我想测试不同的方式给一个函数应用于阵列。
为什么https://software.intel.com/sites/landingpage/IntrinsicsGuide/#expand=3260,2124,4779,4779&cats=Trigonometry&text=_sin
_mm_sin_ps
不知道我的范围,但_mm_sqrt_ps
是什么?
我怎么让他们知道? 并编译它没有错误。
#include <random>
#include <iostream>
#include <cmath>
#include <chrono>
#include <algorithm>
#include <valarray>
#include "immintrin.h"
#include <array>
int main()
{
std::cout<<"start\n";
std::random_device rd;
std::mt19937 gen(rd());
std::uniform_real_distribution<> dis(-1000, 1000);
int N=100;
while(N--)
{
std::cout<<"\nN: "<<N;
const int T1=4E6;
{
int T=T1,T0=T1/4;
std::array<float,T1> array;
while(T--)
{
array[T]=dis(gen);
}
auto start_time = std::chrono::high_resolution_clock::now();
auto it =array.begin();
while(T0--)
{
__m128 X = _mm_loadu_ps(it);
__m128 result = _mm_sin_ps(X);
_mm_storeu_ps(it, result);
it+=4;
}
auto time2=std::chrono::high_resolution_clock::now()-start_time;
std::cout<<"\nintr1: "<<std::chrono::duration_cast<std::chrono::microseconds>(time2).count();
}
}
std::cout<<"\nfin\n";
return 0;
}
编译器
克++ -v
Using built-in specs.
COLLECT_GCC=g++
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/4.8/lto-wrapper
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Ubuntu 4.8.2-19ubuntu1' --with-bugurl=file:///usr/share/doc/gcc-4.8/README.Bugs --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --prefix=/usr --program-suffix=-4.8 --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --with-gxx-include-dir=/usr/include/c++/4.8 --libdir=/usr/lib --enable-nls --with-sysroot=/ --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-gnu-unique-object --disable-libmudflap --enable- plugin --with-system-zlib --disable-browser-plugin --enable-java-awt=gtk --enable-gtk-cairo --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.8-amd64/jre --enable-java-home --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.8-amd64 --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.8-amd64 --with-arch-directory=amd64 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --enable-objc-gc --enable-multiarch --disable-werror --with-arch-32=i686 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --with-tune=generic --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu
Thread model: posix
gcc version 4.8.2 (Ubuntu 4.8.2-19ubuntu1)