Inter-Layer Scheduling Space Exploration for Multi-model Inference on Heterogeneous Chiplets
By Mohanad Odema, Hyoukjun Kwon, Mohammad Abdullah Al Faruque (University of California)
To address increasing compute demand from recent multi-model workloads with heavy models like large language models, 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.
To read the full article, click here
Related Chiplet
- Integrated voltage regulator (IVR) chiplet
- High-performance connectivity chiplets
- eFPGA Chiplet
- DPIQ Tx PICs
- IMDD Tx PICs
Related Technical Papers
- SCAR: Scheduling Multi-Model AI Workloads on Heterogeneous Multi-Chiplet Module Accelerators
- Compass: Mapping Space Exploration for Multi-Chiplet Accelerators Targeting LLM Inference Serving Workloads
- Mapping Space Exploration for Multi-Chiplet Accelerators Targeting LLM Inference Serving Workloads
- Chiplets Are The New Baseline for AI Inference Chips
Latest Technical Papers
- DICE: Detailed Inter-Chiplet End-to-End PHY Modeling for Accurate Chiplet Simulation
- APEX: an Adaptive Photonic-Electronic Chiplet Interconnection Architecture for DNN Inference
- Formal Foundations for Known Good Reliable Die Screening in Chiplet-Based AI Systems-on-Chip
- Optimization of Test-Access Architectures and Test Scheduling for 2.5D/3D Integration
- Learning to Place Chiplets: A Multi-Objective Reinforcement Learning Approach