publications | Charith Mendis

Preprints
Conference and Journal Papers

Preprints

2024

Input-sensitive dense-sparse primitive compositions for GNN acceleration

Damitha Lenadora , Vimarsh Sathia , Gerasimos Gerogiannis , and 3 more authors

2024

arXiv
FLuRKA: Fast fused Low-Rank & Kernel Attention

Ahan Gupta , Yueming Yuan , Yanqi Zhou , and 1 more author

2024

arXiv

Conference and Journal Papers

2024

MLSys

COMET: X86 Cost Model Explanation Framework

Isha Chaudhary , Alex Renda , Charith Mendis, and 1 more author

2024

arXiv
SIGMOD

Dias: Dynamic Rewriting of Pandas Code

Stefanos Baziotis , Daniel Kang , and Charith Mendis

In Proceedings of ACM on Management of Data (SIGMOD) , 2024

arXiv
ASPLOS

Hydride: A Retargetable and Extensible Synthesis-based Compiler for Modern Hardware Architectures

Akash Kothari , Abdul Rafae Noor , Muchen Xu , and 6 more authors

In Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) , 2024
ASPLOS

Two-Face: Combining Collective and One-Sided Accesses for Efficient Distributed SpMM

Charles Block , Gerasimos Gerogiannis , Charith Mendis, and 2 more authors

In Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) , 2024

PDF
ASPLOS

TGLite: A Lightweight Programming Framework for Continuous-Time Temporal Graph Neural Networks

Yufeng Wang , and Charith Mendis

In Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) , 2024

PDF

2023

NeurIPS

Learning Large Graph Property Prediction via Graph Segment Training

Kaidi Cao , Mangpo Phothilimthana , Sami Abu-El-Haija , and 5 more authors

In Advances in Neural Information Processing Systems , 2023

Bib PDF

@inproceedings{neurips23-gst,
  author = {Cao, Kaidi and Phothilimthana, Mangpo and Abu-El-Haija, Sami and Zelle, Dustin and Zhou, Yanqi and Mendis, Charith and Leskovec, Jure and Perozzi, Bryan},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Oh, A. and Neumann, T. and Globerson, A. and Saenko, K. and Hardt, M. and Levine, S.},
  pages = {23345--23361},
  publisher = {Curran Associates, Inc.},
  title = {Learning Large Graph Property Prediction via Graph Segment Training},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/file/48f8143cebe113f4596e1781771578cd-Paper-Conference.pdf},
  volume = {36},
  year = {2023},
}

NeurIPS

TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs

Mangpo Phothilimthana , Sami Abu-El-Haija , Kaidi Cao , and 4 more authors

In Advances in Neural Information Processing Systems , 2023

Bib PDF

@inproceedings{neurips23-tpugraphs,
  author = {Phothilimthana, Mangpo and Abu-El-Haija, Sami and Cao, Kaidi and Fatemi, Bahare and Burrows, Michael and Mendis, Charith and Perozzi, Bryan},
  booktitle = {Advances in Neural Information Processing Systems},
  editor = {Oh, A. and Neumann, T. and Globerson, A. and Saenko, K. and Hardt, M. and Levine, S.},
  pages = {70355--70375},
  publisher = {Curran Associates, Inc.},
  title = {TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/file/ded1a89e2b3b925444ada973af66336e-Paper-Datasets_and_Benchmarks.pdf},
  volume = {36},
  year = {2023},
}

MetaCom

Challenges in Metaverse Research: An Internet of Things Perspective

Tarek Abdelzaher , Matthew Caesar , Charith Mendis, and 3 more authors

In IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom) , 2023

Bib PDF

@inproceedings{metacom23-metaverse,
  author = {Abdelzaher, Tarek and Caesar, Matthew and Mendis, Charith and Nahrstedt, Klara and Srivastava, Mani and Yu, Minlan},
  booktitle = {IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom)},
  title = {Challenges in Metaverse Research: An Internet of Things Perspective},
  year = {2023},
  volume = {},
  number = {},
  pages = {161-170},
  doi = {10.1109/MetaCom57706.2023.00042},
}

MLSys

Unified Convolution Framework: A compiler-based approach to support sparse convolutions

Jaeyeon Won , Changwan Hong , Charith Mendis, and 2 more authors

In Proceedings of Machine Learning and Systems (MLSys) , 2023

Bib PDF

@inproceedings{mlsys23-ucf,
  author = {Won, Jaeyeon and Hong, Changwan and Mendis, Charith and Emer, Joel and Amarasinghe, Saman},
  title = {Unified Convolution Framework: A compiler-based approach to support sparse convolutions},
  keywords = {TACO,ML4C},
  url = {http://groups.csail.mit.edu/commit/papers/2023/2023_MLSys_SparseConvolution_camready.pdf},
  year = {2023},
  address = {Miami, USA},
  booktitle = {Proceedings of Machine Learning and Systems (MLSys)},
}

