forked from bartvdbraak/blender
e3a79258d1
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.
35 lines
940 B
C
35 lines
940 B
C
/*
|
|
* 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
|
|
*/
|
|
|
|
#ifndef __UTIL_SYSTEM_H__
|
|
#define __UTIL_SYSTEM_H__
|
|
|
|
#include "util_string.h"
|
|
|
|
CCL_NAMESPACE_BEGIN
|
|
|
|
int system_cpu_thread_count();
|
|
string system_cpu_brand_string();
|
|
int system_cpu_bits();
|
|
bool system_cpu_support_sse2();
|
|
bool system_cpu_support_sse3();
|
|
bool system_cpu_support_sse41();
|
|
|
|
CCL_NAMESPACE_END
|
|
|
|
#endif /* __UTIL_SYSTEM_H__ */
|
|
|