
// FIXME: False stack overflow report
// UNSUPPORTED: android && asan
``
https://github.com/llvm/llvm-project/pull/96600
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Clang format includes (PR #96599)
llvmbot wrote:
@llvm/pr-subscribers-compiler-rt-sanitizer
Author: Vitaly Buka (vitalybuka)
Changes
---
Full diff: https://github.com/llvm/llvm-project/pull/96599.diff
1 Files Affected:
- (modified) compiler-rt/lib/tsan/rtl/tsan_mman.cpp (+4-3)
``diff
diff --git a/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
b/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
index db5d6d0713ce9..1e579c6a020e9 100644
--- a/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
+++ b/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
@@ -9,17 +9,18 @@
// This file is a part of ThreadSanitizer (TSan), a race detector.
//
//===--===//
+#include "tsan_mman.h"
+
#include "sanitizer_common/sanitizer_allocator_checks.h"
#include "sanitizer_common/sanitizer_allocator_interface.h"
#include "sanitizer_common/sanitizer_allocator_report.h"
#include "sanitizer_common/sanitizer_common.h"
#include "sanitizer_common/sanitizer_errno.h"
#include "sanitizer_common/sanitizer_placement_new.h"
+#include "tsan_flags.h"
#include "tsan_interface.h"
-#include "tsan_mman.h"
-#include "tsan_rtl.h"
#include "tsan_report.h"
-#include "tsan_flags.h"
+#include "tsan_rtl.h"
namespace __tsan {
``
https://github.com/llvm/llvm-project/pull/96599
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Test `__tsan_test_only_on_fork` only on Mac (PR #96597)
llvmbot wrote:
@llvm/pr-subscribers-compiler-rt-sanitizer
Author: Vitaly Buka (vitalybuka)
Changes
According to https://reviews.llvm.org/D114250
this was to handle Mac specific issue, however
the test is Linux only.
The test effectively prevents to lock main allocator
on fork, but we do that on Linux for other
sanitizers for years, and need to do the same
for TSAN to avoid deadlocks.
---
Full diff: https://github.com/llvm/llvm-project/pull/96597.diff
2 Files Affected:
- (modified) compiler-rt/lib/tsan/rtl/tsan_rtl.cpp (+4)
- (renamed) compiler-rt/test/tsan/Darwin/fork_deadlock.cpp ()
``diff
diff --git a/compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
b/compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
index fd9441dfcb53c..2d5992b703a6a 100644
--- a/compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
+++ b/compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
@@ -35,8 +35,10 @@ extern "C" void __tsan_resume() {
__tsan_resumed = 1;
}
+#if SANITIZER_APPLE
SANITIZER_WEAK_DEFAULT_IMPL
void __tsan_test_only_on_fork() {}
+#endif
namespace __tsan {
@@ -828,7 +830,9 @@ void ForkBefore(ThreadState* thr, uptr pc)
SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
// Disables memory write in OnUserAlloc/Free.
thr->ignore_reads_and_writes++;
+# if SANITIZER_APPLE
__tsan_test_only_on_fork();
+# endif
}
static void ForkAfter(ThreadState* thr) SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
diff --git a/compiler-rt/test/tsan/Linux/fork_deadlock.cpp
b/compiler-rt/test/tsan/Darwin/fork_deadlock.cpp
similarity index 100%
rename from compiler-rt/test/tsan/Linux/fork_deadlock.cpp
rename to compiler-rt/test/tsan/Darwin/fork_deadlock.cpp
``
https://github.com/llvm/llvm-project/pull/96597
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Better name for locking functions (PR #96598)
llvmbot wrote:
@llvm/pr-subscribers-compiler-rt-sanitizer
Author: Vitaly Buka (vitalybuka)
Changes
These functions used only for `fork`.
