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

fix group_norm ut

Browse source
This commit is contained in:
luoyu-intel 2024-07-02 06:55:06 +00:00
parent f09b7cb609
commit c675aaf0b5
1 changed files with 6 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml/src/ggml-sycl/norm.cpp
View file

@ -57,6 +57,7 @@ static void group_norm_f32(const float* x, float* dst, const int group_size, con
const int nwarps = nthreads / WARP_SIZE;
assert(nwarps % WARP_SIZE == 0);
start += item_ct1.get_local_id(2);
int nreduce = nwarps / WARP_SIZE;
if (end >= ne_elements) {
end = ne_elements;
@ -87,7 +88,6 @@ static void group_norm_f32(const float* x, float* dst, const int group_size, con
*/
item_ct1.barrier();
tmp = 0.f;
int nreduce = nwarps / WARP_SIZE;
for (size_t i = 0; i < nreduce; i += 1)
{
tmp += s_sum[lane_id + i * WARP_SIZE];
@ -122,7 +122,11 @@ static void group_norm_f32(const float* x, float* dst, const int group_size, con
better performance if there is no access to global memory.
*/
item_ct1.barrier();
tmp = s_sum[lane_id];
tmp = 0.f;
for (size_t i = 0; i < nreduce; i += 1)
{
tmp += s_sum[lane_id + i * WARP_SIZE];
}
tmp = warp_reduce_sum(tmp, item_ct1);
}