Configurable range memory for effective data reuse on programmable accelerators


While programmable accelerators such as application-specific processors and reconfigurable architectures can dramatically speed up compute-intensive <i>kernels</i> of an application, <i>application performance</i> can still be severely limited by the communication between processors. To minimize the communication overhead, a shared memory such as a… (More)
DOI: 10.1145/2566662