Increasing memory miss tolerance for SIMD cores

Manycore processors with wide SIMD cores are becoming a popular choice for the next generation of throughput oriented architectures. We introduce a hardware technique called “diverge on miss” that allows SIMD cores to better tolerate memory latency for workloads with non-contiguous memory access patterns. Individual threads within a SIMD “warp” are allowed to slip behind other threads in the same warp, letting the warp continue execution even if a subset of threads are waiting on memory. Diverge on miss can either increase the performance of a given design by up to a factor of 3.14 for a single warp per core, or reduce the number of warps per core needed to sustain a given level of performance from 16 to 2 warps, reducing the area per core by 35%. Categories and Subject Descriptors C.1 [PROCESSOR ARCHITECTURES]: Multiple Data Stream Architectures (Multiprocessors)

• Type: Conference
• Year: 2009
• Where: SC
• Authors: David Tarjan, Jiayuan Meng, Kevin Skadron
• Keywords: Applied Computing, SC 2009, SIMD Cores, Tolerate Memory Latency, Wide Simd Cores