diff options
| author | Thomas Dinges <blender@dingto.org> | 2014-01-16 20:04:11 +0400 |
|---|---|---|
| committer | Thomas Dinges <blender@dingto.org> | 2014-01-16 20:04:11 +0400 |
| commit | de28a4d4b2c9397c5233a5ee1dbf1400f450a15c (patch) | |
| tree | 1fe23de963e206af3fb2ff2d9e2e3393cd89149c /intern/cycles/kernel/kernel.h | |
| parent | 7c6d52eb07c4bd8142a95eca1dbdc794063859b8 (diff) | |
Cycles: Add an AVX kernel for CPU rendering.
* AVX is available on Intel Sandy Bridge and newer and AMD Bulldozer and newer.
* We don't use dedicated AVX intrinsics yet, but gcc auto vectorization gives a 3% performance improvement for Caminandes. Tested on an i5-3570, Linux x64.
* No change for Windows yet, MSVC 2008 does not support AVX.
Reviewed by: brecht
Differential Revision: https://developer.blender.org/D216
Diffstat (limited to 'intern/cycles/kernel/kernel.h')
| -rw-r--r-- | intern/cycles/kernel/kernel.h | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/intern/cycles/kernel/kernel.h b/intern/cycles/kernel/kernel.h index 01bea10c1e7..039dc791b08 100644 --- a/intern/cycles/kernel/kernel.h +++ b/intern/cycles/kernel/kernel.h @@ -76,6 +76,17 @@ void kernel_cpu_sse41_shader(KernelGlobals *kg, uint4 *input, float4 *output, int type, int i); #endif +#ifdef WITH_CYCLES_OPTIMIZED_KERNEL_AVX +void kernel_cpu_avx_path_trace(KernelGlobals *kg, float *buffer, unsigned int *rng_state, + int sample, int x, int y, int offset, int stride); +void kernel_cpu_avx_convert_to_byte(KernelGlobals *kg, uchar4 *rgba, float *buffer, + float sample_scale, int x, int y, int offset, int stride); +void kernel_cpu_avx_convert_to_half_float(KernelGlobals *kg, uchar4 *rgba, float *buffer, + float sample_scale, int x, int y, int offset, int stride); +void kernel_cpu_avx_shader(KernelGlobals *kg, uint4 *input, float4 *output, + int type, int i); +#endif + CCL_NAMESPACE_END #endif /* __KERNEL_H__ */ |