## News
+- 2026.04
+
+ - Optimize mul_mat by reorder feature for data type: Q4_K, Q5_K, Q_K, Q8_0.
+ - Fused MoE.
+ - Upgrate CI and built package for oneAPI 2025.3.3, support Ubuntu 24.04 built package.
+
- 2026.03
- Support Flash-Attention: less memory usage, performance impact depends on LLM.
./examples/sycl/test.sh
```
+- Run llama-server:
+
+```sh
+./examples/sycl/start-svr.sh -m PATH/MODEL_FILE
+```
+
2. Command line
Launch inference
1. Script
+- Run test:
+
```
examples\sycl\win-test.bat
```
+- Run llama-server:
+
+```
+examples\sycl\win-start-svr.bat -m PATH\MODEL_FILE
+```
+
2. Command line
Launch inference
--- /dev/null
+#!/bin/bash
+
+# MIT license
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: MIT
+
+Help() {
+ cat << EOF
+Usage: $(basename "$0") [OPTIONS]
+
+This script processes files with specified options.
+
+Options:
+ -h, --help Display this help message and exit.
+ -c, --context <value> Set context length. Bigger need more memory.
+ -p, --promote <value> Prompt to start generation with.
+ -m, --model <value> Full model file path.
+ -mg,--main-gpu <value> Set main GPU ID (0 - n) for single GPU mode.
+ -sm,--split-mode <value> How to split the model across multiple GPUs, one of:
+ - none: use one GPU only
+ - layer (default): split layers and KV across GPUs
+ - row: split rows across GPUs
+ -ngl,--n-gpu-layers <value> Max. number of layers to store in VRAM (default: -1)
+ -lv,--log-verbosity <value> Set the verbosity threshold. Messages with a higher verbosity will be
+ ignored. Values:
+ - 0: generic output
+ - 1: error
+ - 2: warning
+ - 3: info
+ - 4: debug
+
+
+EOF
+}
+
+BIN_FILE=./build/bin/llama-server
+SEED=0
+GPUS_SETTING=""
+
+MODEL_FILE=../models/Qwen3.5-4B-Q4_0.gguf
+NGL=99
+CONTEXT=4096
+GGML_SYCL_DEVICE=-1
+SPLIT_MODE=layer
+LOG_VERBOSE=3
+while [[ $# -gt 0 ]]; do
+ case "$1" in
+ -c|--context)
+ CONTEXT=$2
+ # Shift twice to consume both the option flag and its value
+ shift
+ shift
+ ;;
+ -m|--model)
+ MODEL_FILE="$2"
+ # Shift twice to consume both the option flag and its value
+ shift
+ shift
+ ;;
+ -mg|--main-gpu)
+ GGML_SYCL_DEVICE=$2
+ SPLIT_MODE=none
+ # Shift twice to consume both the option flag and its value
+ shift
+ shift
+ ;;
+ -sm|--split-mode)
+ SPLIT_MODE=$2
+ # Shift twice to consume both the option flag and its value
+ shift
+ shift
+ ;;
+ -ngl|--n-gpu-layers)
+ NGL=$2
+ # Shift twice to consume both the option flag and its value
+ shift
+ shift
+ ;;
+ -lv|--log-verbosity)
+ LOG_VERBOSE=$2
+ # Shift twice to consume both the option flag and its value
+ shift
+ shift
+ ;;
+ -h|--help)
+ Help
+ exit 0
+ ;;
+ *)
+ # Handle unknown options or stop processing options
+ echo "Invalid option: $1"
+ # Optional: exit script or shift to treat remaining as positional args
+ exit 1
+ ;;
+ esac
+done
+
+
+
+source /opt/intel/oneapi/setvars.sh
+
+#export GGML_SYCL_DEBUG=1
+
+#ZES_ENABLE_SYSMAN=1, Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory. Recommended to use when --split-mode = layer.
+
+#support malloc device memory more than 4GB.
