Zobrazeno 1 - 6
of 6
pro vyhledávání: '"D. Anoushe Jamshidi"'
Autor:
Jonathan Bailey, Trevor Mudge, Scott Mahlke, Jonathan Beaumont, John Kloosterman, D. Anoushe Jamshidi
Publikováno v:
MICRO
The register file is one of the largest and most power-hungry structures in a Graphics Processing Unit (GPU), because massive multithreading requires all the register state for every active thread to be available. Previous approaches to making regist
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::77bf66081f346a3a2c4c72e3b70f6098
https://doi.org/10.1145/3123939.3123974
https://doi.org/10.1145/3123939.3123974
Publikováno v:
ACM Transactions on Computer Systems. 32:1-29
Approximate computing, where computation accuracy is traded off for better performance or higher data throughput, is one solution that can help data processing keep pace with the current and growing abundance of information. For particular domains, s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c530dc91d34f8d57c0e2caca206ac87c
https://doi.org/10.1145/2631913
https://doi.org/10.1145/2631913
Publikováno v:
HPCA
With the prevalence of GPUs as throughput engines for data parallel workloads, the landscape of GPU computing is changing significantly. Non-graphics workloads with high memory intensity and irregular access patterns are frequently targeted for accel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8432d5108c4e63297c571a939946ea9b
https://doi.org/10.1109/hpca.2015.7056031
https://doi.org/10.1109/hpca.2015.7056031
Publikováno v:
PACT
To achieve high performance on many-core architectures like GPUs, it is crucial to efficiently utilize the available memory bandwidth. Currently, it is common to use fast, on-chip scratchpad memories, like the shared memory available on GPUs' shader
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::045a80629d537f596b745f1828a1fb7d
https://doi.org/10.1145/2628071.2628072
https://doi.org/10.1145/2628071.2628072
Publikováno v:
MICRO
Approximate computing, where computation accuracy is traded off for better performance or higher data throughput, is one solution that can help data processing keep pace with the current and growing overabundance of information. For particular domain
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::450af0fbaccababa8d83bdbb7b4c93db
https://doi.org/10.1145/2540708.2540711
https://doi.org/10.1145/2540708.2540711
Conference
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.