The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Triton: an intermediate language and compiler for tiled neural network computations
Abstract
The validation and deployment of novel research ideas in the field of Deep Learning is often limited by the availability of efficient compute kernels for certain basic primitives. In particular, operations that cannot leverage existing vendor libraries (e.g., cuBLAS, cuDNN) are at risk of facing poor device utilization unless custom implementations are written by experts – usually at the expense of portability. For this reason, the development of new programming abstractions for specifying custom Deep Learning workloads at a minimal performance cost has become crucial. We present Triton, a language and compiler centered around the concept of tile, i.e., statically shaped multi-dimensional sub-arrays. Our approach revolves around (1) a C-based language and an LLVM-based intermediate representation (IR) for expressing tensor programs in terms of operations on parametric tile variables and (2) a set of novel tile-level optimization passes for compiling these programs into efficient GPU code. We demonstrate how Triton can be used to build portable implementations of matrix multiplication and convolution kernels on par with hand-tuned vendor libraries (cuBLAS / cuDNN), or for efficiently implementing recent research ideas such as shift convolutions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“To mitigate the performance bottlenecks in dynamic graph execution, many deep learning systems leverage lowlevel GPU programming libraries and languages (e.g., CUDA [162], Triton [163], TileLang [164], and CUTLASS [165]) to implement their most performance-sensitive kernels.”
From A Survey of Large Language Models (2026) · cites this paper as [163]
In the citing paper
“Kimi K3 outperforms GLM-5.2 on exploit development (32% vs. 24% on ExploitBench; 17 vs.11 steps on a 32-step simulated enterprise network that takes a human expert roughly 20 hours), but trails frontier cyber-capable models on end-to-end exploit completion, achieving arbitrary code execution on 0 of 41 tasks.”
From Kimi K3: Open Frontier Intelligence (2026) · cites this paper as [123]
In the citing paper
“Kimi K3 outperforms GLM-5.2 on exploit development (32% vs. 24% on ExploitBench; 17 vs.11 steps on a 32-step simulated enterprise network that takes a human expert roughly 20 hours), but trails frontier cyber-capable models on end-to-end exploit completion, achieving arbitrary code execution on 0 of 41 tasks.”
From Kimi K3: Open Frontier Intelligence (2026) · cites this paper as [123]
In the citing paper
“An independent joint assessment by the UK AI Security Institute and NIST's Center for AI Standards and Innovation (CAISI) [123] reaches conclusions consistent with ours.”
From Kimi K3: Open Frontier Intelligence (2026) · cites this paper as [123]
In the citing paper
“In general, while JAX is much more high-level than CUDA or Triton (Tillet et al., 2019), it is still much more restrictive than PyTorch (Paszke et al., 2019), can be difficult to debug, and is poorly suited to the heterogeneous computations or conditional branching that are common when implementing environments.”
From XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX (2024) · cites this paper as Tillet et al., 2019
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Williams, S., Waterman, A., & Patterson, D. A. (2009) · Communications of the ACM · doi:10.1145/1498765.1498785 · Cited by 2,798 · cited 1×
“Performance of various implementations of C = AB T vs. Roofline [46] Model (NVIDIA GeForce GTX1070), where A ∈ R 1760 × 1760 and B ∈ R N × 1760 as N modulates arithmetic intensity.”
Proceedings of the 23rd international conference on Machine learning
Cohen, W. W., & Moore, A. (2006) · Cited by 2,647
Proceedings of the 13th International Conference on Neural Information Processing Systems
Leen, T. K., Dietterich, T. G., & Tresp, V. (2000) · Cited by 2,190
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Amodei, D., Anubhai, R., Battenberg, E., Case, C. T., Casper, J., Catanzaro, B., Chen, J., Chrzanowski, M., Coates, A., Diamos, G., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.02595 · Cited by 2,110
MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
Chen, T., Li, M., Li, Y., Lin, M., Wang, N., Wang, M., Xiao, T., Xu, B., Zhang, C., & Zhang, Z. (2015) · arXiv · doi:10.48550/arxiv.1512.01274 · Cited by 1,819
Nickolls, J., Buck, I., Garland, M., & Skadron, K. (2008) · Queue · doi:10.1145/1365490.1365500 · Cited by 1,610
(2008) · doi:10.1145/1401132.1401152 · Cited by 1,575
Automated empirical optimizations of software and the ATLAS project