ISCA

SPADE: A Flexible and Scalable Accelerator for SpMM and SDDMM

Gerasimos Gerogiannis , Serif Yesil , Damitha Lenadora , and 3 more authors

In Proceedings of the 50th Annual International Symposium on Computer Architecture (ISCA) , 2023

Bib PDF

@inproceedings{spade-isca2023,
  author = {Gerogiannis, Gerasimos and Yesil, Serif and Lenadora, Damitha and Cao, Dingyuan and Mendis, Charith and Torrellas, Josep},
  title = {SPADE: A Flexible and Scalable Accelerator for SpMM and SDDMM},
  year = {2023},
  isbn = {9798400700958},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3579371.3589054},
  doi = {10.1145/3579371.3589054},
  booktitle = {Proceedings of the 50th Annual International Symposium on Computer Architecture (ISCA)},
  articleno = {19},
  numpages = {15},
  keywords = {SDDMM, sparse computations, hardware accelerator, SpMM},
  location = {Orlando, FL, USA},
  series = {ISCA '23},
  bib = {https://dblp.org/rec/conf/isca/GerogiannisYLCM23.html?view=bibtex}
}

PPoPP

TGOpt: Redundancy-Aware Optimizations for Temporal Graph Attention Networks

Yufeng Wang , and Charith Mendis

In Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (PPoPP) , 2023

Bib PDF Code

@inproceedings{tgopt-ppopp2023,
  author = {Wang, Yufeng and Mendis, Charith},
  editor = {Dehnavi, Maryam Mehri and Kulkarni, Milind and Krishnamoorthy, Sriram},
  title = {TGOpt: Redundancy-Aware Optimizations for Temporal Graph Attention
                 Networks},
  booktitle = {Proceedings of the 28th {ACM} {SIGPLAN} Annual Symposium on Principles
                 and Practice of Parallel Programming (PPoPP)},
  pages = {354--368},
  publisher = {{ACM}},
  year = {2023},
  url = {https://doi.org/10.1145/3572848.3577490},
  doi = {10.1145/3572848.3577490},
  timestamp = {Wed, 22 Feb 2023 11:49:05 +0100},
  biburl = {https://dblp.org/rec/conf/ppopp/WangM23.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/ppopp/WangM23.html?view=bibtex}
}

ASPLOS

WACO: Learning Workload-Aware Co-optimization of the Format and Schedule of a Sparse Tensor Program

Jaeyeon Won , Charith Mendis, Joel S. Emer , and 1 more author

In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) , 2023

Bib PDF Code

@inproceedings{waco-asplos2023,
  author = {Won, Jaeyeon and Mendis, Charith and Emer, Joel S. and Amarasinghe, Saman P.},
  editor = {Aamodt, Tor M. and Jerger, Natalie D. Enright and Swift, Michael M.},
  title = {{WACO:} Learning Workload-Aware Co-optimization of the Format and
                 Schedule of a Sparse Tensor Program},
  booktitle = {Proceedings of the 28th {ACM} International Conference on Architectural
                 Support for Programming Languages and Operating Systems (ASPLOS)},
  pages = {920--934},
  publisher = {{ACM}},
  year = {2023},
  url = {https://doi.org/10.1145/3575693.3575742},
  doi = {10.1145/3575693.3575742},
  timestamp = {Thu, 02 Feb 2023 08:48:06 +0100},
  biburl = {https://dblp.org/rec/conf/asplos/WonMEA23.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/asplos/WonMEA23.html?view=bibtex}
}

2022

IISWC

GRANITE: A Graph Neural Network Model for Basic Block Throughput Estimation

Ondrej Sýkora , Phitchaya Mangpo Phothilimthana , Charith Mendis, and 1 more author

In IEEE International Symposium on Workload Characterization (IISWC) , 2022

Bib PDF

@inproceedings{granite-iiswc2022,
  author = {S{\'{y}}kora, Ondrej and Phothilimthana, Phitchaya Mangpo and Mendis, Charith and Yazdanbakhsh, Amir},
  title = {{GRANITE:} {A} Graph Neural Network Model for Basic Block Throughput
                 Estimation},
  booktitle = {{IEEE} International Symposium on Workload Characterization (IISWC)},
  pages = {14--26},
  publisher = {{IEEE}},
  year = {2022},
  url = {https://doi.org/10.1109/IISWC55918.2022.00012},
  doi = {10.1109/IISWC55918.2022.00012},
  timestamp = {Wed, 04 Jan 2023 16:48:41 +0100},
  biburl = {https://dblp.org/rec/conf/iiswc/SykoraPMY22.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/iiswc/SykoraPMY22.html?view=bibtex}
}

