用BLIS实现Strassen算法
Implementing Strassen's Algorithm with BLIS
摘要:
我们消除与“街头智慧”关于Strassen的算法的矩阵矩阵乘法(DGEMM)的实际执行。传统观点:它只适用于非常大的矩阵。我们的实现是实用的小矩阵。传统观点认为:被乘的矩阵应该是相对平方的。我们的实现对于rank-k更新是实用的,其中k相对较小(对于像LAPACK这样的库来说是重要的形状)。传统智慧:它本质上需要大量的工作空间。我们的实现不需要超出缓冲区的工作空间已经纳入传统的高性能DGEMM实现。传统观点:Strassen DGEMM接口必须在工作区中传递。我们的实现不需要这样的工作区,可以与标准DGEMM接口插件兼容。传统观点:很难证明多核架构的加速。我们的实现证明了即使在使用240个线程的英特尔(R)至强融核(TM)协处理器上也比传统的DGEMM加速。我们展示了如何分布式存储器矩阵矩阵乘法也受益于这些进步。
英文摘要:
We dispel with "street wisdom" regarding the practical implementation of Strassen's algorithm for matrix-matrix multiplication (DGEMM). Conventional wisdom: it is only practical for very large matrices. Our implementation is practical for small matrices. Conventional wisdom: the matrices being multiplied should be relatively square. Our implementation is practical for rank-k updates, where k is relatively small (a shape of importance for libraries like LAPACK). Conventional wisdom: it inherently requires substantial workspace. Our implementation requires no workspace beyond buffers already incorporated into conventional high-performance DGEMM implementations. Conventional wisdom: a Strassen DGEMM interface must pass in workspace. Our implementation requires no such workspace and can be plug-compatible with the standard DGEMM interface. Conventional wisdom: it is hard to demonstrate speedup on multi-core architectures. Our implementation demonstrates speedup over conventional DGEMM even on an Intel(R) Xeon Phi(TM) coprocessor utilizing 240 threads. We show how a distributed memory matrix-matrix multiplication also benefits from these advances.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。