CGO 2024 – Author Index

A B C D E F G H I J K L M O P Q R S T V W X Y Z

	Abellán, José L.	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi:
	Agostini, Nicolas Bohm	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi:
	Alves, Artur Cesar Araujo	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Amarasinghe, Saman	CGO '24: "AskIt: Unified Programming ..." AskIt: Unified Programming Interface for Programming with Large Language Models Katsumi Okuda and Saman Amarasinghe (Massachusetts Institute of Technology, USA; Mitsubishi Electric Corporation, Japan) @InProceedings{CGO24p49, author = {Katsumi Okuda and Saman Amarasinghe}, title = {AskIt: Unified Programming Interface for Programming with Large Language Models}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {49-48}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p229-p (type: Full Paper (11 pages excl. references)) doi:
	Ancourt, Corinne	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Armengol-Estapé, Jordi	CGO '24: "SLaDe: A Portable Small Language ..." SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly Jordi Armengol-Estapé, Jackson Woodruff, Chris Cummins, and Michael F. P. O'Boyle (University of Edinburgh, United Kingdom; Meta AI Research, USA) @InProceedings{CGO24p81, author = {Jordi Armengol-Estapé and Jackson Woodruff and Chris Cummins and Michael F. P. O'Boyle}, title = {SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {81-80}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p72-p (type: Full Paper (11 pages excl. references)) doi:
	Bao, Guoqing	CGO '24: "PresCount: Effective Register ..." PresCount: Effective Register Allocation for Bank Conflict Reduction Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, and Jianguo Yao (Shanghai Jiao Tong University, China; Shanghai Enflame Technology, China) @InProceedings{CGO24p209, author = {Xiaofeng Guan and Hao Zhou and Guoqing Bao and Handong Li and Liang Zhu and Jianguo Yao}, title = {PresCount: Effective Register Allocation for Bank Conflict Reduction}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {209-208}, doi = {}, year = {2024}, } Article: cgo24main-p16-p (type: Full Paper (11 pages excl. references)) doi:
	Barollet, Théo	CGO '24: "EasyTracker: A Python Library ..." EasyTracker: A Python Library for Controlling and Inspecting Program Execution Théo Barollet, Christophe Guillon, Manuel Selva, François Broquedis, Florent Bouchez-Tichadou, and Fabrice Rastello (University Grenoble Alpes - Inria - CNRS - Grenoble INP - LIG, France) @InProceedings{CGO24p449, author = {Théo Barollet and Christophe Guillon and Manuel Selva and François Broquedis and Florent Bouchez-Tichadou and Fabrice Rastello}, title = {EasyTracker: A Python Library for Controlling and Inspecting Program Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {449-448}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p359-p (type: Full Paper (11 pages excl. references)) doi:
	Barthou, Denis	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Bastoul, Cédric	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Béchennec, Jean-Luc	CGO '24: "SCHEMATIC: Compile-Time Checkpoint ..." SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems Hugo Reymond, Jean-Luc Béchennec, Mikaël Briday, Sébastien Faucou, Isabelle Puaut, and Erven Rohou (Université de Rennes - Inria - CNRS - IRISA, France; Nantes Université - École Centrale Nantes - CNRS - LS2N - UMR 6004, France) @InProceedings{CGO24p321, author = {Hugo Reymond and Jean-Luc Béchennec and Mikaël Briday and Sébastien Faucou and Isabelle Puaut and Erven Rohou}, title = {SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {321-320}, doi = {}, year = {2024}, } Article: cgo24main-p24-p (type: Full Paper (11 pages excl. references)) doi:
	Bellavita, Julian	CGO '24: "Tackling the Matrix Multiplication ..." Tackling the Matrix Multiplication Micro-kernel Generation with Exo Adrián Castelló, Julian Bellavita, Grace Dinh, Yuka Ikarashi, and Héctor Martínez (Universitat Politècnica de València, Spain; Cornell University, USA; University of California at Berkeley, USA; Massachusetts Institute of Technology, USA; Universidad de Córdoba, Spain) @InProceedings{CGO24p225, author = {Adrián Castelló and Julian Bellavita and Grace Dinh and Yuka Ikarashi and Héctor Martínez}, title = {Tackling the Matrix Multiplication Micro-kernel Generation with Exo}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {225-224}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Article: cgo24main-p49-p (type: Full Paper (11 pages excl. references)) doi:
	Bora, Utpal	CGO '24: "OptiWISE: Combining Sampling ..." OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis Yuxin Guo, Alex W. Chadwick, Márton Erdős, Utpal Bora, Ilias Vougioukas, Giacomo Gabrielli, and Timothy M. Jones (University of Cambridge, United Kingdom; Arm, USA; Arm, United Kingdom) @InProceedings{CGO24p465, author = {Yuxin Guo and Alex W. Chadwick and Márton Erdős and Utpal Bora and Ilias Vougioukas and Giacomo Gabrielli and Timothy M. Jones}, title = {OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {465-464}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p78-p (type: Full Paper (11 pages excl. references)) doi:
	Bouchez-Tichadou, Florent	CGO '24: "EasyTracker: A Python Library ..." EasyTracker: A Python Library for Controlling and Inspecting Program Execution Théo Barollet, Christophe Guillon, Manuel Selva, François Broquedis, Florent Bouchez-Tichadou, and Fabrice Rastello (University Grenoble Alpes - Inria - CNRS - Grenoble INP - LIG, France) @InProceedings{CGO24p449, author = {Théo Barollet and Christophe Guillon and Manuel Selva and François Broquedis and Florent Bouchez-Tichadou and Fabrice Rastello}, title = {EasyTracker: A Python Library for Controlling and Inspecting Program Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {449-448}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p359-p (type: Full Paper (11 pages excl. references)) doi:
	Briday, Mikaël	CGO '24: "SCHEMATIC: Compile-Time Checkpoint ..." SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems Hugo Reymond, Jean-Luc Béchennec, Mikaël Briday, Sébastien Faucou, Isabelle Puaut, and Erven Rohou (Université de Rennes - Inria - CNRS - IRISA, France; Nantes Université - École Centrale Nantes - CNRS - LS2N - UMR 6004, France) @InProceedings{CGO24p321, author = {Hugo Reymond and Jean-Luc Béchennec and Mikaël Briday and Sébastien Faucou and Isabelle Puaut and Erven Rohou}, title = {SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {321-320}, doi = {}, year = {2024}, } Article: cgo24main-p24-p (type: Full Paper (11 pages excl. references)) doi:
	Brodman, James	CGO '24: "Experiences Building an MLIR-Based ..." Experiences Building an MLIR-Based SYCL Compiler Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, and James Brodman (Intel Corporation, Canada; Codeplay Software, United Kingdom; Intel Corporation, USA) @InProceedings{CGO24p497, author = {Ettore Tiotto and Víctor Pérez and Whitney Tsang and Lukas Sommer and Julian Oppermann and Victor Lomüller and Mehdi Goli and James Brodman}, title = {Experiences Building an MLIR-Based SYCL Compiler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {497-496}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p70-p (type: Full Paper (11 pages excl. references)) doi:
	Broquedis, François	CGO '24: "EasyTracker: A Python Library ..." EasyTracker: A Python Library for Controlling and Inspecting Program Execution Théo Barollet, Christophe Guillon, Manuel Selva, François Broquedis, Florent Bouchez-Tichadou, and Fabrice Rastello (University Grenoble Alpes - Inria - CNRS - Grenoble INP - LIG, France) @InProceedings{CGO24p449, author = {Théo Barollet and Christophe Guillon and Manuel Selva and François Broquedis and Florent Bouchez-Tichadou and Fabrice Rastello}, title = {EasyTracker: A Python Library for Controlling and Inspecting Program Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {449-448}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p359-p (type: Full Paper (11 pages excl. references)) doi:
	Burgstaller, Bernd	CGO '24: "BEC: Bit-Level Static Analysis ..." BEC: Bit-Level Static Analysis for Reliability against Soft Errors Yousun Ko and Bernd Burgstaller (Yonsei University, South Korea) @InProceedings{CGO24p353, author = {Yousun Ko and Bernd Burgstaller}, title = {BEC: Bit-Level Static Analysis for Reliability against Soft Errors}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {353-352}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p191-p (type: Full Paper (11 pages excl. references)) doi:
	Campanoni, Simone	CGO '24: "Representing Data Collections ..." Representing Data Collections in an SSA Form Tommy McMichen, Nathan Greiner, Peter Zhong, Federico Sossai, Atmn Patel, and Simone Campanoni (Northwestern University, USA) @InProceedings{CGO24p385, author = {Tommy McMichen and Nathan Greiner and Peter Zhong and Federico Sossai and Atmn Patel and Simone Campanoni}, title = {Representing Data Collections in an SSA Form}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {385-384}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p148-p (type: Full Paper (11 pages excl. references)) doi:
	Cano, José	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi:
