Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912296468> ?p ?o ?g. }
- W2912296468 abstract "The increasing deployment of machine learning at the core and at the edge for applications such as video and image recognition has resulted in a number of special purpose accelerators in this domain. However, these accelerators do not have full end-to-end software stacks for application development, resulting in hard-to-develop, proprietary, and suboptimal application programming and executables. In this paper, we describe software stack for a memristor-based hybrid (analog-digital)accelerator. The software stack consists of an ONNX converter, an application optimizer, a compiler, a driver, and emulators. The ONNX converter helps leveraging interoperable neural network models developed on frameworks that support ONNX, such as CNTK, Caffe2, Tensorflow, etc. The application optimization layer adapts these interoperable models to the underlying hardware. The compiler generates executable ISA code that the underlying accelerator can run. Finally, the emulator enables software execution without actual hardware which enables hardware design space exploration and testing. By building a software stack, we have made hybrid memristor-based ML accelerators more accessible to software developers, enabled a generation of better-performing executables, and created an environment that can be leveraged by a multitude of existing neural network models developed using other frameworks to target these accelerators." @default.
- W2912296468 created "2019-02-21" @default.
- W2912296468 creator A5008006179 @default.
- W2912296468 creator A5011784910 @default.
- W2912296468 creator A5018184559 @default.
- W2912296468 creator A5027761275 @default.
- W2912296468 creator A5031161187 @default.
- W2912296468 creator A5032194210 @default.
- W2912296468 creator A5033256912 @default.
- W2912296468 creator A5040404999 @default.
- W2912296468 creator A5040764379 @default.
- W2912296468 creator A5044397100 @default.
- W2912296468 creator A5050532440 @default.
- W2912296468 creator A5053494447 @default.
- W2912296468 creator A5062040311 @default.
- W2912296468 creator A5063931533 @default.
- W2912296468 creator A5065364179 @default.
- W2912296468 creator A5066655033 @default.
- W2912296468 creator A5071889037 @default.
- W2912296468 creator A5076404852 @default.
- W2912296468 creator A5079257666 @default.
- W2912296468 creator A5089206756 @default.
- W2912296468 date "2018-11-01" @default.
- W2912296468 modified "2023-10-17" @default.
- W2912296468 title "Hardware-Software Co-Design for an Analog-Digital Accelerator for Machine Learning" @default.
- W2912296468 cites W1542981317 @default.
- W2912296468 cites W1937359183 @default.
- W2912296468 cites W1968422655 @default.
- W2912296468 cites W1975253511 @default.
- W2912296468 cites W1976075132 @default.
- W2912296468 cites W1980446076 @default.
- W2912296468 cites W1983899098 @default.
- W2912296468 cites W1985587891 @default.
- W2912296468 cites W1989210237 @default.
- W2912296468 cites W1990315422 @default.
- W2912296468 cites W2000057358 @default.
- W2912296468 cites W2000967104 @default.
- W2912296468 cites W2009832130 @default.
- W2912296468 cites W2011992756 @default.
- W2912296468 cites W2012582094 @default.
- W2912296468 cites W2016543087 @default.
- W2912296468 cites W2041135949 @default.
- W2912296468 cites W2044535169 @default.
- W2912296468 cites W2048266589 @default.
- W2912296468 cites W2060969833 @default.
- W2912296468 cites W2062258233 @default.
- W2912296468 cites W2067523571 @default.
- W2912296468 cites W2070167224 @default.
- W2912296468 cites W2081907608 @default.
- W2912296468 cites W2092473657 @default.
- W2912296468 cites W2094037053 @default.
- W2912296468 cites W2094756095 @default.
- W2912296468 cites W2096645269 @default.
- W2912296468 cites W2113637091 @default.
- W2912296468 cites W2117489143 @default.
- W2912296468 cites W2117696986 @default.
- W2912296468 cites W2119068918 @default.
- W2912296468 cites W2123522925 @default.
- W2912296468 cites W2142801765 @default.
- W2912296468 cites W2150662965 @default.
- W2912296468 cites W2151394745 @default.
- W2912296468 cites W2152839228 @default.
- W2912296468 cites W2155954834 @default.
- W2912296468 cites W2169256034 @default.
- W2912296468 cites W2243109068 @default.
- W2912296468 cites W2261808795 @default.
- W2912296468 cites W2285660444 @default.
- W2912296468 cites W2325681100 @default.
- W2912296468 cites W2331737637 @default.
- W2912296468 cites W2396572963 @default.
- W2912296468 cites W2399948372 @default.
- W2912296468 cites W2402098947 @default.
- W2912296468 cites W2466675884 @default.
- W2912296468 cites W2489529491 @default.
- W2912296468 cites W2508576555 @default.
- W2912296468 cites W2508602506 @default.
- W2912296468 cites W2513554817 @default.
- W2912296468 cites W2515287984 @default.
- W2912296468 cites W2516141709 @default.
- W2912296468 cites W2518281301 @default.
- W2912296468 cites W2538785949 @default.
- W2912296468 cites W2541839172 @default.
- W2912296468 cites W2551814622 @default.
- W2912296468 cites W2555835123 @default.
- W2912296468 cites W2565805458 @default.
- W2912296468 cites W2585407525 @default.
- W2912296468 cites W2591675147 @default.
- W2912296468 cites W2604319603 @default.
- W2912296468 cites W2605347906 @default.
- W2912296468 cites W2606722458 @default.
- W2912296468 cites W2613989746 @default.
- W2912296468 cites W2625222559 @default.
- W2912296468 cites W2625457103 @default.
- W2912296468 cites W2626991402 @default.
- W2912296468 cites W2627034335 @default.
- W2912296468 cites W2743826728 @default.
- W2912296468 cites W2765234579 @default.
- W2912296468 cites W2766138099 @default.
- W2912296468 cites W2771276626 @default.
- W2912296468 cites W2782791387 @default.