b215932e69
The current only way to obtain pinned memory with libomptarget is to use a custom allocator llvm_omp_target_alloc_host. This reflects well the CUDA implementation of libomptarget, but it does not correctly expose the AMDGPU runtime API, where any system allocated page can be locked/unlocked through a call to hsa_amd_memory_lock/unlock. This patch enables users to allocate memory through malloc (mmap, sbreak) and then pin the related memory pages with a libomptarget special call. It is a base support in the amdgpu libomptarget plugin to enable users to prelock their host memory pages so that the runtime doesn't need to lock them itself for asynchronous memory transfers. Reviewed By: jdoerfert, ye-luo Differential Revision: https://reviews.llvm.org/D139208
35 lines
1.3 KiB
C
35 lines
1.3 KiB
C
//===--- amdgpu/impl/impl_runtime.h ------------------------------- 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
#ifndef INCLUDE_IMPL_RUNTIME_H_
|
|
#define INCLUDE_IMPL_RUNTIME_H_
|
|
|
|
#include "hsa_api.h"
|
|
|
|
extern "C" {
|
|
|
|
// Check if pointer ptr is already locked
|
|
hsa_status_t is_locked(void *ptr, void **agentBaseAddress);
|
|
|
|
hsa_status_t impl_module_register_from_memory_to_place(
|
|
void *module_bytes, size_t module_size, int DeviceId,
|
|
hsa_status_t (*on_deserialized_data)(void *data, size_t size,
|
|
void *cb_state),
|
|
void *cb_state);
|
|
|
|
hsa_status_t impl_memcpy_h2d(hsa_signal_t signal, void *deviceDest,
|
|
void *hostSrc, size_t size,
|
|
hsa_agent_t device_agent,
|
|
hsa_amd_memory_pool_t MemoryPool);
|
|
|
|
hsa_status_t impl_memcpy_d2h(hsa_signal_t sig, void *hostDest, void *deviceSrc,
|
|
size_t size, hsa_agent_t device_agent,
|
|
hsa_amd_memory_pool_t MemoryPool);
|
|
}
|
|
|
|
#endif // INCLUDE_IMPL_RUNTIME_H_
|