	Cao, Liqing	CGO '24: "Boosting the Performance of ..." Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations Haofeng Li, Jie Lu, Haining Meng, Liqing Cao, Lian Li, and Lin Gao (Institute of Computing Technology at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Zhongguancun Laboratory, China; TianqiSoft, China) @InProceedings{CGO24p369, author = {Haofeng Li and Jie Lu and Haining Meng and Liqing Cao and Lian Li and Lin Gao}, title = {Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {369-368}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p193-p (type: Full Paper (11 pages excl. references)) doi:
	Carloni, Filippo	CGO '24: "One Automaton to Rule Them ..." One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution Luisa Cicolini, Filippo Carloni, Marco D. Santambrogio, and Davide Conficconi (Politecnico di Milano, Italy) @InProceedings{CGO24p241, author = {Luisa Cicolini and Filippo Carloni and Marco D. Santambrogio and Davide Conficconi}, title = {One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {241-240}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p368-p (type: Full Paper (11 pages excl. references)) doi:
	Castelló, Adrián	CGO '24: "Tackling the Matrix Multiplication ..." Tackling the Matrix Multiplication Micro-kernel Generation with Exo Adrián Castelló, Julian Bellavita, Grace Dinh, Yuka Ikarashi, and Héctor Martínez (Universitat Politècnica de València, Spain; Cornell University, USA; University of California at Berkeley, USA; Massachusetts Institute of Technology, USA; Universidad de Córdoba, Spain) @InProceedings{CGO24p225, author = {Adrián Castelló and Julian Bellavita and Grace Dinh and Yuka Ikarashi and Héctor Martínez}, title = {Tackling the Matrix Multiplication Micro-kernel Generation with Exo}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {225-224}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Article: cgo24main-p49-p (type: Full Paper (11 pages excl. references)) doi:
	Chabbi, Milind	CGO '24: "EasyView: Bringing Performance ..." EasyView: Bringing Performance Profiles into Integrated Development Environments Qidong Zhao, Milind Chabbi, and Xu Liu (North Carolina State University, USA; Scalable Machines Research, USA) @InProceedings{CGO24p481, author = {Qidong Zhao and Milind Chabbi and Xu Liu}, title = {EasyView: Bringing Performance Profiles into Integrated Development Environments}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {481-480}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Functional Results Reproduced Article: cgo24main-p107-p (type: Full Paper (11 pages excl. references)) doi: CGO '24: "Unveiling and Vanquishing ..." Unveiling and Vanquishing Goroutine Leaks in Enterprise Microservices: A Dynamic Analysis Approach Georgian-Vlad Saioc, Dmitriy Shirchenko, and Milind Chabbi (Aarhus University, Denmark; Uber Technologies, Denmark; Uber Technologies, USA) @InProceedings{CGO24p513, author = {Georgian-Vlad Saioc and Dmitriy Shirchenko and Milind Chabbi}, title = {Unveiling and Vanquishing Goroutine Leaks in Enterprise Microservices: A Dynamic Analysis Approach}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {513-512}, doi = {}, year = {2024}, } Article: cgo24main-p237-p (type: Full Paper (11 pages excl. references)) doi:
	Chadwick, Alex W.	CGO '24: "OptiWISE: Combining Sampling ..." OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis Yuxin Guo, Alex W. Chadwick, Márton Erdős, Utpal Bora, Ilias Vougioukas, Giacomo Gabrielli, and Timothy M. Jones (University of Cambridge, United Kingdom; Arm, USA; Arm, United Kingdom) @InProceedings{CGO24p465, author = {Yuxin Guo and Alex W. Chadwick and Márton Erdős and Utpal Bora and Ilias Vougioukas and Giacomo Gabrielli and Timothy M. Jones}, title = {OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {465-464}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p78-p (type: Full Paper (11 pages excl. references)) doi:
	Chen, Ciyong	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Cheng, Xianhang	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Cicolini, Luisa	CGO '24: "One Automaton to Rule Them ..." One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution Luisa Cicolini, Filippo Carloni, Marco D. Santambrogio, and Davide Conficconi (Politecnico di Milano, Italy) @InProceedings{CGO24p241, author = {Luisa Cicolini and Filippo Carloni and Marco D. Santambrogio and Davide Conficconi}, title = {One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {241-240}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p368-p (type: Full Paper (11 pages excl. references)) doi:
	Cole, Murray	CGO '24: "Revealing Compiler Heuristics ..." Revealing Compiler Heuristics through Automated Discovery and Optimization Volker Seeker, Chris Cummins, Murray Cole, Björn Franke, Kim Hazelwood, and Hugh Leather (Meta AI Research, USA; University of Edinburgh, United Kingdom) @InProceedings{CGO24p65, author = {Volker Seeker and Chris Cummins and Murray Cole and Björn Franke and Kim Hazelwood and Hugh Leather}, title = {Revealing Compiler Heuristics through Automated Discovery and Optimization}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {65-64}, doi = {}, year = {2024}, } Article: cgo24main-p73-p (type: Full Paper (11 pages excl. references)) doi:
	Conficconi, Davide	CGO '24: "One Automaton to Rule Them ..." One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution Luisa Cicolini, Filippo Carloni, Marco D. Santambrogio, and Davide Conficconi (Politecnico di Milano, Italy) @InProceedings{CGO24p241, author = {Luisa Cicolini and Filippo Carloni and Marco D. Santambrogio and Davide Conficconi}, title = {One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {241-240}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p368-p (type: Full Paper (11 pages excl. references)) doi:
	Consolaro, Gianpietro	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Cui, Jingze	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Cui, Jinku	CGO '24: "DrPy: Pinpointing Inefficient ..." DrPy: Pinpointing Inefficient Memory Usage in Multi-Layer Python Applications Jinku Cui, Qidong Zhao, Yueming Hao, and Xu Liu (North Carolina State University, USA) @InProceedings{CGO24p305, author = {Jinku Cui and Qidong Zhao and Yueming Hao and Xu Liu}, title = {DrPy: Pinpointing Inefficient Memory Usage in Multi-Layer Python Applications}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {305-304}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p141-p (type: Full Paper (11 pages excl. references)) doi:
	Cummins, Chris	CGO '24: "Revealing Compiler Heuristics ..." Revealing Compiler Heuristics through Automated Discovery and Optimization Volker Seeker, Chris Cummins, Murray Cole, Björn Franke, Kim Hazelwood, and Hugh Leather (Meta AI Research, USA; University of Edinburgh, United Kingdom) @InProceedings{CGO24p65, author = {Volker Seeker and Chris Cummins and Murray Cole and Björn Franke and Kim Hazelwood and Hugh Leather}, title = {Revealing Compiler Heuristics through Automated Discovery and Optimization}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {65-64}, doi = {}, year = {2024}, } Article: cgo24main-p73-p (type: Full Paper (11 pages excl. references)) doi: CGO '24: "SLaDe: A Portable Small Language ..." SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly Jordi Armengol-Estapé, Jackson Woodruff, Chris Cummins, and Michael F. P. O'Boyle (University of Edinburgh, United Kingdom; Meta AI Research, USA) @InProceedings{CGO24p81, author = {Jordi Armengol-Estapé and Jackson Woodruff and Chris Cummins and Michael F. P. O'Boyle}, title = {SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {81-80}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p72-p (type: Full Paper (11 pages excl. references)) doi:
	Dehnavi, Maryam Mehri	CGO '24: "A Framework for Fine-Grained ..." A Framework for Fine-Grained Synchronization of Dependent GPU Kernels Abhinav Jangda, Saeed Maleki, Maryam Mehri Dehnavi, Madan Musuvathi, and Olli Saarikivi (Microsoft Research, USA; University of Toronto, Canada) @InProceedings{CGO24p113, author = {Abhinav Jangda and Saeed Maleki and Maryam Mehri Dehnavi and Madan Musuvathi and Olli Saarikivi}, title = {A Framework for Fine-Grained Synchronization of Dependent GPU Kernels}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {113-112}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p62-p (type: Full Paper (11 pages excl. references)) doi:
	Dinh, Grace	CGO '24: "Tackling the Matrix Multiplication ..." Tackling the Matrix Multiplication Micro-kernel Generation with Exo Adrián Castelló, Julian Bellavita, Grace Dinh, Yuka Ikarashi, and Héctor Martínez (Universitat Politècnica de València, Spain; Cornell University, USA; University of California at Berkeley, USA; Massachusetts Institute of Technology, USA; Universidad de Córdoba, Spain) @InProceedings{CGO24p225, author = {Adrián Castelló and Julian Bellavita and Grace Dinh and Yuka Ikarashi and Héctor Martínez}, title = {Tackling the Matrix Multiplication Micro-kernel Generation with Exo}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {225-224}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Article: cgo24main-p49-p (type: Full Paper (11 pages excl. references)) doi:
	Domke, Jens	CGO '24: "Retargeting and Respecializing ..." Retargeting and Respecializing GPU Workloads for Performance Portability Ivan R. Ivanov, Oleksandr Zinenko, Jens Domke, Toshio Endo, and William S. Moses (Tokyo Institute of Technology, Japan; RIKEN R-CCS, Japan; Google DeepMind, France; University of Illinois at Urbana-Champaign, USA; Google DeepMind, USA) @InProceedings{CGO24p145, author = {Ivan R. Ivanov and Oleksandr Zinenko and Jens Domke and Toshio Endo and William S. Moses}, title = {Retargeting and Respecializing GPU Workloads for Performance Portability}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {145-144}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p19-p (type: Full Paper (11 pages excl. references)) doi:
