加速矩阵乘法SSE（C ++） [英] Speed up matrix multiplication by SSE (C++)

问题描述

我需要运行一个矩阵向量乘法每秒240000次。矩阵是5x5并且总是相同的，而向量在每次迭代时改变。数据类型为float。我正在考虑使用一些SSE（或类似的）指令。

I need to run a matrix-vector multiplication 240000 times per second. The matrix is 5x5 and is always the same, whereas the vector changes at each iteration. The data type is float. I was thinking of using some SSE (or similar) instructions.

1）我担心算术运算的数量太少与所涉及的内存操作的数量。你认为我可以得到一些有形的（例如> 20％）的改进吗？

1) I am concerned that the number of arithmetic operations is too small compared to the number of memory operations involved. Do you think I can get some tangible (e.g. > 20%) improvement?

2）我需要英特尔编译器吗？

2) Do I need the Intel compiler to do it?

3）您能指出一些参考资料吗？

3) Can you point out some references?

感谢大家！

推荐答案

Eigen C ++模板库用于向量，矩阵...对于小型固定大小矩阵（以及动态大小的矩阵）都具有

The Eigen C++ template library for vectors, matrices, ... has both

• 优化代码

• optimised code for small fixed size matrices (as well as dynamically sized ones)

使用SSE优化的优化代码

optimised code that uses SSE optimisations

。

这篇关于加速矩阵乘法SSE（C ++）的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！