All-to-all communication is a well known performance bottleneck for many applications, such as the ones that use the Fast-Fourier-Transform (FFT) algorithm. We analyze the performance of all-to-all communication on the Blue Gene/L torus interconnect that has link contention even for all-to-all operations with short messages. We observed that the performance of all-to-all depends on the shape of the processor partition. We present a performance analysis of all-to-all on partitions of various shapes. We then present optimization schemes that substantially improve the performance of all-to-all with short and large messages. In particular, throughput improved from 64% to over 99% of peak on the 65,536 (64 × 32 × 32) node Blue Gene/L machine at the Lawrence Livermore National Lab. We show the impact of the all-to-all performance optimizations in 1-D and 3-D FFT benchmarks. We achieved a performance of over 2.8 TF for the HPC Challenge 1D FFT benchmark with our optimized all-to-all.
展开▼
机译：全面通信是许多应用程序的众所周知的性能瓶颈，例如使用快速傅里叶变换（FFT）算法的应用程序。我们分析了蓝色基因/ L Torus互连上的全部通信的性能，即使对于短消息的全部操作，也具有链接争用。我们观察到全部的性能取决于处理器分区的形状。我们对各种形状的分区提供了对全部的绩效分析。然后，我们提出优化方案，即大大提高了所有与之短的消息的表现。特别是，吞吐量从65,536（64×32×32）节点蓝色基因/ L机器上的64％到超过99％的峰值在Lawrence Livermore国家实验室。我们展示了在1-D和3-D FFT基准中的全面性能优化的影响。对于HPC挑战1D FFT基准，我们实现了超过2.8吨TF的表现，并通过我们的优化全部。
展开▼
