2b8f722e63
The OpenMP device runtime needs to support the OpenMP standard. However constructs like nested parallelism are very uncommon in real application yet lead to complexity in the runtime that is sometimes difficult to optimize out. As a stop-gap for performance we should supply an argument that selectively disables this feature. This patch adds the `-fopenmp-assume-no-nested-parallelism` argument which explicitly disables the usee of nested parallelism in OpenMP. Reviewed By: carlo.bertolli Differential Revision: https://reviews.llvm.org/D132074
55 lines
1.6 KiB
C++
55 lines
1.6 KiB
C++
//===--- Configuration.h - OpenMP device configuration interface -- 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// API to query the global (constant) device environment.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef OMPTARGET_CONFIGURATION_H
|
|
#define OMPTARGET_CONFIGURATION_H
|
|
|
|
#include "Types.h"
|
|
|
|
namespace _OMP {
|
|
namespace config {
|
|
|
|
enum DebugKind : uint32_t {
|
|
Assertion = 1U << 0,
|
|
FunctionTracing = 1U << 1,
|
|
CommonIssues = 1U << 2,
|
|
};
|
|
|
|
/// Return the number of devices in the system, same number as returned on the
|
|
/// host by omp_get_num_devices.
|
|
uint32_t getNumDevices();
|
|
|
|
/// Return the device number in the system for omp_get_device_num.
|
|
uint32_t getDeviceNum();
|
|
|
|
/// Return the user choosen debug level.
|
|
uint32_t getDebugKind();
|
|
|
|
/// Return the amount of dynamic shared memory that was allocated at launch.
|
|
uint64_t getDynamicMemorySize();
|
|
|
|
/// Return if debugging is enabled for the given debug kind.
|
|
bool isDebugMode(DebugKind Level);
|
|
|
|
/// Indicates if this kernel may require thread-specific states, or if it was
|
|
/// explicitly disabled by the user.
|
|
bool mayUseThreadStates();
|
|
|
|
/// Indicates if this kernel may require data environments for nested
|
|
/// parallelism, or if it was explicitly disabled by the user.
|
|
bool mayUseNestedParallelism();
|
|
|
|
} // namespace config
|
|
} // namespace _OMP
|
|
|
|
#endif
|