Clint Whaley, R., Petitet, A., & Dongarra, J. J. (2001) · Parallel Computing · doi:10.1016/s0167-8191(00)00087-9 · Cited by 1,317
Fast Algorithms for Convolutional Neural Networks
Lavin, A., & Gray, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.435 · Cited by 915
(2013) · doi:10.1145/2491956.2462176 · Cited by 885
Fixed Point Quantization of Deep Convolutional Networks
Lin, D. D., Talathi, S. S., & Annapureddy, V. S. (2015) · arXiv · doi:10.48550/arxiv.1511.06393 · Cited by 684
BLIS: A Framework for Rapidly Instantiating BLAS Functionality
Van Zee, F. G., & van de Geijn, R. A. (2015) · ACM Transactions on Mathematical Software · doi:10.1145/2764454 · Cited by 356
Glow: Graph Lowering Compiler Techniques for Neural Networks
Rotem, N., Fix, J., Abdulrasool, S., Catron, G., Deng, S., Dzhabarov, R., Gibson, N., Hegeman, J. W., Lele, M., Levenstein, R., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.00907 · Cited by 174
A three-dimensional approach to parallel matrix multiplication
Agarwal, R. C., Balle, S. M., Gustavson, F. G., Joshi, M., & Palkar, P. (1995) · IBM Journal of Research and Development · doi:10.1147/rd.395.0575 · Cited by 158
McKeeman, W. M. (1965) · Communications of the ACM · doi:10.1145/364995.365000 · Cited by 158
TVM: End-to-End Optimization Stack for Deep LearningPreprint
Chen, T., Moreau, T., Jiang, Z., Shen, H., Yan, E., Wang, L., Hu, Y., Ceze, L., Guestrin, C., & Krishnamurthy, A. (2018) · arXiv (Cornell University) · Cited by 123
CLBlast: A Tuned OpenCL BLAS Library
Nugteren, C. (2018) · International Workshop on OpenCL · doi:10.1145/3204919.3204924 · Cited by 96
Embedded Binarized Neural NetworksPreprint
McDanel, B., Teerapittayanon, S., & Kung, H. T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.02260 · Cited by 88
Self-citationMemory access coalescing: a technique for eliminating redundant memory accesses
Davidson, J. W., & Jinturkar, S. (1994) · ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) · doi:10.1145/178243.178259 · Cited by 88
Accelerating GPU Kernels for Dense Linear Algebra
Nath, R., Tomov, S. Z., & Dongarra, J. J. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19328-6_10 · Cited by 66
Algorithms for compile-time memory optimization
Gergov, J. (1999) · Symposium on Discrete Algorithms · Cited by 65
Parameterized tiling revisited
Baskaran, M. M., Hartono, A., Tavarageri, S., Henretty, T. S., Ramanujam, J., & Sadayappan, P. (2010) · Proceedings of the CGO/Proceedings of the ... CGO · doi:10.1145/1772954.1772983 · Cited by 60
Diesel: DSL for linear algebra and neural net computations on GPUs
Elango, V., Rubin, N., Ravishankar, M., Sandanagobalane, H., & Grover, V. (2018) · ACM SIGPLAN International Workshop on Machine Learning and Programming Languages (MAPL) · doi:10.1145/3211346.3211354 · Cited by 56
Simple and Efficient Construction of Static Single Assignment Form
Braun, M., Buchwald, S., Hack, S., Leißa, R., Mallon, C., & Zwinkau, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-37051-9_6 · Cited by 53
Code generation in the polytope model
Griebl, M., Lengauer, C., & Wetzel, S. (1998) · doi:10.5555/522344.825673 · Cited by 44
Predicated static single assignment
Carter, L., Simon, B., Calder, B., Carter, L., & Jeanne Ferrante, Y. (1999) · doi:10.5555/520793.825741 · Cited by 40
Defensive loop tiling for shared cache
Bao, B., & Ding, C. (2013) · Proceedings of the CGO/Proceedings of the ... CGO · doi:10.1109/cgo.2013.6495008 · Cited by 38
Input-aware auto-tuning of compute-bound HPC kernels
Tillet, P., & Cox, D. (2017) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/3126908.3126939 · Cited by 36
Self-citationBenchmarking the NVIDIA V100 GPU and Tensor Cores
Martineau, M., Atkinson, P., & McIntosh‐Smith, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-10549-5_35 · Cited by 28
Efficient static single assignment form for predication
Stoutchinin, A., & de Ferrière, F. (2005) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro.2001.991116 · Cited by 18
TurboTiling: Leveraging Prefetching to Boost Performance of Tiled Codes
Mehta, S., Garg, R., Trivedi, N., & Yew, P.-C. (2016) · International Conference on Supercomputing · doi:10.1145/2925426.2926288 · Cited by 13
Efficient static single assignment form for predication
Stoutchinin, A., & de Ferrière, F. (2001) · doi:10.5555/563998.564022 · Cited by 12
Revisiting Loop Tiling for Datacenters: Live and Let Live
Zhao, J., Cui, H., Zhang, Y., Xue, J., & Feng, X. (2018) · International Conference on Supercomputing · doi:10.1145/3205289.3205306 · Cited by 7
(1998) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1109/pact.1998.727124 · Cited by 2
BLISlab: A Sandbox for Optimizing GEMM
Huang, J., & van de Geijn, R. A. (2016) · arXiv · doi:10.48550/arxiv.1609.00076
Research works printed but not linked: 9
