Title | ||
---|---|---|
In-Package Domain-Specific ASICs for Intel® Stratix® 10 FPGAs: A Case Study of Accelerating Deep Learning Using TensorTile ASIC |
Abstract | ||
---|---|---|
FPGAs or ASICs? FPGAs are extremely flexible while ASICs offer top efficiency. We believe that FPGAs and ASICs are better together, to offer flexibility and efficiency. We propose single-package heterogeneous 2.5D integration of FPGAs and ASICs, using Intel's Embedded Multi-Die Interconnect Bridge (EMIB). Since the ASICs are separate chips from the FPGA, this approach (1) does not change FPGA fabric, allowing re-use of existing ecosystems (FPGA chips, packaging, boards, software), and (2) allows freedom in ASIC design (area/freq/process/etc unconstrained by FPGA fabric). Intel® Stratix® 10 FPGAs already have EMIBs, enabling single-package integration with other chips, or “tiles”. We propose leveraging them to mix-and-match any domain-specific ASICs with Stratix10 FPGAs. In particular, this work focuses on deep learning (DL) domain, which demands efficient tensor (matrix/vector) operations. We propose TensorTile ASICs for Stratix10 FPGAs to provide ASIC-level tensor performance, while relying on FPGA's flexibility for application-specific operations (e.g., Winograd). Our evaluation shows: (1) a small TensorTile offer much better tensor throughput than a large Stratix102800 FPGA; (2) FPGAs and TensorTiles mix-and-match provide scalable solutions (e.g., ~69 peak INT8 TOPs with 1×TensorTile+small Stratix10-400 FPGA, to ~194 peak FP16 TOPs with 6×TensorTiles+large Stratix10-2800); (3) AlexNet performance (performance/Watt) of Intel's DL FPGA design improved by 4× (3.3×) when enhanced with 2×TensorTiles. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/FPL.2018.00027 | 2018 28th International Conference on Field Programmable Logic and Applications (FPL) |
Keywords | DocType | ISSN |
Deep learning,system in package,architecture,accelerator | Conference | 1946-147X |
ISBN | Citations | PageRank |
978-1-5386-8518-1 | 0 | 0.34 |
References | Authors | |
3 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Eriko Nurvitadhi | 1 | 399 | 33.08 |
Jeffrey J. Cook | 2 | 110 | 7.45 |
Asit K. Mishra | 3 | 1216 | 46.21 |
Debbie Marr | 4 | 175 | 12.39 |
Kevin Nealis | 5 | 4 | 1.74 |
philip colangelo | 6 | 10 | 4.58 |
Andrew C. Ling | 7 | 150 | 12.10 |
Davor Capalija | 8 | 130 | 9.33 |
Utku Aydonat | 9 | 170 | 9.98 |
Aravind Dasu | 10 | 10 | 4.47 |
Sergey Shumarayev | 11 | 0 | 1.35 |