radv: use a mask for VBOs and shaders prefetching

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>

src/amd/vulkan/radv_cmd_buffer.c

@@ -37,6 +37,20 @@
 
 #include "ac_debug.h"
 
+enum {
+	RADV_PREFETCH_VBO_DESCRIPTORS	= (1 << 0),
+	RADV_PREFETCH_VS		= (1 << 1),
+	RADV_PREFETCH_TCS		= (1 << 2),
+	RADV_PREFETCH_TES		= (1 << 3),
+	RADV_PREFETCH_GS		= (1 << 4),
+	RADV_PREFETCH_PS		= (1 << 5),
+	RADV_PREFETCH_SHADERS		= (RADV_PREFETCH_VS  |
+					   RADV_PREFETCH_TCS |
+					   RADV_PREFETCH_TES |
+					   RADV_PREFETCH_GS  |
+					   RADV_PREFETCH_PS)
+};
+
 static void radv_handle_image_transition(struct radv_cmd_buffer *cmd_buffer,
 					 struct radv_image *image,
 					 VkImageLayout src_layout,
@@ -617,17 +631,6 @@ radv_emit_prefetch_TC_L2_async(struct radv_cmd_buffer *cmd_buffer, uint64_t va,
 		si_cp_dma_prefetch(cmd_buffer, va, size);
 }
 
-static void
-radv_emit_VBO_descriptors_prefetch(struct radv_cmd_buffer *cmd_buffer)
-{
-	if (cmd_buffer->state.vb_prefetch_dirty) {
-		radv_emit_prefetch_TC_L2_async(cmd_buffer,
-					       cmd_buffer->state.vb_va,
-					       cmd_buffer->state.vb_size);
-		cmd_buffer->state.vb_prefetch_dirty = false;
-	}
-}
-
 static void
 radv_emit_shader_prefetch(struct radv_cmd_buffer *cmd_buffer,
 			  struct radv_shader_variant *shader)
@@ -649,18 +652,35 @@ static void
 radv_emit_prefetch(struct radv_cmd_buffer *cmd_buffer,
 		   struct radv_pipeline *pipeline)
 {
-	radv_emit_shader_prefetch(cmd_buffer,
-				  pipeline->shaders[MESA_SHADER_VERTEX]);
-	radv_emit_VBO_descriptors_prefetch(cmd_buffer);
-	radv_emit_shader_prefetch(cmd_buffer,
-				  pipeline->shaders[MESA_SHADER_TESS_CTRL]);
-	radv_emit_shader_prefetch(cmd_buffer,
-				  pipeline->shaders[MESA_SHADER_TESS_EVAL]);
-	radv_emit_shader_prefetch(cmd_buffer,
-				  pipeline->shaders[MESA_SHADER_GEOMETRY]);
-	radv_emit_shader_prefetch(cmd_buffer, pipeline->gs_copy_shader);
-	radv_emit_shader_prefetch(cmd_buffer,
-				  pipeline->shaders[MESA_SHADER_FRAGMENT]);
+	struct radv_cmd_state *state = &cmd_buffer->state;
+
+	if (state->prefetch_L2_mask & RADV_PREFETCH_VS)
+		radv_emit_shader_prefetch(cmd_buffer,
+					  pipeline->shaders[MESA_SHADER_VERTEX]);
+
+	if (state->prefetch_L2_mask & RADV_PREFETCH_VBO_DESCRIPTORS)
+		radv_emit_prefetch_TC_L2_async(cmd_buffer, state->vb_va,
+					       state->vb_size);
+
+	if (state->prefetch_L2_mask & RADV_PREFETCH_TCS)
+		radv_emit_shader_prefetch(cmd_buffer,
+					  pipeline->shaders[MESA_SHADER_TESS_CTRL]);
+
+	if (state->prefetch_L2_mask & RADV_PREFETCH_TES)
+		radv_emit_shader_prefetch(cmd_buffer,
+					  pipeline->shaders[MESA_SHADER_TESS_EVAL]);
+
+	if (state->prefetch_L2_mask & RADV_PREFETCH_GS) {
+		radv_emit_shader_prefetch(cmd_buffer,
+					  pipeline->shaders[MESA_SHADER_GEOMETRY]);
+		radv_emit_shader_prefetch(cmd_buffer, pipeline->gs_copy_shader);
+	}
+
+	if (state->prefetch_L2_mask & RADV_PREFETCH_PS)
+		radv_emit_shader_prefetch(cmd_buffer,
+					  pipeline->shaders[MESA_SHADER_FRAGMENT]);
+
+	state->prefetch_L2_mask = 0;
 }
 
 static void
@@ -1504,7 +1524,7 @@ radv_cmd_buffer_update_vertex_descriptors(struct radv_cmd_buffer *cmd_buffer, bo
 
 		cmd_buffer->state.vb_va = va;
 		cmd_buffer->state.vb_size = count * 16;
-		cmd_buffer->state.vb_prefetch_dirty = true;
+		cmd_buffer->state.prefetch_L2_mask |= RADV_PREFETCH_VBO_DESCRIPTORS;
 	}
 	cmd_buffer->state.dirty &= ~RADV_CMD_DIRTY_VERTEX_BUFFER;
 
@@ -2310,6 +2330,9 @@ void radv_CmdBindPipeline(
 		cmd_buffer->state.last_first_instance = -1;
 		cmd_buffer->state.last_vertex_offset = -1;
 
+		/* Prefetch all pipeline shaders at first draw time. */
+		cmd_buffer->state.prefetch_L2_mask |= RADV_PREFETCH_SHADERS;
+
 		radv_bind_dynamic_state(cmd_buffer, &pipeline->dynamic_state);
 
 		if (pipeline->graphics.esgs_ring_size > cmd_buffer->esgs_ring_size_needed)
@@ -3053,7 +3076,7 @@ radv_draw(struct radv_cmd_buffer *cmd_buffer,
 		 * run in parallel, but starting the draw first is more
 		 * important.
 		 */
-		if (pipeline_is_dirty) {
+		if (cmd_buffer->state.prefetch_L2_mask) {
 			radv_emit_prefetch(cmd_buffer,
 					   cmd_buffer->state.pipeline);
 		}
@@ -3063,7 +3086,7 @@ radv_draw(struct radv_cmd_buffer *cmd_buffer,
 		 */
 		si_emit_cache_flush(cmd_buffer);
 
-		if (pipeline_is_dirty) {
+		if (cmd_buffer->state.prefetch_L2_mask) {
 			radv_emit_prefetch(cmd_buffer,
 					   cmd_buffer->state.pipeline);
 		}

src/amd/vulkan/radv_private.h

@@ -915,13 +915,14 @@ struct radv_descriptor_state {
 
 struct radv_cmd_state {
 	/* Vertex descriptors */
-	bool                                          vb_prefetch_dirty;
 	uint64_t                                      vb_va;
 	unsigned                                      vb_size;
 
 	bool predicating;
 	uint32_t                                      dirty;
 
+	uint32_t                                      prefetch_L2_mask;
+
 	struct radv_pipeline *                        pipeline;
 	struct radv_pipeline *                        emitted_pipeline;
 	struct radv_pipeline *                        compute_pipeline;