ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-23 14:32:23 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into metal-and-alloc

Browse Source
This commit is contained in:
Georgi Gerganov 2023-09-12 14:02:43 +03:00
commit de94c783ee
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
2 changed files with 15 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
ggml.c
View File

@ -17283,10 +17283,18 @@ static thread_ret_t ggml_graph_compute_thread(void * data) {
} else {
// wait for other threads to finish
const int last = node_n;
do {
//sched_yield();
while (true) {
// TODO: this sched_yield can have significant impact on the performance - either positive or negative
// depending on the workload and the operating system.
// since it is not clear what is the best approach, it should potentially become user-configurable
// ref: https://github.com/ggerganov/ggml/issues/291
#if defined(GGML_USE_ACCELERATE) || defined(GGML_USE_OPENBLAS)
sched_yield();
#endif
node_n = atomic_load(&state->shared->node_n);
} while (node_n == last);
if (node_n != last) break;
};
}
// check if we should stop

7
whisper.cpp
View File

@ -5332,7 +5332,8 @@ WHISPER_API const char * whisper_bench_ggml_mul_mat_str(int n_threads) {
// b: N*N*sizeof(float)
// c: N*N*sizeof(float)
// when F16 is used, there is an extra work buffer of size N*N*sizeof(float)
std::vector<char> buf(4llu*N_max*N_max*sizeof(float) + 4*512);
std::vector<uint8_t> buf(3llu*N_max*N_max*sizeof(float) + 3*ggml_tensor_overhead());
std::vector<uint8_t> work;
// put a bunch of random data in the buffer
for (size_t i = 0; i < buf.size(); i++) buf[i] = i;
@ -5387,12 +5388,12 @@ WHISPER_API const char * whisper_bench_ggml_mul_mat_str(int n_threads) {
double tsum = 0.0;
// heat-up
ggml_graph_compute_with_ctx(ctx0, &gf, n_threads);
ggml_graph_compute_helper(work, &gf, n_threads);
for (int i = 0; i < n_max; ++i) {
const int64_t t0 = ggml_time_us();
ggml_graph_compute_with_ctx(ctx0, &gf, n_threads);
ggml_graph_compute_helper(work, &gf, n_threads);
const int64_t t1 = ggml_time_us();