radv: reduce CPU overhead merging bo lists.

Just noticed we do a fair bit of unneeded searching here.

Since we know that the buffers in a CS are unique already,
the first time we get any buffers, we can just memcpy those into
place, and when we are searching for subsequent CSes, we only
have to search up until where the previous unique buffers were.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Signed-off-by: Dave Airlie <airlied@redhat.com>

diff --git a/src/amd/vulkan/winsys/amdgpu/radv_amdgpu_cs.c b/src/amd/vulkan/winsys/amdgpu/radv_amdgpu_cs.c
index b58f5db06223b9f3dfc731dbda9128a65e848eaf..9e468bd4ca8ddd6d7ab388cf1a3ca2f6d913bcae 100644 (file)
--- a/src/amd/vulkan/winsys/amdgpu/radv_amdgpu_cs.c
+++ b/src/amd/vulkan/winsys/amdgpu/radv_amdgpu_cs.c
@@ -486,9 +486,19 @@ static int radv_amdgpu_create_bo_list(struct radv_amdgpu_winsys *ws,
                        else
                                cs = (struct radv_amdgpu_cs*)cs_array[i];
 
+                       if (!cs->num_buffers)
+                               continue;
+
+                       if (unique_bo_count == 0) {
+                               memcpy(handles, cs->handles, cs->num_buffers * sizeof(amdgpu_bo_handle));
+                               memcpy(priorities, cs->priorities, cs->num_buffers * sizeof(uint8_t));
+                               unique_bo_count = cs->num_buffers;
+                               continue;
+                       }
+                       int unique_bo_so_far = unique_bo_count;
                        for (unsigned j = 0; j < cs->num_buffers; ++j) {
                                bool found = false;
-                               for (unsigned k = 0; k < unique_bo_count; ++k) {
+                               for (unsigned k = 0; k < unique_bo_so_far; ++k) {
                                        if (handles[k] == cs->handles[j]) {
                                                found = true;
                                                priorities[k] = MAX2(priorities[k],