Skip to content

threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling #12995

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 31, 2025
Merged

threading: support for GGML_SCHED_PRIO_LOW, update thread info on Windows to avoid throttling #12995

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
199a838
threading: support for GGML_SCHED_PRIO_LOW, update thread info on Win…
max-krasnyansky Apr 17, 2025
9087dd2
threading: disable SetThreadInfo() calls for older Windows versions
max-krasnyansky Apr 17, 2025
ac35e50
Update tools/llama-bench/llama-bench.cpp
max-krasnyansky May 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1348,9 +1348,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
));
add_opt(common_arg(
{"--prio"}, "N",
string_format("set process/thread priority : 0-normal, 1-medium, 2-high, 3-realtime (default: %d)\n", params.cpuparams.priority),
string_format("set process/thread priority : low(-1), normal(0), medium(1), high(2), realtime(3) (default: %d)\n", params.cpuparams.priority),
[](common_params & params, int prio) {
if (prio < 0 || prio > 3) {
if (prio < GGML_SCHED_PRIO_LOW || prio > GGML_SCHED_PRIO_REALTIME) {
throw std::invalid_argument("invalid value");
}
params.cpuparams.priority = (enum ggml_sched_priority) prio;
Expand Down
2 changes: 2 additions & 0 deletions common/common.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -203,6 +203,7 @@ bool set_process_priority(enum ggml_sched_priority prio) {

DWORD p = NORMAL_PRIORITY_CLASS;
switch (prio) {
case GGML_SCHED_PRIO_LOW: p = BELOW_NORMAL_PRIORITY_CLASS; break;
case GGML_SCHED_PRIO_NORMAL: p = NORMAL_PRIORITY_CLASS; break;
case GGML_SCHED_PRIO_MEDIUM: p = ABOVE_NORMAL_PRIORITY_CLASS; break;
case GGML_SCHED_PRIO_HIGH: p = HIGH_PRIORITY_CLASS; break;
Expand All @@ -228,6 +229,7 @@ bool set_process_priority(enum ggml_sched_priority prio) {

int p = 0;
switch (prio) {
case GGML_SCHED_PRIO_LOW: p = 5; break;
case GGML_SCHED_PRIO_NORMAL: p = 0; break;
case GGML_SCHED_PRIO_MEDIUM: p = -5; break;
case GGML_SCHED_PRIO_HIGH: p = -10; break;
Expand Down
1 change: 1 addition & 0 deletions ggml/include/ggml.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2181,6 +2181,7 @@ extern "C" {

// scheduling priorities
enum ggml_sched_priority {
GGML_SCHED_PRIO_LOW = -1,
GGML_SCHED_PRIO_NORMAL,
GGML_SCHED_PRIO_MEDIUM,
GGML_SCHED_PRIO_HIGH,
Expand Down
23 changes: 23 additions & 0 deletions ggml/src/ggml-cpu/ggml-cpu.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2418,12 +2418,32 @@ static bool ggml_thread_apply_priority(int32_t prio) {
// This is up to the applications.
DWORD p = THREAD_PRIORITY_NORMAL;
switch (prio) {
case GGML_SCHED_PRIO_LOW: p = THREAD_PRIORITY_BELOW_NORMAL; break;
case GGML_SCHED_PRIO_NORMAL: p = THREAD_PRIORITY_NORMAL; break;
case GGML_SCHED_PRIO_MEDIUM: p = THREAD_PRIORITY_ABOVE_NORMAL; break;
case GGML_SCHED_PRIO_HIGH: p = THREAD_PRIORITY_HIGHEST; break;
case GGML_SCHED_PRIO_REALTIME: p = THREAD_PRIORITY_TIME_CRITICAL; break;
}

if (prio != GGML_SCHED_PRIO_LOW) {
// Tell Windows that this thread should not be throttled (needs its own CPU core).
// Newer Windows 11 versions aggresively park (offline) CPU cores and often place
// all our threads onto the first 4 cores which results in terrible performance with
// n_threads > 4
#if _WIN32_WINNT >= 0x0602
THREAD_POWER_THROTTLING_STATE t;
ZeroMemory(&t, sizeof(t));
t.Version = THREAD_POWER_THROTTLING_CURRENT_VERSION;
t.ControlMask = THREAD_POWER_THROTTLING_EXECUTION_SPEED;
t.StateMask = 0;

if (!SetThreadInformation(GetCurrentThread(), ThreadPowerThrottling, &t, sizeof(t))) {
GGML_LOG_DEBUG("failed to disable thread power throttling %d : (%d)\n", prio, (int) GetLastError());
return false;
}
#endif
}

if (prio == GGML_SCHED_PRIO_NORMAL) {
// Keep inherited policy/priority
return true;
Expand Down Expand Up @@ -2451,6 +2471,8 @@ static bool ggml_thread_apply_priority(int32_t prio) {
struct sched_param p;
int32_t policy = SCHED_OTHER;
switch (prio) {
// TODO: there seems to be no way to set lower prio on Apple platforms
case GGML_SCHED_PRIO_LOW: policy = SCHED_OTHER; p.sched_priority = 0; break;
case GGML_SCHED_PRIO_NORMAL: policy = SCHED_OTHER; p.sched_priority = 0; break;
case GGML_SCHED_PRIO_MEDIUM: policy = SCHED_FIFO; p.sched_priority = 40; break;
case GGML_SCHED_PRIO_HIGH: policy = SCHED_FIFO; p.sched_priority = 80; break;
Expand Down Expand Up @@ -2507,6 +2529,7 @@ static bool ggml_thread_apply_priority(int32_t prio) {
struct sched_param p;
int32_t policy = SCHED_OTHER;
switch (prio) {
case GGML_SCHED_PRIO_LOW: policy = SCHED_BATCH; p.sched_priority = 0; break;
case GGML_SCHED_PRIO_NORMAL: policy = SCHED_OTHER; p.sched_priority = 0; break;
case GGML_SCHED_PRIO_MEDIUM: policy = SCHED_FIFO; p.sched_priority = 40; break;
case GGML_SCHED_PRIO_HIGH: policy = SCHED_FIFO; p.sched_priority = 80; break;
Expand Down
2 changes: 1 addition & 1 deletion tools/llama-bench/llama-bench.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -315,7 +315,7 @@ static void print_usage(int /* argc */, char ** argv) {
printf(" --numa <distribute|isolate|numactl> numa mode (default: disabled)\n");
printf(" -r, --repetitions <n> number of times to repeat each test (default: %d)\n",
cmd_params_defaults.reps);
printf(" --prio <0|1|2|3> process/thread priority (default: %d)\n",
printf(" --prio <-1,0|1|2|3> process/thread priority (default: %d)\n",
cmd_params_defaults.prio);
printf(" --delay <0...N> (seconds) delay between each test (default: %d)\n",
cmd_params_defaults.delay);
Expand Down
Loading