vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

rm get_work_group_size() by local cache for performance (#8286)

Browse source 
Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>
This commit is contained in:
Neo Zhang Jianyu 2024-07-05 10:32:29 +08:00 • committed by GitHub
parent a38b884c6c
commit f09b7cb609
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 17 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

15
ggml/src/ggml-sycl/common.hpp
View file

@ -47,10 +47,6 @@ static int g_ggml_sycl_debug = 0;
} \
}()
// #define DEBUG_SYCL_MALLOC
static int g_work_group_size = 0;
// typedef sycl::half ggml_fp16_t;
#define __SYCL_ARCH__ DPCT_COMPATIBILITY_TEMP
#define VER_4VEC 610 // todo for hardward optimize.
@ -193,6 +189,8 @@ struct ggml_sycl_device_info {
sycl_device_info devices[GGML_SYCL_MAX_DEVICES] = {};
std::array<float, GGML_SYCL_MAX_DEVICES> default_tensor_split = {};
int max_work_group_sizes[GGML_SYCL_MAX_DEVICES] = {0};
};
const ggml_sycl_device_info & ggml_sycl_info();
@ -295,15 +293,6 @@ struct ggml_backend_sycl_context {
}
};
// common host functions
static inline int get_work_group_size(const sycl::device& device) {
dpct::device_info prop;
dpct::get_device_info(prop, device);
return prop.get_max_work_group_size();
}
// common device functions
static __dpct_inline__ float warp_reduce_sum(float x,

18
ggml/src/ggml-sycl/norm.cpp
View file

@ -181,7 +181,7 @@ static void rms_norm_f32(const float* x, float* dst, const int ncols, const floa
static void norm_f32_sycl(const float* x, float* dst, const int ncols,
const int nrows, const float eps,
queue_ptr stream) {
queue_ptr stream, int device) {
GGML_ASSERT(ncols % WARP_SIZE == 0);
if (ncols < 1024) {
const sycl::range<3> block_dims(1, 1, WARP_SIZE);
@ -197,7 +197,7 @@ static void norm_f32_sycl(const float* x, float* dst, const int ncols,
});
}
else {
const int work_group_size = get_work_group_size(stream->get_device());
const int work_group_size = ggml_sycl_info().max_work_group_sizes[device];
const sycl::range<3> block_dims(1, 1, work_group_size);
/*
DPCT1049:17: The work-group size passed to the SYCL kernel may exceed
@ -222,7 +222,7 @@ static void norm_f32_sycl(const float* x, float* dst, const int ncols,
static void group_norm_f32_sycl(const float* x, float* dst,
const int num_groups, const int group_size,
const int ne_elements, queue_ptr stream) {
const int ne_elements, queue_ptr stream, int device) {
static const float eps = 1e-6f;
if (group_size < 1024) {
const sycl::range<3> block_dims(1, 1, WARP_SIZE);
@ -240,7 +240,7 @@ static void group_norm_f32_sycl(const float* x, float* dst,
});
}
else {
const int work_group_size = get_work_group_size(stream->get_device());
const int work_group_size = ggml_sycl_info().max_work_group_sizes[device];
const sycl::range<3> block_dims(1, 1, work_group_size);
/*
DPCT1049:18: The work-group size passed to the SYCL kernel may exceed
@ -269,7 +269,7 @@ static void group_norm_f32_sycl(const float* x, float* dst,
static void rms_norm_f32_sycl(const float* x, float* dst, const int ncols,
const int nrows, const float eps,
queue_ptr stream) {
queue_ptr stream, int device) {
GGML_ASSERT(ncols % WARP_SIZE == 0);
// printf("%s ncols=%d, nrows=%d, WARP_SIZE=%d\n", __func__, ncols, nrows, WARP_SIZE);
if (ncols < 1024) {
@ -286,7 +286,7 @@ static void rms_norm_f32_sycl(const float* x, float* dst, const int ncols,
});
}
else {
const int work_group_size = get_work_group_size(stream->get_device());
const int work_group_size = ggml_sycl_info().max_work_group_sizes[device];
const sycl::range<3> block_dims(1, 1, work_group_size);
/*
DPCT1049:19: The work-group size passed to the SYCL kernel may exceed
@ -322,7 +322,7 @@ void ggml_sycl_op_norm(ggml_backend_sycl_context& ctx, const ggml_tensor* src0,
float eps;
memcpy(&eps, dst->op_params, sizeof(float));
norm_f32_sycl(src0_dd, dst_dd, ne00, nrows, eps, main_stream);
norm_f32_sycl(src0_dd, dst_dd, ne00, nrows, eps, main_stream, ctx.device);
(void)src1;
(void)dst;
@ -340,7 +340,7 @@ void ggml_sycl_op_group_norm(ggml_backend_sycl_context& ctx, const ggml_tensor*
int num_groups = dst->op_params[0];
int group_size = src0->ne[0] * src0->ne[1] * ((src0->ne[2] + num_groups - 1) / num_groups);
group_norm_f32_sycl(src0_dd, dst_dd, num_groups, group_size, src0->ne[0] * src0->ne[1] * src0->ne[2], main_stream);
group_norm_f32_sycl(src0_dd, dst_dd, num_groups, group_size, src0->ne[0] * src0->ne[1] * src0->ne[2], main_stream, ctx.device);
(void)src1;
(void)dst;
@ -362,7 +362,7 @@ void ggml_sycl_op_rms_norm(ggml_backend_sycl_context& ctx, const ggml_tensor* sr
float eps;
memcpy(&eps, dst->op_params, sizeof(float));
rms_norm_f32_sycl(src0_dd, dst_dd, ne00, nrows, eps, main_stream);
rms_norm_f32_sycl(src0_dd, dst_dd, ne00, nrows, eps, main_stream, ctx.device);
(void)src1;
(void)dst;