be6f110bc0
Summary:
Currently we build the OpenMP device runtime as part of the `offload/`
project. This is problematic because it has several restrictions when
compared to the normal offloading runtime. It can only be built with an
up-to-date clang and we need to set the target appropriately. Currently
we hack around this by creating the compiler invocation manually, but
this patch moves it into a separate runtimes build.
This follows the same build we use for libc, libc++, compiler-rt, and
flang-rt. This also moves it from `offload/` into `openmp/` because it
is still the `openmp/` runtime and I feel it is more appropriate. We do
want a generic `offload/` library at some point, but it would be trivial
to then add that as a separate library now that we have the
infrastructure that makes adding these new libraries trivial.
This most importantly will require that users update their build
configs, mostly adding the following lines at a minimum. I was debating
whether or not I should 'auto-upgrade' this, but I just went with a
warning.
```
-DLLVM_RUNTIME_TARGETS='default;amdgcn-amd-amdhsa;nvptx64-nvidia-cuda' \
-DRUNTIMES_nvptx64-nvidia-cuda_LLVM_ENABLE_RUNTIMES=openmp \
-DRUNTIMES_amdgcn-amd-amdhsa_LLVM_ENABLE_RUNTIMES=openmp \
```
This also changed where the `.bc` version of the library lives, but it's
still created.
69 lines
2.1 KiB
C++
69 lines
2.1 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 "Shared/Environment.h"
|
|
|
|
#include "DeviceTypes.h"
|
|
|
|
namespace ompx {
|
|
namespace config {
|
|
|
|
/// 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 chosen debug level.
|
|
uint32_t getDebugKind();
|
|
|
|
/// Return if teams oversubscription is assumed
|
|
uint32_t getAssumeTeamsOversubscription();
|
|
|
|
/// Return if threads oversubscription is assumed
|
|
uint32_t getAssumeThreadsOversubscription();
|
|
|
|
/// Return the amount of dynamic shared memory that was allocated at launch.
|
|
uint64_t getDynamicMemorySize();
|
|
|
|
/// Returns the cycles per second of the device's fixed frequency clock.
|
|
uint64_t getClockFrequency();
|
|
|
|
/// Returns the pointer to the beginning of the indirect call table.
|
|
void *getIndirectCallTablePtr();
|
|
|
|
/// Returns the size of the indirect call table.
|
|
uint64_t getIndirectCallTableSize();
|
|
|
|
/// Returns the size of the indirect call table.
|
|
uint64_t getHardwareParallelism();
|
|
|
|
/// Return if debugging is enabled for the given debug kind.
|
|
bool isDebugMode(DeviceDebugKind 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 ompx
|
|
|
|
#endif
|