2019-08-03 16:42:13 +02:00
|
|
|
//===---------- speculation.cpp - Utilities for Speculation ----------===//
|
|
|
|
//
|
|
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "llvm/ExecutionEngine/Orc/Speculation.h"
|
|
|
|
#include "llvm/IR/BasicBlock.h"
|
|
|
|
#include "llvm/IR/Function.h"
|
|
|
|
#include "llvm/IR/IRBuilder.h"
|
|
|
|
#include "llvm/IR/Instruction.h"
|
|
|
|
#include "llvm/IR/Instructions.h"
|
|
|
|
#include "llvm/IR/LLVMContext.h"
|
|
|
|
#include "llvm/IR/Module.h"
|
|
|
|
#include "llvm/IR/Type.h"
|
|
|
|
#include "llvm/IR/Verifier.h"
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
|
|
|
|
namespace orc {
|
|
|
|
|
|
|
|
// ImplSymbolMap methods
|
|
|
|
void ImplSymbolMap::trackImpls(SymbolAliasMap ImplMaps, JITDylib *SrcJD) {
|
|
|
|
assert(SrcJD && "Tracking on Null Source .impl dylib");
|
|
|
|
std::lock_guard<std::mutex> Lockit(ConcurrentAccess);
|
|
|
|
for (auto &I : ImplMaps) {
|
|
|
|
auto It = Maps.insert({I.first, {I.second.Aliasee, SrcJD}});
|
|
|
|
// check rationale when independent dylibs have same symbol name?
|
|
|
|
assert(It.second && "ImplSymbols are already tracked for this Symbol?");
|
|
|
|
(void)(It);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
[ORCv2] - New Speculate Query Implementation
Summary:
This patch introduces, SequenceBBQuery - new heuristic to find likely next callable functions it tries to find the blocks with calls in order of execution sequence of Blocks.
It still uses BlockFrequencyAnalysis to find high frequency blocks. For a handful of hottest blocks (plan to customize), the algorithm traverse and discovered the caller blocks along the way to Entry Basic Block and Exit Basic Block. It uses Block Hint, to stop traversing the already visited blocks in both direction. It implicitly assumes that once the block is visited during discovering entry or exit nodes, revisiting them again does not add much. It also branch probability info (cached result) to traverse only hot edges (planned to customize) from hot blocks. Without BPI, the algorithm mostly return's all the blocks in the CFG with calls.
It also changes the heuristic queries, so they don't maintain states. Hence it is safe to call from multiple threads.
It also implements, new instrumentation to avoid jumping into JIT on every call to the function with the help _orc_speculate.decision.block and _orc_speculate.block.
"Speculator Registration Mechanism is also changed" - kudos to @lhames
Open to review, mostly looking to change implementation of SequeceBBQuery heuristics with good data structure choices.
Reviewers: lhames, dblaikie
Reviewed By: lhames
Subscribers: mgorny, hiraditya, mgrang, llvm-commits, lhames
Tags: #speculative_compilation_in_orc, #llvm
Differential Revision: https://reviews.llvm.org/D66399
llvm-svn: 370092
2019-08-27 20:23:36 +02:00
|
|
|
// Trigger Speculative Compiles.
|
|
|
|
void Speculator::speculateForEntryPoint(Speculator *Ptr, uint64_t StubId) {
|
|
|
|
assert(Ptr && " Null Address Received in orc_speculate_for ");
|
|
|
|
Ptr->speculateFor(StubId);
|
|
|
|
}
|
|
|
|
|
|
|
|
Error Speculator::addSpeculationRuntime(JITDylib &JD,
|
|
|
|
MangleAndInterner &Mangle) {
|
|
|
|
JITEvaluatedSymbol ThisPtr(pointerToJITTargetAddress(this),
|
|
|
|
JITSymbolFlags::Exported);
|
|
|
|
JITEvaluatedSymbol SpeculateForEntryPtr(
|
|
|
|
pointerToJITTargetAddress(&speculateForEntryPoint),
|
|
|
|
JITSymbolFlags::Exported);
|
|
|
|
return JD.define(absoluteSymbols({
|
|
|
|
{Mangle("__orc_speculator"), ThisPtr}, // Data Symbol
|
|
|
|
{Mangle("__orc_speculate_for"), SpeculateForEntryPtr} // Callable Symbol
|
|
|
|
}));
|
|
|
|
}
|
|
|
|
|
2019-08-03 16:42:13 +02:00
|
|
|
// If two modules, share the same LLVMContext, different threads must
|
[ORCv2] - New Speculate Query Implementation
Summary:
This patch introduces, SequenceBBQuery - new heuristic to find likely next callable functions it tries to find the blocks with calls in order of execution sequence of Blocks.
