Towards Highly Efficient DGEMM on the Emerging SW26010 Many-Core Processor
| Autor: | Rongfen Lin, Chao Yang, Qiao Sun, Lijuan Jiang, Peng Zhang, Wanwang Yin, Wenjing Ma, Yulong Ao, Fangfang Liu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
020203 distributed computing
Memory hierarchy Computer science Instruction scheduling 020207 software engineering 02 engineering and technology Parallel computing SW26010 Supercomputer Basic Linear Algebra Subprograms Instruction set Computer architecture Asynchronous communication 0202 electrical engineering electronic engineering information engineering Multiplication Block (data storage) Sunway TaihuLight |
| Zdroj: | ICPP |
| DOI: | 10.1109/icpp.2017.51 |
| Popis: | The matrix-matrix multiplication is an essential building block that can be found in various scientific and engineering applications. High-performance implementations of the matrix-matrix multiplication on state-of-the-art processors may be of great importance for both the vendors and the users. In this paper, we present a detailed methodology of implementing and optimizing the double-precision general format matrix-matrix multiplication (DGEMM) kernel on the emerging SW26010 processor, which is used to build the Sunway TaihuLight supercomputer. We propose a three level blocking algorithm to orchestrate data on the memory hierarchy and expose parallelism on different hardware levels, and design a collective data sharing scheme by using the register communication mechanism to exchange data efficiently among different cores. On top of those, further optimizations are done based on a data-thread mapping method for efficient data distribution, a double buffering scheme for asynchronous DMA data transfer, and an instruction scheduling method for maximizing the pipeline usage. Experiment results show that the proposed DGEMM implementation can fully exploit the unique hardware features provided by SW26010 and can sustain up to 95% of the peak performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|