DGX-A100 Face to Face DGX-2-Performance, Power and Thermal Behavior Evaluation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27740%2F21%3A10247602" target="_blank" >RIV/61989100:27740/21:10247602 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.mdpi.com/1996-1073/14/2/376" target="_blank" >https://www.mdpi.com/1996-1073/14/2/376</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/en14020376" target="_blank" >10.3390/en14020376</a>

Jazyk výsledku

angličtina

Název v původním jazyce

DGX-A100 Face to Face DGX-2-Performance, Power and Thermal Behavior Evaluation

Popis výsledku v původním jazyce

Nvidia is a leading producer of GPUs for high-performance computing and artificial intelligence, bringing top performance and energy-efficiency. We present performance, power consumption, and thermal behavior analysis of the new Nvidia DGX-A100 server equipped with eight A100 Ampere microarchitecture GPUs. The results are compared against the previous generation of the server, Nvidia DGX-2, based on Tesla V100 GPUs. We developed a synthetic benchmark to measure the raw performance of floating-point computing units including Tensor Cores. Furthermore, thermal stability was investigated. In addition, Dynamic Frequency and Voltage Scaling (DVFS) analysis was performed to determine the best energy-efficient configuration of the GPUs executing workloads of various arithmetical intensities. Under the energy-optimal configuration the A100 GPU reaches efficiency of 51 GFLOPS/W for double-precision workload and 91 GFLOPS/W for tensor core double precision workload, which makes the A100 the most energy-efficient server accelerator for scientific simulations in the market.

Název v anglickém jazyce

DGX-A100 Face to Face DGX-2-Performance, Power and Thermal Behavior Evaluation

Popis výsledku anglicky

Nvidia is a leading producer of GPUs for high-performance computing and artificial intelligence, bringing top performance and energy-efficiency. We present performance, power consumption, and thermal behavior analysis of the new Nvidia DGX-A100 server equipped with eight A100 Ampere microarchitecture GPUs. The results are compared against the previous generation of the server, Nvidia DGX-2, based on Tesla V100 GPUs. We developed a synthetic benchmark to measure the raw performance of floating-point computing units including Tensor Cores. Furthermore, thermal stability was investigated. In addition, Dynamic Frequency and Voltage Scaling (DVFS) analysis was performed to determine the best energy-efficient configuration of the GPUs executing workloads of various arithmetical intensities. Under the energy-optimal configuration the A100 GPU reaches efficiency of 51 GFLOPS/W for double-precision workload and 91 GFLOPS/W for tensor core double precision workload, which makes the A100 the most energy-efficient server accelerator for scientific simulations in the market.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LM2018140" target="_blank" >LM2018140: e-Infrastruktura CZ</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Energies

ISSN

1996-1073

e-ISSN

—

Svazek periodika

14

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

18

Strana od-do

—

Kód UT WoS článku

000611196800001

EID výsledku v databázi Scopus

2-s2.0-85107118476