Search papers, labs, and topics across Lattice.
Affiliation:
4
0
4
This paper introduces AccelForge, which improves upon existing accelerator modeling frameworks in capabilities, speed, and ease-of-use and includes fast mappers that enable accurate evaluation in orders of magnitude less (computer and human) time.
Campaign diagrams reveal that reducing operational intensity can paradoxically enhance performance, challenging conventional optimization strategies.
Forget brute-force search: a new mapper finds provably optimal accelerator mappings with fusion for Transformers over 1000x faster.
Find optimal DNN accelerator mappings in under a minute, something previously impossible, and expose the suboptimality of prior mapping heuristics.
