论文信息 - Performance and Energy Implications of Many-Core Caches for Throughput Computing

Performance and Energy Implications of Many-Core Caches for Throughput Computing

Processors that target throughput computing often have many cores, which stresses the cache hierarchy. logically centralized, shared data storage is needed for many-core chips to provide high cache throughput for heavily read-write shared lines. techniques to reduce on-die and off-die traffic have a dramatic energy benefit for many-core chips.

Christopher J. Hughes | Yen-Kuang Chen | Changkyu Kim

[1] Michael Zhang,et al. Victim Migration: Dynamically Adapting Between Private and Shared CMP Caches , 2005 .

[2] Doug Burger,et al. An adaptive, non-uniform cache structure for wire-delay dominated on-chip caches , 2002, ASPLOS X.

[3] Kai Li,et al. The PARSEC benchmark suite: Characterization and architectural implications , 2008, 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT).

[4] Jaehyuk Huh,et al. A NUCA Substrate for Flexible CMP Cache Sharing , 2007, IEEE Transactions on Parallel and Distributed Systems.

[5] Pradeep Dubey,et al. Convergence of Recognition, Mining, and Synthesis Workloads and Its Implications , 2008, Proceedings of the IEEE.

[6] Jichuan Chang,et al. Cooperative Caching for Chip Multiprocessors , 2006, 33rd International Symposium on Computer Architecture (ISCA'06).

[7] William J. Dally. The end of denial architecture and the rise of throughput computing , 2009, DAC 2009.

[8] Anoop Gupta,et al. The SPLASH-2 programs: characterization and methodological considerations , 1995, ISCA.

[9] Pradeep Dubey,et al. Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU , 2010, ISCA.