	Dong, Rongchao	CGO '24: "A System-Level Dynamic Binary ..." A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules Jinhu Jiang, Chaoyi Liang, Rongchao Dong, Zhaohui Yang, Zhongjun Zhou, Wenwen Wang, Pen-Chung Yew, and Weihua Zhang (Fudan University, China; University of Georgia, USA; University of Minnesota at Twin Cities, USA) @InProceedings{CGO24p529, author = {Jinhu Jiang and Chaoyi Liang and Rongchao Dong and Zhaohui Yang and Zhongjun Zhou and Wenwen Wang and Pen-Chung Yew and Weihua Zhang}, title = {A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {529-528}, doi = {}, year = {2024}, } Article: cgo24main-p51-p (type: Full Paper (11 pages excl. references)) doi:
	Du, Longsheng	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Dubach, Christophe	CGO '24: "Latent Idiom Recognition for ..." Latent Idiom Recognition for a Minimalist Functional Array Language using Equality Saturation Jonathan Van der Cruysse and Christophe Dubach (McGill University, Canada) @InProceedings{CGO24p337, author = {Jonathan Van der Cruysse and Christophe Dubach}, title = {Latent Idiom Recognition for a Minimalist Functional Array Language using Equality Saturation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {337-336}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p104-p (type: Full Paper (11 pages excl. references)) doi:
	Endo, Toshio	CGO '24: "Retargeting and Respecializing ..." Retargeting and Respecializing GPU Workloads for Performance Portability Ivan R. Ivanov, Oleksandr Zinenko, Jens Domke, Toshio Endo, and William S. Moses (Tokyo Institute of Technology, Japan; RIKEN R-CCS, Japan; Google DeepMind, France; University of Illinois at Urbana-Champaign, USA; Google DeepMind, USA) @InProceedings{CGO24p145, author = {Ivan R. Ivanov and Oleksandr Zinenko and Jens Domke and Toshio Endo and William S. Moses}, title = {Retargeting and Respecializing GPU Workloads for Performance Portability}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {145-144}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p19-p (type: Full Paper (11 pages excl. references)) doi:
	Engelke, Alexis	CGO '24: "Compile-Time Analysis of Compiler ..." Compile-Time Analysis of Compiler Frameworks for Query Compilation Alexis Engelke and Tobias Schwarz (TU Munich, Germany) @InProceedings{CGO24p289, author = {Alexis Engelke and Tobias Schwarz}, title = {Compile-Time Analysis of Compiler Frameworks for Query Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {289-288}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p29-p (type: Full Paper (11 pages excl. references)) doi:
	Erdős, Márton	CGO '24: "OptiWISE: Combining Sampling ..." OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis Yuxin Guo, Alex W. Chadwick, Márton Erdős, Utpal Bora, Ilias Vougioukas, Giacomo Gabrielli, and Timothy M. Jones (University of Cambridge, United Kingdom; Arm, USA; Arm, United Kingdom) @InProceedings{CGO24p465, author = {Yuxin Guo and Alex W. Chadwick and Márton Erdős and Utpal Bora and Ilias Vougioukas and Giacomo Gabrielli and Timothy M. Jones}, title = {OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {465-464}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p78-p (type: Full Paper (11 pages excl. references)) doi:
	Fan, Yuyou	CGO '24: "High-Throughput, Formal-Methods-Assisted ..." High-Throughput, Formal-Methods-Assisted Fuzzing for LLVM Yuyou Fan and John Regehr (University of Utah, USA) @InProceedings{CGO24p433, author = {Yuyou Fan and John Regehr}, title = {High-Throughput, Formal-Methods-Assisted Fuzzing for LLVM}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {433-432}, doi = {}, year = {2024}, } Article: cgo24main-p241-p (type: Full Paper (11 pages excl. references)) doi:
	Faucou, Sébastien	CGO '24: "SCHEMATIC: Compile-Time Checkpoint ..." SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems Hugo Reymond, Jean-Luc Béchennec, Mikaël Briday, Sébastien Faucou, Isabelle Puaut, and Erven Rohou (Université de Rennes - Inria - CNRS - IRISA, France; Nantes Université - École Centrale Nantes - CNRS - LS2N - UMR 6004, France) @InProceedings{CGO24p321, author = {Hugo Reymond and Jean-Luc Béchennec and Mikaël Briday and Sébastien Faucou and Isabelle Puaut and Erven Rohou}, title = {SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {321-320}, doi = {}, year = {2024}, } Article: cgo24main-p24-p (type: Full Paper (11 pages excl. references)) doi:
	Franke, Björn	CGO '24: "Revealing Compiler Heuristics ..." Revealing Compiler Heuristics through Automated Discovery and Optimization Volker Seeker, Chris Cummins, Murray Cole, Björn Franke, Kim Hazelwood, and Hugh Leather (Meta AI Research, USA; University of Edinburgh, United Kingdom) @InProceedings{CGO24p65, author = {Volker Seeker and Chris Cummins and Murray Cole and Björn Franke and Kim Hazelwood and Hugh Leather}, title = {Revealing Compiler Heuristics through Automated Discovery and Optimization}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {65-64}, doi = {}, year = {2024}, } Article: cgo24main-p73-p (type: Full Paper (11 pages excl. references)) doi:
	Fu, Hao	CGO '24: "Ecmas: Efficient Circuit Mapping ..." Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code Mingzheng Zhu, Hao Fu, Jun Wu, Chi Zhang, Wei Xie, and Xiang-Yang Li (University of Science and Technology of China, China) @InProceedings{CGO24p193, author = {Mingzheng Zhu and Hao Fu and Jun Wu and Chi Zhang and Wei Xie and Xiang-Yang Li}, title = {Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {193-192}, doi = {}, year = {2024}, } Article: cgo24main-p100-p (type: Full Paper (11 pages excl. references)) doi:
	Fu, Qiang	CGO '24: "JITSPMM: Just-in-Time Instruction ..." JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication Qiang Fu, Thomas B. Rolinger, and H. Howie Huang (Advanced Micro Devices, USA; NVIDIA, USA; George Washington University, USA) @InProceedings{CGO24p561, author = {Qiang Fu and Thomas B. Rolinger and H. Howie Huang}, title = {JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {561-560}, doi = {}, year = {2024}, } Article: cgo24main-p81-p (type: Full Paper (11 pages excl. references)) doi:
	Gabrielli, Giacomo	CGO '24: "OptiWISE: Combining Sampling ..." OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis Yuxin Guo, Alex W. Chadwick, Márton Erdős, Utpal Bora, Ilias Vougioukas, Giacomo Gabrielli, and Timothy M. Jones (University of Cambridge, United Kingdom; Arm, USA; Arm, United Kingdom) @InProceedings{CGO24p465, author = {Yuxin Guo and Alex W. Chadwick and Márton Erdős and Utpal Bora and Ilias Vougioukas and Giacomo Gabrielli and Timothy M. Jones}, title = {OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {465-464}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p78-p (type: Full Paper (11 pages excl. references)) doi:
	Gao, Lin	CGO '24: "Boosting the Performance of ..." Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations Haofeng Li, Jie Lu, Haining Meng, Liqing Cao, Lian Li, and Lin Gao (Institute of Computing Technology at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Zhongguancun Laboratory, China; TianqiSoft, China) @InProceedings{CGO24p369, author = {Haofeng Li and Jie Lu and Haining Meng and Liqing Cao and Lian Li and Lin Gao}, title = {Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {369-368}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p193-p (type: Full Paper (11 pages excl. references)) doi:
	Geeson, Luke	CGO '24: "Compiler Testing with Relaxed ..." Compiler Testing with Relaxed Memory Models Luke Geeson and Lee Smith (University College London, United Kingdom; Arm, United Kingdom) @InProceedings{CGO24p417, author = {Luke Geeson and Lee Smith}, title = {Compiler Testing with Relaxed Memory Models}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {417-416}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p169-p (type: Full Paper (11 pages excl. references)) doi:
	Georgakoudis, Giorgis	CGO '24: "Enhancing Performance through ..." Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs Alnis Murtovi, Giorgis Georgakoudis, Konstantinos Parasyris, Chunhua Liao, Ignacio Laguna, and Bernhard Steffen (TU Dortmund, Germany; Lawrence Livermore National Laboratory, USA) @InProceedings{CGO24p129, author = {Alnis Murtovi and Giorgis Georgakoudis and Konstantinos Parasyris and Chunhua Liao and Ignacio Laguna and Bernhard Steffen}, title = {Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {129-128}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p103-p (type: Full Paper (11 pages excl. references)) doi:
	Gibson, Perry	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi:
	Goli, Mehdi	CGO '24: "Experiences Building an MLIR-Based ..." Experiences Building an MLIR-Based SYCL Compiler Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, and James Brodman (Intel Corporation, Canada; Codeplay Software, United Kingdom; Intel Corporation, USA) @InProceedings{CGO24p497, author = {Ettore Tiotto and Víctor Pérez and Whitney Tsang and Lukas Sommer and Julian Oppermann and Victor Lomüller and Mehdi Goli and James Brodman}, title = {Experiences Building an MLIR-Based SYCL Compiler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {497-496}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p70-p (type: Full Paper (11 pages excl. references)) doi:
