diff options
author | Sergey Sharybin <sergey.vfx@gmail.com> | 2015-04-27 22:13:03 +0300 |
---|---|---|
committer | Sergey Sharybin <sergey.vfx@gmail.com> | 2015-04-27 22:38:32 +0300 |
commit | ae7d84dbc1936ef7ddd00f9c22d074389f97f04f (patch) | |
tree | 7103596bc78785ed769e90c1570d654cc14a839d /intern/cycles/kernel/closure/bsdf_toon.h | |
parent | 278ff15c7f3c4a91ba049b7a13ecf8a4183ebf67 (diff) |
Cycles: Use native saturate function for CUDA
This more a workaround for CUDA optimizer which can't optimize clamp(x, 0, 1)
into a single instruction and uses 4 instructions instead.
Original patch by @lockal with own modification:
Don't make changes outside of the kernel. They don't make any difference
anyway and term saturate() has a bit different meaning outside of kernel.
This gives around 2% of speedup in Barcelona file, but in more complex shader
setups with lots of math nodes with clamping speedup could be much nicer.
Subscribers: dingto
Projects: #cycles
Differential Revision: https://developer.blender.org/D1224
Diffstat (limited to 'intern/cycles/kernel/closure/bsdf_toon.h')
-rw-r--r-- | intern/cycles/kernel/closure/bsdf_toon.h | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/intern/cycles/kernel/closure/bsdf_toon.h b/intern/cycles/kernel/closure/bsdf_toon.h index df03942638f..e5b6ab93a64 100644 --- a/intern/cycles/kernel/closure/bsdf_toon.h +++ b/intern/cycles/kernel/closure/bsdf_toon.h @@ -40,8 +40,8 @@ CCL_NAMESPACE_BEGIN ccl_device int bsdf_diffuse_toon_setup(ShaderClosure *sc) { sc->type = CLOSURE_BSDF_DIFFUSE_TOON_ID; - sc->data0 = clamp(sc->data0, 0.0f, 1.0f); - sc->data1 = clamp(sc->data1, 0.0f, 1.0f); + sc->data0 = saturate(sc->data0); + sc->data1 = saturate(sc->data1); return SD_BSDF|SD_BSDF_HAS_EVAL; } @@ -120,8 +120,8 @@ ccl_device int bsdf_diffuse_toon_sample(const ShaderClosure *sc, float3 Ng, floa ccl_device int bsdf_glossy_toon_setup(ShaderClosure *sc) { sc->type = CLOSURE_BSDF_GLOSSY_TOON_ID; - sc->data0 = clamp(sc->data0, 0.0f, 1.0f); - sc->data1 = clamp(sc->data1, 0.0f, 1.0f); + sc->data0 = saturate(sc->data0); + sc->data1 = saturate(sc->data1); return SD_BSDF|SD_BSDF_HAS_EVAL; } |