Task superscalar: an out-of-order task pipeline
Tipus de documentText en actes de congrés
EditorIEEE Computer Society Publications
Condicions d'accésAccés obert
Projecte de la Comissió EuropeaTERAFLUX - Exploiting dataflow parallelism in Teradevice Computing (EC-FP7-249013)
We present Task Superscalar, an abstraction of instruction-level out-of-order pipeline that operates at the tasklevel. Like ILP pipelines, which uncover parallelism in a sequential instruction stream, task superscalar uncovers tasklevel parallelism among tasks generated by a sequential thread. Utilizing intuitive programmer annotations of task inputs and outputs, the task superscalar pipeline dynamically detects intertask data dependencies, identifies task-level parallelism, and executes tasks out-of-order. Furthermore, we propose a design for a distributed task superscalar pipeline frontend, that can be embedded into any manycore fabric, and manages cores as functional units. We show that our proposed mechanism is capable of driving hundreds of cores simultaneously with non-speculative tasks, which allows our pipeline to sustain work windows consisting of tens of thousands of tasks. We further show that our pipeline can maintain a decode rate faster than 60ns per task and dynamically uncover data dependencies among as many as ~50,000 in-flight tasks, using 7MB of on-chip eDRAM storage. This configuration achieves speedups of 95–255x (average 183x) over sequential execution for nine scientific benchmarks, running on a simulated CMP with 256 cores. Task superscalar thus enables programmers to exploit manycore systems effectively, while simultaneously simplifying their programming model.
CitacióEtsion, Y. [et al.]. Task superscalar: an out-of-order task pipeline. A: IEEE/ACM International Symposium on Microarchitecture. "43rd Annual ACM/IEEE International Symposium on Microarchitecture". Atlanta: IEEE Computer Society Publications, 2010, p. 89-100.