AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

radv: allocate only 1 GDS OA counter for gfx10 NGG streamout

Browse Source 
It works with just one counter.

This mitigates https://gitlab.freedesktop.org/drm/amd/-/issues/2902
quite a lot when you run dEQP-VK.transform_feedback.* in parallel on
more than 16 threads with RDNA3.

For example, on my GPU the kernel reports 16 GDS OA counters which means
that if you run VKCTS with 16 threads (ie. 16 Vulkan devices are
created) it's fine. Otherwise, the kernel might report ENOMEM.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25619>
This commit is contained in:
Samuel Pitoiset
2023-10-09 16:38:42 +02:00
committed by Marge Bot
parent 7c7684c656
commit bbf135db3d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/amd/vulkan/radv_queue.c
+1 -1
View File
@@ -953,7 +953,7 @@ radv_update_preamble_cs(struct radv_queue_state *queue, struct radv_device *devi
if (!queue->ring_info.gds_oa && needs->gds_oa) {
assert(device->physical_device->rad_info.gfx_level >= GFX10);
result = ws->buffer_create(ws, 4, 1, RADEON_DOMAIN_OA, ring_bo_flags, RADV_BO_PRIORITY_SCRATCH, 0, &gds_oa_bo);
result = ws->buffer_create(ws, 1, 1, RADEON_DOMAIN_OA, ring_bo_flags, RADV_BO_PRIORITY_SCRATCH, 0, &gds_oa_bo);
if (result != VK_SUCCESS)
goto fail;