---
Full diff: https://github.com/llvm/llvm-project/pull/96598.diff
4 Files Affected:
- (modified) compiler-rt/lib/asan/asan_interceptors.cpp (+1-1)
- (modified) compiler-rt/lib/tsan/rtl/tsan_mman.cpp (+2-2)
- (modified) compiler-rt/lib/tsan/rtl/tsan_mman.h (+2-2)
- (modified) compiler-rt/lib/tsan/rtl/tsan_rtl.cpp (+6-5)
``diff
diff --git a/compiler-rt/lib/asan/asan_interceptors.cpp
b/compiler-rt/lib/asan/asan_interceptors.cpp
index f8f86a766b204..cb2fcfb5a3517 100644
--- a/compiler-rt/lib/asan/asan_interceptors.cpp
+++ b/compiler-rt/lib/asan/asan_interceptors.cpp
@@ -334,7 +334,7 @@ INTERCEPTOR(int, pthread_timedjoin_np, void *thread, void
**ret,
#endif
DEFINE_INTERNAL_PTHREAD_FUNCTIONS
-#endif // ASAN_INTERCEPT_PTHREAD_CREATE
+# endif // ASAN_INTERCEPT_PTHREAD_CREATE
#if ASAN_INTERCEPT_SWAPCONTEXT
static void ClearShadowMemoryForContextStack(uptr stack, uptr ssize) {
diff --git a/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
b/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
index 6f118e0979e2d..db5d6d0713ce9 100644
--- a/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
+++ b/compiler-rt/lib/tsan/rtl/tsan_mman.cpp
@@ -115,12 +115,12 @@ ScopedGlobalProcessor::~ScopedGlobalProcessor() {
gp->mtx.Unlock();
}
-void AllocatorLock() SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
+void AllocatorLockBeforeFork() SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
global_proc()->internal_alloc_mtx.Lock();
InternalAllocatorLock();
}
-void AllocatorUnlock() SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
+void AllocatorUnlockAfterFork(bool child) SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
InternalAllocatorUnlock();
global_proc()->internal_alloc_mtx.Unlock();
}
diff --git a/compiler-rt/lib/tsan/rtl/tsan_mman.h
b/compiler-rt/lib/tsan/rtl/tsan_mman.h
index 2095f28c0253e..f01bbc4d15718 100644
--- a/compiler-rt/lib/tsan/rtl/tsan_mman.h
+++ b/compiler-rt/lib/tsan/rtl/tsan_mman.h
@@ -24,8 +24,8 @@ void ReplaceSystemMalloc();
void AllocatorProcStart(Processor *proc);
void AllocatorProcFinish(Processor *proc);
void AllocatorPrintStats();
-void AllocatorLock();
-void AllocatorUnlock();
+void AllocatorLockBeforeFork();
+void AllocatorUnlockAfterFork(bool child);
void GlobalProcessorLock();
void GlobalProcessorUnlock();
diff --git a/compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
b/compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
index 2d5992b703a6a..e5ebb65754b32 100644
--- a/compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
+++ b/compiler-rt/lib/tsan/rtl/tsan_rtl.cpp
@@ -815,7 +815,7 @@ void ForkBefore(ThreadState* thr, uptr pc)
SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
ctx->thread_registry.Lock();
ctx->slot_mtx.Lock();
ScopedErrorReportLock::Lock();
- AllocatorLock();
+ AllocatorLockBeforeFork();
// Suppress all reports in the pthread_atfork callbacks.
// Reports will deadlock on the report_mtx.
// We could ignore sync operations as well,
@@ -835,11 +835,12 @@ void ForkBefore(ThreadState* thr, uptr pc)
SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
# endif
}
-static void ForkAfter(ThreadState* thr) SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
+static void ForkAfter(ThreadState* thr,
+ bool child) SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
thr->suppress_reports--; // Enabled in ForkBefore.
thr->ignore_interceptors--;
thr->ignore_reads_and_writes--;
- AllocatorUnlock();
+ AllocatorUnlockAfterFork(child);
ScopedErrorReportLock::Unlock();
ctx->slot_mtx.Unlock();
ctx->thread_registry.Unlock();
@@ -849,10 +850,10 @@ static void ForkAfter(ThreadState* thr)
SANITIZER_NO_THREAD_SAFETY_ANALYSIS {
GlobalProcessorUnlock();
}
-void ForkParentAfter(ThreadState* thr, uptr pc) { ForkAfter(thr); }
+void ForkParentAfter(ThreadState* thr, uptr pc) { ForkAfter(thr, false); }
void ForkChildAfter(ThreadState* thr, uptr pc, bool start_thread) {
- ForkAfter(thr);
+ ForkAfter(thr, true);
u32 nthread = ctx->thread_registry.OnFork(thr->tid);
VPrintf(1,
"ThreadSanitizer: forked new process with pid %d,"
``
https://github.com/llvm/llvm-project/pull/96598
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Lock/Unlock allocator and stacks on fork (PR #96600)
https://github.com/vitalybuka created https://github.com/llvm/llvm-project/pull/96600 We do that for other Sanitizers, and we should do the same for TSAN. There are know deadlocks reports here. ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Clang format includes (PR #96599)
https://github.com/vitalybuka created https://github.com/llvm/llvm-project/pull/96599 None ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [nfc][tsan] Better name for locking functions (PR #96598)
https://github.com/vitalybuka created https://github.com/llvm/llvm-project/pull/96598 These functions used only for `fork`. ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [tsan] Test `__tsan_test_only_on_fork` only on Mac (PR #96597)
