| commit | 09b5704840594f5776fa3cd4911f43c8261a5ec2 | [log] [tgz] |
|---|---|---|
| author | Pedro Gonnet <[email protected]> | Mon Sep 02 12:00:11 2024 |
| committer | XNNPACK Team <[email protected]> | Tue Jan 07 14:24:12 2025 |
| tree | 1a8f71e239023e1cdf733fd756e399f4d5425061 | |
| parent | 847fb990fada8bdbd184f5897424cc1969ec8f91 [diff] |
Use the new `pthreadpool_parallelize_1d_dynamic` strategy in the unary and binary ops, where appropriate. PiperOrigin-RevId: 670177277
pthreadpool is a portable and efficient thread pool implementation. It provides similar functionality to #pragma omp parallel for, but with additional features.
This is a Google-maintained fork of the original http://github.com/Maratyszcza/pthreadpool repository.
The following example demonstrates using the thread pool for parallel addition of two arrays:
static void add_arrays(struct array_addition_context* context, size_t i) { context->sum[i] = context->augend[i] + context->addend[i]; } #define ARRAY_SIZE 4 int main() { double augend[ARRAY_SIZE] = { 1.0, 2.0, 4.0, -5.0 }; double addend[ARRAY_SIZE] = { 0.25, -1.75, 0.0, 0.5 }; double sum[ARRAY_SIZE]; pthreadpool_t threadpool = pthreadpool_create(0); assert(threadpool != NULL); const size_t threads_count = pthreadpool_get_threads_count(threadpool); printf("Created thread pool with %zu threads\n", threads_count); struct array_addition_context context = { augend, addend, sum }; pthreadpool_parallelize_1d(threadpool, (pthreadpool_task_1d_t) add_arrays, (void*) &context, ARRAY_SIZE, PTHREADPOOL_FLAG_DISABLE_DENORMALS /* flags */); pthreadpool_destroy(threadpool); threadpool = NULL; printf("%8s\t%.2lf\t%.2lf\t%.2lf\t%.2lf\n", "Augend", augend[0], augend[1], augend[2], augend[3]); printf("%8s\t%.2lf\t%.2lf\t%.2lf\t%.2lf\n", "Addend", addend[0], addend[1], addend[2], addend[3]); printf("%8s\t%.2lf\t%.2lf\t%.2lf\t%.2lf\n", "Sum", sum[0], sum[1], sum[2], sum[3]); return 0; }