Optimizing Matrix Multiplication on Intel® Xeon Phi TH x200 Architecture
| Autor: | Murat Efe Guney, Kazushige Goto, Shane Story, Louise Huot, Arthur Mitrano, Sarah Knepper, Timothy B. Costa |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
020203 distributed computing
Computer science Subroutine 02 engineering and technology Parallel computing ComputerSystemsOrganization_PROCESSORARCHITECTURES Matrix multiplication 020202 computer hardware & architecture Set (abstract data type) Kernel (linear algebra) Vectorization (mathematics) 0202 electrical engineering electronic engineering information engineering Multiplication Architecture Xeon Phi |
| Zdroj: | ARITH |
| DOI: | 10.1109/arith.2017.19 |
| Popis: | Matrix multiplication is ubiquitous in scientific computing. From computational science to machine learning, a large and diverse set of applications rely on the performance of general matrix-matrix multiplication (GEMM) subroutines. The Intel® Math Kernel Library(R) provides highly optimized GEMM subroutines that take full advantage of the available parallelism and vectorization in both Intel® Xeon® and Intel® Xeon Phi(TM) processors. In this paper we discuss the optimization of GEMM subroutines for the Intel® Xeon Phi(TM) x200 (code-named Knights Landing). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|