Name
Abstract | ||
|---|---|---|
Compute in-memory (CIM) is a promising technique that minimizes data transport, the primary performance bottleneck and energy cost of most data intensive applications. This has found wide-spread adoption in accelerating neural networks for machine learning applications. Utilizing a crossbar architecture with emerging non-volatile memories (eNVM) such as dense resistive random access memory (RRAM) or phase change random access memory (PCRAM), various forms of neural networks can be implemented to greatly reduce power and increase on chip memory capacity. However, compute in-memory faces its own limitations at both the circuit and the device levels. Although compute in-memory using the crossbar architecture can greatly reduce data transport, the rigid nature of these large fixed weight matrices forfeits the flexibility of traditional CMOS and SRAM based designs. In this work, we explore the different synchronization barriers that occur from the CIM constraints. Furthermore, we propose a new allocation algorithm and data flow based on input data distributions to maximize utilization and performance for compute-in memory based designs. We demonstrate a 7.47× performance improvement over a naive allocation method for CIM accelerators on ResNet18. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/VLSI-SOC46417.2020.9344086 | 2020 IFIP/IEEE 28th International Conference on Very Large Scale Integration (VLSI-SOC) |
Keywords | DocType | ISSN |
crossbar architecture,allocation algorithm,data flow,input data distributions,array utilization,compute in-memory fabrics,data transport,energy cost,data intensive applications,neural networks,machine learning applications,nonvolatile memories,phase change random access memory,chip memory capacity,SRAM based designs | Conference | 2324-8432 |
ISBN | Citations | PageRank |
978-1-7281-5410-7 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Brian Crafton | 1 | 0 | 0.34 |
| Samuel Spetalnick | 2 | 0 | 0.34 |
| Gauthaman Murali | 3 | 4 | 3.27 |
| Tushar Krishna | 4 | 1864 | 86.95 |
| Sung Kyu Lim | 5 | 1688 | 168.71 |
| Arijit Raychowdhury | 6 | 284 | 48.04 |