Academic Journal
Key Operator Vectorization for LeNet and ResNet Based on Buddy Compiler.
| Title: | Key Operator Vectorization for LeNet and ResNet Based on Buddy Compiler. |
|---|---|
| Authors: | Chen, Juncheng, Chen, Weiwei, Cai, Zhi |
| Source: | Applied Sciences (2076-3417); Sep2025, Vol. 15 Issue 17, p9523, 17p |
| Subject Terms: | Deep learning, Compilers (Computer programs), Prediction models, Mathematical optimization |
| Abstract: | Deep learning has emerged as a prominent focus in both academia and industry, with a wide range of models being applied across diverse domains. Fast and efficient model inference is essential for the practical deployment of deep learning models. Under specific hardware constraints, accelerating inference remains a key research challenge. Common techniques for model acceleration include quantization, pruning, and vectorization. Although quantization and pruning primarily reduce model precision or complexity to enhance efficiency, this paper concentrates on vectorization, a technique that accelerates models by increasing the parallelism of operator execution. Based on the open-source Buddy-MLIR project, this work implements vectorization optimizations for Matmul, Conv2d, and Max Pooling operations to improve inference performance. These optimizations are designed as compiler passes and integrated into the Buddy-MLIR framework, offering a general solution for vectorizing such operators. Two optimization approaches are proposed: general vectorization and adaptive vectorization. Compared to the standard MLIR lowering pipeline and the fully optimized LLVM backend, the proposed general and adaptive vectorization methods reduce the inference latency of LeNet-5 by 26.7 % and 37.3 % , respectively. For the more complex ResNet-18 model, these methods achieve latency reductions of 79.9 % and 82.6 % , respectively. [ABSTRACT FROM AUTHOR] |
| Copyright of Applied Sciences (2076-3417) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Complementary Index |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=20763417&ISBN=&volume=15&issue=17&date=20250901&spage=9523&pages=9523-9539&title=Applied Sciences (2076-3417)&atitle=Key%20Operator%20Vectorization%20for%20LeNet%20and%20ResNet%20Based%20on%20Buddy%20Compiler.&aulast=Chen%2C%20Juncheng&id=DOI:10.3390/app15179523 Name: Full Text Finder (for New FTF UI) (ns324271) Category: fullText Text: Full Text Finder MouseOverText: Full Text Finder |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 187980398 RelevancyScore: 1023 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1023.08752441406 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Key Operator Vectorization for LeNet and ResNet Based on Buddy Compiler. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Chen%2C+Juncheng%22">Chen, Juncheng</searchLink><br /><searchLink fieldCode="AR" term="%22Chen%2C+Weiwei%22">Chen, Weiwei</searchLink><br /><searchLink fieldCode="AR" term="%22Cai%2C+Zhi%22">Cai, Zhi</searchLink> – Name: TitleSource Label: Source Group: Src Data: Applied Sciences (2076-3417); Sep2025, Vol. 15 Issue 17, p9523, 17p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Compilers+%28Computer+programs%29%22">Compilers (Computer programs)</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Deep learning has emerged as a prominent focus in both academia and industry, with a wide range of models being applied across diverse domains. Fast and efficient model inference is essential for the practical deployment of deep learning models. Under specific hardware constraints, accelerating inference remains a key research challenge. Common techniques for model acceleration include quantization, pruning, and vectorization. Although quantization and pruning primarily reduce model precision or complexity to enhance efficiency, this paper concentrates on vectorization, a technique that accelerates models by increasing the parallelism of operator execution. Based on the open-source Buddy-MLIR project, this work implements vectorization optimizations for Matmul, Conv2d, and Max Pooling operations to improve inference performance. These optimizations are designed as compiler passes and integrated into the Buddy-MLIR framework, offering a general solution for vectorizing such operators. Two optimization approaches are proposed: general vectorization and adaptive vectorization. Compared to the standard MLIR lowering pipeline and the fully optimized LLVM backend, the proposed general and adaptive vectorization methods reduce the inference latency of LeNet-5 by 26.7 % and 37.3 % , respectively. For the more complex ResNet-18 model, these methods achieve latency reductions of 79.9 % and 82.6 % , respectively. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Applied Sciences (2076-3417) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=187980398 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/app15179523 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 17 StartPage: 9523 Subjects: – SubjectFull: Deep learning Type: general – SubjectFull: Compilers (Computer programs) Type: general – SubjectFull: Prediction models Type: general – SubjectFull: Mathematical optimization Type: general Titles: – TitleFull: Key Operator Vectorization for LeNet and ResNet Based on Buddy Compiler. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Chen, Juncheng – PersonEntity: Name: NameFull: Chen, Weiwei – PersonEntity: Name: NameFull: Cai, Zhi IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: Sep2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 20763417 Numbering: – Type: volume Value: 15 – Type: issue Value: 17 Titles: – TitleFull: Applied Sciences (2076-3417) Type: main |
| ResultId | 1 |