https://github.com/vitalybuka created https://github.com/llvm/llvm-project/pull/96597 According to https://reviews.llvm.org/D114250 this was to handle Mac specific issue, however the test is Linux only. The test effectively prevents to lock main allocator on fork, but we do that on Linux for other sanitizers for years, and need to do the same for TSAN to avoid deadlocks. ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [sanitizer] Rename DEFINE_REAL_PTHREAD_FUNCTIONS (PR #96527)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96527 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [sanitizer] Rename DEFINE_REAL_PTHREAD_FUNCTIONS (PR #96527)
https://github.com/vitalybuka updated https://github.com/llvm/llvm-project/pull/96527 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Name similarity function matching (PR #95884)
shawbyoung wrote: > Can you please also note the runtime of the namespace-filtered pairwise > checks? This would guide us in whether to add a BB count filtering. Ran BOLT on the adpublisher binary – with name similarity function matching, total execution time of rewrite passes was 2235.2883 seconds (1989.1823 wall clock) with an edit distance threshold of 20 and 2194.1708 seconds (1986.2007 wall clock) with an edit distance threshold of 10. Without name similarity matching, total execution time of rewrite passes was 520.4121 seconds (296.4178 wall clock). https://github.com/llvm/llvm-project/pull/95884 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Function matching with function calls as anchors (PR #96596)
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96596
>From 05d59574d6260b98a469921eb2fccf5398bfafb6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 24 Jun 2024 23:00:59 -0700
Subject: [PATCH 1/2] Added call to matchWithCallsAsAnchors
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 3 +++
1 file changed, 3 insertions(+)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index aafffac3d4b1c..1a0e5d239d252 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -479,6 +479,9 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
matchProfileToFunction(YamlBF, *BF);
+ uint64_t MatchedWithCallsAsAnchors = 0;
+ matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
+
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 77ef0008f4f5987719555e6cc3e32da812ae0f31 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 24 Jun 2024 23:11:43 -0700
Subject: [PATCH 2/2] Changed CallHashToBF representation
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 15 ++-
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index 1a0e5d239d252..91b01a99c7485 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -29,6 +29,10 @@ static llvm::cl::opt
cl::desc("ignore hash while reading function profile"),
cl::Hidden, cl::cat(BoltOptCategory));
+llvm::cl::opt MatchWithCallsAsAnchors("match-with-calls-as-anchors",
+ cl::desc("Matches with calls as anchors"),
+ cl::Hidden, cl::cat(BoltOptCategory));
+
llvm::cl::opt ProfileUseDFS("profile-use-dfs",
cl::desc("use DFS order for YAML profile"),
cl::Hidden, cl::cat(BoltOptCategory));
@@ -353,7 +357,7 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
llvm_unreachable("Unhandled HashFunction");
};
- std::unordered_map CallHashToBF;
+ std::unordered_map CallHashToBF;
for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
if (ProfiledFunctions.count(BF))
@@ -375,12 +379,12 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
for (const std::string : FunctionNames)
HashString.append(FunctionName);
}
-CallHashToBF.emplace(ComputeCallHash(HashString), BF);
+CallHashToBF[ComputeCallHash(HashString)] = BF;
}
std::unordered_map ProfiledFunctionIdToName;
- for (const yaml::bolt::BinaryFunctionProfile YamlBF : YamlBP.Functions)
+ for (const yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
ProfiledFunctionIdToName[YamlBF.Id] = YamlBF.Name;
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions) {
@@ -401,7 +405,7 @@ void YAMLProfileReader::matchWithCallsAsAnchors(
auto It = CallHashToBF.find(Hash);
if (It == CallHashToBF.end())
continue;
-matchProfileToFunction(YamlBF, It->second);
+matchProfileToFunction(YamlBF, *It->second);
++MatchedWithCallsAsAnchors;
}
}
@@ -480,7 +484,8 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
matchProfileToFunction(YamlBF, *BF);
uint64_t MatchedWithCallsAsAnchors = 0;
- matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
+ if (opts::MatchWithCallsAsAnchors)
+matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [BOLT] Function matching with function calls as anchors (PR #96596)
https://github.com/shawbyoung updated
https://github.com/llvm/llvm-project/pull/96596
>From 05d59574d6260b98a469921eb2fccf5398bfafb6 Mon Sep 17 00:00:00 2001
From: shawbyoung
Date: Mon, 24 Jun 2024 23:00:59 -0700
Subject: [PATCH] Added call to matchWithCallsAsAnchors
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 3 +++
1 file changed, 3 insertions(+)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp
b/bolt/lib/Profile/YAMLProfileReader.cpp
index aafffac3d4b1c..1a0e5d239d252 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -479,6 +479,9 @@ Error YAMLProfileReader::readProfile(BinaryContext ) {
if (!YamlBF.Used && BF && !ProfiledFunctions.count(BF))
matchProfileToFunction(YamlBF, *BF);
+ uint64_t MatchedWithCallsAsAnchors = 0;
+ matchWithCallsAsAnchors(BC, MatchedWithCallsAsAnchors);
+
for (yaml::bolt::BinaryFunctionProfile : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
