commit | a61ed1ab70389c62f6f699ca1a30a2421d3ea594 | [log] [tgz] |
---|---|---|
author | Marat Dukhan <maratek@google.com> | Tue Apr 14 14:33:30 2020 -0700 |
committer | Marat Dukhan <maratek@google.com> | Tue Apr 14 14:33:30 2020 -0700 |
tree | 878ae2bc4ef19eab2d68f5209de60ff8acc734d7 | |
parent | bfa3b9ce6cb71dc8b792e39d24717320a4f92572 [diff] |
Use load-acquire + store-release on synchronization variables Synchronization using relaxed atomics + fences instead of LA/SR violates C11/C++11 memory model and cause failures under thread sanitizer
pthreadpool is a portable and efficient thread pool implementation. It provides similar functionality to #pragma omp parallel for
, but with additional features.
The following example demonstates 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; }