MEMORY ALLOCATION IN DISTRIBUTED MEMORIES FOR MULTIPROCESSING

摘要

In some aspects, finer grained parallelism is achieved by segmenting programmatic workloads into smaller discretized portions, where a first element can be indicative both of a configuration or program to be executed, and a first data set to be used in such execution, while a second element can be indicative of a second data element or group. The discretized portions can cause program execute on distributed processors. Approaches to selecting processors, and allocating local memory associated with those processors are disclosed. In one example, discretized portions that share a program have an anti-affinity to cause dispersion, for initial execution assignment. Flags, such as programmer and compiler generated flags can be used in determining such allocations. Workloads can be grouped according to compatibility of memory usage requirements.

主权项

1. A machine-implemented method of scheduling computation tasks, comprising:
identifying a set of computation tasks to be executed on a plurality of processing units; profiling the computation tasks of the set according to parameters comprising memory access requirements and computation requirements of the computation tasks; grouping instances of the computation tasks for execution into groups by identifying computation tasks that have compatible memory access requirements and computation requirements; and scheduling groupings of computation tasks to be executed on the plurality of processing units.