nach oben

Empirical Software Engineering

Erschienen in:

01.12.2022

On the usage and development of deep learning compilers: an empirical study on TVM

verfasst von: Xiongfei Wu, Jinqiu Yang, Lei Ma, Yinxing Xue, Jianjun Zhao

Erschienen in: Empirical Software Engineering | Ausgabe 7/2022

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Recent advances in deploying deep learning (DL) models have inspired the innovation of DL compilers from both industry and academia such as Facebook Glow and TVM. Given the importance of DL compilers, we seek for answering the important question to ease the adoption and development of TVM: What challenges do users face when using DL compilers and what are common challenges for developers when developing DL compilers. This paper presents the first empirical study on identifying the challenges in both usage and development of a DL compiler. We choose TVM as the representative DL compiler and manually inspect 347 sampled posts from its official discuss forum. We identify a taxonomy of challenges in usage of TVM consisting of 15 categories and seven types of common topics about developing TVM. Furthermore, we characterize TVM bugs in total of four impacts to obtain an initial understanding on defects of TVM through manual inspection of 44 bug reports and propose five implications for both developers and researchers in order to improve the development practices and build more robust DL compilers.

Vorheriger Artikel SPVF: security property assisted vulnerability fixing via attention-based models

Nächster Artikel The human experience of comprehending source code in virtual reality

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Dataset:https://bit.ly/3I9xohu

Introducing Hexagon backend: https://discuss.tvm.apache.org/t/introducing-hexagon-backend/2421

Use TVM for TI DSP: https://discuss.tvm.apache.org/t/use-tvm-for-ti-dsp/1200

Apache TVM Community: https://discuss.tvm.apache.org/

Glow discussion forum: https://discuss.pytorch.org/c/glow/10

Tensor Comprehensions slack channel: https://tensorcomprehensions.slack.com/

OPENVINO forum: https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/bd-p/distribution-openvino-toolkit

https://discuss.tvm.apache.org/t/request-for-invite-to-the-slack-channel/2888/17

Install from Source: https://tvm.apache.org/docs/install/from_source.html

https://discuss.tvm.apache.org/t/cant-run-rpc-gpu-tutorial-on-my-own-device/564/9

https://discuss.tvm.apache.org/t/solved-qeustions-about-gpu-memory-usage/5309

C++ doyxgen API: https://tvm.apache.org/docs/api/doxygen/index.html

https://bit.ly/3nbNNH5

https://discuss.tvm.apache.org/t/how-should-you-index-dltensors-in-c-for-the-multi-dimensional-case/6257

https://discuss.tvm.apache.org/t/can-tvm-now-support-dynamic-shaped-tensors/5094

https://github.com/apache/tvm/graphs/contributors

https://github.com/apache/tvm/pull/2116#issuecomment-444726352

https://discuss.tvm.apache.org/t/rfc-incorporate-existing-relay-aot-compiler-in-mainline/7393

https://discuss.tvm.apache.org/t/discuss-contributing-new-docs-for-inferbound/2151

https://tvm.apache.org/docs/contribute/community.html#general-development-process

https://facebookresearch.github.io/TensorComprehensions/installation.html#advanced-development-mode-installation

https://bit.ly/3I9xohu

TVM Change LOG: https://github.com/apache/tvm/blob/main/NEWS.md

TVM Community Guideline: https://tvm.apache.org/docs/contribute/community.html#reviewers

Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray D G, Steiner B, Tucker P, Vasudevan V, Warden P, Wicke M, Yu Y, Zheng X (2016) Tensorflow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX conference on operating systems design and implementation, USENIX Association, USA, OSDI’16, pp 265–283

Abdelfattah M S, Han D, Bitar A, DiCecco R, O’Connell S, Shanker N, Chu J, Prins I, Fender J, Ling A C, Chiu G R (2018) Dla: compiler and fpga overlay for neural network inference acceleration. In: 2018 28th International conference on field programmable logic and applications (FPL). https://doi.org/10.1109/FPL.2018.00077, pp 411–4117

Badue C, Guidolini R, Carneiro R V, Azevedo P, Cardoso V B, Forechi A, Jesus L, Berriel R, Paixão T M, Mutz F, de Paula Veronese L, Oliveira-Santos T, De Souza A F (2021) Self-driving cars: a survey. Expert Syst Appl 113816:165. https://doi.org/10.1016/j.eswa.2020.113816. http://www.sciencedirect.com/science/article/pii/S095741742030628X