+export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
+echo "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=${UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS}"
+
+if [ $GGML_SYCL_DEVICE -ne -1 ]; then
+ echo "Use $GGML_SYCL_DEVICE as main GPU"
+ #use signle GPU only
+ GPUS_SETTING="-mg $GGML_SYCL_DEVICE -sm ${SPLIT_MODE}"
+ export ONEAPI_DEVICE_SELECTOR="level_zero:${$GGML_SYCL_DEVICE}"
+ echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
+else
+ echo "Use all Intel GPUs, including iGPU & dGPU"
+ GPUS_SETTING="-sm ${SPLIT_MODE}"
+ fi
+
+echo "run cmd: ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 200 -e -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap "
+ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap --host 0.0.0.0 --port 8000
+
+
GPUS_SETTING=""
INPUT_PROMPT="Building a website can be done in 10 simple steps:\nStep 1:"
-MODEL_FILE=models/llama-2-7b.Q4_0.gguf
+MODEL_FILE=../models/llama-2-7b.Q4_0.gguf
NGL=99
CONTEXT=4096
GGML_SYCL_DEVICE=-1
export ONEAPI_DEVICE_SELECTOR="level_zero:${$GGML_SYCL_DEVICE}"
echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
else
- echo "Use all Intel GPUs, including iGPU & dGPU"
+ echo "Use all Intel GPUs, including iGPU & dGPU"
+ GPUS_SETTING="-sm ${SPLIT_MODE}"
fi
-echo "run cmd: ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap "
-ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap
+echo "run cmd: ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 200 -e -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap "
+ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 200 -e -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap
--- /dev/null
+:: MIT license
+:: Copyright (C) 2024 Intel Corporation
+:: SPDX-License-Identifier: MIT
+
+@echo off
+setlocal EnableExtensions EnableDelayedExpansion
+
+set "BIN_FILE=.\build\bin\llama-server.exe"
+set "SEED=0"
+set "GPUS_SETTING="
+
+set "MODEL_FILE=..\models\Qwen3.5-4B-Q4_0.gguf"
+set "NGL=99"
+set "CONTEXT=4096"
+set "GGML_SYCL_DEVICE=-1"
+set "SPLIT_MODE=layer"
+set "LOG_VERBOSE=3"
+
+if "%~1"=="" goto after_args
+
+:parse_args
+if "%~1"=="" goto after_args
+
+if /I "%~1"=="-c" (
+ if "%~2"=="" goto missing_value
+ set "CONTEXT=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--context" (
+ if "%~2"=="" goto missing_value
+ set "CONTEXT=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-m" (
+ if "%~2"=="" goto missing_value
+ set "MODEL_FILE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--model" (
+ if "%~2"=="" goto missing_value
+ set "MODEL_FILE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-mg" (
+ if "%~2"=="" goto missing_value
+ set "GGML_SYCL_DEVICE=%~2"
+ set "SPLIT_MODE=none"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--main-gpu" (
+ if "%~2"=="" goto missing_value
+ set "GGML_SYCL_DEVICE=%~2"
+ set "SPLIT_MODE=none"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-sm" (
+ if "%~2"=="" goto missing_value
+ set "SPLIT_MODE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--split-mode" (
+ if "%~2"=="" goto missing_value
+ set "SPLIT_MODE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-ngl" (
+ if "%~2"=="" goto missing_value
+ set "NGL=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--n-gpu-layers" (
+ if "%~2"=="" goto missing_value
+ set "NGL=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-lv" (
+ if "%~2"=="" goto missing_value
+ set "LOG_VERBOSE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--log-verbosity" (
+ if "%~2"=="" goto missing_value
+ set "LOG_VERBOSE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-h" goto help
+if /I "%~1"=="--help" goto help
+
+echo Invalid option: %~1
+exit /b 1
+
+:missing_value
+echo Missing value for option: %~1
+exit /b 1
+
+:help
+echo Usage: %~n0 [OPTIONS]
+echo.
+echo This script processes files with specified options.
+echo.
