Exploiting Native Hardware Heterogeneity: Custom GPSIMD Operators for Accelerating Emerging LLM Memory on AWS Trainium
cs.DC
Submitted: 2026-11-09
Updated: 2026-11-09
Comments: https://github.com/OswaldHe/neuron-gpsimd-tool
Code: https://github.com/OswaldHe/neuron-gpsimd-tool
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
- Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends