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

Cycles: test code for sse 4.1 kernel and alignment for some vector types.

Browse Source 
This is mostly work towards enabling the __KERNEL_SSE__ option to start using
SIMD operations for vector math operations. This 4.1 kernel performes about 8%
faster with that option but overall is still slower than without the option.

WITH_CYCLES_OPTIMIZED_KERNEL_SSE41 is the cmake flag for testing this kernel.

Alignment of int3, int4, float3, float4 to 16 bytes seems to give a slight 1-2%
speedup on tested systems with the current kernel already, so is enabled now.
This commit is contained in:
Martijn Berger
2013-11-22 14:16:47 +01:00
committed by Brecht Van Lommel
parent 5feb0d2bfe
commit e3a79258d1
11 changed files with 187 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
intern/cycles/kernel/kernel_sse41.cpp Normal file
View File

@@ -0,0 +1,76 @@
/*
* Copyright 2011-2013 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
*/
/* Optimized CPU kernel entry points. This file is compiled with SSE3/SSSE3
* optimization flags and nearly all functions inlined, while kernel.cpp
* is compiled without for other CPU's. */
#ifdef WITH_OPTIMIZED_KERNEL
/* SSE optimization disabled for now on 32 bit, see bug #36316 */
#if !(defined(__GNUC__) && (defined(i386) || defined(_M_IX86)))
#define __KERNEL_SSE2__
#define __KERNEL_SSE3__
#define __KERNEL_SSSE3__
#define __KERNEL_SSE41__
#endif
#include "kernel.h"
#include "kernel_compat_cpu.h"
#include "kernel_math.h"
#include "kernel_types.h"
#include "kernel_globals.h"
#include "kernel_film.h"
#include "kernel_path.h"
#include "kernel_displace.h"
CCL_NAMESPACE_BEGIN
/* Path Tracing */
void kernel_cpu_sse41_path_trace(KernelGlobals *kg, float *buffer, unsigned int *rng_state, int sample, int x, int y, int offset, int stride)
{
#ifdef __BRANCHED_PATH__
if(kernel_data.integrator.branched)
kernel_branched_path_trace(kg, buffer, rng_state, sample, x, y, offset, stride);
else
#endif
kernel_path_trace(kg, buffer, rng_state, sample, x, y, offset, stride);
}
/* Film */
void kernel_cpu_sse41_convert_to_byte(KernelGlobals *kg, uchar4 *rgba, float *buffer, float sample_scale, int x, int y, int offset, int stride)
{
kernel_film_convert_to_byte(kg, rgba, buffer, sample_scale, x, y, offset, stride);
}
void kernel_cpu_sse41_convert_to_half_float(KernelGlobals *kg, uchar4 *rgba, float *buffer, float sample_scale, int x, int y, int offset, int stride)
{
kernel_film_convert_to_half_float(kg, rgba, buffer, sample_scale, x, y, offset, stride);
}
/* Shader Evaluate */
void kernel_cpu_sse41_shader(KernelGlobals *kg, uint4 *input, float4 *output, int type, int i)
{
kernel_shader_evaluate(kg, input, output, (ShaderEvalType)type, i);
}
CCL_NAMESPACE_END
#endif