Zobrazeno 1 - 10
of 221
pro vyhledávání: '"Scalar processor"'
Vectorizing compilers employ divergence analysis to detect at which program point a specific variable is uniform, i.e. has the same value on all SPMD threads that execute this program point. They exploit uniformity to retain branching to counter bran
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::761954afd500d5ca31d9f535c6d84dfc
Autor:
Jean-Frederic Christmann, Bastien Giraud, Subhasish Mitra, Lorenzo Ciampolini, Maha Kooli, Henri-Pierre Charles, F. Lepin, Pascal Vivet, M. Diallo, R. Gauchi, J.-P. Noel, B. Blampey, M. Pezzin
Publikováno v:
IEEE Solid-State Circuits Letters. 3:286-289
In the context of highly data-centric applications, close reconciliation of computation and storage should significantly reduce the energy-consuming process of data movement. This letter proposes a computational SRAM (C-SRAM) combining in- and near-m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e18d4a44928a4c355c4854ff31297ae3
https://doi.org/10.1109/lssc.2020.3010377
https://doi.org/10.1109/lssc.2020.3010377
Autor:
John Wright, Krste Asanovic, Borivoje Nikolic, Colin Schmidt, Ben Keller, Jerry Zhao, Alon Amid, Jarno Salomaa, Albert Ou, Howard Mao, Keertana Settaluri
Publikováno v:
IEEE Solid-State Circuits Letters. 3:210-213
This letter presents a RISC-V System-on-Chip (SoC) with fully integrated switched-capacitor DC–DC converters, adaptive clock generators, mixed-precision floating-point vector accelerators, a 5-Gb/s serial memory interface, and an integrated power m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85bd1c0dc9d1c1380db594cc4e6d908c
https://doi.org/10.1109/lssc.2020.3010295
https://doi.org/10.1109/lssc.2020.3010295
Publikováno v:
ISSCC
The Hexagon™ compute DSP (CDSP) integrates a master VLIW scalar processor and a slave vector coprocessor to enable high-performance and energy-efficient computing for multimedia, voice, audio, vision, imaging, and machine-learning (ML) applications
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4056805b1ea14c34a674962673152043
https://doi.org/10.1109/isscc42613.2021.9366001
https://doi.org/10.1109/isscc42613.2021.9366001
Publikováno v:
DDECS
2020 23rd International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS)
2020 23rd International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS)
In the past, in most General-Purpose Graphic Processing Units (GPGPUs) application fields (e.g., multimedia and gaming), the reliability features were not so relevant. Nowadays, GPGPUs are used in new domains, such as the automotive one, where reliab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::60d56bab69f3715da97065ed2e5cd698
https://zenodo.org/record/4545632
https://zenodo.org/record/4545632
Autor:
Henri-Pierre Charles, Pascal Vivet, R. Gauchi, Maha Kooli, V. Egloff, Bastien Giraud, J.-P. Noel, J-M. Portal
Publikováno v:
2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)
2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), Mar 2020, Grenoble, France. pp.1187-1192, ⟨10.23919/DATE48585.2020.9116506⟩
DATE
2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), Mar 2020, Grenoble, France. pp.1187-1192, ⟨10.23919/DATE48585.2020.9116506⟩
DATE
International audience; This paper presents a new methodology for automating the Computational SRAM (C-SRAM) design based on off-the-shelf memory compilers and a configurable RTL IP. The main goal is to drastically reduce the development effort compa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f228f74888e4b73e5769fbd5327fc969
https://hal-cea.archives-ouvertes.fr/cea-02889406/document
https://hal-cea.archives-ouvertes.fr/cea-02889406/document
Publikováno v:
2020 22th International Conference on Digital Signal Processing and its Applications (DSPA).
In this paper, we consider the implementation of a recurrent artificial neural network LSTM on the NM6407 digital signal processor (DSP) that is optimized for performing vector and matrix calculations. It contains two NeuroMatrix NMC4 cores, each of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f73e8b679037c0532da2a2f3c710999
https://doi.org/10.1109/dspa48919.2020.9213291
https://doi.org/10.1109/dspa48919.2020.9213291
Publikováno v:
2020 IEEE 38th VLSI Test Symposium (VTS)
VTS
VTS
General Purpose Graphic Processing Units (GPGPUs) are effective solutions for high-demanding data processing applications. Recently, they started to be used even in safety-critical applications, such as autonomous car driving systems. GPGPUs are impl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76b3d41e22f105bfc68415f3edca01cd
Autor:
Zaki Su’ud, Sunarko
Publikováno v:
Kerntechnik. 82:225-231
Lagrangian Particle Dispersion Method (LPDM) is applied to model atmospheric dispersion of radioactive material in a meso-scale of a few tens of kilometers for site study purpose. Empirical relationships are used to determine the dispersion coefficie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3a414abd0f236c87c5be045f6af4f94e
https://doi.org/10.3139/124.110646
https://doi.org/10.3139/124.110646
Autor:
Ryusuke Egawa, Shintaro Momose, Kazuhiko Komatsu, Yoko Isobe, Hiroyuki Takizawa, Akihiro Musa, Hiroaki Kobayashi
Publikováno v:
The Journal of Supercomputing. 73:3948-3976
Achieving a high sustained simulation performance is the most important concern in the HPC community. To this end, many kinds of HPC system architectures have been proposed, and the diversity of the HPC systems grows rapidly. Under this circumstance,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93acefa2912733866163b75e1c7f0df4
https://doi.org/10.1007/s11227-017-1993-y
https://doi.org/10.1007/s11227-017-1993-y