Bagherzadeh M, Khatchadourian R (2019) Going big: a large-scale study on what big data developers ask. In: Proceedings of the 2019 27th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering, ESEC/FSE 2019. https://doi.org/10.1145/3338906.3338939. Association for Computing Machinery, New York, pp 432–442

Berg B L, Lune H, Lune H (2004) Qualitative research methods for the social sciences, vol 5. Pearson, Boston

Boemer F, Lao Y, Cammarota R, Wierzynski C (2019) Ngraph-he: a graph compiler for deep learning on homomorphically encrypted data. In: Proceedings of the 16th ACM international conference on computing frontiers, CF ’19. https://doi.org/10.1145/3310273.3323047. Association for Computing Machinery, New York, pp 3–13

Chen T (2020) Language server tool to navigate across packedfunc ffi for ides like vscode and emacs. https://bit.ly/3oO6Qso, retrieved on December 9, 2020

Chen A, Chen PTH (2021) Demystifying the challenges and benefits of analyzing user-reported logs in bug reports. Empirical Software Engineering

Chen T, Moreau T, Jiang Z, Zheng L, Yan E, Cowan M, Shen H, Wang L, Hu Y, Ceze L, Guestrin C, Krishnamurthy A (2018a) Tvm: an automated end-to-end optimizing compiler for deep learning. In: Proceedings of the 13th USENIX conference on operating systems design and implementation, USENIX Association, USA, OSDI’18, pp 579–594

Chen T, Zheng L, Yan E, Jiang Z, Moreau T, Ceze L, Guestrin C, Krishnamurthy A (2018b) Learning to optimize tensor programs. In: Proceedings of the 32nd international conference on neural information processing systems, NIPS’18. Curran Associates Inc., Red Hook, pp 3393–3404

Chen Z, Cao Y, Liu Y, Wang H, Xie T, Liu X (2020) A comprehensive study on challenges in deploying deep learning based software. In: Proceedings of the 28th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering, ESEC/FSE 2020. https://doi.org/10.1145/3368089.3409759. Association for Computing Machinery, New York, pp 750–762

Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20(1):37–46. https://doi.org/10.1177/001316446002000104CrossRef

Cyphers S, Bansal A K, Bhiwandiwalla A, Bobba J, Brookhart M, Chakraborty A, Constable W, Convey C, Cook L, Kanawi O, Kimball R, Knight J, Korovaiko N, Vijay V K, Lao Y, Lishka C R, Menon J, Myers J, Narayana S A, Procter A, Webb T J (2018) Intel ngraph: an intermediate representation, compiler, and executor for deep learning. CoRR arXiv:1801.08058. 1801.08058

Deng L, Liu Y (2018) Deep learning in natural language processing. Springer, BerlinCrossRef

Fakoor R, Ladhak F, Nazi A, Huber M (2013) Using deep learning to enhance cancer diagnosis and classification. In: Proceedings of the international conference on machine learning, vol 28. ACM, New York

Fischer M, Pinzger M, Gall H (2003) Analyzing and relating bug report data for feature tracking. In: 10th Working conference on reverse engineering, 2003. WCRE 2003. Proceedings. https://doi.org/10.1109/WCRE.2003.1287240, pp 90–99

Foundation A (2020) Mxxnet. https://mxnet.apache.org/, retrieved on January 4, 2021

Garcia J, Feng Y, Shen J, Almanee S, Xia Y, Chen Q A (2020) A comprehensive study of autonomous vehicle bugs. In: 2020 IEEE/ACM 42nd international conference on software engineering (ICSE), pp 385–396

Github search api (2021) https://docs.github.com/en/rest/reference/search, retrieved on May 10, 2021

Gulzar M A, Interlandi M, Yoo S, Tetali S D, Condie T, Millstein T, Kim M (2016) Bigdebug: debugging primitives for interactive big data processing in spark. In: Proceedings of the 38th international conference on software engineering, ICSE ’16. https://doi.org/10.1145/2884781.2884813. Association for Computing Machinery, New York, pp 784–795

Hemanth DJ, Estrela VV (2017) Deep learning for image processing applications, vol 31. IOS Press

Hoang V C D, Koehn P, Haffari G, Cohn T (2018) Iterative back-translation for neural machine translation. In: Proceedings of the 2nd workshop on neural machine translation and generation, pp 18–24

