radv: only load needed depth clear regs for fast depth clears

Similar to how the driver sets the depth clear regs after a
fast depth clear. Most of the time, this will copy a 32-bit reg
instead of a 64-bit reg.

Signed-off-by: Samuel Pitoiset <[email protected]>
Reviewed-by: Bas Nieuwenhuizen <[email protected]>

1 files changed, 12 insertions, 2 deletions

diff --git a/src/amd/vulkan/radv_cmd_buffer.c b/src/amd/vulkan/radv_cmd_buffer.c
index ae522d2088f..7d86eee9791 100644
--- a/src/amd/vulkan/radv_cmd_buffer.c
+++ b/src/amd/vulkan/radv_cmd_buffer.c
@@ -1331,20 +1331,30 @@ static void
 radv_load_depth_clear_regs(struct radv_cmd_buffer *cmd_buffer,
 			   struct radv_image *image)
 {
+	VkImageAspectFlags aspects = vk_format_aspects(image->vk_format);
 	uint64_t va = radv_buffer_get_va(image->bo);
 	va += image->offset + image->clear_value_offset;
+	unsigned reg_offset = 0, reg_count = 0;
 
 	if (!image->surface.htile_size)
 		return;
 
+	if (aspects & VK_IMAGE_ASPECT_STENCIL_BIT) {
+		++reg_count;
+	} else {
+		++reg_offset;
+		va += 4;
+	}
+	if (aspects & VK_IMAGE_ASPECT_DEPTH_BIT)
+		++reg_count;
 
 	radeon_emit(cmd_buffer->cs, PKT3(PKT3_COPY_DATA, 4, 0));
 	radeon_emit(cmd_buffer->cs, COPY_DATA_SRC_SEL(COPY_DATA_MEM) |
 				    COPY_DATA_DST_SEL(COPY_DATA_REG) |
-				    COPY_DATA_COUNT_SEL);
+				    (reg_count == 2 ? COPY_DATA_COUNT_SEL : 0));
 	radeon_emit(cmd_buffer->cs, va);
 	radeon_emit(cmd_buffer->cs, va >> 32);
-	radeon_emit(cmd_buffer->cs, R_028028_DB_STENCIL_CLEAR >> 2);
+	radeon_emit(cmd_buffer->cs, (R_028028_DB_STENCIL_CLEAR + 4 * reg_offset) >> 2);
 	radeon_emit(cmd_buffer->cs, 0);
 
 	radeon_emit(cmd_buffer->cs, PKT3(PKT3_PFP_SYNC_ME, 0, 0));