PLDI

All You Need is Superword-Level Parallelism: Systematic Control-Flow Vectorization with SLP

Yishen Chen , Charith Mendis, and Saman Amarasinghe

In Proceedings of the 43rd ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI) , 2022

Bib PDF

@inproceedings{superslp-pldi2022,
  author = {Chen, Yishen and Mendis, Charith and Amarasinghe, Saman},
  title = {All You Need is Superword-Level Parallelism: Systematic Control-Flow Vectorization with SLP},
  year = {2022},
  isbn = {9781450392655},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://groups.csail.mit.edu/commit/papers/2022/pldi22-vegen.pdf},
  doi = {10.1145/3519939.3523701},
  booktitle = {Proceedings of the 43rd ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI)},
  pages = {301--315},
  numpages = {15},
  keywords = {SLP},
  location = {San Diego, CA, USA},
  series = {PLDI 2022},
  bib = {https://dblp.org/rec/conf/pldi/ChenMA22.html?view=bibtex}
}

2021

ASPLOS

VeGen: A Vectorizer Generator for SIMD and Beyond

Yishen Chen , Charith Mendis, Michael Carbin , and 1 more author

In Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) , 2021

Bib PDF Video

@inproceedings{vegen-asplos2021,
  author = {Chen, Yishen and Mendis, Charith and Carbin, Michael and Amarasinghe, Saman},
  title = {VeGen: A Vectorizer Generator for SIMD and Beyond},
  year = {2021},
  isbn = {9781450383172},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3445814.3446692},
  doi = {10.1145/3445814.3446692},
  booktitle = {Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
  pages = {902–914},
  numpages = {13},
  keywords = {optimization, auto-vectorization, non-SIMD},
  location = {Virtual, USA},
  series = {ASPLOS '21},
  bib = {https://dblp.org/rec/conf/asplos/ChenMCA21.html?view=bibtex},
}

MLSys

A Learned Performance Model for Tensor Processing Units

Sam Kaufman , Phitchaya Phothilimthana , Yanqi Zhou , and 4 more authors

In Proceedings of Machine Learning and Systems (MLSys) , 2021

Bib PDF

@inproceedings{tpu-costmodel-mlsys2021,
  author = {Kaufman, Sam and Phothilimthana, Phitchaya and Zhou, Yanqi and Mendis, Charith and Roy, Sudip and Sabne, Amit and Burrows, Mike},
  booktitle = {Proceedings of Machine Learning and Systems (MLSys)},
  editor = {Smola, A. and Dimakis, A. and Stoica, I.},
  pages = {387--400},
  title = {A Learned Performance Model for Tensor Processing Units},
  url = {https://proceedings.mlsys.org/paper/2021/file/85d8ce590ad8981ca2c8286f79f59954-Paper.pdf},
  volume = {3},
  year = {2021},
  bdsk-url-1 = {https://proceedings.mlsys.org/paper/2021/file/85d8ce590ad8981ca2c8286f79f59954-Paper.pdf},
  award = {used in production at Google in the XLA TPU compiler},
  bib = {https://dblp.org/rec/conf/mlsys/KaufmanPZM0SB21.html?view=bibtex}
}

2020

MICRO

DiffTune: Optimizing CPU Simulator Parameters with Learned Differentiable Surrogates

Alex Renda , Yishen Chen , Charith Mendis, and 1 more author

In 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) , 2020

Bib PDF Video

@inproceedings{difftune-micro2020,
  author = {Renda, Alex and Chen, Yishen and Mendis, Charith and Carbin, Michael},
  title = {DiffTune: Optimizing {CPU} Simulator Parameters with Learned Differentiable
                 Surrogates},
  booktitle = {53rd Annual {IEEE/ACM} International Symposium on Microarchitecture
                 (MICRO)},
  pages = {442--455},
  publisher = {{IEEE}},
  year = {2020},
  url = {https://doi.org/10.1109/MICRO50266.2020.00045},
  doi = {10.1109/MICRO50266.2020.00045},
  timestamp = {Tue, 17 Nov 2020 13:33:12 +0100},
  biburl = {https://dblp.org/rec/conf/micro/RendaCMC20.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/micro/RendaCMC20.html?view=bibtex},
}