+echo Options:
+echo -h, --help Display this help message and exit.
+echo -c, --context ^<value^> Set context length. Bigger need more memory.
+echo -m, --model ^<value^> Full model file path.
+echo -mg,--main-gpu ^<value^> Set main GPU ID (0 - n) for single GPU mode.
+echo -sm,--split-mode ^<value^> How to split the model across multiple GPUs, one of:
+echo - none: use one GPU only
+echo - layer (default): split layers and KV across GPUs
+echo - row: split rows across GPUs
+echo -ngl,--n-gpu-layers ^<value^> Max. number of layers to store in VRAM (default: -1)
+echo -lv,--log-verbosity ^<value^> Set the verbosity threshold. Messages with a higher verbosity will be
+echo ignored. Values:
+echo - 0: generic output
+echo - 1: error
+echo - 2: warning
+echo - 3: info
+echo - 4: debug
+exit /b 0
+
+:after_args
+
+REM In Windows CMD, source is not available; call oneAPI setvars if present.
+if exist "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" (
+ call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" >nul
+) else (
+ echo Warning: oneAPI setvars.bat not found. Continuing without environment setup.
+)
+
+REM Support malloc device memory more than 4GB.
+set "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1"
+echo UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=%UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS%
+
+if not "%GGML_SYCL_DEVICE%"=="-1" (
+ echo Use %GGML_SYCL_DEVICE% as main GPU
+ REM Use single GPU only.
+ set "GPUS_SETTING=-mg %GGML_SYCL_DEVICE% -sm %SPLIT_MODE%"
+ set "ONEAPI_DEVICE_SELECTOR=level_zero:%GGML_SYCL_DEVICE%"
+ echo ONEAPI_DEVICE_SELECTOR=%ONEAPI_DEVICE_SELECTOR%
+) else (
+ echo Use all Intel GPUs, including iGPU ^& dGPU
+ set "GPUS_SETTING=-sm %SPLIT_MODE%"
+)
+
+echo run cmd: ZES_ENABLE_SYSMAN=1 %BIN_FILE% -m "%MODEL_FILE%" -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --mmap --host 0.0.0.0 --port 8000
+set "ZES_ENABLE_SYSMAN=1"
+%BIN_FILE% -m "%MODEL_FILE%" -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --mmap --host 0.0.0.0 --port 8000
+
+endlocal
+
:: Copyright (C) 2024 Intel Corporation
:: SPDX-License-Identifier: MIT
-set INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
-@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
-:: support malloc device memory more than 4GB.
-set UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
-set LOAD_MODE="--mmap"
-.\build\bin\llama-completion.exe -m models\llama-2-7b.Q4_0.gguf -no-cnv -p %INPUT2% -n 400 -e -ngl 99 -s 0 %LOAD_MODE%
+@echo off
+setlocal EnableExtensions EnableDelayedExpansion
+
+REM MIT license
+REM Copyright (C) 2024 Intel Corporation
+REM SPDX-License-Identifier: MIT
+
+set "BIN_FILE=.\build\bin\llama-completion.exe"
+set "SEED=0"
+set "GPUS_SETTING="
+
+set "INPUT_PROMPT=Building a website can be done in 10 simple steps:^nStep 1:"
+set "MODEL_FILE=..\models\llama-2-7b.Q4_0.gguf"
+set "NGL=99"
+set "CONTEXT=4096"
+set "GGML_SYCL_DEVICE=-1"
+set "SPLIT_MODE=layer"
+set "LOG_VERBOSE=3"
+
+if "%~1"=="" goto after_args
+
+:parse_args
+if "%~1"=="" goto after_args
+
+if /I "%~1"=="-c" (
+ if "%~2"=="" goto missing_value
+ set "CONTEXT=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--context" (
+ if "%~2"=="" goto missing_value
+ set "CONTEXT=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-p" (
