.png){kind=icon}
.png){kind=icon}
Return
LRMP: Layer Replication with Mixed Precision for spatial in-memory DNN accelerators
.png){kind=icon}
OA
AI
DOI：10.3389/frai.2024.1268317.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In-memory computing (IMC) with non-volatile memories (NVMs) has emerged as a promising approach to address the rapidly growing computational demands of Deep Neural Networks (DNNs). Mapping DNN layers spatially onto NVM-based IMC accelerators achieves high degrees of parallelism. However, two challenges that arise in this approach are the highly non-uniform distribution of layer processing times and high area requirements. We propose LRMP, a method to jointly apply layer replication and mixed precision quantization to improve the performance of DNNs when mapped to area-constrained IMC accelerators. LRMP uses a combination of reinforcement learning and mixed integer linear programming to search the replication-quantization design space using a model that is closely informed by the target hardware architecture. Across five DNN benchmarks, LRMP achieves 2.6-9.3x latency and 8-18x throughput improvement at minimal (<1%) degradation in accuracy.
Keywords:
in-memory computing
analog accelerator
quantization
reinforcement learning
mixed integer linear programming
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
F
IF:
4.7
Papers:
2.4K
Citations:
4.4K
