×
Jul 22, 2019 · We propose PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from Instruction Set Architecture to high-level ...
We propose PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from instruction set architecture to high-level language compiler.
PROMISE achieves 2.3× delay and 4.5× energy savings, and 14% additional energy savings with compiler optimization, on average for diverse ML algorithms as ...
This work proposes PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from Instruction Set Architecture to high-level language ...
Sep 1, 2019 · We propose PROMISE, the first end-to-end design of a PROgrammable MIxed-Signal accElerator from Instruction Set Architecture to high-level ...
This course aims to teach students how to design machine learning algorithms in chips directly, which mainly focuses on circuit and system implementations [8] .
Kang, M, Srivastava, P, Adve, V, Kim, N, and Shanbhag, N. "An energy-efficient programmable mixed-signal accelerator for machine learning algorithms". IEEE ...
Jul 6, 2020 · We introduce ''aCortex,'' an extremely energy-efficient, fast, compact, and versatile neuro- morphic processor architecture suitable for the ...
Jul 19, 2018 · Our experiments show that PROMISE can accelerate diverse ML algorithms with energy efficiency competitive even with fixed-function digital ASICs ...
People also ask
Our experiments show that PROMISE can accelerate diverse ML algorithms with energy efficiency competitive to fixed-function digital ASICs for specific ML.