GPU cache management based on locality type detection

Zhang, Xianwei; Kalamatianos, John; Beckmann, Bradford

GPU cache management based on locality type detection

Patent · Tue Nov 01 04:00:00 EDT 2022

OSTI ID:1986767

Zhang, Xianwei; Kalamatianos, John; Beckmann, Bradford

Wavefront loading in a processor is managed and includes monitoring a selected wavefront of a set of wavefronts. Reuse of memory access requests for the selected wavefront is counted. A cache hit rate in one or more caches of the processor is determined based on the counted reuse. Based on the cache hit rate, subsequent memory requests of other wavefronts of the set of wavefronts are modified by including a type of reuse of cache lines in requests to the caches. In the caches, storage of data in the caches is based on the type of reuse indicated by the subsequent memory access requests. Reused cache lines are protected by preventing cache line contents from being replaced by another cache line for a duration of processing the set of wavefronts. Caches are bypassed when streaming access requests are made.

Research Organization:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States); Advanced Micro Devices, Inc., Santa Clara, CA (United States)

Sponsoring Organization:: USDOE

DOE Contract Number:: AC52-07NA27344

Assignee:: Advanced Micro Devices, Inc. (Santa Clara, CA)

Patent Number(s):: 11,487,671

Application Number:: 16/446,119

OSTI ID:: 1986767

Country of Publication:: United States

Language:: English

References (6)

Adaptive GPU cache bypassing Tian, Yingying; Puthoor, Sooraj; Greathouse, Joseph L. Proceedings of the 8th Workshop on General Purpose Processing using GPUs https://doi.org/10.1145/2716282.2716283	conference	February 2015
Space/time trade-offs in hash coding with allowable errors Bloom, Burton H. Communications of the ACM, Vol. 13, Issue 7, p. 422-426 https://doi.org/10.1145/362686.362692	journal	July 1970
Adaptive Cache Management for Energy-Efficient GPU Computing Chen, Xuhao; Chang, Li-Wen; Rodrigues, Christopher I. 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture https://doi.org/10.1109/MICRO.2014.11	conference	December 2014
Access Pattern-Aware Cache Management for Improving Data Utilization in GPU Koo, Gunjae; Oh, Yunho; Ro, Won Woo Proceedings of the 44th Annual International Symposium on Computer Architecture https://doi.org/10.1145/3079856.3080239	conference	June 2017
Priority-based cache allocation in throughput processors Li, Dong; Rhu, Minsoo; Johnson, Daniel R. 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA) https://doi.org/10.1109/HPCA.2015.7056024	conference	February 2015
An efficient compiler framework for cache bypassing on GPUs Xie, Xiaolong; Liang, Yun; Sun, Guangyu 2013 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) https://doi.org/10.1109/ICCAD.2013.6691165	conference	November 2013

Similar Records

Prioritizing local and remote memory access in a non-uniform memory access architecture

Patent · Mon Nov 16 23:00:00 EST 2020 · OSTI ID:1771644

Dynamic cache bypassing

Patent · Tue Mar 24 00:00:00 EDT 2020 · OSTI ID:1637804

Cache management based on access type priority

Patent · Tue Sep 26 00:00:00 EDT 2023 · OSTI ID:2222369

GPU cache management based on locality type detection

Citation Formats

References (6)

Similar Records

Related Subjects