OuterSPACE: An Outer Product Based Sparse Matrix Multiplication Accelerator

By S. Pal, Jonathan Beaumont, Dong-hyeon Park, Aporva Amarnath, Siying Feng, C. Chakrabarti, Hun-Seok Kim, David T. Blaauw, T. Mudge, Ronald Dreslinski Jr.. International Symposium on High-Performance Computer Architecture, 2018

319 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/061edcbe54d23e6c8688525503ebc643c30d44a0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Song Han
2. Tushar Krishna
3. Zhekai Zhang
4. Hanrui Wang

In Computer Vision and Pattern Recognition

1. Song Han
2. Tushar Krishna
3. Hanrui Wang
4. Hyoukjun Kwon
5. Zhekai Zhang
6. Dipankar Das
7. Bharat Kaul
8. A. Samajdar

In Hardware and Architecture

1. Song Han
2. Tushar Krishna
3. Zhekai Zhang
4. Hanrui Wang

Citations in the corpus

• AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing (2019, unknown): “Pal [54] proposes an outer-product-based SpMM architecture.”
• SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning (2020, background): “However, it is not friendly to CPUs and GPUs and requires dedicated hardware [23], [24] to support sparse matrix multiplication, which may consume extra efforts for design”
• SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training (2020, methodology): “We compare SIGMA against other state-of-the-art accelerators: TPU [4], EIE [19], SCNN [33], OuterSPACE [32], Eyeriss v2 [11], Packed Systolic [26], and Cambricon-X [47].”