From: Marek Olšák <marek.ol...@amd.com>
---
src/gallium/auxiliary/util/u_helpers.c | 37 +++++++++++++++++++++++---
1 file changed, 33 insertions(+), 4 deletions(-)
diff --git a/src/gallium/auxiliary/util/u_helpers.c
b/src/gallium/auxiliary/util/u_helpers.c
index 14367e5a118..3194c2e4e7a 100644
--- a/src/gallium/auxiliary/util/u_helpers.c
+++ b/src/gallium/auxiliary/util/u_helpers.c
@@ -114,57 +114,86 @@ util_upload_index_buffer(struct pipe_context *pipe,
u_upload_data(pipe->stream_uploader, start_offset,
info->count * info->index_size, 4,
(char*)info->index.user + start_offset,
out_offset, out_buffer);
u_upload_unmap(pipe->stream_uploader);
*out_offset -= start_offset;
return *out_buffer != NULL;
}
+#ifdef HAVE_PTHREAD_SETAFFINITY
+
static unsigned L3_cache_number;
-static once_flag init_cache_number_flag = ONCE_FLAG_INIT;
+static once_flag thread_pinning_once_flag = ONCE_FLAG_INIT;
+
+static void
+util_set_full_cpu_affinity(void)
+{
+ cpu_set_t cpuset;
+
+ CPU_ZERO(&cpuset);
+ for (unsigned i = 0; i < CPU_SETSIZE; i++)
+ CPU_SET(i, &cpuset);
+
+ pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+}
static void
-util_init_cache_number(void)
+util_init_thread_pinning(void)
{
/* Get a semi-random number. */
int64_t t = os_time_get_nano();
L3_cache_number = (t ^ (t >> 8) ^ (t >> 16));
+
+ /* Reset thread affinity for all children of fork and exec to prevent
+ * spawned processes and threads from inheriting the current thread's
+ * affinity.
+ *
+ * What happens if a driver is unloaded and the app creates a thread?
+ */
+ pthread_atfork(NULL, NULL, util_set_full_cpu_affinity);
}
+#endif
+
/**
* Called by MakeCurrent. Used to notify the driver that the application
* thread may have been changed.
*
* The function pins the current thread and driver threads to a group of
* CPU cores that share the same L3 cache. This is needed for good multi-
* threading performance on AMD Zen CPUs.
*
* \param upper_thread thread in the state tracker that also needs to be
* pinned.
*/
void
util_context_thread_changed(struct pipe_context *ctx, thrd_t *upper_thread)
{
-#ifdef HAVE_PTHREAD
+#ifdef HAVE_PTHREAD_SETAFFINITY
+ /* If pinning has no effect, don't do anything. */
+ if (util_cpu_caps.nr_cpus == util_cpu_caps.cores_per_L3)
+ return;
+
thrd_t current = thrd_current();
int cache = util_get_L3_for_pinned_thread(current,
util_cpu_caps.cores_per_L3);
+ call_once(&thread_pinning_once_flag, util_init_thread_pinning);
+
/* If the main thread is not pinned, choose the L3 cache. */
if (cache == -1) {
unsigned num_L3_caches = util_cpu_caps.nr_cpus /
util_cpu_caps.cores_per_L3;
/* Choose a different L3 cache for each subsequent MakeCurrent. */
- call_once(&init_cache_number_flag, util_init_cache_number);
cache = p_atomic_inc_return(&L3_cache_number) % num_L3_caches;
util_pin_thread_to_L3(current, cache, util_cpu_caps.cores_per_L3);
}
/* Tell the driver to pin its threads to the same L3 cache. */
if (ctx->set_context_param) {
ctx->set_context_param(ctx, PIPE_CONTEXT_PARAM_PIN_THREADS_TO_L3_CACHE,
cache);
}
--
2.17.1
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