+ if "%~2"=="" goto missing_value
+ set "INPUT_PROMPT=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--promote" (
+ if "%~2"=="" goto missing_value
+ set "INPUT_PROMPT=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-m" (
+ if "%~2"=="" goto missing_value
+ set "MODEL_FILE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--model" (
+ if "%~2"=="" goto missing_value
+ set "MODEL_FILE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-mg" (
+ if "%~2"=="" goto missing_value
+ set "GGML_SYCL_DEVICE=%~2"
+ set "SPLIT_MODE=none"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--main-gpu" (
+ if "%~2"=="" goto missing_value
+ set "GGML_SYCL_DEVICE=%~2"
+ set "SPLIT_MODE=none"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-sm" (
+ if "%~2"=="" goto missing_value
+ set "SPLIT_MODE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--split-mode" (
+ if "%~2"=="" goto missing_value
+ set "SPLIT_MODE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-ngl" (
+ if "%~2"=="" goto missing_value
+ set "NGL=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--n-gpu-layers" (
+ if "%~2"=="" goto missing_value
+ set "NGL=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-lv" (
+ if "%~2"=="" goto missing_value
+ set "LOG_VERBOSE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+if /I "%~1"=="--log-verbosity" (
+ if "%~2"=="" goto missing_value
+ set "LOG_VERBOSE=%~2"
+ shift
+ shift
+ goto parse_args
+)
+
+if /I "%~1"=="-h" goto help
+if /I "%~1"=="--help" goto help
+
+echo Invalid option: %~1
+exit /b 1
+
+:missing_value
+echo Missing value for option: %~1
+exit /b 1
+
+:help
+echo Usage: %~n0 [OPTIONS]
+echo.
+echo This script processes files with specified options.
+echo.
+echo Options:
+echo -h, --help Display this help message and exit.
+echo -c, --context ^<value^> Set context length. Bigger need more memory.
+echo -p, --promote ^<value^> Prompt to start generation with.
+echo -m, --model ^<value^> Full model file path.
+echo -mg,--main-gpu ^<value^> Set main GPU ID (0 - n) for single GPU mode.
+echo -sm,--split-mode ^<value^> How to split the model across multiple GPUs, one of:
+echo - none: use one GPU only
+echo - layer (default): split layers and KV across GPUs
+echo - row: split rows across GPUs
+echo -ngl,--n-gpu-layers ^<value^> Max. number of layers to store in VRAM (default: -1)
+echo -lv,--log-verbosity ^<value^> Set the verbosity threshold. Messages with a higher verbosity will be
+echo ignored. Values:
+echo - 0: generic output
+echo - 1: error
+echo - 2: warning
+echo - 3: info
+echo - 4: debug
+exit /b 0
+
+:after_args
+
+REM In Windows CMD, source is not available; call oneAPI setvars if present.
+if exist "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" (
+ call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" >nul
+) else (
+ echo Warning: oneAPI setvars.bat not found. Continuing without environment setup.
+)
+
+REM Support malloc device memory more than 4GB.
+set "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1"
+echo UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=%UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS%
+
+if not "%GGML_SYCL_DEVICE%"=="-1" (
+ echo Use %GGML_SYCL_DEVICE% as main GPU
+ REM Use single GPU only.
