2 citations · 4 across the 5 of their papers we have counts for
6 papers
MegaFlux: Skew-Resilient MoE Megakernels via Pipelined Expert Replication
Jianzhu Yao, Siva Kumar Sastry Hari, Vignesh Balaji +4
Mixture-of-experts (MoE) megakernels fuse expert-parallel communication with expert computation. However, under fixed expert placement, routing skew creates GPU stragglers: overloa…
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…
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…
Neat: Low-Complexity, Efficient On-Chip Cache Coherence
Rui Zhang, Swarnendu Biswas, Vignesh Balaji +2
Cache coherence protocols such as MESI that use writer-initiated invalidation have high complexity and sometimes have poor performance and energy usage, especially under false shar…
Optimizing Graph Processing and Preprocessing with Hardware Assisted Propagation Blocking
Vignesh Balaji, Brandon Lucia
Extensive prior research has focused on alleviating the characteristic poor cache locality of graph analytics workloads. However, graph pre-processing tasks remain relatively unexp…
Flexible Support for Fast Parallel Commutative Updates
Vignesh Balaji, Dhruva Tirumala, Brandon Lucia
Privatizing data is a useful strategy for increasing parallelism in a shared memory multithreaded program. Independent cores can compute independently on duplicates of shared data,…