It still uses BlockFrequencyAnalysis to find high frequency blocks. For a handful of hottest blocks (plan to customize), the algorithm traverse and discovered the caller blocks along the way to Entry Basic Block and Exit Basic Block. It uses Block Hint, to stop traversing the already visited blocks in both direction. It implicitly assumes that once the block is visited during discovering entry or exit nodes, revisiting them again does not add much. It also branch probability info (cached result) to traverse only hot edges (planned to customize) from hot blocks. Without BPI, the algorithm mostly return's all the blocks in the CFG with calls.
It also changes the heuristic queries, so they don't maintain states. Hence it is safe to call from multiple threads.
It also implements, new instrumentation to avoid jumping into JIT on every call to the function with the help _orc_speculate.decision.block and _orc_speculate.block.
"Speculator Registration Mechanism is also changed" - kudos to @lhames
Open to review, mostly looking to change implementation of SequeceBBQuery heuristics with good data structure choices.
Reviewers: lhames, dblaikie
Reviewed By: lhames
Subscribers: mgorny, hiraditya, mgrang, llvm-commits, lhames
Tags: #speculative_compilation_in_orc, #llvm
Differential Revision: https://reviews.llvm.org/D66399
llvm-svn: 370092
2019-08-27 20:23:36 +02:00
|
|
|
// not access them concurrently without locking the associated LLVMContext
|
|
|
|
// this implementation follows this contract.
|
2020-09-11 18:23:14 +02:00
|
|
|
void IRSpeculationLayer::emit(std::unique_ptr<MaterializationResponsibility> R,
|
2019-08-03 16:42:13 +02:00
|
|
|
ThreadSafeModule TSM) {
|
|
|
|
|
|
|
|
assert(TSM && "Speculation Layer received Null Module ?");
|
|
|
|
assert(TSM.getContext().getContext() != nullptr &&
|
|
|
|
"Module with null LLVMContext?");
|
|
|
|
|
[ORCv2] - New Speculate Query Implementation
Summary:
This patch introduces, SequenceBBQuery - new heuristic to find likely next callable functions it tries to find the blocks with calls in order of execution sequence of Blocks.
It still uses BlockFrequencyAnalysis to find high frequency blocks. For a handful of hottest blocks (plan to customize), the algorithm traverse and discovered the caller blocks along the way to Entry Basic Block and Exit Basic Block. It uses Block Hint, to stop traversing the already visited blocks in both direction. It implicitly assumes that once the block is visited during discovering entry or exit nodes, revisiting them again does not add much. It also branch probability info (cached result) to traverse only hot edges (planned to customize) from hot blocks. Without BPI, the algorithm mostly return's all the blocks in the CFG with calls.
It also changes the heuristic queries, so they don't maintain states. Hence it is safe to call from multiple threads.
It also implements, new instrumentation to avoid jumping into JIT on every call to the function with the help _orc_speculate.decision.block and _orc_speculate.block.
"Speculator Registration Mechanism is also changed" - kudos to @lhames
Open to review, mostly looking to change implementation of SequeceBBQuery heuristics with good data structure choices.
Reviewers: lhames, dblaikie
Reviewed By: lhames
Subscribers: mgorny, hiraditya, mgrang, llvm-commits, lhames
Tags: #speculative_compilation_in_orc, #llvm
Differential Revision: https://reviews.llvm.org/D66399
llvm-svn: 370092
2019-08-27 20:23:36 +02:00
|
|
|
// Instrumentation of runtime calls, lock the Module
|
|
|
|
TSM.withModuleDo([this, &R](Module &M) {
|
|
|
|
auto &MContext = M.getContext();
|
|
|
|
auto SpeculatorVTy = StructType::create(MContext, "Class.Speculator");
|
|
|
|
auto RuntimeCallTy = FunctionType::get(
|
|
|
|
Type::getVoidTy(MContext),
|
|
|
|
{SpeculatorVTy->getPointerTo(), Type::getInt64Ty(MContext)}, false);
|
|
|
|
auto RuntimeCall =
|
|
|
|
Function::Create(RuntimeCallTy, Function::LinkageTypes::ExternalLinkage,
|
|
|
|
"__orc_speculate_for", &M);
|
|
|
|
auto SpeclAddr = new GlobalVariable(
|
|
|
|
M, SpeculatorVTy, false, GlobalValue::LinkageTypes::ExternalLinkage,
|
|
|
|
nullptr, "__orc_speculator");
|
|
|
|
|
|
|
|
IRBuilder<> Mutator(MContext);
|
|
|
|
|
|
|
|
// QueryAnalysis allowed to transform the IR source, one such example is
|
|
|
|
// Simplify CFG helps the static branch prediction heuristics!