Humbatova N, Jahangirova G, Bavota G, Riccio V, Stocco A, Tonella P (2020) Taxonomy of real faults in deep learning systems. In: Proceedings of the ACM/IEEE 42nd international conference on software engineering, ICSE ’20. https://doi.org/10.1145/3377811.3380395. Association for Computing Machinery, New York, pp 1110–1121

Intel (2020) Accelerate fast math with intel oneapi math kernel library. https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/onemkl.html, retrieved on December 9, 2020

Islam M J, Nguyen G, Pan R, Rajan H (2019) A comprehensive study on deep learning bug characteristics. In: Proceedings of the 2019 27th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering. ESEC/FSE 2019. https://doi.org/10.1145/3338906.3338955. Association for Computing Machinery, New York, pp 510–520

Jouppi N P, Young C, Patil N, Patterson D, Agrawal G, Bajwa R, Bates S, Bhatia S, Boden N, Borchers A, Boyle R, Cantin PL, Chao C, Clark C, Coriell J, Daley M, Dau M, Dean J, Gelb B, Ghaemmaghami TV, Gottipati R, Gulland W, Hagmann R, Ho CR, Hogberg D, Hu J, Hundt R, Hurt D, Ibarz J, Jaffey A, Jaworski A, Kaplan A, Khaitan H, Killebrew D, Koch A, Kumar N, Lacy S, Laudon J, Law J, Le D, Leary C, Liu Z, Lucke K, Lundin A, MacKean G, Maggiore A, Mahony M, Miller K, Nagarajan R, Narayanaswami R, Ni R, Nix K, Norrie T, Omernick M, Penukonda N, Phelps A, Ross J, Ross M, Salek A, Samadiani E, Severn C, Sizikov G, Snelham M, Souter J, Steinberg D, Swing A, Tan M, Thorson G, Tian B, Toma H, Tuttle E, Vasudevan V, Walter R, Wang W, Wilcox E, Yoon DH (2017) In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th annual international symposium on computer architecture, ISCA ’17. https://doi.org/10.1145/3079856.3080246. Association for Computing Machinery, New York, pp 1–12

Kingsley-Hughes A (2017) Inside apple’s new a11 bionic processor. ZDNet, September

Lacey G, Taylor G W, Areibi S (2016) Deep learning on fpgas: past, present, and future. arXiv:160204283. https://arxiv.org/abs/1602.04283

Leary C, Wang T (2017) XLA: TensorFlow, Compiled!. TensorFlow Dev Summit 2017

LeCun Y (2019) 1.1 deep learning hardware: Past, present, and future. In: 2019 IEEE International Solid- State Circuits Conference—(ISSCC). https://doi.org/10.1109/ISSCC.2019.8662396, pp 12–19

Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324. https://doi.org/10.1109/5.726791CrossRef

Li M, Liu Y, Liu X, Sun Q, You X, Yang H, Luan Z, Gan L, Yang G, Qian D (2021) The deep learning compiler: a comprehensive survey. IEEE Trans Parallel Distrib Syst 32(3):708–727. https://doi.org/10.1109/TPDS.2020.3030548CrossRef

Liu C, Yang J, Tan L, Hafiz M (2013) R2fix: automatically generating bug fixes from bug reports. In: 2013 IEEE Sixth international conference on software testing, verification and validation. https://doi.org/10.1109/ICST.2013.24, pp 282–291

Liu S, Du Z, Tao J, Han D, Luo T, Xie Y, Chen Y, Chen T (2016) Cambricon: an instruction set architecture for neural networks. In: 2016 ACM/IEEE 43rd annual international symposium on computer architecture (ISCA). IEEE, pp 393–405

Moreau T, Chen T, Jiang Z, Ceze L, Guestrin C, Krishnamurthy A (2018) VTA: an open hardware-software stack for deep learning. CoRR. arXiv:1807.04188. 1807.04188, 1807.04188

Nguyen G, Dlugolinsky S, Bobák M, Tran V, López García A, Heredia I, Malík P, Hluchy L (2019) Machine learning and deep learning frameworks and libraries for large-scale data mining: a survey. Artif Intell Rev 52(1):77–124. https://doi.org/10.1007/s10462-018-09679-zCrossRef

NVIDIA (2020) Nvidia cudnn. https://developer.nvidia.com/cudnn, retrieved on December 9, 2020

ONNX (2020) Open nueral network exchange. https://onnx.ai/, retrieved on December 9, 2020

Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, Desmaison A, Köpf A, Yang E, DeVito Z, Raison M, Tejani A, Chilamkurthy S, Steiner B, Fang L, Bai J, Chintala S (2019) Pytorch: an imperative style, high-performance deep learning library. In: Wallach H M, Larochelle H, Beygelzimer A, d’Alché-Buc F, Fox E B, Garnett R (eds) Advances in neural information processing systems 32: annual conference on neural information processing systems 2019, neurIPS 2019, December 8–14, 2019. http://papers.nips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library, Vancouver, pp 8024–8035

Ragan-Kelley J, Barnes C, Adams A, Paris S, Durand F, Amarasinghe S (2013) Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. SIGPLAN Not 48(6):519–530. https://doi.org/10.1145/2499370.2462176CrossRef

Roesch J, Lyubomirsky S, Weber L, Pollock J, Kirisame M, Chen T, Tatlock Z (2018) Relay: a new ir for machine learning frameworks. In: Proceedings of the 2nd ACM SIGPLAN international workshop on machine learning and programming languages, MAPL 2018, p 58–68. https://doi.org/10.1145/3211346.3211348. Association for Computing Machinery, New York

Rotem N, Fix J, Abdulrasool S, Deng S, Dzhabarov R, Hegeman J, Levenstein R, Maher B, Satish N, Olesen J, Park J, Rakhov A, Smelyanskiy M (2018) Glow: graph lowering compiler techniques for neural networks. CoRR arXiv:1805.00907. 1805.00907, 1805.00907

Rumelhart D E, Hinton G E, Williams R J (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536CrossRefMATH

Saha R K, Lease M, Khurshid S, Perry D E (2013) Improving bug localization using structured information retrieval. In: 2013 28th IEEE/ACM International conference on automated software engineering (ASE). https://doi.org/10.1109/ASE.2013.6693093, pp 345–355

Schmidhuber J, Hochreiter S (1997) Long short-term memory. Neural Comput 9(8):1735–1780CrossRef

Tompson J, Schlachter K (2012) An introduction to the opencl programming model

TVM (2020a) About vta. https://tvm.apache.org/vta, retrieved on December 9, 2020

TVM (2020b) Dive into deep learning compiler. https://tvm.d2l.ai/, retrieved on December 9, 2020

TVM (2020c) Tvm language reference. https://tvm.apache.org/docs/langref/index.html, retrieved on December 9, 2020

TVM (2020d) Tvm start up tutorial. https://tvm.apache.org/docs/tutorials, retrieved on December 9, 2020

TVMConf (2019) Tvm conference keynote. https://tvmconf.org/slides/2019/tvmconf-keynote-dec19.pdf, retrieved on December 9, 2020

TvmDeveloper (2018a) Datalayout structure. https://discuss.tvm.apache.org/t/datalayout-structure/80, retrieved on December 9, 2020

TvmDeveloper (2018b) Int8 quantization proposal. https://discuss.tvm.apache.org/t/int8-quantization-proposal/516, retrieved on December 9, 2020

TvmDeveloper (2018c) Tvm benchmark. https://github.com/apache/tvm/wiki/Benchmark, retrieved on December 9, 2020

TVMDeveloper (2019) Improving quantization accuracy with more precise bias. https://discuss.tvm.apache.org/t/improving-quantization-accuracy-with-more-precise-bias/2444, retrieved on December 9, 2020

TvmDeveloper (2020a) Naming consistency: util vs utils. https://discuss.tvm.apache.org/t/naming-consistency-util-vs-utils/6434, retrieved on December 9, 2020

TvmDeveloper (2020b) Tvm docs: deploy and integration. https://tvm.apache.org/docs/deploy/index.html, retrieved on December 9, 2020

TvmDeveloper (2020c) Tvm documents: runtime. https://tvm.apache.org/docs/dev/runtime.html#module, retrieved on December 9, 2020

TvmDocs (2020) Pattern matching in relay. https://tvm.apache.org/docs/langref/relay_pattern.html#pattern-language-design, retrieved on December 9, 2020

TvmUser (2018a) [autotvm] localrunner not working on windows. https://discuss.tvm.apache.org/t/autotvm-localrunner-not-working-on-windows/969, retrieved on December 9, 2020

TvmUser (2018b) [compiler] cannot compile operator mean for cuda target. https://discuss.tvm.apache.org/t/compiler-cannot-compile-operator-mean-for-cuda-target/1110, retrieved on December 9, 2020

