The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Workshop:P3HPC: 2021 International Workshop on Performance, Portability, and Productivity in HPC
Authors: Mariia Krainiuk (Intel Corporation), Mehdi Goli (Codeplay Software Ltd), and Vincent Pascuzzi (Lawrence Berkeley National Laboratory (LBNL))
Abstract: To HPC and AI analytics engineers, math primitives like basic linear algebra subprograms or random number generators are key functionalities that have highly optimized implementations for different CPUs, GPUs, and other accelerators. However, developers must deal with different programming models and interfaces provided by various hardware vendors due to a lack of industry-standard interfaces for math primitives.
We introduce the SYCL-based open-source interfaces for math primitives, oneMKL open-source interface project as a viable approach for bridging the cross-platform performance portability gap for math primitives across various HPC architectures. Exploiting the SYCL interoperability feature, this project enables the integration of optimized vendor-dependent libraries to maximize code reusability without compromising the performance. The cross-platform performance portability of the project was carried out on two major HPC hardware, including Intel CPU and NVIDIA GPU and an integrated Intel GPU. Our results state competitive performance with native optimized vendor-dependent libraries.