|
|
|
|
for (auto &Fn : M.getFunctionList()) {
|
|
|
|
if (!Fn.isDeclaration()) {
|
|
|
|
|
|
|
|
auto IRNames = QueryAnalysis(Fn);
|
|
|
|
// Instrument and register if Query has result
|
|
|
|
if (IRNames.hasValue()) {
|
|
|
|
|
|
|
|
// Emit globals for each function.
|
|
|
|
auto LoadValueTy = Type::getInt8Ty(MContext);
|
|
|
|
auto SpeculatorGuard = new GlobalVariable(
|
|
|
|
M, LoadValueTy, false, GlobalValue::LinkageTypes::InternalLinkage,
|
|
|
|
ConstantInt::get(LoadValueTy, 0),
|
|
|
|
"__orc_speculate.guard.for." + Fn.getName());
|
[Alignment][NFC] Deprecate Align::None()
Summary:
This is a follow up on https://reviews.llvm.org/D71473#inline-647262.
There's a caveat here that `Align(1)` relies on the compiler understanding of `Log2_64` implementation to produce good code. One could use `Align()` as a replacement but I believe it is less clear that the alignment is one in that case.
Reviewers: xbolva00, courbet, bollu
Subscribers: arsenm, dylanmckay, sdardis, nemanjai, jvesely, nhaehnle, hiraditya, kbarton, jrtc27, atanasyan, jsji, Jim, kerbowa, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D73099
2020-01-21 15:00:04 +01:00
|
|
|
SpeculatorGuard->setAlignment(Align(1));
|
[ORCv2] - New Speculate Query Implementation
Summary:
This patch introduces, SequenceBBQuery - new heuristic to find likely next callable functions it tries to find the blocks with calls in order of execution sequence of Blocks.
It still uses BlockFrequencyAnalysis to find high frequency blocks. For a handful of hottest blocks (plan to customize), the algorithm traverse and discovered the caller blocks along the way to Entry Basic Block and Exit Basic Block. It uses Block Hint, to stop traversing the already visited blocks in both direction. It implicitly assumes that once the block is visited during discovering entry or exit nodes, revisiting them again does not add much. It also branch probability info (cached result) to traverse only hot edges (planned to customize) from hot blocks. Without BPI, the algorithm mostly return's all the blocks in the CFG with calls.
It also changes the heuristic queries, so they don't maintain states. Hence it is safe to call from multiple threads.
It also implements, new instrumentation to avoid jumping into JIT on every call to the function with the help _orc_speculate.decision.block and _orc_speculate.block.
"Speculator Registration Mechanism is also changed" - kudos to @lhames
Open to review, mostly looking to change implementation of SequeceBBQuery heuristics with good data structure choices.
Reviewers: lhames, dblaikie
Reviewed By: lhames
Subscribers: mgorny, hiraditya, mgrang, llvm-commits, lhames
Tags: #speculative_compilation_in_orc, #llvm
Differential Revision: https://reviews.llvm.org/D66399
llvm-svn: 370092
2019-08-27 20:23:36 +02:00
|
|
|
SpeculatorGuard->setUnnamedAddr(GlobalValue::UnnamedAddr::Local);
|
|
|
|
|
|
|
|
BasicBlock &ProgramEntry = Fn.getEntryBlock();
|
|
|
|
// Create BasicBlocks before the program's entry basicblock
|
|
|
|
BasicBlock *SpeculateBlock = BasicBlock::Create(
|
|
|
|
MContext, "__orc_speculate.block", &Fn, &ProgramEntry);
|
|
|
|
BasicBlock *SpeculateDecisionBlock = BasicBlock::Create(
|
|
|
|
MContext, "__orc_speculate.decision.block", &Fn, SpeculateBlock);
|
|
|
|
|
|
|
|
assert(SpeculateDecisionBlock == &Fn.getEntryBlock() &&
|
|
|
|
"SpeculateDecisionBlock not updated?");
|
|
|
|
Mutator.SetInsertPoint(SpeculateDecisionBlock);
|
|
|
|
|
|
|
|
auto LoadGuard =
|
|
|
|
Mutator.CreateLoad(LoadValueTy, SpeculatorGuard, "guard.value");
|
|
|
|
// if just loaded value equal to 0,return true.
