ICLDisco/parsec
PaRSEC is a generic framework for architecture aware scheduling and management of micro-tasks on distributed, GPU accelerated, many-core heterogeneous architectures. PaRSEC assigns computation threads to the cores, GPU accelerators, overlaps communications and computations and uses a dynamic, fully-distributed scheduler based on architectural features such as NUMA nodes and algorithmic features such as data reuse.
CNOASSERTION
Stargazers
- 3ravCracow
- abel0bVoie lactée
- abouteillerICL, University of Tennessee
- ajay-mkVirginia Tech
- anyin233Hefei,Anhui China
- bosilcaNVidia
- cheng-hsiang-chiuUniversity of Wisconsin
- davidbrownellAtlanta, GA
- dian-lun-linIntel Labs
- edwardnjust
- greecket
- hartwiganztUniversity of Tennessee
- hyviquelUNICAMP
- jsboerChinese Academy of Sciences University
- Julius-Plehn
- learning-chip
- lwshanbdStony Brook University
- lzanottoParallel Bits
- LZengHui
- milthorpeAustralian National University
- QingleiCao
- qiujiyan
- shriram-jaganBay Area
- sinainnet
- SyamVangaraMcGill University
- thomasgillis@NVIDIA
- tsung-wei-huangDepartment of ECE, University of Wisconsin at Madison
- twinroot
- ultimatileISSP, UTokyo
- v0droFujitsu Research, Japan
- WaldonChenHefei, Anhui, China
- wpybtwMSRA
- wu-kanSun Yat-sen University
- wxbbuaa2011UCAS
- yu-pei
- zhangpan1992hangzhou