- Tianqi Chen , Thierry Moreau , Ziheng Jiang , Haichen Shen , Eddie Q. Yan , Leyuan Wang , Yuwei Hu , Luis Ceze , Carlos Guestrin , and Arvind Krishnamurthy . 2018 . TVM: End-to-End Optimization Stack for Deep Learning. CoRR abs/1802.04799 (2018). Tianqi Chen, Thierry Moreau, Ziheng Jiang, Haichen Shen, Eddie Q. Yan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: End-to-End Optimization Stack for Deep Learning. CoRR abs/1802.04799 (2018). · arXiv
- 10.5555/314500.315082 · doi:10.5555/314500.315082
- Scott Gray and Alex Radford ans Diederik P. Kingma . 2017. Gpu kernels for block-sparse weights. CoRR abs/1711.09224 ( 2017 ). Scott Gray and Alex Radford ans Diederik P. Kingma. 2017. Gpu kernels for block-sparse weights. CoRR abs/1711.09224 (2017). · arXiv
- Sharan Narang , Eric Undersander , and Gregory F . Diamos . 2017 . Block-Sparse Recurrent Neural Networks. CoRR abs/1711.02782 (2017). Sharan Narang, Eric Undersander, and Gregory F. Diamos. 2017. Block-Sparse Recurrent Neural Networks. CoRR abs/1711.02782 (2017). · arXiv
- 10.5555/1964238.1964250 · doi:10.5555/1964238.1964250
- Travis Oliphant . 2006-. NumPy: A guide to NumPy . USA : Trelgol Publishing . ( 2006 -). http://www.numpy.org/ [Online; accessed <today>]. Travis Oliphant. 2006-. NumPy: A guide to NumPy. USA: Trelgol Publishing. (2006-). http://www.numpy.org/ [Online; accessed <today>].
- Didem Unat , Tan Nguyen , Weiqun Zhang , Muhammed Nufail Farooqi , Burak Bastem , George Michelogiannakis, Ann Almgren, editor=" Kunkel Julian M. Shalf, John", Pavan Balaji , and Jack Dongarra. 2016 ". TiDA: High-Level Programming Abstractions for Data Locality Management . Didem Unat, Tan Nguyen, Weiqun Zhang, Muhammed Nufail Farooqi, Burak Bastem, George Michelogiannakis, Ann Almgren, editor=" Kunkel Julian M. Shalf, John", Pavan Balaji, and Jack Dongarra. 2016". TiDA: High-Level Programming Abstractions for Data Locality Management.
- Nicolas Vasilache , Oleksandr Zinenko , Theodoros Theodoridis , Priya Goyal , Zachary DeVito , William S. Moses , Sven Verdoolaege , Andrew Adams , and Albert Cohen . 2018 . Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. CoRR abs/1802.04730 (2018). Nicolas Vasilache, Oleksandr Zinenko, Theodoros Theodoridis, Priya Goyal, Zachary DeVito, William S. Moses, Sven Verdoolaege, Andrew Adams, and Albert Cohen. 2018. Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. CoRR abs/1802.04730 (2018). · arXiv
- Bichen Wu , Alvin Wan , Xiangyu Yue , Peter H. Jin , Sicheng Zhao , Noah Golmant , Amir Gholaminejad , Joseph Gonzalez , and Kurt Keutzer . 2017 . Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions. CoRR abs/1711.08141 (2017). Bichen Wu, Alvin Wan, Xiangyu Yue, Peter H. Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, and Kurt Keutzer. 2017. Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions. CoRR abs/1711.08141 (2017). · arXiv
Cited by
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Ansel, J., Yang, E., He, H., Gimelshein, N., Jain, A., Voznesensky, M., Bao, B., Bell, P., Berard, D., Burovski, E., et al. (2024) · Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2 · doi:10.1145/3620665.3640366 · Cited by 737
Self-citationTraining a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., DasSarma, N., Drain, D., Fort, S., Ganguli, D., Henighan, T., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.05862 · Cited by 442
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Dai, D., Deng, C., Zhao, C., Xu, R. X., Gao, H., Chen, D., Li, J., Zeng, W., Yu, X., Wu, Y., et al. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.70 · Cited by 291
FlashInfer: Efficient and Customizable Attention Engine for LLM Inference ServingPreprint
Ye, Z., Chen, L., Lai, R., Lin, W., Zhang, Y., Wang, S. W., Chen, T., Kasikci, B., Grover, V., Krishnamurthy, A., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.01005 · Cited by 454
Metadata
- Authors
- Tillet, P., Kung, H. T., & Cox, D.
- Affiliations
- Harvard University (US)
- Venue
- Proceedings of the 3rd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages
- Publisher
- ACM
- Published
- 2019-06-22
- Pages
- 10-19
- OpenAlex
- W2954698171
- Cited by
- 318
- References
- 41
- Citations by year
- 2026: 122 · 2025: 102 · 2024: 49 · 2023: 20 · 2022: 11 · 2021: 9 · 2020: 4 · 2019: 1
- FWCI
- 4.92
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGPLAN International Workshop on Machine Learning and Programming Languages (MAPL) (publishedVersion)
- Funders
- Nvidia
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- Triton, intermediate representation, compilers, deep learning workloads, programming abstractions, portability, GPU programming, device utilization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.