TvmUser (2018c) Global sync across different blocks in ir builder. https://discuss.tvm.apache.org/t/global-sync-across-different-blocks-in-ir-builder/477, retrieved on December 9, 2020

TvmUser (2018d) How to load and read the.params in big endian system? https://discuss.tvm.apache.org/t/how-to-load-and-read-the-params-in-big-endian-system/203, retrieved on December 9, 2020

TvmUser (2018e) Int8 quantization proposal. https://discuss.tvm.apache.org/t/int8-quantization-proposal/516, retrieved on December 9, 2020

TvmUser (2018f) Registering operator attributes for relay pattern matching. https://discuss.tvm.apache.org/t/registering-operator-attributes-for-relay-pattern-matching/8894, retrieved on December 9, 2020

TvmUser (2018g) [solved] how to export model library to so file instead of tar for armv7 on x86 box. https://discuss.tvm.apache.org/t/solved-how-to-export-model-library-to-so-file-instead-of-tar-for-armv7-on-x86-box/970, retrieved on December 9, 2020

TvmUser (2019a) Compile official mobilenet onnx, get a very slow performance. https://discuss.tvm.apache.org/t/compile-official-mobilenet-onnx-get-a-very-slow-performance/2839, retrieved on December 9, 2020

TvmUser (2019b) [cuda]got error: Cuda error launch out of resources. https://discuss.tvm.apache.org/t/cuda-got-error-cuda-error-launch-out-of-resources/4173, retrieved on December 9, 2020

TvmUser (2019c) An error when doing autotune tensorflow net uisng opencl on intel integrated graphics. https://discuss.tvm.apache.org/t/an-error-when-doing-autotune-tensorflow-net-uisng-opencl-on-intel-integrated-graphics/4143https://discuss.tvm.apache.org/t/an-error-when-doing-autotune-tensorflow-net-uisng-opencl-on-intel-integrated-graphics/4143, retrieved on December 9, 2020

TvmUser (2019d) [frontend] tensorflow op: Fifoqueuev2 and queuedequeuemanyv2 are not supported. https://discuss.tvm.apache.org/t/frontend-tensorflow-op-fifoqueuev2-and-queuedequeuemanyv2-are-not-supported/1596, retrieved on December 9, 2020

TvmUser (2019e) Limit cpu cores for auto tuned model. https://discuss.tvm.apache.org/t/limit-cpu-cores-for-auto-tuned-model/2384, retrieved on December 9, 2020

TvmUser (2019f) [quantization] how to quantize transpose and nn.pad operators? https://discuss.tvm.apache.org/t/quantization-how-to-quantize-transpose-and-nn-pad-operators/3861, retrieved on December 9, 2020

TvmUser (2019g) Ssd gluoncv: incorrect inference result on opencl arm mali. https://discuss.tvm.apache.org/t/ssd-gluoncv-incorrect-inference-result-on-opencl-arm-mali/2848, retrieved on December 9, 2020

TvmUser (2019h) Tensorarray globalvar and globaltypevar confusion. https://discuss.tvm.apache.org/t/tensorarray-globalvar-and-globaltypevar-confusion/4567, retrieved on December 9, 2020

TvmUser (2019i) What’s the difference between build() and create_executor() in tvm.relay.build_module? https://discuss.tvm.apache.org/t/whats-the-difference-between-build-and-create-executor-in-tvm-relay-build-module/1967, retrieved on December 9, 2020

TvmUser (2019j) What’s the model bias in tvm paper. https://discuss.tvm.apache.org/t/whats-the-model-bias-in-tvm-paper/2963, retrieved on December 9, 2020

TvmUser (2020a) Can tvm now support batched inference? autotvm runs twice as long as tensorflow. https://discuss.tvm.apache.org/t/can-tvm-now-support-batched-inference-autotvm-runs-twice-as-long-as-tensorflow/6405, retrieved on December 9, 2020

TvmUser (2020b) Complex pattern matching in relay. https://discuss.tvm.apache.org/t/complex-pattern-matching-in-relay/5633, retrieved on December 9, 2020

TvmUser (2020c) [resolved][performance regression] migrate all low-level passes to the pass manager pr causing regression. https://discuss.tvm.apache.org/t/resolved-performance-regression-migrate-all-low-level-passes-to-the-pass-manager-pr-causing-regression/6246, retrieved on December 9, 2020

