Implicit sync kicks in when a buffer is used by two different amdgpu
contexts simultaneously. Jobs that use explicit synchronization
mechanisms end up needlessly waiting to be scheduled for long periods
of time in order to achieve serialized execution.
This patch disables implicit synchronization for all radv allocations.
The only systems that require implicit synchronization are DRI2/3 and
PRIME.
Signed-off-by: Andres Rodriguez <andresx7 at gmail.com>
---
src/amd/vulkan/winsys/amdgpu/radv_amdgpu_bo.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/src/amd/vulkan/winsys/amdgpu/radv_amdgpu_bo.c b/src/amd/vulkan/winsys/amdgpu/radv_amdgpu_bo.c
index 325f875..9dc7559 100644
--- a/src/amd/vulkan/winsys/amdgpu/radv_amdgpu_bo.c
+++ b/src/amd/vulkan/winsys/amdgpu/radv_amdgpu_bo.c
@@ -330,6 +330,7 @@ radv_amdgpu_winsys_bo_create(struct radeon_winsys *_ws,
request.flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
if (flags & RADEON_FLAG_GTT_WC)
request.flags |= AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+ request.flags |= AMDGPU_GEM_CREATE_EXPLICIT_SYNC;
r = amdgpu_bo_alloc(ws->dev, &request, &buf_handle);
if (r) {
--
2.9.3
