AxPIKE: instruction-level injection and evaluation of approximate computing
Representing the interaction between accurate and approximate hardware modules at the architecture level is essential to understand the impact of Approximate Computing in a general-purpose computing scenario. However, extensive effort is required to model approximations into a baseline instruction-l...
| Principais autores: | Felzmann, Isaías Bittencourt, Fabrício Filho, João, Wanner, Lucas Francisco |
|---|---|
| Formato: | Trabalho Apresentado em Evento |
| Idioma: | Inglês |
| Publicado em: |
Campo Mourao
2022
|
| Assuntos: | |
| Acesso em linha: |
http://repositorio.utfpr.edu.br/jspui/handle/1/29756 |
| Tags: |
Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
|
| id |
riut-1-29756 |
|---|---|
| recordtype |
dspace |
| spelling |
riut-1-297562022-09-28T06:07:15Z AxPIKE: instruction-level injection and evaluation of approximate computing Felzmann, Isaías Bittencourt Fabrício Filho, João Wanner, Lucas Francisco Teoria da aproximação Arquitetura de computador Simulação (Computadores) Sistema de memória de computadores Approximation theory Computer architecture Computer simulation Computer storage devices CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Representing the interaction between accurate and approximate hardware modules at the architecture level is essential to understand the impact of Approximate Computing in a general-purpose computing scenario. However, extensive effort is required to model approximations into a baseline instruction-level simulator and collect its execution metrics. In this work, we present the AxPIKE ISA simulation environment, a tool that allows designers to inject models of hardware approximation at the instruction level and evaluate their impact on the quality of results. AxPIKE embeds a high-level representation of a RISC-V system and produces a dedicated control mechanism, that allows the simulated software to manage the approximate behavior of compatible execution scenarios. The environment also provides detailed execution statistics that are forwarded to dedicated tools for energy accounting. We apply the AxPIKE environment to inject integer multiplication and memory access approximations into different applications and demonstrate how the generated statistics are translated into energy-quality trade-offs. 2022-09-27T17:04:52Z 5000 2022-09-27T17:04:52Z 2021-02-01 conferenceObject FELZMANN, Isaías; FABRÍCIO FILHO, João; WANNER, Lucas. AxPIKE: instruction-level injection and evaluation of approximate computing. In: DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION, 2021, Grenoble. Anais eletrônicos […]. Piscataway: IEEE Operations Center, 2021. p. 491-494. DOI: 10.23919/DATE51398.2021.9474258. Disponível em: https://ieeexplore.ieee.org/document/9474258. Acesso em: 27 jun. 2022. http://repositorio.utfpr.edu.br/jspui/handle/1/29756 DOI: 10.23919/DATE51398.2021.9474258 eng Design, Automation & Test in Europe Conference & Exhibition https://ieeexplore.ieee.org/document/9474258 embargoedAccess https://ieeexplore.ieee.org/document/9474055 application/pdf Campo Mourao Estados unidos |
| institution |
Universidade Tecnológica Federal do Paraná |
| collection |
RIUT |
| language |
Inglês |
| topic |
Teoria da aproximação Arquitetura de computador Simulação (Computadores) Sistema de memória de computadores Approximation theory Computer architecture Computer simulation Computer storage devices CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
| spellingShingle |
Teoria da aproximação Arquitetura de computador Simulação (Computadores) Sistema de memória de computadores Approximation theory Computer architecture Computer simulation Computer storage devices CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Felzmann, Isaías Bittencourt Fabrício Filho, João Wanner, Lucas Francisco AxPIKE: instruction-level injection and evaluation of approximate computing |
| description |
Representing the interaction between accurate and approximate hardware modules at the architecture level is essential to understand the impact of Approximate Computing in a general-purpose computing scenario. However, extensive effort is required to model approximations into a baseline instruction-level simulator and collect its execution metrics. In this work, we present the AxPIKE ISA simulation environment, a tool that allows designers to inject models of hardware approximation at the instruction level and evaluate their impact on the quality of results. AxPIKE embeds a high-level representation of a RISC-V system and produces a dedicated control mechanism, that allows the simulated software to manage the approximate behavior of compatible execution scenarios. The environment also provides detailed execution statistics that are forwarded to dedicated tools for energy accounting. We apply the AxPIKE environment to inject integer multiplication and memory access approximations into different applications and demonstrate how the generated statistics are translated into energy-quality trade-offs. |
| format |
Trabalho Apresentado em Evento |
| author |
Felzmann, Isaías Bittencourt Fabrício Filho, João Wanner, Lucas Francisco |
| author_sort |
Felzmann, Isaías Bittencourt |
| title |
AxPIKE: instruction-level injection and evaluation of approximate computing |
| title_short |
AxPIKE: instruction-level injection and evaluation of approximate computing |
| title_full |
AxPIKE: instruction-level injection and evaluation of approximate computing |
| title_fullStr |
AxPIKE: instruction-level injection and evaluation of approximate computing |
| title_full_unstemmed |
AxPIKE: instruction-level injection and evaluation of approximate computing |
| title_sort |
axpike: instruction-level injection and evaluation of approximate computing |
| publisher |
Campo Mourao |
| publishDate |
2022 |
| citation |
FELZMANN, Isaías; FABRÍCIO FILHO, João; WANNER, Lucas. AxPIKE: instruction-level injection and evaluation of approximate computing. In: DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION, 2021, Grenoble. Anais eletrônicos […]. Piscataway: IEEE Operations Center, 2021. p. 491-494. DOI: 10.23919/DATE51398.2021.9474258. Disponível em: https://ieeexplore.ieee.org/document/9474258. Acesso em: 27 jun. 2022. DOI: 10.23919/DATE51398.2021.9474258 |
| url |
http://repositorio.utfpr.edu.br/jspui/handle/1/29756 |
| _version_ |
1805313929582215168 |
| score |
10,814766 |