llama.cpp/ggml-sycl/common.cpp
Meng, Hengyu 7b2f4a7d19
[SYCL] remove global variables (#7710)
* separate DPCT helpers outside

* replace global variables with context

* remove useless extra

* update mul_mat condition

* remove duplicate buft initialization

* remove duplicate extra and global work group size

* remove useless backend check

* remove duplicated extras

* use macro for group_size and remove cuda-related
2024-06-15 14:05:10 +08:00

54 lines
1.5 KiB
C++

//
// MIT license
// Copyright (C) 2024 Intel Corporation
// SPDX-License-Identifier: MIT
//
//
// 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 "common.hpp"
int get_current_device_id() {
return dpct::dev_mgr::instance().current_device_id();
}
void* ggml_sycl_host_malloc(size_t size) try {
if (getenv("GGML_SYCL_NO_PINNED") != nullptr) {
return nullptr;
}
void* ptr = nullptr;
// allow to use dpct::get_in_order_queue() for host malloc
dpct::err0 err = CHECK_TRY_ERROR(
ptr = (void*)sycl::malloc_host(size, dpct::get_in_order_queue()));
if (err != 0) {
// clear the error
fprintf(
stderr,
"WARNING: failed to allocate %.2f MB of pinned memory: %s\n",
size / 1024.0 / 1024.0,
"syclGetErrorString is not supported");
return nullptr;
}
return ptr;
} catch (sycl::exception const& exc) {
std::cerr << exc.what() << "Exception caught at file:" << __FILE__
<< ", line:" << __LINE__ << std::endl;
std::exit(1);
}
void ggml_sycl_host_free(void* ptr) try {
// allow to use dpct::get_in_order_queue() for host malloc
SYCL_CHECK(CHECK_TRY_ERROR(sycl::free(ptr, dpct::get_in_order_queue())));
} catch (sycl::exception const& exc) {
std::cerr << exc.what() << "Exception caught at file:" << __FILE__
<< ", line:" << __LINE__ << std::endl;
std::exit(1);
}