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
- DPIQ Tx PICs
- IMDD Tx PICs
- Near-Packaged Optics (NPO) Chiplet Solution
- High Performance Droplet
- Interconnect Chiplet
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
- Mapping Space Exploration for Multi-Chiplet Accelerators Targeting LLM Inference Serving Workloads
- Escaping Flatland: A Placement Flow for Enabling 3D FPGAs
- 3D optoelectronics and co-packaged optics: when solving the wrong problems stalls deployment
- Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling
- WarPGNN: A Parametric Thermal Warpage Analysis Framework with Physics-aware Graph Neural Network