Technically not passing all buffers used by a kernel is undefined behavior. We haven't had any issues with this so far on AMD or Nvidia, but it's known to be a problem with Intel and we received a report from AMD that this is a problem on newer hardware, so we need to make this change at some point. Unfortunately there a cost to being correct, about 5% for the benchmark scenes. For low sample counts it's even worse, I've seen up to 50% slowdown. For the latter case I think adjusting tile updating logic can help, but not sure what that would look like yet (it would be just a few lines change however).
		
			
				
	
	
		
			27 lines
		
	
	
		
			900 B
		
	
	
	
		
			Common Lisp
		
	
	
	
	
	
			
		
		
	
	
			27 lines
		
	
	
		
			900 B
		
	
	
	
		
			Common Lisp
		
	
	
	
	
	
| /*
 | |
|  * Copyright 2011-2017 Blender Foundation
 | |
|  *
 | |
|  * Licensed under the Apache License, Version 2.0 (the "License");
 | |
|  * you may not use this file except in compliance with the License.
 | |
|  * You may obtain a copy of the License at
 | |
|  *
 | |
|  * http://www.apache.org/licenses/LICENSE-2.0
 | |
|  *
 | |
|  * Unless required by applicable law or agreed to in writing, software
 | |
|  * distributed under the License is distributed on an "AS IS" BASIS,
 | |
|  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 | |
|  * See the License for the specific language governing permissions and
 | |
|  * limitations under the License.
 | |
|  */
 | |
| 
 | |
| #include "kernel/kernel_compat_opencl.h"
 | |
| #include "kernel/split/kernel_split_common.h"
 | |
| #include "kernel/split/kernel_shader_setup.h"
 | |
| 
 | |
| #define KERNEL_NAME shader_setup
 | |
| #define LOCALS_TYPE unsigned int
 | |
| #include "kernel/kernels/opencl/kernel_split_function.h"
 | |
| #undef KERNEL_NAME
 | |
| #undef LOCALS_TYPE
 | |
| 
 |