From 6bf4115c13962c99d1cdc97f2be92c4922f3fd33 Mon Sep 17 00:00:00 2001 From: Hristo Gueorguiev Date: Wed, 3 May 2017 15:30:45 +0200 Subject: Cycles: Split kernel - sort shaders Reduce thread divergence in kernel_shader_eval. Rays are sorted in blocks of 2048 according to shader->id. On R9 290 Classroom is ~30% faster, and Pabellon Barcelone is ~8% faster. No sorting for CUDA split kernel. Reviewers: sergey, maiself Reviewed By: maiself Differential Revision: https://developer.blender.org/D2598 --- intern/cycles/kernel/kernels/opencl/kernel_split.cl | 2 ++ 1 file changed, 2 insertions(+) (limited to 'intern/cycles/kernel/kernels/opencl/kernel_split.cl') diff --git a/intern/cycles/kernel/kernels/opencl/kernel_split.cl b/intern/cycles/kernel/kernels/opencl/kernel_split.cl index 732cda30115..8de82db7afe 100644 --- a/intern/cycles/kernel/kernels/opencl/kernel_split.cl +++ b/intern/cycles/kernel/kernels/opencl/kernel_split.cl @@ -23,6 +23,8 @@ #include "kernel/kernels/opencl/kernel_do_volume.cl" #include "kernel/kernels/opencl/kernel_indirect_background.cl" #include "kernel/kernels/opencl/kernel_queue_enqueue.cl" +#include "kernel/kernels/opencl/kernel_shader_setup.cl" +#include "kernel/kernels/opencl/kernel_shader_sort.cl" #include "kernel/kernels/opencl/kernel_shader_eval.cl" #include "kernel/kernels/opencl/kernel_holdout_emission_blurring_pathtermination_ao.cl" #include "kernel/kernels/opencl/kernel_subsurface_scatter.cl" -- cgit v1.2.3