6024e5c395
clang 20.0.0 (based on r547379) from build 12806354. Bug: http://b/379133546 Test: N/A Change-Id: I2eb8938af55d809de674be63cb30cf27e801862b Upstream-Commit: ad834e67b1105d15ef907f6255d4c96e8e733f57
74 lines
3.1 KiB
C++
74 lines
3.1 KiB
C++
//===- LoopGeneratorsGOMP.h - IR helper to create loops ---------*- C++ -*-===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file contains functions to create scalar and OpenMP parallel loops
|
|
// as LLVM-IR.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
#ifndef POLLY_LOOP_GENERATORS_GOMP_H
|
|
#define POLLY_LOOP_GENERATORS_GOMP_H
|
|
|
|
#include "polly/CodeGen/IRBuilder.h"
|
|
#include "polly/CodeGen/LoopGenerators.h"
|
|
#include "polly/Support/ScopHelper.h"
|
|
#include "llvm/ADT/SetVector.h"
|
|
|
|
namespace polly {
|
|
|
|
/// This ParallelLoopGenerator subclass handles the generation of parallelized
|
|
/// code, utilizing the GNU OpenMP library.
|
|
class ParallelLoopGeneratorGOMP final : public ParallelLoopGenerator {
|
|
public:
|
|
/// Create a parallel loop generator for the current function.
|
|
ParallelLoopGeneratorGOMP(PollyIRBuilder &Builder, const DataLayout &DL)
|
|
: ParallelLoopGenerator(Builder, DL) {}
|
|
|
|
// The functions below may be used if one does not want to generate a
|
|
// specific OpenMP parallel loop, but generate individual parts of it
|
|
// (e.g. the subfunction definition).
|
|
|
|
/// Create a runtime library call to spawn the worker threads.
|
|
///
|
|
/// @param SubFn The subfunction which holds the loop body.
|
|
/// @param SubFnParam The parameter for the subfunction (basically the struct
|
|
/// filled with the outside values).
|
|
/// @param LB The lower bound for the loop we parallelize.
|
|
/// @param UB The upper bound for the loop we parallelize.
|
|
/// @param Stride The stride of the loop we parallelize.
|
|
void createCallSpawnThreads(Value *SubFn, Value *SubFnParam, Value *LB,
|
|
Value *UB, Value *Stride);
|
|
|
|
void deployParallelExecution(Function *SubFn, Value *SubFnParam, Value *LB,
|
|
Value *UB, Value *Stride) override;
|
|
|
|
Function *prepareSubFnDefinition(Function *F) const override;
|
|
|
|
std::tuple<Value *, Function *> createSubFn(Value *Stride, AllocaInst *Struct,
|
|
SetVector<Value *> UsedValues,
|
|
ValueMapT &VMap) override;
|
|
|
|
/// Create a runtime library call to join the worker threads.
|
|
void createCallJoinThreads();
|
|
|
|
/// Create a runtime library call to get the next work item.
|
|
///
|
|
/// @param LBPtr A pointer value to store the work item begin in.
|
|
/// @param UBPtr A pointer value to store the work item end in.
|
|
///
|
|
/// @returns A true value if the work item is not empty.
|
|
Value *createCallGetWorkItem(Value *LBPtr, Value *UBPtr);
|
|
|
|
/// Create a runtime library call to allow cleanup of the thread.
|
|
///
|
|
/// @note This function is called right before the thread will exit the
|
|
/// subfunction and only if the runtime system depends on it.
|
|
void createCallCleanupThread();
|
|
};
|
|
} // end namespace polly
|
|
#endif
|