Sotabase

Career

· Adjunct Assistant Professor, University of Illinois Urbana-Champaign2020–2021
· PhD in Computer Science, Massachusetts Institute of Technology2013–2020
· S.M. in Computer Science, Massachusetts Institute of Technology2013–2015
· B.Sc. in Electronics and Telecommunication Engineering, University of Moratuwa2013–

Publications (67)

Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks
International Conference on Machine Learning · 2018
179
cited
Making caches work for graph analytics
2017 IEEE International Conference on Big Data (Big Data) · 2016
129
cited
A Learned Performance Model for Tensor Processing Units
Conference on Machine Learning and Systems · 2021
94
cited
VeGen: a vectorizer generator for SIMD and beyond
International Conference on Architectural Support for Programming Languages and Operating Systems · 2021
47
cited
Compiler Auto-Vectorization with Imitation Learning
Neural Information Processing Systems · 2019
43
cited
DiffTune: Optimizing CPU Simulator Parameters with Learned Differentiable Surrogates
Micro · 2020
41
cited
goSLP: globally optimized superword level parallelism framework
Proc. ACM Program. Lang. · 2018
41
cited
Helium: lifting high-performance stencil kernels from stripped x86 binaries to halide DSL code
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2015
41
cited
BHive: A Benchmark Suite and Measurement Framework for Validating x86-64 Basic Block Performance Models
IEEE International Symposium on Workload Characterization · 2019
32
cited
WACO: Learning Workload-Aware Co-optimization of the Format and Schedule of a Sparse Tensor Program
International Conference on Architectural Support for Programming Languages and Operating Systems · 2023
31
cited
TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs
Neural Information Processing Systems · 2023
29
cited
GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation
IEEE International Symposium on Workload Characterization · 2022
25
cited
SPADE: A Flexible and Scalable Accelerator for SpMM and SDDMM
International Symposium on Computer Architecture · 2023
23
cited
All you need is superword-level parallelism: systematic control-flow vectorization with SLP
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2022
21
cited
Optimizing Cache Performance for Graph Analytics
arXiv.org · 2016
17
cited
TGOpt: Redundancy-Aware Optimizations for Temporal Graph Attention Networks
ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming · 2023
17
cited
Parallelizing WFST speech decoders
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2016
15
cited
Transforming the Hybrid Cloud for Emerging AI Workloads
arXiv.org · 2024
14
cited
Unified Convolution Framework: A compiler-based approach to support sparse convolutions
Conference on Machine Learning and Systems · 2023
11
cited
Learning Large Graph Property Prediction via Graph Segment Training
Neural Information Processing Systems · 2023
10
cited
Sotabase
Charith Mendis | Researcher Profile | Sotabase | Sotabase