+ set "GPUS_SETTING=-mg %GGML_SYCL_DEVICE% -sm %SPLIT_MODE%"
+ set "ONEAPI_DEVICE_SELECTOR=level_zero:%GGML_SYCL_DEVICE%"
+ echo ONEAPI_DEVICE_SELECTOR=%ONEAPI_DEVICE_SELECTOR%
+) else (
+ echo Use all Intel GPUs, including iGPU ^& dGPU
+ set "GPUS_SETTING=-sm %SPLIT_MODE%"
+)
+
+echo run cmd: ZES_ENABLE_SYSMAN=1 %BIN_FILE% -m %MODEL_FILE% -no-cnv -p "%INPUT_PROMPT%" -n 200 -e -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --mmap
+set "ZES_ENABLE_SYSMAN=1"
+%BIN_FILE% -m "%MODEL_FILE%" -no-cnv -p "%INPUT_PROMPT%" -n 200 -e -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --mmap
+
+endlocal
+
// cudaOccupancyMaxActiveBlocksPerMultiprocessor
bool vmm; // virtual memory support
size_t total_vram;
- //sycl_hw_info hw_info; \\ device id and aarch, currently not used
+ sycl_hw_info hw_info;
optimize_feature opt_feature;
};
info.max_work_group_sizes[i] = prop.get_max_work_group_size();
info.devices[i].max_wg_per_cu = info.max_work_group_sizes[i] / prop.get_max_compute_units();
+ info.devices[i].hw_info = get_device_hw_info(&device);
}
// Dispatch becomes obscure with the reorder, MMVQ when the reorder optimization
// is enabled takes precedence over DMMV, the current if-else implementation
// requires disabling DMMV if both conditions are met
+
if (!g_ggml_sycl_prioritize_dmmv && ((should_reorder_tensor(ctx, dst) &&
ggml_sycl_supports_reorder_mmvq(src0->type)))) {
- use_dequantize_mul_mat_vec = use_dequantize_mul_mat_vec && !use_mul_mat_vec_q;
+ // Arc770 get benefit with Q4_0 by skipping it.
+ if (!(ggml_sycl_info().devices[ctx.device].hw_info.arch ==
+ gpu_arch::intel_gpu_acm_g10 &&
+ src0->type == GGML_TYPE_Q4_0)) {
+ use_dequantize_mul_mat_vec =
+ use_dequantize_mul_mat_vec && !use_mul_mat_vec_q;
+ }
}
if (!split && src0->type == GGML_TYPE_F16 && ggml_is_permuted(src0) && ggml_is_permuted(src1) && src1->ne[1] == 1) {
#include "sycl_hw.hpp"
-// TODO: currently not used
-/*
-sycl_hw_info get_device_hw_info(sycl::device *device_ptr) {
- sycl_hw_info res;
- int32_t id = device_ptr->get_info<sycl::ext::intel::info::device::device_id>();
- res.device_id = id;
+using namespace std;
- syclex::architecture arch = device_ptr->get_info<syclex::info::device::architecture>();
- res.arch = arch;
+/*defined in
+* /opt/intel/oneapi/compiler/latest/include/sycl/ext/oneapi/experimental/device_architecture.def
+*/
+static map<gpu_arch, std::pair<const char*, sycl_intel_gpu_family>> arch2name = {
+ {gpu_arch::intel_gpu_bdw, {"intel_gpu_bdw", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_skl, {"intel_gpu_skl", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_kbl, {"intel_gpu_kbl", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_cfl, {"intel_gpu_cfl", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_apl, {"intel_gpu_apl", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_glk, {"intel_gpu_glk", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_whl, {"intel_gpu_whl", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_aml, {"intel_gpu_aml", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_cml, {"intel_gpu_cml", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_icllp, {"intel_gpu_icllp", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_ehl, {"intel_gpu_ehl", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_tgllp, {"intel_gpu_tgllp", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_rkl, {"intel_gpu_rkl", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_adl_s, {"intel_gpu_adl_s", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_adl_p, {"intel_gpu_adl_p", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_adl_n, {"intel_gpu_adl_n", GPU_FAMILY_IGPU_NON_XE}},
