ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-22 16:38:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

sycl: cleanup oneDNN related code (llama/12097)

Browse Source
This commit is contained in:
Svetlozar Georgiev
2025-03-21 02:15:56 +00:00
committed by Georgi Gerganov
parent 8058f19d0b
commit 5b854ebba5
4 changed files with 79 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
ggml/src/ggml-sycl/common.hpp
View File

@ -170,7 +170,6 @@ static size_t g_scratch_offset = 0;
int get_current_device_id();
inline dpct::err0 ggml_sycl_set_device(const int device) try {
int current_device_id;
SYCL_CHECK(CHECK_TRY_ERROR(current_device_id = get_current_device_id()));
@ -242,6 +241,14 @@ struct ggml_sycl_pool_alloc {
}
}
T * realloc(size_t size) {
GGML_ASSERT(pool != nullptr);
if (ptr)
pool->free(ptr, actual_size);
ptr = (T *) pool->alloc(size * sizeof(T), &this->actual_size);
return ptr;
}
// size is in number of elements
T * alloc(size_t size) {
GGML_ASSERT(pool != nullptr);
@ -371,10 +378,29 @@ struct ggml_backend_sycl_context {
dnnl::stream stream_dnnl() {
return stream_dnnl(device, 0);
}
dnnl::memory get_scratchpad_mem(const dnnl::memory::desc & scratchpad_md,
const dnnl::engine & eng, const queue_ptr q) {
ggml_sycl_pool_alloc<uint8_t> * pool;
auto it = scratchpad_map.find(q);
if (it == scratchpad_map.end()) {
scratchpad_map[q] = std::make_unique<ggml_sycl_pool_alloc<uint8_t>>(this->pool());
pool = scratchpad_map[q].get();
} else {
pool = it->second.get();
}
size_t scratchpad_size = scratchpad_md.get_size();
if (scratchpad_size > pool->actual_size) {
pool->realloc(scratchpad_size);
}
void * mem_ptr = pool->get();
return dnnl::memory(scratchpad_md, eng, mem_ptr);
}
#endif
// pool
std::unique_ptr<ggml_sycl_pool> pools[GGML_SYCL_MAX_DEVICES];
std::unordered_map<sycl::queue *, std::unique_ptr<ggml_sycl_pool_alloc<uint8_t>>> scratchpad_map;
std::unique_ptr<ggml_sycl_pool> host_pools[GGML_SYCL_MAX_DEVICES];