Cr8-xyz/blender
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Cycles: Tweak inline policy for some functions

Browse Source 
The goal is to make Experimental kernel closer in performance to the
official kernel, avoiding spills and such.

There should not be big impact on official kernel, own tests showed
few percent performance drop on laptop's GPU. CPU was always the
same speed on AVX, AVX2 and SSE4.1 CPUs i've been testing here.

This seems to be the last essential step before we can get rid of
Experimental kernel and enable SSS officially on GPU without causing
some major performance issues.

Surely some more tweaks are possibly required, but that we can do
for until cows go home anyway.
This commit is contained in:
Sergey Sharybin
2016-01-14 14:53:05 +05:00
parent 5af103fe00
commit 1f273cec00
6 changed files with 42 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
intern/cycles/kernel/svm/svm_tex_coord.h
View File

@@ -99,12 +99,12 @@ ccl_device void svm_node_tex_coord(KernelGlobals *kg,
stack_store_float3(stack, out_offset, data);
}
ccl_device void svm_node_tex_coord_bump_dx(KernelGlobals *kg,
ShaderData *sd,
int path_flag,
float *stack,
uint4 node,
int *offset)
ccl_device_inline void svm_node_tex_coord_bump_dx(KernelGlobals *kg,
ShaderData *sd,
int path_flag,
float *stack,
uint4 node,
int *offset)
{
#ifdef __RAY_DIFFERENTIALS__
float3 data;
@@ -184,12 +184,12 @@ ccl_device void svm_node_tex_coord_bump_dx(KernelGlobals *kg,
#endif
}
ccl_device void svm_node_tex_coord_bump_dy(KernelGlobals *kg,
ShaderData *sd,
int path_flag,
float *stack,
uint4 node,
int *offset)
ccl_device_inline void svm_node_tex_coord_bump_dy(KernelGlobals *kg,
ShaderData *sd,
int path_flag,
float *stack,
uint4 node,
int *offset)
{
#ifdef __RAY_DIFFERENTIALS__
float3 data;