Tensor Casting: Co-Designing Algorithm-Architecture for Personalized Recommendation Training

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 37
  • Download : 0
Personalized recommendations are one of the most widely deployed machine learning (ML) workload serviced from cloud datacenters. As such, architectural solutions for high-performance recommendation inference have recently been the target of several prior literatures. Unfortunately, little have been explored and understood regarding the training side of this emerging ML workload. In this paper, we first perform a detailed workload characterization study on training recommendations, root-causing sparse embedding layer training as one of the most significant performance bottlenecks. We then propose our algorithm-Architecture co-design called Tensor Casting, which enables the development of a generic accelerator architecture for tensor gather-scatter that encompasses all the key primitives of training embedding layers. When prototyped on a real CPUGPU system, Tensor Casting provides 1.9-21 \times improvements in training throughput compared to state-of-The-Art approaches.
Publisher
IEEE Computer Society
Issue Date
2021-03-01
Language
English
Citation

The 27th IEEE International Symposium on High-Performance Computer Architecture (HPCA-27), pp.235 - 248

ISSN
1530-0897
DOI
10.1109/HPCA51647.2021.00029
URI
http://hdl.handle.net/10203/285734
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0