Inter-Layer Scheduling Space Exploration for Multi-model Inference on Heterogeneous Chiplets
(2312.09401)Abstract
To address increasing compute demand from recent multi-model workloads with heavy models like LLMs, we propose to deploy heterogeneous chiplet-based multi-chip module (MCM)-based accelerators. We develop an advanced scheduling framework for heterogeneous MCM accelerators that comprehensively consider complex heterogeneity and inter-chiplet pipelining. Our experiments using our framework on GPT-2 and ResNet-50 models on a 4-chiplet system have shown upto 2.2x and 1.9x increase in throughput and energy efficiency, compared to a monolithic accelerator with an optimized output-stationary dataflow.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.