5 papers
PerfReasoning: How Well Do LLMs Reason on Hardware Performance?
Dan Zhao, Karthikeyan Sankaralingam, Christos Kozyrakis +1
Performance modeling is central to hardware design and software optimization, yet constructing these models requires structured reasoning about computation, data reuse, storage, an…
Ave: Guiding Agentic GPU Optimization Using Data-Flow Invariants
Haohui Mai, Xiaoyan Guo, Xiangyun Ding +7
LLM coding agents can generate correct GPU kernels, but their performance still trails expert libraries. Reaching peak throughput requires coordinating low-level optimizations such…
Improving Efficiency of GPU Kernel Optimization Agents using a Domain-Specific Language and Speed-of-Light Guidance
Siva Kumar Sastry Hari, Vignesh Balaji, Sana Damani +2
Optimizing GPU kernels with LLM agents is an iterative process over a large design space. Every candidate must be generated, compiled, validated, and profiled, so fewer trials will…
LIMINAL: Exploring The Frontiers of LLM Decode Performance
Michael Davies, Neal Crago, Karthikeyan Sankaralingam +1
The rapid advancement of Large Language Models (LLMs) necessitates a deep understanding of their fundamental performance limits. This paper investigates the limits of LLM inference…
Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
Vignesh Balaji, Christos Kozyrakis, Gal Chechik +1
Graph Neural Networks (GNNs) enable learning on realworld graphs and mini-batch training has emerged as the de facto standard for training GNNs because it can scale to very large g…