TY  - CONF
AU  - John, Chelsea Maria
AU  - Herten, Andreas
AU  - Penke, Carolin
AU  - Nassyr, Stepan
TI  - Performance and Power: Systematic Evaluation of AI Workloads on Accelerators with CARAML
M1  - FZJ-2024-06447
SP  - Nan
PY  - 2024
N1  - Also available at: https://arxiv.org/abs/2409.12994
AB  - The rapid advancement of machine learning (ML) technologies has driven the development of specialized hardware accelerators designed to facilitate more efficient model training. This paper introduces the CARAML benchmark suite, which is employed to assess performance and energy consumption during the training of transformer-based large language models and computer vision models on a range of hardware accelerators, including systems from NVIDIA, AMD, and Graphcore. CARAML provides a compact, automated, extensible, and reproducible framework for assessing the performance and energy of ML workloads across various novel hardware architectures. The design and implementation of CARAML, along with a custom power measurement tool called jpwr, are discussed in detail.
T2  - Supercomputing Conference 2024, 2024 International Workshop on Performance, Portability, and Productivity in HPC
CY  - 17 Nov 2024 - 22 Nov 2024, Atlanta (USA)
Y2  - 17 Nov 2024 - 22 Nov 2024
M2  - Atlanta, USA
LB  - PUB:(DE-HGF)8
UR  - <Go to ISI:>//WOS:001451792300127
DO  - DOI:10.1109/SCW63240.2024.00158
UR  - https://juser.fz-juelich.de/record/1033567
ER  -