5 papers
Precision As You Need: Stochastic Computing Is a Dense Adaptive Quantizer
Haoran Jin, Kangqi Zhang, Jirong Yang +4
Matrix multiplications dominate the inference cost of modern transformer-based vision models, yet existing efficiency techniques such as post-training quantization and mixed-precis…
Fengshui: Demystifying Chiplet Ecosystem and Bespoke Neural Network Accelerator Codesign
Haoran Jin, Jirong Yang, Zhiheng Zhang +5
Modern ML workloads, with stringent latency and energy constraints, are increasingly hard to run efficiently on homogeneous commodity hardware. We argue that operator-level disaggr…
Rethinking Agentic Kernel Generation for Emerging Accelerators
Ruijie Gao, Jirong Yang, Barry Lyu +2
Emerging accelerators often lack mature compiler backends, motivating neural agents that generate and repair kernels from architectural documentation and simulator feedback. This a…
Opus: Photonic Rail-Optimized Fabric in ML Datacenters
Eric Ding, Barry Lyu, Bhaskar Kataria +1
Rail-optimized network fabrics have become the de facto datacenter scale-out fabric for large-scale ML training. However, the use of high-radix electrical switches to provide all-t…
Mozart: A Chiplet Ecosystem-Accelerator Codesign Framework for Composable Bespoke Application Specific Integrated Circuits
Haoran Jin, Jirong Yang, Yunpeng Liu +3
Modern AI acceleration faces a fundamental challenge: conventional assumptions about memory requirements, batching effectiveness, and latency-throughput tradeoffs are systemwide ge…