2019

Revec: program rejuvenation through revectorization

Charith Mendis, Ajay Jain , Paras Jain , and 1 more author

In Proceedings of the 28th International Conference on Compiler Construction (CC) , 2019

Bib PDF Video

@inproceedings{revec-cc2019,
  author = {Mendis, Charith and Jain, Ajay and Jain, Paras and Amarasinghe, Saman P.},
  editor = {Amaral, Jos{\'{e}} Nelson and Kulkarni, Milind},
  title = {Revec: program rejuvenation through revectorization},
  booktitle = {Proceedings of the 28th International Conference on Compiler Construction
                 (CC)},
  pages = {29--41},
  publisher = {{ACM}},
  year = {2019},
  url = {https://doi.org/10.1145/3302516.3307357},
  doi = {10.1145/3302516.3307357},
  timestamp = {Sun, 02 Oct 2022 15:56:08 +0200},
  biburl = {https://dblp.org/rec/conf/cc/MendisJJA19.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/cc/MendisJJA19.html?view=bibtex},
}

ICML

Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks

Charith Mendis, Alex Renda , Saman P. Amarasinghe , and 1 more author

In Proceedings of the 36th International Conference on Machine Learning (ICML) , 2019

Bib PDF Code

@inproceedings{ithemal-icml2019,
  author = {Mendis, Charith and Renda, Alex and Amarasinghe, Saman P. and Carbin, Michael},
  editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  title = {Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation
                 using Deep Neural Networks},
  booktitle = {Proceedings of the 36th International Conference on Machine Learning (ICML)},
  series = {Proceedings of Machine Learning Research},
  volume = {97},
  pages = {4505--4515},
  publisher = {{PMLR}},
  year = {2019},
  url = {http://proceedings.mlr.press/v97/mendis19a.html},
  timestamp = {Tue, 11 Jun 2019 15:37:38 +0200},
  biburl = {https://dblp.org/rec/conf/icml/MendisRAC19.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  award = {Best Paper award at the ML for systems workshop co-located with ISCA'19},
  bib = {https://dblp.org/rec/conf/icml/MendisRAC19.html?view=bibtex},
}

IISWC

BHive: A Benchmark Suite and Measurement Framework for Validating x86-64 Basic Block Performance Models

Yishen Chen , Ajay Brahmakshatriya , Charith Mendis, and 5 more authors

In IEEE International Symposium on Workload Characterization (IISWC) , 2019

Bib PDF Code

@inproceedings{bhive-iiswc2019,
  author = {Chen, Yishen and Brahmakshatriya, Ajay and Mendis, Charith and Renda, Alex and Atkinson, Eric and S{\'{y}}kora, Ondrej and Amarasinghe, Saman P. and Carbin, Michael},
  title = {BHive: {A} Benchmark Suite and Measurement Framework for Validating
                 x86-64 Basic Block Performance Models},
  booktitle = {{IEEE} International Symposium on Workload Characterization (IISWC)},
  pages = {167--177},
  publisher = {{IEEE}},
  year = {2019},
  url = {https://doi.org/10.1109/IISWC47752.2019.9042166},
  doi = {10.1109/IISWC47752.2019.9042166},
  timestamp = {Mon, 23 Mar 2020 13:15:20 +0100},
  biburl = {https://dblp.org/rec/conf/iiswc/ChenBMRASAC19.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/iiswc/ChenBMRASAC19.html?view=bibtex},
}

NeurIPS

Compiler Auto-Vectorization with Imitation Learning

Charith Mendis, Cambridge Yang , Yewen Pu , and 2 more authors

In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems (NeurIPS) , 2019

Bib PDF

@inproceedings{vemal-neurips2019,
  author = {Mendis, Charith and Yang, Cambridge and Pu, Yewen and Amarasinghe, Saman P. and Carbin, Michael},
  editor = {Wallach, Hanna M. and Larochelle, Hugo and Beygelzimer, Alina and d'Alch{\'{e}}{-}Buc, Florence and Fox, Emily B. and Garnett, Roman},
  title = {Compiler Auto-Vectorization with Imitation Learning},
  booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
                 on Neural Information Processing Systems (NeurIPS)},
  pages = {14598--14609},
  year = {2019},
  timestamp = {Mon, 16 May 2022 15:41:51 +0200},
  biburl = {https://dblp.org/rec/conf/nips/MendisYPAC19.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/nips/MendisYPAC19.html?view=bibtex}
}

