OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

glthread: don't use atomics for refcounting to decrease overhead on AMD Zen

Browse Source 
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4314>
This commit is contained in:
Marek Olšák
2020-03-22 14:45:14 -04:00
committed by Marge Bot
parent 7f22e0fd29
commit befbd54864
2 changed files with 33 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/mesa/main/glthread.h
View File

@@ -114,6 +114,7 @@ struct glthread_state
struct gl_buffer_object *upload_buffer;
uint8_t *upload_ptr;
unsigned upload_offset;
int upload_buffer_private_refcount;
/** Caps. */
GLboolean SupportsBufferUploads;

33
src/mesa/main/glthread_bufferobj.c
View File

@@ -97,11 +97,39 @@ _mesa_glthread_upload(struct gl_context *ctx, const void *data,
return;
}
if (glthread->upload_buffer_private_refcount > 0) {
p_atomic_add(&glthread->upload_buffer->RefCount,
-glthread->upload_buffer_private_refcount);
glthread->upload_buffer_private_refcount = 0;
}
_mesa_reference_buffer_object(ctx, &glthread->upload_buffer, NULL);
glthread->upload_buffer =
new_upload_buffer(ctx, default_size, &glthread->upload_ptr);
glthread->upload_offset = 0;
offset = 0;
/* Since atomic operations are very very slow when 2 threads are not
* sharing one L3 cache (which can happen on AMD Zen), prevent using
* atomics as follows:
*
* This function has to return a buffer reference to the caller.
* Instead of atomic_inc for every call, it does all possible future
* increments in advance when the upload buffer is allocated.
* The maximum number of times the function can be called per upload
* buffer is default_size, because the minimum allocation size is 1.
* Therefore the function can only return default_size number of
* references at most, so we will never need more. This is the number
* that is added to RefCount at allocation.
*
* upload_buffer_private_refcount tracks how many buffer references
* are left to return to callers. If the buffer is full and there are
* still references left, they are atomically subtracted from RefCount
* before the buffer is unreferenced.
*
* This can increase performance by 20%.
*/
glthread->upload_buffer->RefCount += default_size;
glthread->upload_buffer_private_refcount = default_size;
}
/* Upload data. */
@@ -112,8 +140,11 @@ _mesa_glthread_upload(struct gl_context *ctx, const void *data,
glthread->upload_offset = offset + size;
*out_offset = offset;
assert(*out_buffer == NULL);
_mesa_reference_buffer_object(ctx, out_buffer, glthread->upload_buffer);
assert(glthread->upload_buffer_private_refcount > 0);
*out_buffer = glthread->upload_buffer;
glthread->upload_buffer_private_refcount--;
}
/** Tracks the current bindings for the vertex array and index array buffers.