TvmUser (2020d) [rfc] improve pull requests with respect to bug fixes. https://discuss.tvm.apache.org/t/rfc-improve-pull-requests-with-respect-to-bug-fixes/6529, retrieved on December 9, 2020

TvmUser (2020e) Rocm ’segmentation fault’ error when auto-tuning. https://discuss.tvm.apache.org/t/autotvm-stuck-during-tuning/6011, retrieved on December 9, 2020

TvmUser (2020f) Rpc error for large arrays. https://discuss.tvm.apache.org/t/rpc-error-for-large-arrays/6591, retrived on December 9, 2020

TvmUser (2020g) Same shape pattern. https://discuss.tvm.apache.org/t/same-shape-pattern/7012, retrieved on December 9, 2020

TvmUser (2020h) Support for tvm relay with wasm runtime. https://discuss.tvm.apache.org/t/support-for-tvm-relay-with-wasm-runtime/6765, retrieved on December 9, 2020

TvmUser (2020i) Where is dldatatype defined? https://discuss.tvm.apache.org/t/where-is-dldatatype-defined/6071, retrieved on December 9, 2020

Vasilache N, Zinenko O, Theodoridis T, Goyal P, DeVito Z, Moses W S, Verdoolaege S, Adams A, Cohen A (2018) Tensor comprehensions: framework-agnostic high-performance machine learning abstractions. arXiv:1802.04730. 1802.04730, 1802.04730

Wang S, Lo D (2016) Amalgam+: composing rich information sources for accurate bug localization. J Softw Evol Process 28(10):921–942. https://doi.org/10.1002/smr.1801CrossRef

Wang X, Tu Z, Wang L, Shi S (2020) Tencent ai lab machine translation systems for the wmt20 biomedical translation task. In: Proceedings of the fifth conference on machine translation, pp 881–886

Xing Y, Weng J, Wang Y, Sui L, Shan Y, Wang Y (2019) An in-depth comparison of compilers for deep neural networks on hardware, pp 1–8. https://doi.org/10.1109/ICESS.2019.8782480

Zhang Y, Chen Y, Cheung S C, Xiong Y, Zhang L (2018) An empirical study on tensorflow program bugs. In: Proceedings of the 27th ACM SIGSOFT international symposium on software testing and analysis, ISSTA 2018. https://doi.org/10.1145/3213846.3213866. Association for Computing Machinery, New York, pp 129–140

Zhang T, Gao C, Ma L, Lyu M, Kim M (2019) An empirical study of common challenges in developing deep learning applications. In: 2019 IEEE 30th international symposium on software reliability engineering (ISSRE). https://doi.org/10.1109/ISSRE.2019.00020, pp 104–115

Zhang X, Xie X, Ma L, Du X, Hu Q, Liu Y, Zhao J, Sun M (2020) Towards characterizing adversarial defects of deep learning software from the lens of uncertainty. In: Proceedings of the ACM/IEEE 42nd international conference on software engineering, ICSE ’20. https://doi.org/10.1145/3377811.3380368. Association for Computing Machinery, New York, pp 739–751

Zimmermann T, Premraj R, Bettenburg N, Just S, Schroter A, Weiss C (2010) What makes a good bug report? IEEE Trans Softw Eng 36 (5):618–643. https://doi.org/10.1109/TSE.2010.63CrossRef

Titel: On the usage and development of deep learning compilers: an empirical study on TVM
verfasst von: Xiongfei Wu
Jinqiu Yang
Lei Ma
Yinxing Xue
Jianjun Zhao
Publikationsdatum: 01.12.2022
Verlag: Springer US
Erschienen in: Empirical Software Engineering / Ausgabe 7/2022
Print ISSN: 1382-3256
Elektronische ISSN: 1573-7616
DOI: https://doi.org/10.1007/s10664-022-10221-7

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Springer Professional "Wirtschaft+Technik"

Weitere Artikel der Ausgabe 7/2022

Intensifying the search-based optimization of product line architectures with crossover operators

Motivating members’ involvement to effectually conduct collaborative software process tailoring

SmartFast: an accurate and robust formal analysis tool for Ethereum smart contracts

C2M: a maturity model for the evaluation of communication in distributed software development

StateAFL: Greybox fuzzing for stateful network servers

Using Screenshot Attachments in Issue Reports for Triaging

Premium Partner