G-Power, an architecture-level GPU power modeling framework that utilizes additional known GPU chips to provide additional knowledge and adopts a three-phase algorithm consisting of pre-training with additional known chips, attention-inspired aggregation, and fine-tuning on the target GPU.
Qi-Jun Zhang, Yao Lu, Shang Liu et al.· 0 citations
AgentZip is presented, the first memory compression system designed specifically for AI-agent sandboxes, which broadens the compression scope to any page with a profitable representation and shifts overhead control from compression-time page selection to restore-time prefetching.
Meng-Ming Li, Ce-Yu Xu, Qi-Jun Zhang et al.· 0 citations
FSGen is proposed, an agile framework for attention-based LLM accelerator generation with an early-stage PPA estimator that supports fused operator dataflows and sparsity with a diverse design space and finds designs with 1.4x better power efficiency or 10x speedup with similar PPA metrics compared to prior work.
A novel open-source framework named OSCAR is proposed, which, given a set of hardware and workload specifications, provides architecture-level power estimation and can also automatically generate Chisel and synthesizable RTL of the custom AI chip.
J. Mok, Qi-Jun Zhang, Di Pang et al.· ACM Transactions on Design A...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