|
|
|
|
auto CanSpeculate =
|
|
|
|
Mutator.CreateICmpEQ(LoadGuard, ConstantInt::get(LoadValueTy, 0),
|
|
|
|
"compare.to.speculate");
|
|
|
|
Mutator.CreateCondBr(CanSpeculate, SpeculateBlock, &ProgramEntry);
|
|
|
|
|
|
|
|
Mutator.SetInsertPoint(SpeculateBlock);
|
|
|
|
auto ImplAddrToUint =
|
|
|
|
Mutator.CreatePtrToInt(&Fn, Type::getInt64Ty(MContext));
|
|
|
|
Mutator.CreateCall(RuntimeCallTy, RuntimeCall,
|
|
|
|
{SpeclAddr, ImplAddrToUint});
|
|
|
|
Mutator.CreateStore(ConstantInt::get(LoadValueTy, 1),
|
|
|
|
SpeculatorGuard);
|
|
|
|
Mutator.CreateBr(&ProgramEntry);
|
|
|
|
|
|
|
|
assert(Mutator.GetInsertBlock()->getParent() == &Fn &&
|
|
|
|
"IR builder association mismatch?");
|
|
|
|
S.registerSymbols(internToJITSymbols(IRNames.getValue()),
|
2020-09-11 18:23:14 +02:00
|
|
|
&R->getTargetJITDylib());
|
[ORCv2] - New Speculate Query Implementation
Summary:
This patch introduces, SequenceBBQuery - new heuristic to find likely next callable functions it tries to find the blocks with calls in order of execution sequence of Blocks.
It still uses BlockFrequencyAnalysis to find high frequency blocks. For a handful of hottest blocks (plan to customize), the algorithm traverse and discovered the caller blocks along the way to Entry Basic Block and Exit Basic Block. It uses Block Hint, to stop traversing the already visited blocks in both direction. It implicitly assumes that once the block is visited during discovering entry or exit nodes, revisiting them again does not add much. It also branch probability info (cached result) to traverse only hot edges (planned to customize) from hot blocks. Without BPI, the algorithm mostly return's all the blocks in the CFG with calls.
It also changes the heuristic queries, so they don't maintain states. Hence it is safe to call from multiple threads.
It also implements, new instrumentation to avoid jumping into JIT on every call to the function with the help _orc_speculate.decision.block and _orc_speculate.block.
"Speculator Registration Mechanism is also changed" - kudos to @lhames
Open to review, mostly looking to change implementation of SequeceBBQuery heuristics with good data structure choices.
Reviewers: lhames, dblaikie
Reviewed By: lhames
Subscribers: mgorny, hiraditya, mgrang, llvm-commits, lhames
Tags: #speculative_compilation_in_orc, #llvm
Differential Revision: https://reviews.llvm.org/D66399
llvm-svn: 370092
2019-08-27 20:23:36 +02:00
|
|
|
}
|
2019-08-03 16:42:13 +02:00
|
|
|
}
|
|
|
|
}
|
[ORCv2] - New Speculate Query Implementation
Summary:
This patch introduces, SequenceBBQuery - new heuristic to find likely next callable functions it tries to find the blocks with calls in order of execution sequence of Blocks.
It still uses BlockFrequencyAnalysis to find high frequency blocks. For a handful of hottest blocks (plan to customize), the algorithm traverse and discovered the caller blocks along the way to Entry Basic Block and Exit Basic Block. It uses Block Hint, to stop traversing the already visited blocks in both direction. It implicitly assumes that once the block is visited during discovering entry or exit nodes, revisiting them again does not add much. It also branch probability info (cached result) to traverse only hot edges (planned to customize) from hot blocks. Without BPI, the algorithm mostly return's all the blocks in the CFG with calls.
It also changes the heuristic queries, so they don't maintain states. Hence it is safe to call from multiple threads.
It also implements, new instrumentation to avoid jumping into JIT on every call to the function with the help _orc_speculate.decision.block and _orc_speculate.block.
"Speculator Registration Mechanism is also changed" - kudos to @lhames
Open to review, mostly looking to change implementation of SequeceBBQuery heuristics with good data structure choices.
Reviewers: lhames, dblaikie
Reviewed By: lhames
Subscribers: mgorny, hiraditya, mgrang, llvm-commits, lhames
Tags: #speculative_compilation_in_orc, #llvm
Differential Revision: https://reviews.llvm.org/D66399
llvm-svn: 370092
2019-08-27 20:23:36 +02:00
|
|
|
});
|
|
|
|
|
|
|
|
assert(!TSM.withModuleDo([](const Module &M) { return verifyModule(M); }) &&
|
2019-08-03 16:42:13 +02:00
|
|
|
"Speculation Instrumentation breaks IR?");
|
|
|
|
|
|
|
|
NextLayer.emit(std::move(R), std::move(TSM));
|
|
|
|
}
|
|
|
|
|
|
|
|
} // namespace orc
|
|
|
|
} // namespace llvm
|