A Hierarchical Task Scheduler for Heterogeneous Computing




Heterogeneous computing is one of the future directions of HPC. Task scheduling in heterogeneous computing has to balance the challenge of optimizing the application performance and the need for an intuitive interface with the programming runtime to maintain programming portability. The challenge is further compounded by the varying data communication time between tasks.In this paper, we propose RANGER, a hardware-assisted task-scheduling framework. By integrating RISC-V cores with accelerators, the RANGER scheduling framework breaks scheduling into global and local levels. At the local level,RANGER further partitions each task into fine-grained subtasks to reduce the overall makespan. At the global level, RANGER maintains the coarse granularity of the task specification, thereby maintaining programming portability. Our extensive experimental results demonstrate that RANGER achieves on average 12.7×performance improvement while only requires 2.7% of area overhead

Read Publication Related Projects Sawtooth

Last Updated: March 31, 2021 - 10:47 am