高性能SIMT中的动态翘曲调整
Dynamic Warp Resizing in High-Performance SIMT
摘要:
现代GPU在每个指令处同步分组在线程束中的线程。这些结果提高了SIMD效率,并使共享获取和解码资源成为可能。每个线程束中包含的线程数(或线程束大小)会影响发散、同步开销和内存访问合并的效率。小的warp减少了与分支和内存发散相关的性能损失,但代价是减少了内存合并。大的翘曲显著增强了内存合并,但也增加了分支和内存发散。动态工作负载行为,包括分支/内存发散和合并,是确定返回最佳性能的线程束大小的重要因素。最佳翘曲大小可以从一个工作负载到另一个工作负载或从一个程序阶段到下一个程序阶段而变化。基于这一观察,我们提出了动态变形调整(DWR)。DWR采用创新的微架构步骤,在运行时根据程序特性调整翘曲大小。DWR优于静态翘曲大小决策,高达1.7倍至2.28倍,而施加不到1%的面积开销。我们调查了各种替代配置,并表明DWR性能更好,更窄的SIMD和更大的缓存。
英文摘要:
Modern GPUs synchronize threads grouped in a warp at every instruction. These results in improving SIMD efficiency and makes sharing fetch and decode resources possible. The number of threads included in each warp (or warp size) affects divergence, synchronization overhead and the efficiency of memory access coalescing. Small warps reduce the performance penalty associated with branch and memory divergence at the expense of a reduction in memory coalescing. Large warps enhance memory coalescing significantly but also increase branch and memory divergence. Dynamic workload behavior, including branch/memory divergence and coalescing, is an important factor in determining the warp size returning best performance. Optimal warp size can vary from one workload to another or from one program phase to the next. Based on this observation, we propose Dynamic Warp Resizing (DWR). DWR takes innovative microarchitectural steps to adjust warp size during runtime and according to program characteristics. DWR outperforms static warp size decisions, up to 1.7X to 2.28X, while imposing less than 1% area overhead. We investigate various alternative configurations and show that DWR performs better for narrower SIMD and larger caches.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。