XcalableMP 2.0 and Future Directions

This chapter presents the XcalableMP on the Fugaku supercomputer, the Japanese flagship supercomputer developed by FLAGSHIP2020 project in RIKEN R-CCS. The porting and the performance evaluation were done as a part of this project, and the XcalableMP is available for the Fugaku users for improving the productivity and performance of parallel programing. The performance of XcalableMP on the Fugaku is enhanced by the manycore processor and a new Tofu-D interconnect. We are now working on the next version, XcalableMP 2.0, for cutting-edge high-performance systems with manycore processors by multithreading and multi-tasking with integrations of PGAS model and synchronization models. We conclude this book with retrospectives and challenges for future PGAS models.

Enhancing Programmability in NoC-Based Lightweight Manycore Processors with a Portable MPI Library

The performance and energy efficiency provided by lightweight manycores is undeniable. However, the lack of rich and portable support for these processors makes software development challenging. To address this problem, we propose a portable and lightweight MPI library (LWMPI) designed from scratch to cope with restrictions and intricacies of lightweight manycores. We integrated LWMPI into a distributed OS that targets these processors and evaluated it on the Kalray MPPA-256 processor. Results obtained with three applications from a representative benchmark suite unveiled that LWMPI achieves similar performance scalability in comparison with the low-level vendor-specific API narrowed for MPPA-256, while exposing a richer programming interface.

MALT manycore processors capabilities in image processing tasks

В статье рассматриваются результаты экспериментальной оценки производительности и энергоэффективности многоядерных процессоров MALT в задачах обработки изображений на примере фильтрации изображения с помощью оператора Собеля. Измерения осуществлялись с использованием низкоуровневого эмулятора MALTemu, прототипа процессора в ПЛИС и экспериментальной СБИС модели MALT-Cv2 Rev1. Полученные результаты сравниваются с аналогичными результатами для процессоров общего назначения (последовательная реализация) и графических процессоров с поддержкой технологии CUDA. In this paper we consider the experimental performance and energy efficiency evaluation in image processing tasks for the MALT manycore processors. The image filtering with the Sobel operator is used as an example. Measurements are conducted using the MALTemu low level emulator, an FPGA processor prototype and an experimental ASIC model MALT-Cv2 Rev1. The obtained results are compared with similar results for a general purpose CPU (sequential implementation) and a GPU with the CUDA technology support.