Abstract | ||
---|---|---|
Modern GPGPUs support the concurrent execution of thousands of threads to provide an energy-efficient platform. However, the massive multi-threading of GPGPUs incurs serious cache contention, as the cache lines brought by one thread can easily be evicted by other threads in the small shared cache. In this paper, we propose a software-hardware cooperative approach that exploits the spatial locality... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/LCA.2017.2693371 | IEEE Computer Architecture Letters |
Keywords | Field | DocType |
Instruction sets,Cache memory,Dispatching,Two dimensional displays,Graphics processing units | Win32 Thread Information Block,Locality,Locality of reference,Shared memory,Computer science,Cache,Instruction set,Parallel computing,Thread (computing),Cache algorithms,Real-time computing | Journal |
Volume | Issue | ISSN |
16 | 2 | 1556-6056 |
Citations | PageRank | References |
3 | 0.36 | 8 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Li-Jhan Chen | 1 | 3 | 0.36 |
Hsiang-Yun Cheng | 2 | 61 | 6.07 |
Po-Han Wang | 3 | 44 | 3.04 |
Chia-Lin Yang | 4 | 1033 | 76.39 |