CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-13 10:57:15 +00:00
Code Issues Packages Projects Releases 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
17 changed files with 205 additions and 187 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
ggml/src/ggml-sycl/common.cpp
View File

@@ -11,6 +11,7 @@
//
#include "common.hpp"
#include "ggml-impl.h"
int get_current_device_id() {
return dpct::dev_mgr::instance().current_device_id();
@@ -28,11 +29,7 @@ void* ggml_sycl_host_malloc(size_t size) try {
if (err != 0) {
// clear the error
fprintf(
stderr,
"WARNING: failed to allocate %.2f MB of pinned memory: %s\n",
size / 1024.0 / 1024.0,
"syclGetErrorString is not supported");
GGML_LOG_ERROR("WARNING: failed to allocate %.2f MB of pinned memory: %s\n", size / 1024.0 / 1024.0, "syclGetErrorString is not supported");
return nullptr;
}
@@ -66,18 +63,12 @@ int64_t downsample_sycl_global_range(int64_t accumulate_block_num, int64_t block
void ggml_sycl_op_flatten(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
const ggml_tensor *src1, ggml_tensor *dst,
const ggml_sycl_op_flatten_t op) try {
const int64_t nrows0 = ggml_nrows(src0);
const bool use_src1 = src1 != nullptr;
const int64_t nrows1 = use_src1 ? ggml_nrows(src1) : 1;
GGML_ASSERT(!use_src1 || src1->backend != GGML_BACKEND_TYPE_GPU_SPLIT);
GGML_ASSERT( dst->backend != GGML_BACKEND_TYPE_GPU_SPLIT);
ggml_tensor_extra_gpu * src0_extra = (ggml_tensor_extra_gpu *) src0->extra;
ggml_tensor_extra_gpu * src1_extra = use_src1 ? (ggml_tensor_extra_gpu *) src1->extra : nullptr;
ggml_tensor_extra_gpu * dst_extra = (ggml_tensor_extra_gpu *) dst->extra;
// dd = data device
float * src0_ddf = (float *) src0->data;
float * src1_ddf = use_src1 ? (float *) src1->data : nullptr;