SEARCH
ISTC-CC NEWSLETTER
RESEARCH HIGHLIGHTS
Ling Liu's SC13 paper "Large Graph Processing Without the Overhead" featured by HPCwire.
ISTC-CC provides a listing of useful benchmarks for cloud computing.
Another list highlighting Open Source Software Releases.
Second GraphLab workshop should be even bigger than the first! GraphLab is a new programming framework for graph-style data analytics.
ISTC-CC Abstract
Exploiting Inter-Warp Heterogeneity to Improve GPGPU Performance
Proceedings of the 24th International Conference on Parallel Architectures and Compilation Techniques (PACT), San Francisco, CA, USA, October 18 - 21, 2015.
Rachata Ausavarungnirun, Saugata Ghose, Onur Kayiran†‡, Gabriel L. Loh†,
Chita R. Das‡, Mahmut T. Kandemir‡, Onur Mutlu
Carnegie Mellon University
† Advanced Micro Devices, Inc.
‡ Pennsylvania State University
In a GPU, all threads within a warp execute the same instruction in lockstep. For a memory instruction, this can lead to memory divergence: the memory requests for some threads are serviced early, while the remaining requests incur long latencies. This divergence stalls the warp, as it cannot execute the next instruction until all requests from the current instruction complete.
In this work, we make three new observations. First, GPGPU warps exhibit heterogeneous memory divergence behavior at the shared cache: some warps have most of their requests hit in the cache (high cache utility), while other warps see most of their request miss (low cache utility). Second, a warp retains the same divergence behavior for long periods of execution. Third, due to high memory level parallelism, requests going to the shared cache can incur queuing delays as large as hundreds of cycles, exacerbating the effects of memory divergence.
We propose a set of techniques, collectively called Memory Divergence Correction (MeDiC), that reduce the negative performance impact of memory divergence and cache queuing. MeDiC uses warp divergence characterization to guide three components: (1) a cache bypassing mechanism that exploits the latency tolerance of low cache utility warps to both alleviate queuing delay and increase the hit rate for high cache utility warps, (2) a cache insertion policy that prevents data from high cache utility warps from being prematurely evicted, and (3) a memory controller that prioritizes the few requests received from high cache utility warps to minimize stall time. We compare MeDiC to four cache management techniques, and find that it delivers an average speedup of 21.8%, and 20.1% higher energy efficiency, over a state-of-the-art GPU cache management mechanism across 15 different GPGPU applications.
FULL PAPER: pdf