Vignesh Balaji

Hi! I am a Senior Research Scientist at the Architecture Research Group (ARG) at NVIDIA

Before joining NVIDIA, I completed my PhD at the ECE department at Carnegie Mellon University where I worked with Professor Brandon Lucia. My dissertation research focused on developing architectural support for optimizing irregular applications (particularly, graph processing applications)

• Google Scholar
• CV

Publications

"Symphony: Orchestrating Sparse and Dense Tensors with Hierarchical Heterogeneous Processing" ,
Michael Pellauer, Jason Clemons, Vignesh Balaji, Neal Crago, Aamer Jaleel, Donghyuk Lee, Mike O'Connor, Angshuman Parashar, Sean Treichler, Po-An Tsai, Steve W. Keckler, and Joel S. Emer,
ACM Transactions on Computer Systems (TOCS Nov 2023 issue)
[paper]

"Community-based Matrix Reordering for Sparse Linear Algebra Optimization" ,
Vignesh Balaji, Neal Crago, Aamer Jaleel, and Stephen W. Keckler,
IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS 2023)
[paper] [slides]

"Improving Locality of Irregular Updates with Hardware Assisted Propagation Blocking" ★ ,
Vignesh Balaji, and Brandon Lucia,
International Symposium on High Performance Computer Architecture (HPCA 2022)
★ (BEST PAPER NOMINEE)
[preprint] [slides] [teaser] [talk]

"P-OPT: Practical Optimal Cache Replacement for Graph Analytics" ★ ,
Vignesh Balaji, Neal Crago, Aamer Jaleel, and Brandon Lucia,
International Symposium on High Performance Computer Architecture (HPCA 2021)
★ (BEST PAPER NOMINEE)
[paper] [slides] [teaser] [talk] [github]

"Optimizing Graph Processing and Preprocessing with Hardware Assisted Propagation Blocking",
Vignesh Balaji, and Brandon Lucia,
ArXiv 2020
[paper]

"Peacenik: Architecture Support for Not Failing under Fail-Stop Memory Consistency",
Rui Zhang, Swarnendu Biswas, Vignesh Balaji, Michael D. Bond, and Brandon Lucia,
International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2020)
[paper] [slides] [github]

"Combining Data Duplication and Graph Reordering to Accelerate Parallel Graph Processing",
Vignesh Balaji, and Brandon Lucia,
International Symposium on High-Performance Parallel and Distributed Computing (HDPC 2019)
[paper] [slides] [github]

"When is Graph Reordering an Optimization? Studying the effect of lightweight graph reordering across applications and input graphs" ★ ,
Vignesh Balaji, and Brandon Lucia,
IEEE International Symposium on Workload Characterization (IISWC 2018)
★ (BEST PAPER AWARD)
[preprint] [slides] [github]

"Flexible Support for Fast Parallel Commutative Updates",
Vignesh Balaji, Dhruva Tirumala and Brandon Lucia,
ArXiv 2018
[paper]

"An Architecture and Programming Model for Accelerating Parallel Commutative Computations via Privatization",
Vignesh Balaji, Dhruva Tirumala and Brandon Lucia,
Symposium on Principles and Practice of Parallel Programming (PPoPP 2017)
[poster]

Interesting Stuff

Contact