GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent
This work addresses efficiency issues in DNN training for hardware and AI practitioners, but it is incremental as it builds on existing processing-in-memory techniques.
The paper tackles the problem of accelerating deep neural network training by proposing GradPIM, a processing-in-memory architecture that improves performance and reduces memory bandwidth requirements, with minimal overhead to existing protocols and DRAM area.
In this paper, we present GradPIM, a processing-in-memory architecture which accelerates parameter updates of deep neural networks training. As one of processing-in-memory techniques that could be realized in the near future, we propose an incremental, simple architectural design that does not invade the existing memory protocol. Extending DDR4 SDRAM to utilize bank-group parallelism makes our operation designs in processing-in-memory (PIM) module efficient in terms of hardware cost and performance. Our experimental results show that the proposed architecture can improve the performance of DNN training and greatly reduce memory bandwidth requirement while posing only a minimal amount of overhead to the protocol and DRAM area.