HePGA: A Heterogeneous Processing-in-Memory based GNN Training Accelerator
By: Chukwufumnanya Ogbogu , Gaurav Narang , Biresh Kumar Joardar and more
Potential Business Impact:
Makes computers learn faster and use less power.
Processing-In-Memory (PIM) architectures offer a promising approach to accelerate Graph Neural Network (GNN) training and inference. However, various PIM devices such as ReRAM, FeFET, PCM, MRAM, and SRAM exist, with each device offering unique trade-offs in terms of power, latency, area, and non-idealities. A heterogeneous manycore architecture enabled by 3D integration can combine multiple PIM devices on a single platform, to enable energy-efficient and high-performance GNN training. In this work, we propose a 3D heterogeneous PIM-based accelerator for GNN training referred to as HePGA. We leverage the unique characteristics of GNN layers and associated computing kernels to optimize their mapping on to different PIM devices as well as planar tiers. Our experimental analysis shows that HePGA outperforms existing PIM-based architectures by up to 3.8x and 6.8x in energy-efficiency (TOPS/W) and compute efficiency (TOPS/mm2) respectively, without sacrificing the GNN prediction accuracy. Finally, we demonstrate the applicability of HePGA to accelerate inferencing of emerging transformer models.
Similar Papers
HH-PIM: Dynamic Optimization of Power and Performance with Heterogeneous-Hybrid PIM for Edge AI Devices
Hardware Architecture
Saves energy for smart devices doing AI.
HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference
Hardware Architecture
Makes AI models run much faster and use less power.
HPIM: Heterogeneous Processing-In-Memory-based Accelerator for Large Language Models Inference
Hardware Architecture
Makes AI understand words much faster.