Files
llama.cpp/ggml/src/ggml-sycl/convert.hpp
Neo Zhang Jianyu 08d5986290 [SYCL] Optimize mul_mat for Q4_0 on Intel GPU (#12035)
* opt performance by reorder for Intel GPU

* detect hw type and save opt feature, and print opt feature

* correct name

* support optimize graph once when compute graph, record the opt status in tensor->extra, make CI passed

* add env variable GGML_SYCL_DISABLE_OPT for debug

* use syclex::architecture replace the custom hw define, update the guide for GGML_SYCL_DISABLE_OPT

* add performance data

* mv getrows functions to separeted files

* fix global variables

---------

Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>
2025-02-24 22:33:23 +08:00

28 lines
818 B
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
//
#ifndef GGML_SYCL_CONVERT_HPP
#define GGML_SYCL_CONVERT_HPP
#include "common.hpp"
template <typename T>
using to_t_sycl_t = void (*)(const void *__restrict__ x, T *__restrict__ y,
int64_t k, dpct::queue_ptr stream);
typedef to_t_sycl_t<float> to_fp32_sycl_t;
typedef to_t_sycl_t<sycl::half> to_fp16_sycl_t;
to_fp16_sycl_t ggml_get_to_fp16_sycl(ggml_type type, ggml_tensor *dst);
to_fp32_sycl_t ggml_get_to_fp32_sycl(ggml_type type, ggml_tensor *dst);
#endif // GGML_SYCL_CONVERT_HPP