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

[SYCL] Fix WARP_SIZE=16 bug of Intel GPU (#8266)

Browse source 
* fix group_norm ut

* split softmax

* fix softmax

* add concat support condition

* revert debug code

* move QK_WARP_SIZE to presets.hpp
This commit is contained in:
luoyu-intel 2024-07-05 05:06:13 +00:00 • committed by GitHub
parent e235b267a2
commit a9554e20b6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 301 additions and 257 deletions
Download patch file Download diff file Expand all files Collapse all files

31
ggml/src/ggml-sycl/dmmv.cpp
View file

@ -3,6 +3,7 @@
#include "dequantize.hpp"
#include "presets.hpp"
static void convert_f16(const void * vx, const int ib, const int iqs, dfloat2 & v){
const sycl::half *x = (const sycl::half *)vx;
@ -227,7 +228,7 @@ static void dequantize_mul_mat_vec_q2_k(const void *__restrict__ vx,
// sum up partial sums and write back result
#pragma unroll
for (int mask = WARP_SIZE / 2; mask > 0; mask >>= 1) {
for (int mask = QK_WARP_SIZE / 2; mask > 0; mask >>= 1) {
tmp +=
dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask);
}
@ -346,7 +347,7 @@ static void dequantize_mul_mat_vec_q3_k(const void *__restrict__ vx,
// sum up partial sums and write back result
#pragma unroll
for (int mask = WARP_SIZE / 2; mask > 0; mask >>= 1) {
for (int mask = QK_WARP_SIZE / 2; mask > 0; mask >>= 1) {
tmp +=
dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask);
}
@ -499,7 +500,7 @@ static void dequantize_mul_mat_vec_q4_k(const void *__restrict__ vx,
// sum up partial sums and write back result
#pragma unroll
for (int mask = WARP_SIZE / 2; mask > 0; mask >>= 1) {
for (int mask = QK_WARP_SIZE / 2; mask > 0; mask >>= 1) {
tmp +=
dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask);
}
@ -633,7 +634,7 @@ static void dequantize_mul_mat_vec_q5_k(const void *__restrict__ vx,
// sum up partial sums and write back result
#pragma unroll
for (int mask = WARP_SIZE / 2; mask > 0; mask >>= 1) {
for (int mask = QK_WARP_SIZE / 2; mask > 0; mask >>= 1) {
tmp +=
dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask);
}
@ -748,7 +749,7 @@ static void dequantize_mul_mat_vec_q6_k(const void * __restrict__ vx, const floa
// sum up partial sums and write back result
#pragma unroll
for (int mask = WARP_SIZE / 2; mask > 0; mask >>= 1) {
for (int mask = QK_WARP_SIZE / 2; mask > 0; mask >>= 1) {
tmp +=
dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask);
}
@ -873,10 +874,10 @@ static void dequantize_mul_mat_vec_q2_K_sycl(const void *vx, const float *y,
const int ny = 2; // very slightly faster than 1 even when K_QUANTS_PER_ITERATION = 2
const int block_num_y = (nrows + ny - 1) / ny;
const sycl::range<3> block_nums(1, 1, block_num_y);
const sycl::range<3> block_dims(1, ny, WARP_SIZE);
const sycl::range<3> block_dims(1, ny, QK_WARP_SIZE);
stream->parallel_for(
sycl::nd_range<3>(block_nums * block_dims, block_dims),
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(WARP_SIZE)]] {
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(QK_WARP_SIZE)]] {
dequantize_mul_mat_vec_q2_k(vx, y, dst, ncols, nrows, item_ct1);
});
}
@ -889,10 +890,10 @@ static void dequantize_mul_mat_vec_q3_K_sycl(const void *vx, const float *y,
const int ny = 2 / K_QUANTS_PER_ITERATION;
const int block_num_y = (nrows + ny - 1) / ny;
const sycl::range<3> block_nums(1, 1, block_num_y);
const sycl::range<3> block_dims(1, ny, WARP_SIZE);
const sycl::range<3> block_dims(1, ny, QK_WARP_SIZE);
stream->parallel_for(
sycl::nd_range<3>(block_nums * block_dims, block_dims),
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(WARP_SIZE)]] {
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(QK_WARP_SIZE)]] {
dequantize_mul_mat_vec_q3_k(vx, y, dst, ncols, nrows, item_ct1);
});
}
@ -905,10 +906,10 @@ static void dequantize_mul_mat_vec_q4_K_sycl(const void *vx, const float *y,
const int ny = 2 / K_QUANTS_PER_ITERATION;
const int block_num_y = (nrows + ny - 1) / ny;
const sycl::range<3> block_nums(1, 1, block_num_y);
const sycl::range<3> block_dims(1, ny, WARP_SIZE);
const sycl::range<3> block_dims(1, ny, QK_WARP_SIZE);
stream->parallel_for(
sycl::nd_range<3>(block_nums * block_dims, block_dims),
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(WARP_SIZE)]] {
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(QK_WARP_SIZE)]] {
dequantize_mul_mat_vec_q4_k(vx, y, dst, ncols, nrows, item_ct1);
});
}
@ -918,10 +919,10 @@ static void dequantize_mul_mat_vec_q5_K_sycl(const void *vx, const float *y,
const int nrows,
dpct::queue_ptr stream) {
GGML_ASSERT(ncols % QK_K == 0);
const sycl::range<3> block_dims(1, 1, WARP_SIZE);
const sycl::range<3> block_dims(1, 1, QK_WARP_SIZE);
stream->parallel_for(
sycl::nd_range<3>(sycl::range<3>(1, 1, nrows) * block_dims, block_dims),
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(WARP_SIZE)]] {
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(QK_WARP_SIZE)]] {
dequantize_mul_mat_vec_q5_k(vx, y, dst, ncols, item_ct1);
});
}
@ -934,10 +935,10 @@ static void dequantize_mul_mat_vec_q6_K_sycl(const void *vx, const float *y,
const int ny = 2 / K_QUANTS_PER_ITERATION;
const int block_num_y = (nrows + ny - 1) / ny;
const sycl::range<3> block_nums(1, 1, block_num_y);
const sycl::range<3> block_dims(1, ny, WARP_SIZE);
const sycl::range<3> block_dims(1, ny, QK_WARP_SIZE);
stream->parallel_for(
sycl::nd_range<3>(block_nums * block_dims, block_dims),
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(WARP_SIZE)]] {
[=](sycl::nd_item<3> item_ct1) [[intel::reqd_sub_group_size(QK_WARP_SIZE)]] {
dequantize_mul_mat_vec_q6_k(vx, y, dst, ncols, nrows, item_ct1);
});
}