Showing cs.DCShow all
3 papers · 1 filter
cs.DC2026
Microbenchmark-Driven Analytical Performance Modeling Across Modern GPU Architectures
Aaron Jarmusch, Sunita Chandrasekaran
Rapidly evolving GPU architectures featuring complex memory hierarchies, matrix units, and varied precision formats continue to widen the gap between theoretical peaks and achievab…
cs.DC2026
Execution-Centric Characterization of FP8 Matrix Cores, Asynchronous Execution, and Structured Sparsity on AMD MI300A
Aaron Jarmusch, Connor Vitz, Sunita Chandrasekaran
The AMD MI300A APU integrates CDNA3 GPUs with high-bandwidth memory and advanced accelerator features: FP8 matrix cores, asynchronous compute engines (ACE), and 2:4 structured spar…
cs.DC2025
Dissecting the NVIDIA Blackwell Architecture with Microbenchmarks
Aaron Jarmusch, Nathan Graddon, Sunita Chandrasekaran
The rapid development in scientific research provides a need for more compute power, which is partly being solved by GPUs. This paper presents a microarchitectural analysis of the…