ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

SYCL: Reduce most of the compiler warnings (#10748)

Browse source 
* Try to reduce some unused and typecast warnings

* Reduce compiler warnings step 2

* add a newline at the end of the file

* Initialize nreduce as size_t

* [SYCL] Remove pragma directives from mmq.cpp

* SYCL: mmq add condition to prevent blocks_per_tile_x_row variable from becoming 0

* SYCL softmax: Initialize nreduce as size_t

* ggml-sycl.cpp: fix some trailing whitespaces

* SYCL: remove the unused variables instead of commenting it out

* SYCL poo2d kernel: set NAN for invalid pooling op

* SYCL gemm.hpp: remove pragma directives

* SYCL gemm.hpp: use const cast to properly support dnnl::memory

* SYCL: wkv6 remove a comment

* SYCL: clean comments step 2

* SYCL: clean comments and variables step 3

* SYCL: Use GGML_UNUSED for unused variables

* SYCL: remove extra empty lines and a comment

* Remove TODO

* cleanup spaces

* add a stdout for unsupported op

* use sycl printf over fprintf

* remove prints for CI

* SYCL ggml-sycl: pool2D use sycl::nan and remove if-else block

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
This commit is contained in:
Akarshan Biswas 2024-12-13 12:12:15 +05:30 • committed by GitHub
parent d583cd03f6
commit 83ed24a97b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 205 additions and 187 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ggml/src/ggml-sycl/norm.cpp
View file

@ -31,7 +31,7 @@ static void norm_f32(const float* x, float* dst, const int ncols, const float ep
*/
item_ct1.barrier(sycl::access::fence_space::local_space);
mean_var = 0.f;
int nreduce = nwarps / WARP_SIZE;
size_t nreduce = nwarps / WARP_SIZE;
for (size_t i = 0; i < nreduce; i += 1)
{
mean_var += s_sum[lane_id + i * WARP_SIZE];
@ -55,7 +55,7 @@ static void group_norm_f32(const float* x, float* dst, const int group_size, con
const int nthreads = item_ct1.get_local_range(2);
const int nwarps = nthreads / WARP_SIZE;
start += item_ct1.get_local_id(2);
int nreduce = nwarps / WARP_SIZE;
size_t nreduce = nwarps / WARP_SIZE;
if (end >= ne_elements) {
end = ne_elements;
@ -163,7 +163,7 @@ static void rms_norm_f32(const float* x, float* dst, const int ncols, const floa
converged control flow. You may need to adjust the code.
*/
item_ct1.barrier(sycl::access::fence_space::local_space);
int nreduce = nwarps / WARP_SIZE;
size_t nreduce = nwarps / WARP_SIZE;
tmp = 0.f;
for (size_t i = 0; i < nreduce; i += 1)
{
@ -352,6 +352,7 @@ void ggml_sycl_op_group_norm(ggml_backend_sycl_context& ctx, const ggml_tensor*
(void)src1;
(void)dst;
(void)src1_dd;
GGML_UNUSED(ctx);
}
void ggml_sycl_op_rms_norm(ggml_backend_sycl_context& ctx, const ggml_tensor* src0,