AUGEM: automatically generate high performance dense linear algebra kernels on x86 CPUs

  • Authors:

  • Qian Wang;Xianyi Zhang;Yunquan Zhang;Qing Yi

  • Affiliations:

  • University of Chinese, Beijing, China;University of Chinese, Beijing, China;Institute of Software, Chinese Academy of Sciences, Beijing, China;University of Colorado at Colorado Springs, Colorado

  • Venue:
  • SC '13 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Basic Liner algebra subprograms (BLAS) is a fundamental library in scientific computing. In this paper, we present a template-based optimization framework, AUGEM, which can automatically generate fully optimized assembly code for several dense linear algebra (DLA) kernels, such as GEMM, GEMV, AXPY and DOT, on varying multi-core CPUs without requiring any manual interference from developers. In particular, based on domain-specific knowledge about algorithms of the DLA kernels, we use a collection of parameterized code templates to formulate a number of commonly occurring instruction sequences within the optimized low-level C code of these DLA kernels. Then, our framework uses a specialized low-level C optimizer to identify instruction sequences that match the pre-defined code templates and thereby translates them into extremely efficient SSE/AVX instructions. The DLA kernels generated by our template-based approach surpass the implementations of Intel MKL and AMD ACML BLAS libraries, on both Intel Sandy Bridge and AMD Piledriver processors.