+ {gpu_arch::intel_gpu_dg1, {"intel_gpu_dg1", GPU_FAMILY_DGPU_CLIENT_GAME}},
+ {gpu_arch::intel_gpu_acm_g10, {"intel_gpu_acm_g10", GPU_FAMILY_DGPU_CLIENT_GAME}},
+ {gpu_arch::intel_gpu_acm_g11, {"intel_gpu_acm_g11", GPU_FAMILY_DGPU_CLIENT_GAME}},
+ {gpu_arch::intel_gpu_acm_g12, {"intel_gpu_acm_g12", GPU_FAMILY_DGPU_CLIENT_GAME}},
+ {gpu_arch::intel_gpu_pvc, {"intel_gpu_pvc", GPU_FAMILY_DGPU_CLOUD}},
+ {gpu_arch::intel_gpu_pvc_vg, {"intel_gpu_pvc_vg", GPU_FAMILY_DGPU_CLOUD}},
+ {gpu_arch::intel_gpu_mtl_u, {"intel_gpu_mtl_u", GPU_FAMILY_IGPU_XE}},
+ {gpu_arch::intel_gpu_mtl_h, {"intel_gpu_mtl_h", GPU_FAMILY_IGPU_XE}},
+ {gpu_arch::intel_gpu_arl_h, {"intel_gpu_arl_h", GPU_FAMILY_IGPU_XE}},
+ {gpu_arch::intel_gpu_bmg_g21, {"intel_gpu_bmg_g21", GPU_FAMILY_DGPU_CLIENT_GAME}},
+ {gpu_arch::intel_gpu_bmg_g31, {"intel_gpu_bmg_g31", GPU_FAMILY_DGPU_CLIENT_GAME}},
+ {gpu_arch::intel_gpu_lnl_m, {"intel_gpu_lnl_m", GPU_FAMILY_IGPU_XE}},
+ {gpu_arch::intel_gpu_ptl_h, {"intel_gpu_ptl_h", GPU_FAMILY_IGPU_XE}},
+ {gpu_arch::intel_gpu_ptl_u, {"intel_gpu_ptl_u", GPU_FAMILY_IGPU_XE}},
+ {gpu_arch::intel_gpu_wcl, {"intel_gpu_wcl", GPU_FAMILY_IGPU_XE}}
+};
+
+
+sycl_hw_info get_device_hw_info(sycl::device* device_ptr) {
+ sycl_hw_info res;
+ int32_t id =
+ device_ptr->get_info<sycl::ext::intel::info::device::device_id>();
+ res.device_id = id;
+
+ res.name = device_ptr->get_info<sycl::info::device::name>();
- return res;
+ syclex::architecture arch =
+ device_ptr->get_info<syclex::info::device::architecture>();
+ res.arch = arch;
+
+ map<syclex::architecture,
+ std::pair<const char*, sycl_intel_gpu_family>>::iterator it =
+ arch2name.find(res.arch);
+ if (it != arch2name.end()) {
+ res.arch_name = it->second.first;
+ res.gpu_family = it->second.second;
+ } else {
+ res.arch_name = "unknown";
+ res.gpu_family = GPU_FAMILY_UKNOWN;
+ }
+
+ return res;
}
-*/
#include <sycl/sycl.hpp>
namespace syclex = sycl::ext::oneapi::experimental;
+using gpu_arch = sycl::ext::oneapi::experimental::architecture;
+
+// It's used to mark the GPU computing capacity
+// The value must flow the order of performance.
+enum sycl_intel_gpu_family {
+ GPU_FAMILY_UKNOWN = -1,
+ // iGPU without Xe core, before Meteor Lake iGPU(Xe)
+ GPU_FAMILY_IGPU_NON_XE = 0,
+ // iGPU with Xe core, Meteor Lake iGPU or newer.
+ GPU_FAMILY_IGPU_XE = 1,
+ // dGPU for gaming in client/data center (DG1/FLex 140 or newer).
+ GPU_FAMILY_DGPU_CLIENT_GAME = 2,
+ // dGPU for AI in cloud, PVC or newer.
+ GPU_FAMILY_DGPU_CLOUD = 3
+};
-// TODO: currently not used
-/*
struct sycl_hw_info {
syclex::architecture arch;
+ const char* arch_name;
int32_t device_id;
+ std::string name;
+ sycl_intel_gpu_family gpu_family;
};
-bool is_in_vector(std::vector<int> &vec, int item);
-
sycl_hw_info get_device_hw_info(sycl::device *device_ptr);
-*/
-
#endif // SYCL_HW_HPP
overview / pkg / ggml / sources / llama.cpp / commitdiff