2018

OOPSLA

goSLP: globally optimized superword level parallelism framework

Charith Mendis, and Saman P. Amarasinghe

Proc. ACM Program. Lang. (OOPSLA), 2018

Bib PDF Video

@article{goslp-oopsla2018,
  author = {Mendis, Charith and Amarasinghe, Saman P.},
  title = {goSLP: globally optimized superword level parallelism framework},
  journal = {Proc. {ACM} Program. Lang. (OOPSLA)},
  volume = {2},
  number = {{OOPSLA}},
  pages = {110:1--110:28},
  year = {2018},
  url = {https://doi.org/10.1145/3276480},
  doi = {10.1145/3276480},
  timestamp = {Sun, 02 Oct 2022 15:26:02 +0200},
  biburl = {https://dblp.org/rec/journals/pacmpl/MendisA18.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/journals/pacmpl/MendisA18.html?view=bibtex},
}

2017

BigData

Making caches work for graph analytics

Yunming Zhang , Vladimir Kiriansky , Charith Mendis, and 2 more authors

In IEEE International Conference on Big Data (BigData) , 2017

Bib PDF

@inproceedings{cagra-bigdata2017,
  author = {Zhang, Yunming and Kiriansky, Vladimir and Mendis, Charith and Amarasinghe, Saman P. and Zaharia, Matei},
  editor = {Nie, Jian{-}Yun and Obradovic, Zoran and Suzumura, Toyotaro and Ghosh, Rumi and Nambiar, Raghunath and Wang, Chonggang and Zang, Hui and Baeza{-}Yates, Ricardo and Hu, Xiaohua and Kepner, Jeremy and Cuzzocrea, Alfredo and Tang, Jian and Toyoda, Masashi},
  title = {Making caches work for graph analytics},
  booktitle = {{IEEE} International Conference on Big Data (BigData)},
  pages = {293--302},
  publisher = {{IEEE} Computer Society},
  year = {2017},
  url = {https://doi.org/10.1109/BigData.2017.8257937},
  doi = {10.1109/BigData.2017.8257937},
  timestamp = {Fri, 19 Nov 2021 16:08:20 +0100},
  biburl = {https://dblp.org/rec/conf/bigdataconf/ZhangKMAZ17.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  award = {Best Student Paper award},
  bib = {https://dblp.org/rec/conf/bigdataconf/ZhangKMAZ17.html?view=bibtex}
}

2016

ICASSP

Parallelizing WFST speech decoders

Charith Mendis, Jasha Droppo , Saeed Maleki , and 3 more authors

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2016

Bib PDF

@inproceedings{par-wfst-icassp2016,
  author = {Mendis, Charith and Droppo, Jasha and Maleki, Saeed and Musuvathi, Madanlal and Mytkowicz, Todd and Zweig, Geoffrey},
  title = {Parallelizing {WFST} speech decoders},
  booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal
                 Processing (ICASSP)},
  pages = {5325--5329},
  publisher = {{IEEE}},
  year = {2016},
  url = {https://doi.org/10.1109/ICASSP.2016.7472694},
  doi = {10.1109/ICASSP.2016.7472694},
  timestamp = {Sun, 25 Oct 2020 23:13:48 +0100},
  biburl = {https://dblp.org/rec/conf/icassp/MendisDMMMZ16.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/icassp/MendisDMMMZ16.html?view=bibtex}
}

2015

PLDI

Helium: lifting high-performance stencil kernels from stripped x86 binaries to halide DSL code

Charith Mendis, Jeffrey Bosboom , Kevin Wu , and 5 more authors

In Proceedings of the 36th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) , 2015

Bib PDF

@inproceedings{helium-pldi2015,
  author = {Mendis, Charith and Bosboom, Jeffrey and Wu, Kevin and Kamil, Shoaib and Ragan{-}Kelley, Jonathan and Paris, Sylvain and Zhao, Qin and Amarasinghe, Saman P.},
  editor = {Grove, David and Blackburn, Stephen M.},
  title = {Helium: lifting high-performance stencil kernels from stripped x86
                 binaries to halide {DSL} code},
  booktitle = {Proceedings of the 36th {ACM} {SIGPLAN} Conference on Programming
                 Language Design and Implementation (PLDI)},
  pages = {391--402},
  publisher = {{ACM}},
  year = {2015},
  url = {https://doi.org/10.1145/2737924.2737974},
  doi = {10.1145/2737924.2737974},
  timestamp = {Thu, 24 Nov 2022 09:18:38 +0100},
  biburl = {https://dblp.org/rec/conf/pldi/MendisBWKRPZA15.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  bib = {https://dblp.org/rec/conf/pldi/MendisBWKRPZA15.html?view=bibtex},
  web = {http://projects.csail.mit.edu/helium/}
}