	Gordon, Vahl Scott	CGO '24: "Instruction Scheduling for ..." Instruction Scheduling for the GPU on the GPU Ghassan Shobaki, Pınar Muyan-Özçelik, Josh Hutton, Bruce Linck, Vladislav Malyshenko, Austin Kerbow, Ronaldo Ramirez-Ortega, and Vahl Scott Gordon (California State University, Sacramento, USA; Advanced Micro Devices, USA) @InProceedings{CGO24p545, author = {Ghassan Shobaki and Pınar Muyan-Özçelik and Josh Hutton and Bruce Linck and Vladislav Malyshenko and Austin Kerbow and Ronaldo Ramirez-Ortega and Vahl Scott Gordon}, title = {Instruction Scheduling for the GPU on the GPU}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {545-544}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p69-p (type: Full Paper (11 pages excl. references)) doi:
	Greiner, Nathan	CGO '24: "Representing Data Collections ..." Representing Data Collections in an SSA Form Tommy McMichen, Nathan Greiner, Peter Zhong, Federico Sossai, Atmn Patel, and Simone Campanoni (Northwestern University, USA) @InProceedings{CGO24p385, author = {Tommy McMichen and Nathan Greiner and Peter Zhong and Federico Sossai and Atmn Patel and Simone Campanoni}, title = {Representing Data Collections in an SSA Form}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {385-384}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p148-p (type: Full Paper (11 pages excl. references)) doi:
	Guan, Xiaofeng	CGO '24: "PresCount: Effective Register ..." PresCount: Effective Register Allocation for Bank Conflict Reduction Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, and Jianguo Yao (Shanghai Jiao Tong University, China; Shanghai Enflame Technology, China) @InProceedings{CGO24p209, author = {Xiaofeng Guan and Hao Zhou and Guoqing Bao and Handong Li and Liang Zhu and Jianguo Yao}, title = {PresCount: Effective Register Allocation for Bank Conflict Reduction}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {209-208}, doi = {}, year = {2024}, } Article: cgo24main-p16-p (type: Full Paper (11 pages excl. references)) doi:
	Guillon, Christophe	CGO '24: "EasyTracker: A Python Library ..." EasyTracker: A Python Library for Controlling and Inspecting Program Execution Théo Barollet, Christophe Guillon, Manuel Selva, François Broquedis, Florent Bouchez-Tichadou, and Fabrice Rastello (University Grenoble Alpes - Inria - CNRS - Grenoble INP - LIG, France) @InProceedings{CGO24p449, author = {Théo Barollet and Christophe Guillon and Manuel Selva and François Broquedis and Florent Bouchez-Tichadou and Fabrice Rastello}, title = {EasyTracker: A Python Library for Controlling and Inspecting Program Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {449-448}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p359-p (type: Full Paper (11 pages excl. references)) doi:
	Guo, Yuxin	CGO '24: "OptiWISE: Combining Sampling ..." OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis Yuxin Guo, Alex W. Chadwick, Márton Erdős, Utpal Bora, Ilias Vougioukas, Giacomo Gabrielli, and Timothy M. Jones (University of Cambridge, United Kingdom; Arm, USA; Arm, United Kingdom) @InProceedings{CGO24p465, author = {Yuxin Guo and Alex W. Chadwick and Márton Erdős and Utpal Bora and Ilias Vougioukas and Giacomo Gabrielli and Timothy M. Jones}, title = {OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {465-464}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p78-p (type: Full Paper (11 pages excl. references)) doi:
	Hakimi, Milad	CGO '24: "TapeFlow: Streaming Gradient ..." TapeFlow: Streaming Gradient Tapes in Automatic Differentiation Milad Hakimi and Arrvindh Shriraman (Simon Fraser University, Canada) @InProceedings{CGO24p97, author = {Milad Hakimi and Arrvindh Shriraman}, title = {TapeFlow: Streaming Gradient Tapes in Automatic Differentiation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {97-96}, doi = {}, year = {2024}, } Article: cgo24main-p55-p (type: Full Paper (11 pages excl. references)) doi:
	Han, Ruobing	CGO '24: "Enabling Fine-Grained Incremental ..." Enabling Fine-Grained Incremental Builds by Making Compiler Stateful Ruobing Han, Jisheng Zhao, and Hyesoon Kim (Georgia Institute of Technology, USA) @InProceedings{CGO24p273, author = {Ruobing Han and Jisheng Zhao and Hyesoon Kim}, title = {Enabling Fine-Grained Incremental Builds by Making Compiler Stateful}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {273-272}, doi = {}, year = {2024}, } Article: cgo24main-p121-p (type: Full Paper (11 pages excl. references)) doi:
	Hao, Yueming	CGO '24: "DrPy: Pinpointing Inefficient ..." DrPy: Pinpointing Inefficient Memory Usage in Multi-Layer Python Applications Jinku Cui, Qidong Zhao, Yueming Hao, and Xu Liu (North Carolina State University, USA) @InProceedings{CGO24p305, author = {Jinku Cui and Qidong Zhao and Yueming Hao and Xu Liu}, title = {DrPy: Pinpointing Inefficient Memory Usage in Multi-Layer Python Applications}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {305-304}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p141-p (type: Full Paper (11 pages excl. references)) doi:
	Haris, Jude	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi:
	Hashemian, Shideh	CGO '24: "A Tensor Algebra Compiler ..." A Tensor Algebra Compiler for Sparse Differentiation Amir Shaikhha, Mathieu Huot, and Shideh Hashemian (University of Edinburgh, United Kingdom; University of Oxford, United Kingdom) @InProceedings{CGO24p1, author = {Amir Shaikhha and Mathieu Huot and Shideh Hashemian}, title = {A Tensor Algebra Compiler for Sparse Differentiation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {1-0}, doi = {}, year = {2024}, } Article: cgo24main-p38-p (type: Full Paper (11 pages excl. references)) doi:
	Hazelwood, Kim	CGO '24: "Revealing Compiler Heuristics ..." Revealing Compiler Heuristics through Automated Discovery and Optimization Volker Seeker, Chris Cummins, Murray Cole, Björn Franke, Kim Hazelwood, and Hugh Leather (Meta AI Research, USA; University of Edinburgh, United Kingdom) @InProceedings{CGO24p65, author = {Volker Seeker and Chris Cummins and Murray Cole and Björn Franke and Kim Hazelwood and Hugh Leather}, title = {Revealing Compiler Heuristics through Automated Discovery and Optimization}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {65-64}, doi = {}, year = {2024}, } Article: cgo24main-p73-p (type: Full Paper (11 pages excl. references)) doi:
	He, Wenlei	CGO '24: "Revamping Sampling-Based PGO ..." Revamping Sampling-Based PGO with Context-Sensitivity and Pseudo-instrumentation Wenlei He, Hongtao Yu, Lei Wang, and Taewook Oh (Meta, USA) @InProceedings{CGO24p401, author = {Wenlei He and Hongtao Yu and Lei Wang and Taewook Oh}, title = {Revamping Sampling-Based PGO with Context-Sensitivity and Pseudo-instrumentation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {401-400}, doi = {}, year = {2024}, } Article: cgo24main-p138-p (type: Full Paper (11 pages excl. references)) doi:
	Huang, H. Howie	CGO '24: "JITSPMM: Just-in-Time Instruction ..." JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication Qiang Fu, Thomas B. Rolinger, and H. Howie Huang (Advanced Micro Devices, USA; NVIDIA, USA; George Washington University, USA) @InProceedings{CGO24p561, author = {Qiang Fu and Thomas B. Rolinger and H. Howie Huang}, title = {JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {561-560}, doi = {}, year = {2024}, } Article: cgo24main-p81-p (type: Full Paper (11 pages excl. references)) doi:
	Huot, Mathieu	CGO '24: "A Tensor Algebra Compiler ..." A Tensor Algebra Compiler for Sparse Differentiation Amir Shaikhha, Mathieu Huot, and Shideh Hashemian (University of Edinburgh, United Kingdom; University of Oxford, United Kingdom) @InProceedings{CGO24p1, author = {Amir Shaikhha and Mathieu Huot and Shideh Hashemian}, title = {A Tensor Algebra Compiler for Sparse Differentiation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {1-0}, doi = {}, year = {2024}, } Article: cgo24main-p38-p (type: Full Paper (11 pages excl. references)) doi:
	Hutton, Josh	CGO '24: "Instruction Scheduling for ..." Instruction Scheduling for the GPU on the GPU Ghassan Shobaki, Pınar Muyan-Özçelik, Josh Hutton, Bruce Linck, Vladislav Malyshenko, Austin Kerbow, Ronaldo Ramirez-Ortega, and Vahl Scott Gordon (California State University, Sacramento, USA; Advanced Micro Devices, USA) @InProceedings{CGO24p545, author = {Ghassan Shobaki and Pınar Muyan-Özçelik and Josh Hutton and Bruce Linck and Vladislav Malyshenko and Austin Kerbow and Ronaldo Ramirez-Ortega and Vahl Scott Gordon}, title = {Instruction Scheduling for the GPU on the GPU}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {545-544}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p69-p (type: Full Paper (11 pages excl. references)) doi:
	Ikarashi, Yuka	CGO '24: "Tackling the Matrix Multiplication ..." Tackling the Matrix Multiplication Micro-kernel Generation with Exo Adrián Castelló, Julian Bellavita, Grace Dinh, Yuka Ikarashi, and Héctor Martínez (Universitat Politècnica de València, Spain; Cornell University, USA; University of California at Berkeley, USA; Massachusetts Institute of Technology, USA; Universidad de Córdoba, Spain) @InProceedings{CGO24p225, author = {Adrián Castelló and Julian Bellavita and Grace Dinh and Yuka Ikarashi and Héctor Martínez}, title = {Tackling the Matrix Multiplication Micro-kernel Generation with Exo}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {225-224}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Article: cgo24main-p49-p (type: Full Paper (11 pages excl. references)) doi:
	Ivanov, Ivan R.	CGO '24: "Retargeting and Respecializing ..." Retargeting and Respecializing GPU Workloads for Performance Portability Ivan R. Ivanov, Oleksandr Zinenko, Jens Domke, Toshio Endo, and William S. Moses (Tokyo Institute of Technology, Japan; RIKEN R-CCS, Japan; Google DeepMind, France; University of Illinois at Urbana-Champaign, USA; Google DeepMind, USA) @InProceedings{CGO24p145, author = {Ivan R. Ivanov and Oleksandr Zinenko and Jens Domke and Toshio Endo and William S. Moses}, title = {Retargeting and Respecializing GPU Workloads for Performance Portability}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {145-144}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p19-p (type: Full Paper (11 pages excl. references)) doi:
	Jangda, Abhinav	CGO '24: "A Framework for Fine-Grained ..." A Framework for Fine-Grained Synchronization of Dependent GPU Kernels Abhinav Jangda, Saeed Maleki, Maryam Mehri Dehnavi, Madan Musuvathi, and Olli Saarikivi (Microsoft Research, USA; University of Toronto, Canada) @InProceedings{CGO24p113, author = {Abhinav Jangda and Saeed Maleki and Maryam Mehri Dehnavi and Madan Musuvathi and Olli Saarikivi}, title = {A Framework for Fine-Grained Synchronization of Dependent GPU Kernels}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {113-112}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p62-p (type: Full Paper (11 pages excl. references)) doi:
	Jayaweera, Malith	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi: CGO '24: "Energy-Aware Tile Size Selection ..." Energy-Aware Tile Size Selection for Affine Programs on GPUs Malith Jayaweera, Martin Kong, Yanzhi Wang, and David Kaeli (Northeastern University, USA; Ohio State University, USA) @InProceedings{CGO24p17, author = {Malith Jayaweera and Martin Kong and Yanzhi Wang and David Kaeli}, title = {Energy-Aware Tile Size Selection for Affine Programs on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {17-16}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p83-p (type: Full Paper (11 pages excl. references)) doi:
	Jiang, Jinhu	CGO '24: "A System-Level Dynamic Binary ..." A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules Jinhu Jiang, Chaoyi Liang, Rongchao Dong, Zhaohui Yang, Zhongjun Zhou, Wenwen Wang, Pen-Chung Yew, and Weihua Zhang (Fudan University, China; University of Georgia, USA; University of Minnesota at Twin Cities, USA) @InProceedings{CGO24p529, author = {Jinhu Jiang and Chaoyi Liang and Rongchao Dong and Zhaohui Yang and Zhongjun Zhou and Wenwen Wang and Pen-Chung Yew and Weihua Zhang}, title = {A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {529-528}, doi = {}, year = {2024}, } Article: cgo24main-p51-p (type: Full Paper (11 pages excl. references)) doi:
	Jin, Baihui	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Jones, Timothy M.	CGO '24: "OptiWISE: Combining Sampling ..." OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis Yuxin Guo, Alex W. Chadwick, Márton Erdős, Utpal Bora, Ilias Vougioukas, Giacomo Gabrielli, and Timothy M. Jones (University of Cambridge, United Kingdom; Arm, USA; Arm, United Kingdom) @InProceedings{CGO24p465, author = {Yuxin Guo and Alex W. Chadwick and Márton Erdős and Utpal Bora and Ilias Vougioukas and Giacomo Gabrielli and Timothy M. Jones}, title = {OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {465-464}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p78-p (type: Full Paper (11 pages excl. references)) doi:
	Kaeli, David	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi: CGO '24: "Energy-Aware Tile Size Selection ..." Energy-Aware Tile Size Selection for Affine Programs on GPUs Malith Jayaweera, Martin Kong, Yanzhi Wang, and David Kaeli (Northeastern University, USA; Ohio State University, USA) @InProceedings{CGO24p17, author = {Malith Jayaweera and Martin Kong and Yanzhi Wang and David Kaeli}, title = {Energy-Aware Tile Size Selection for Affine Programs on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {17-16}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p83-p (type: Full Paper (11 pages excl. references)) doi:
	Kerbow, Austin	CGO '24: "Instruction Scheduling for ..." Instruction Scheduling for the GPU on the GPU Ghassan Shobaki, Pınar Muyan-Özçelik, Josh Hutton, Bruce Linck, Vladislav Malyshenko, Austin Kerbow, Ronaldo Ramirez-Ortega, and Vahl Scott Gordon (California State University, Sacramento, USA; Advanced Micro Devices, USA) @InProceedings{CGO24p545, author = {Ghassan Shobaki and Pınar Muyan-Özçelik and Josh Hutton and Bruce Linck and Vladislav Malyshenko and Austin Kerbow and Ronaldo Ramirez-Ortega and Vahl Scott Gordon}, title = {Instruction Scheduling for the GPU on the GPU}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {545-544}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p69-p (type: Full Paper (11 pages excl. references)) doi:
	Kim, Hyesoon	CGO '24: "Enabling Fine-Grained Incremental ..." Enabling Fine-Grained Incremental Builds by Making Compiler Stateful Ruobing Han, Jisheng Zhao, and Hyesoon Kim (Georgia Institute of Technology, USA) @InProceedings{CGO24p273, author = {Ruobing Han and Jisheng Zhao and Hyesoon Kim}, title = {Enabling Fine-Grained Incremental Builds by Making Compiler Stateful}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {273-272}, doi = {}, year = {2024}, } Article: cgo24main-p121-p (type: Full Paper (11 pages excl. references)) doi:
	Ko, Yousun	CGO '24: "BEC: Bit-Level Static Analysis ..." BEC: Bit-Level Static Analysis for Reliability against Soft Errors Yousun Ko and Bernd Burgstaller (Yonsei University, South Korea) @InProceedings{CGO24p353, author = {Yousun Ko and Bernd Burgstaller}, title = {BEC: Bit-Level Static Analysis for Reliability against Soft Errors}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {353-352}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p191-p (type: Full Paper (11 pages excl. references)) doi:
	Kong, Martin	CGO '24: "Energy-Aware Tile Size Selection ..." Energy-Aware Tile Size Selection for Affine Programs on GPUs Malith Jayaweera, Martin Kong, Yanzhi Wang, and David Kaeli (Northeastern University, USA; Ohio State University, USA) @InProceedings{CGO24p17, author = {Malith Jayaweera and Martin Kong and Yanzhi Wang and David Kaeli}, title = {Energy-Aware Tile Size Selection for Affine Programs on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {17-16}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p83-p (type: Full Paper (11 pages excl. references)) doi:
	Laguna, Ignacio	CGO '24: "Enhancing Performance through ..." Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs Alnis Murtovi, Giorgis Georgakoudis, Konstantinos Parasyris, Chunhua Liao, Ignacio Laguna, and Bernhard Steffen (TU Dortmund, Germany; Lawrence Livermore National Laboratory, USA) @InProceedings{CGO24p129, author = {Alnis Murtovi and Giorgis Georgakoudis and Konstantinos Parasyris and Chunhua Liao and Ignacio Laguna and Bernhard Steffen}, title = {Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {129-128}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p103-p (type: Full Paper (11 pages excl. references)) doi:
	Lavery, Dan	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Leather, Hugh	CGO '24: "Revealing Compiler Heuristics ..." Revealing Compiler Heuristics through Automated Discovery and Optimization Volker Seeker, Chris Cummins, Murray Cole, Björn Franke, Kim Hazelwood, and Hugh Leather (Meta AI Research, USA; University of Edinburgh, United Kingdom) @InProceedings{CGO24p65, author = {Volker Seeker and Chris Cummins and Murray Cole and Björn Franke and Kim Hazelwood and Hugh Leather}, title = {Revealing Compiler Heuristics through Automated Discovery and Optimization}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {65-64}, doi = {}, year = {2024}, } Article: cgo24main-p73-p (type: Full Paper (11 pages excl. references)) doi:
	Li, Handong	CGO '24: "PresCount: Effective Register ..." PresCount: Effective Register Allocation for Bank Conflict Reduction Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, and Jianguo Yao (Shanghai Jiao Tong University, China; Shanghai Enflame Technology, China) @InProceedings{CGO24p209, author = {Xiaofeng Guan and Hao Zhou and Guoqing Bao and Handong Li and Liang Zhu and Jianguo Yao}, title = {PresCount: Effective Register Allocation for Bank Conflict Reduction}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {209-208}, doi = {}, year = {2024}, } Article: cgo24main-p16-p (type: Full Paper (11 pages excl. references)) doi:
	Li, Haofeng	CGO '24: "Boosting the Performance of ..." Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations Haofeng Li, Jie Lu, Haining Meng, Liqing Cao, Lian Li, and Lin Gao (Institute of Computing Technology at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Zhongguancun Laboratory, China; TianqiSoft, China) @InProceedings{CGO24p369, author = {Haofeng Li and Jie Lu and Haining Meng and Liqing Cao and Lian Li and Lin Gao}, title = {Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {369-368}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p193-p (type: Full Paper (11 pages excl. references)) doi:
	Li, Jianhui	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Li, Lian	CGO '24: "Boosting the Performance of ..." Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations Haofeng Li, Jie Lu, Haining Meng, Liqing Cao, Lian Li, and Lin Gao (Institute of Computing Technology at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Zhongguancun Laboratory, China; TianqiSoft, China) @InProceedings{CGO24p369, author = {Haofeng Li and Jie Lu and Haining Meng and Liqing Cao and Lian Li and Lin Gao}, title = {Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {369-368}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p193-p (type: Full Paper (11 pages excl. references)) doi:
	Li, Xiang-Yang	CGO '24: "Ecmas: Efficient Circuit Mapping ..." Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code Mingzheng Zhu, Hao Fu, Jun Wu, Chi Zhang, Wei Xie, and Xiang-Yang Li (University of Science and Technology of China, China) @InProceedings{CGO24p193, author = {Mingzheng Zhu and Hao Fu and Jun Wu and Chi Zhang and Wei Xie and Xiang-Yang Li}, title = {Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {193-192}, doi = {}, year = {2024}, } Article: cgo24main-p100-p (type: Full Paper (11 pages excl. references)) doi:
	Liang, Chaoyi	CGO '24: "A System-Level Dynamic Binary ..." A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules Jinhu Jiang, Chaoyi Liang, Rongchao Dong, Zhaohui Yang, Zhongjun Zhou, Wenwen Wang, Pen-Chung Yew, and Weihua Zhang (Fudan University, China; University of Georgia, USA; University of Minnesota at Twin Cities, USA) @InProceedings{CGO24p529, author = {Jinhu Jiang and Chaoyi Liang and Rongchao Dong and Zhaohui Yang and Zhongjun Zhou and Wenwen Wang and Pen-Chung Yew and Weihua Zhang}, title = {A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {529-528}, doi = {}, year = {2024}, } Article: cgo24main-p51-p (type: Full Paper (11 pages excl. references)) doi:
	Liao, Chunhua	CGO '24: "Enhancing Performance through ..." Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs Alnis Murtovi, Giorgis Georgakoudis, Konstantinos Parasyris, Chunhua Liao, Ignacio Laguna, and Bernhard Steffen (TU Dortmund, Germany; Lawrence Livermore National Laboratory, USA) @InProceedings{CGO24p129, author = {Alnis Murtovi and Giorgis Georgakoudis and Konstantinos Parasyris and Chunhua Liao and Ignacio Laguna and Bernhard Steffen}, title = {Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {129-128}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p103-p (type: Full Paper (11 pages excl. references)) doi:
	Lin, Eric	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Linck, Bruce	CGO '24: "Instruction Scheduling for ..." Instruction Scheduling for the GPU on the GPU Ghassan Shobaki, Pınar Muyan-Özçelik, Josh Hutton, Bruce Linck, Vladislav Malyshenko, Austin Kerbow, Ronaldo Ramirez-Ortega, and Vahl Scott Gordon (California State University, Sacramento, USA; Advanced Micro Devices, USA) @InProceedings{CGO24p545, author = {Ghassan Shobaki and Pınar Muyan-Özçelik and Josh Hutton and Bruce Linck and Vladislav Malyshenko and Austin Kerbow and Ronaldo Ramirez-Ortega and Vahl Scott Gordon}, title = {Instruction Scheduling for the GPU on the GPU}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {545-544}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p69-p (type: Full Paper (11 pages excl. references)) doi:
	Liu, Xu	CGO '24: "DrPy: Pinpointing Inefficient ..." DrPy: Pinpointing Inefficient Memory Usage in Multi-Layer Python Applications Jinku Cui, Qidong Zhao, Yueming Hao, and Xu Liu (North Carolina State University, USA) @InProceedings{CGO24p305, author = {Jinku Cui and Qidong Zhao and Yueming Hao and Xu Liu}, title = {DrPy: Pinpointing Inefficient Memory Usage in Multi-Layer Python Applications}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {305-304}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p141-p (type: Full Paper (11 pages excl. references)) doi: CGO '24: "EasyView: Bringing Performance ..." EasyView: Bringing Performance Profiles into Integrated Development Environments Qidong Zhao, Milind Chabbi, and Xu Liu (North Carolina State University, USA; Scalable Machines Research, USA) @InProceedings{CGO24p481, author = {Qidong Zhao and Milind Chabbi and Xu Liu}, title = {EasyView: Bringing Performance Profiles into Integrated Development Environments}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {481-480}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Functional Results Reproduced Article: cgo24main-p107-p (type: Full Paper (11 pages excl. references)) doi:
	Lomüller, Victor	CGO '24: "Experiences Building an MLIR-Based ..." Experiences Building an MLIR-Based SYCL Compiler Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, and James Brodman (Intel Corporation, Canada; Codeplay Software, United Kingdom; Intel Corporation, USA) @InProceedings{CGO24p497, author = {Ettore Tiotto and Víctor Pérez and Whitney Tsang and Lukas Sommer and Julian Oppermann and Victor Lomüller and Mehdi Goli and James Brodman}, title = {Experiences Building an MLIR-Based SYCL Compiler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {497-496}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p70-p (type: Full Paper (11 pages excl. references)) doi:
	Lossing, Nelson	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Lu, Jie	CGO '24: "Boosting the Performance of ..." Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations Haofeng Li, Jie Lu, Haining Meng, Liqing Cao, Lian Li, and Lin Gao (Institute of Computing Technology at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Zhongguancun Laboratory, China; TianqiSoft, China) @InProceedings{CGO24p369, author = {Haofeng Li and Jie Lu and Haining Meng and Liqing Cao and Lian Li and Lin Gao}, title = {Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {369-368}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p193-p (type: Full Paper (11 pages excl. references)) doi:
	Mahmud, Jalal	CGO '24: "Seer: Predictive Runtime Kernel ..." Seer: Predictive Runtime Kernel Selection for Irregular Problems Ryan Swann, Muhammad Osama, Karthik Sangaiah, and Jalal Mahmud (AMD, USA) @InProceedings{CGO24p161, author = {Ryan Swann and Muhammad Osama and Karthik Sangaiah and Jalal Mahmud}, title = {Seer: Predictive Runtime Kernel Selection for Irregular Problems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {161-160}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p238-p (type: Full Paper (11 pages excl. references)) doi:
	Maleki, Saeed	CGO '24: "A Framework for Fine-Grained ..." A Framework for Fine-Grained Synchronization of Dependent GPU Kernels Abhinav Jangda, Saeed Maleki, Maryam Mehri Dehnavi, Madan Musuvathi, and Olli Saarikivi (Microsoft Research, USA; University of Toronto, Canada) @InProceedings{CGO24p113, author = {Abhinav Jangda and Saeed Maleki and Maryam Mehri Dehnavi and Madan Musuvathi and Olli Saarikivi}, title = {A Framework for Fine-Grained Synchronization of Dependent GPU Kernels}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {113-112}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p62-p (type: Full Paper (11 pages excl. references)) doi:
	Malyshenko, Vladislav	CGO '24: "Instruction Scheduling for ..." Instruction Scheduling for the GPU on the GPU Ghassan Shobaki, Pınar Muyan-Özçelik, Josh Hutton, Bruce Linck, Vladislav Malyshenko, Austin Kerbow, Ronaldo Ramirez-Ortega, and Vahl Scott Gordon (California State University, Sacramento, USA; Advanced Micro Devices, USA) @InProceedings{CGO24p545, author = {Ghassan Shobaki and Pınar Muyan-Özçelik and Josh Hutton and Bruce Linck and Vladislav Malyshenko and Austin Kerbow and Ronaldo Ramirez-Ortega and Vahl Scott Gordon}, title = {Instruction Scheduling for the GPU on the GPU}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {545-544}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p69-p (type: Full Paper (11 pages excl. references)) doi:
	Martínez, Héctor	CGO '24: "Tackling the Matrix Multiplication ..." Tackling the Matrix Multiplication Micro-kernel Generation with Exo Adrián Castelló, Julian Bellavita, Grace Dinh, Yuka Ikarashi, and Héctor Martínez (Universitat Politècnica de València, Spain; Cornell University, USA; University of California at Berkeley, USA; Massachusetts Institute of Technology, USA; Universidad de Córdoba, Spain) @InProceedings{CGO24p225, author = {Adrián Castelló and Julian Bellavita and Grace Dinh and Yuka Ikarashi and Héctor Martínez}, title = {Tackling the Matrix Multiplication Micro-kernel Generation with Exo}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {225-224}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Article: cgo24main-p49-p (type: Full Paper (11 pages excl. references)) doi:
	McMichen, Tommy	CGO '24: "Representing Data Collections ..." Representing Data Collections in an SSA Form Tommy McMichen, Nathan Greiner, Peter Zhong, Federico Sossai, Atmn Patel, and Simone Campanoni (Northwestern University, USA) @InProceedings{CGO24p385, author = {Tommy McMichen and Nathan Greiner and Peter Zhong and Federico Sossai and Atmn Patel and Simone Campanoni}, title = {Representing Data Collections in an SSA Form}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {385-384}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p148-p (type: Full Paper (11 pages excl. references)) doi:
	Mei, Yijie	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Meng, Haining	CGO '24: "Boosting the Performance of ..." Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations Haofeng Li, Jie Lu, Haining Meng, Liqing Cao, Lian Li, and Lin Gao (Institute of Computing Technology at Chinese Academy of Sciences, China; University of Chinese Academy of Sciences, China; Zhongguancun Laboratory, China; TianqiSoft, China) @InProceedings{CGO24p369, author = {Haofeng Li and Jie Lu and Haining Meng and Liqing Cao and Lian Li and Lin Gao}, title = {Boosting the Performance of Multi-solver IFDS Algorithms with Flow-Sensitivity Optimizations}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {369-368}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p193-p (type: Full Paper (11 pages excl. references)) doi:
	Moses, William S.	CGO '24: "Retargeting and Respecializing ..." Retargeting and Respecializing GPU Workloads for Performance Portability Ivan R. Ivanov, Oleksandr Zinenko, Jens Domke, Toshio Endo, and William S. Moses (Tokyo Institute of Technology, Japan; RIKEN R-CCS, Japan; Google DeepMind, France; University of Illinois at Urbana-Champaign, USA; Google DeepMind, USA) @InProceedings{CGO24p145, author = {Ivan R. Ivanov and Oleksandr Zinenko and Jens Domke and Toshio Endo and William S. Moses}, title = {Retargeting and Respecializing GPU Workloads for Performance Portability}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {145-144}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p19-p (type: Full Paper (11 pages excl. references)) doi:
	Murtovi, Alnis	CGO '24: "Enhancing Performance through ..." Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs Alnis Murtovi, Giorgis Georgakoudis, Konstantinos Parasyris, Chunhua Liao, Ignacio Laguna, and Bernhard Steffen (TU Dortmund, Germany; Lawrence Livermore National Laboratory, USA) @InProceedings{CGO24p129, author = {Alnis Murtovi and Giorgis Georgakoudis and Konstantinos Parasyris and Chunhua Liao and Ignacio Laguna and Bernhard Steffen}, title = {Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {129-128}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p103-p (type: Full Paper (11 pages excl. references)) doi:
	Musuvathi, Madan	CGO '24: "A Framework for Fine-Grained ..." A Framework for Fine-Grained Synchronization of Dependent GPU Kernels Abhinav Jangda, Saeed Maleki, Maryam Mehri Dehnavi, Madan Musuvathi, and Olli Saarikivi (Microsoft Research, USA; University of Toronto, Canada) @InProceedings{CGO24p113, author = {Abhinav Jangda and Saeed Maleki and Maryam Mehri Dehnavi and Madan Musuvathi and Olli Saarikivi}, title = {A Framework for Fine-Grained Synchronization of Dependent GPU Kernels}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {113-112}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p62-p (type: Full Paper (11 pages excl. references)) doi:
	Muyan-Özçelik, Pınar	CGO '24: "Instruction Scheduling for ..." Instruction Scheduling for the GPU on the GPU Ghassan Shobaki, Pınar Muyan-Özçelik, Josh Hutton, Bruce Linck, Vladislav Malyshenko, Austin Kerbow, Ronaldo Ramirez-Ortega, and Vahl Scott Gordon (California State University, Sacramento, USA; Advanced Micro Devices, USA) @InProceedings{CGO24p545, author = {Ghassan Shobaki and Pınar Muyan-Özçelik and Josh Hutton and Bruce Linck and Vladislav Malyshenko and Austin Kerbow and Ronaldo Ramirez-Ortega and Vahl Scott Gordon}, title = {Instruction Scheduling for the GPU on the GPU}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {545-544}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p69-p (type: Full Paper (11 pages excl. references)) doi:
	O'Boyle, Michael F. P.	CGO '24: "SLaDe: A Portable Small Language ..." SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly Jordi Armengol-Estapé, Jackson Woodruff, Chris Cummins, and Michael F. P. O'Boyle (University of Edinburgh, United Kingdom; Meta AI Research, USA) @InProceedings{CGO24p81, author = {Jordi Armengol-Estapé and Jackson Woodruff and Chris Cummins and Michael F. P. O'Boyle}, title = {SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {81-80}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p72-p (type: Full Paper (11 pages excl. references)) doi:
	Oh, Taewook	CGO '24: "Revamping Sampling-Based PGO ..." Revamping Sampling-Based PGO with Context-Sensitivity and Pseudo-instrumentation Wenlei He, Hongtao Yu, Lei Wang, and Taewook Oh (Meta, USA) @InProceedings{CGO24p401, author = {Wenlei He and Hongtao Yu and Lei Wang and Taewook Oh}, title = {Revamping Sampling-Based PGO with Context-Sensitivity and Pseudo-instrumentation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {401-400}, doi = {}, year = {2024}, } Article: cgo24main-p138-p (type: Full Paper (11 pages excl. references)) doi:
	Okuda, Katsumi	CGO '24: "AskIt: Unified Programming ..." AskIt: Unified Programming Interface for Programming with Large Language Models Katsumi Okuda and Saman Amarasinghe (Massachusetts Institute of Technology, USA; Mitsubishi Electric Corporation, Japan) @InProceedings{CGO24p49, author = {Katsumi Okuda and Saman Amarasinghe}, title = {AskIt: Unified Programming Interface for Programming with Large Language Models}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {49-48}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p229-p (type: Full Paper (11 pages excl. references)) doi:
	Oppermann, Julian	CGO '24: "Experiences Building an MLIR-Based ..." Experiences Building an MLIR-Based SYCL Compiler Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, and James Brodman (Intel Corporation, Canada; Codeplay Software, United Kingdom; Intel Corporation, USA) @InProceedings{CGO24p497, author = {Ettore Tiotto and Víctor Pérez and Whitney Tsang and Lukas Sommer and Julian Oppermann and Victor Lomüller and Mehdi Goli and James Brodman}, title = {Experiences Building an MLIR-Based SYCL Compiler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {497-496}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p70-p (type: Full Paper (11 pages excl. references)) doi:
	Osama, Muhammad	CGO '24: "Seer: Predictive Runtime Kernel ..." Seer: Predictive Runtime Kernel Selection for Irregular Problems Ryan Swann, Muhammad Osama, Karthik Sangaiah, and Jalal Mahmud (AMD, USA) @InProceedings{CGO24p161, author = {Ryan Swann and Muhammad Osama and Karthik Sangaiah and Jalal Mahmud}, title = {Seer: Predictive Runtime Kernel Selection for Irregular Problems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {161-160}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p238-p (type: Full Paper (11 pages excl. references)) doi:
	Parasyris, Konstantinos	CGO '24: "Enhancing Performance through ..." Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs Alnis Murtovi, Giorgis Georgakoudis, Konstantinos Parasyris, Chunhua Liao, Ignacio Laguna, and Bernhard Steffen (TU Dortmund, Germany; Lawrence Livermore National Laboratory, USA) @InProceedings{CGO24p129, author = {Alnis Murtovi and Giorgis Georgakoudis and Konstantinos Parasyris and Chunhua Liao and Ignacio Laguna and Bernhard Steffen}, title = {Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {129-128}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p103-p (type: Full Paper (11 pages excl. references)) doi:
	Patel, Atmn	CGO '24: "Representing Data Collections ..." Representing Data Collections in an SSA Form Tommy McMichen, Nathan Greiner, Peter Zhong, Federico Sossai, Atmn Patel, and Simone Campanoni (Northwestern University, USA) @InProceedings{CGO24p385, author = {Tommy McMichen and Nathan Greiner and Peter Zhong and Federico Sossai and Atmn Patel and Simone Campanoni}, title = {Representing Data Collections in an SSA Form}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {385-384}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p148-p (type: Full Paper (11 pages excl. references)) doi:
	Pérez, Víctor	CGO '24: "Experiences Building an MLIR-Based ..." Experiences Building an MLIR-Based SYCL Compiler Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, and James Brodman (Intel Corporation, Canada; Codeplay Software, United Kingdom; Intel Corporation, USA) @InProceedings{CGO24p497, author = {Ettore Tiotto and Víctor Pérez and Whitney Tsang and Lukas Sommer and Julian Oppermann and Victor Lomüller and Mehdi Goli and James Brodman}, title = {Experiences Building an MLIR-Based SYCL Compiler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {497-496}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p70-p (type: Full Paper (11 pages excl. references)) doi:
	Puaut, Isabelle	CGO '24: "SCHEMATIC: Compile-Time Checkpoint ..." SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems Hugo Reymond, Jean-Luc Béchennec, Mikaël Briday, Sébastien Faucou, Isabelle Puaut, and Erven Rohou (Université de Rennes - Inria - CNRS - IRISA, France; Nantes Université - École Centrale Nantes - CNRS - LS2N - UMR 6004, France) @InProceedings{CGO24p321, author = {Hugo Reymond and Jean-Luc Béchennec and Mikaël Briday and Sébastien Faucou and Isabelle Puaut and Erven Rohou}, title = {SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {321-320}, doi = {}, year = {2024}, } Article: cgo24main-p24-p (type: Full Paper (11 pages excl. references)) doi:
	Qin, Zhennan	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Ramirez-Ortega, Ronaldo	CGO '24: "Instruction Scheduling for ..." Instruction Scheduling for the GPU on the GPU Ghassan Shobaki, Pınar Muyan-Özçelik, Josh Hutton, Bruce Linck, Vladislav Malyshenko, Austin Kerbow, Ronaldo Ramirez-Ortega, and Vahl Scott Gordon (California State University, Sacramento, USA; Advanced Micro Devices, USA) @InProceedings{CGO24p545, author = {Ghassan Shobaki and Pınar Muyan-Özçelik and Josh Hutton and Bruce Linck and Vladislav Malyshenko and Austin Kerbow and Ronaldo Ramirez-Ortega and Vahl Scott Gordon}, title = {Instruction Scheduling for the GPU on the GPU}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {545-544}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p69-p (type: Full Paper (11 pages excl. references)) doi:
	Rastello, Fabrice	CGO '24: "EasyTracker: A Python Library ..." EasyTracker: A Python Library for Controlling and Inspecting Program Execution Théo Barollet, Christophe Guillon, Manuel Selva, François Broquedis, Florent Bouchez-Tichadou, and Fabrice Rastello (University Grenoble Alpes - Inria - CNRS - Grenoble INP - LIG, France) @InProceedings{CGO24p449, author = {Théo Barollet and Christophe Guillon and Manuel Selva and François Broquedis and Florent Bouchez-Tichadou and Fabrice Rastello}, title = {EasyTracker: A Python Library for Controlling and Inspecting Program Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {449-448}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p359-p (type: Full Paper (11 pages excl. references)) doi:
	Razanajato, Harenome	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Regehr, John	CGO '24: "High-Throughput, Formal-Methods-Assisted ..." High-Throughput, Formal-Methods-Assisted Fuzzing for LLVM Yuyou Fan and John Regehr (University of Utah, USA) @InProceedings{CGO24p433, author = {Yuyou Fan and John Regehr}, title = {High-Throughput, Formal-Methods-Assisted Fuzzing for LLVM}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {433-432}, doi = {}, year = {2024}, } Article: cgo24main-p241-p (type: Full Paper (11 pages excl. references)) doi:
	Reymond, Hugo	CGO '24: "SCHEMATIC: Compile-Time Checkpoint ..." SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems Hugo Reymond, Jean-Luc Béchennec, Mikaël Briday, Sébastien Faucou, Isabelle Puaut, and Erven Rohou (Université de Rennes - Inria - CNRS - IRISA, France; Nantes Université - École Centrale Nantes - CNRS - LS2N - UMR 6004, France) @InProceedings{CGO24p321, author = {Hugo Reymond and Jean-Luc Béchennec and Mikaël Briday and Sébastien Faucou and Isabelle Puaut and Erven Rohou}, title = {SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {321-320}, doi = {}, year = {2024}, } Article: cgo24main-p24-p (type: Full Paper (11 pages excl. references)) doi:
	Rohou, Erven	CGO '24: "SCHEMATIC: Compile-Time Checkpoint ..." SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems Hugo Reymond, Jean-Luc Béchennec, Mikaël Briday, Sébastien Faucou, Isabelle Puaut, and Erven Rohou (Université de Rennes - Inria - CNRS - IRISA, France; Nantes Université - École Centrale Nantes - CNRS - LS2N - UMR 6004, France) @InProceedings{CGO24p321, author = {Hugo Reymond and Jean-Luc Béchennec and Mikaël Briday and Sébastien Faucou and Isabelle Puaut and Erven Rohou}, title = {SCHEMATIC: Compile-Time Checkpoint Placement and Memory Allocation for Intermittent Systems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {321-320}, doi = {}, year = {2024}, } Article: cgo24main-p24-p (type: Full Paper (11 pages excl. references)) doi:
	Rolinger, Thomas B.	CGO '24: "JITSPMM: Just-in-Time Instruction ..." JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication Qiang Fu, Thomas B. Rolinger, and H. Howie Huang (Advanced Micro Devices, USA; NVIDIA, USA; George Washington University, USA) @InProceedings{CGO24p561, author = {Qiang Fu and Thomas B. Rolinger and H. Howie Huang}, title = {JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {561-560}, doi = {}, year = {2024}, } Article: cgo24main-p81-p (type: Full Paper (11 pages excl. references)) doi:
	Rubin, Norm	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi:
	Saarikivi, Olli	CGO '24: "A Framework for Fine-Grained ..." A Framework for Fine-Grained Synchronization of Dependent GPU Kernels Abhinav Jangda, Saeed Maleki, Maryam Mehri Dehnavi, Madan Musuvathi, and Olli Saarikivi (Microsoft Research, USA; University of Toronto, Canada) @InProceedings{CGO24p113, author = {Abhinav Jangda and Saeed Maleki and Maryam Mehri Dehnavi and Madan Musuvathi and Olli Saarikivi}, title = {A Framework for Fine-Grained Synchronization of Dependent GPU Kernels}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {113-112}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p62-p (type: Full Paper (11 pages excl. references)) doi:
	Saioc, Georgian-Vlad	CGO '24: "Unveiling and Vanquishing ..." Unveiling and Vanquishing Goroutine Leaks in Enterprise Microservices: A Dynamic Analysis Approach Georgian-Vlad Saioc, Dmitriy Shirchenko, and Milind Chabbi (Aarhus University, Denmark; Uber Technologies, Denmark; Uber Technologies, USA) @InProceedings{CGO24p513, author = {Georgian-Vlad Saioc and Dmitriy Shirchenko and Milind Chabbi}, title = {Unveiling and Vanquishing Goroutine Leaks in Enterprise Microservices: A Dynamic Analysis Approach}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {513-512}, doi = {}, year = {2024}, } Article: cgo24main-p237-p (type: Full Paper (11 pages excl. references)) doi:
	Sangaiah, Karthik	CGO '24: "Seer: Predictive Runtime Kernel ..." Seer: Predictive Runtime Kernel Selection for Irregular Problems Ryan Swann, Muhammad Osama, Karthik Sangaiah, and Jalal Mahmud (AMD, USA) @InProceedings{CGO24p161, author = {Ryan Swann and Muhammad Osama and Karthik Sangaiah and Jalal Mahmud}, title = {Seer: Predictive Runtime Kernel Selection for Irregular Problems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {161-160}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p238-p (type: Full Paper (11 pages excl. references)) doi:
	Santambrogio, Marco D.	CGO '24: "One Automaton to Rule Them ..." One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution Luisa Cicolini, Filippo Carloni, Marco D. Santambrogio, and Davide Conficconi (Politecnico di Milano, Italy) @InProceedings{CGO24p241, author = {Luisa Cicolini and Filippo Carloni and Marco D. Santambrogio and Davide Conficconi}, title = {One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {241-240}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p368-p (type: Full Paper (11 pages excl. references)) doi:
	Schwarz, Tobias	CGO '24: "Compile-Time Analysis of Compiler ..." Compile-Time Analysis of Compiler Frameworks for Query Compilation Alexis Engelke and Tobias Schwarz (TU Munich, Germany) @InProceedings{CGO24p289, author = {Alexis Engelke and Tobias Schwarz}, title = {Compile-Time Analysis of Compiler Frameworks for Query Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {289-288}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p29-p (type: Full Paper (11 pages excl. references)) doi:
	Seeker, Volker	CGO '24: "Revealing Compiler Heuristics ..." Revealing Compiler Heuristics through Automated Discovery and Optimization Volker Seeker, Chris Cummins, Murray Cole, Björn Franke, Kim Hazelwood, and Hugh Leather (Meta AI Research, USA; University of Edinburgh, United Kingdom) @InProceedings{CGO24p65, author = {Volker Seeker and Chris Cummins and Murray Cole and Björn Franke and Kim Hazelwood and Hugh Leather}, title = {Revealing Compiler Heuristics through Automated Discovery and Optimization}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {65-64}, doi = {}, year = {2024}, } Article: cgo24main-p73-p (type: Full Paper (11 pages excl. references)) doi:
	Selva, Manuel	CGO '24: "EasyTracker: A Python Library ..." EasyTracker: A Python Library for Controlling and Inspecting Program Execution Théo Barollet, Christophe Guillon, Manuel Selva, François Broquedis, Florent Bouchez-Tichadou, and Fabrice Rastello (University Grenoble Alpes - Inria - CNRS - Grenoble INP - LIG, France) @InProceedings{CGO24p449, author = {Théo Barollet and Christophe Guillon and Manuel Selva and François Broquedis and Florent Bouchez-Tichadou and Fabrice Rastello}, title = {EasyTracker: A Python Library for Controlling and Inspecting Program Execution}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {449-448}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p359-p (type: Full Paper (11 pages excl. references)) doi:
	Shaikhha, Amir	CGO '24: "A Tensor Algebra Compiler ..." A Tensor Algebra Compiler for Sparse Differentiation Amir Shaikhha, Mathieu Huot, and Shideh Hashemian (University of Edinburgh, United Kingdom; University of Oxford, United Kingdom) @InProceedings{CGO24p1, author = {Amir Shaikhha and Mathieu Huot and Shideh Hashemian}, title = {A Tensor Algebra Compiler for Sparse Differentiation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {1-0}, doi = {}, year = {2024}, } Article: cgo24main-p38-p (type: Full Paper (11 pages excl. references)) doi:
	Shirchenko, Dmitriy	CGO '24: "Unveiling and Vanquishing ..." Unveiling and Vanquishing Goroutine Leaks in Enterprise Microservices: A Dynamic Analysis Approach Georgian-Vlad Saioc, Dmitriy Shirchenko, and Milind Chabbi (Aarhus University, Denmark; Uber Technologies, Denmark; Uber Technologies, USA) @InProceedings{CGO24p513, author = {Georgian-Vlad Saioc and Dmitriy Shirchenko and Milind Chabbi}, title = {Unveiling and Vanquishing Goroutine Leaks in Enterprise Microservices: A Dynamic Analysis Approach}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {513-512}, doi = {}, year = {2024}, } Article: cgo24main-p237-p (type: Full Paper (11 pages excl. references)) doi:
	Shobaki, Ghassan	CGO '24: "Instruction Scheduling for ..." Instruction Scheduling for the GPU on the GPU Ghassan Shobaki, Pınar Muyan-Özçelik, Josh Hutton, Bruce Linck, Vladislav Malyshenko, Austin Kerbow, Ronaldo Ramirez-Ortega, and Vahl Scott Gordon (California State University, Sacramento, USA; Advanced Micro Devices, USA) @InProceedings{CGO24p545, author = {Ghassan Shobaki and Pınar Muyan-Özçelik and Josh Hutton and Bruce Linck and Vladislav Malyshenko and Austin Kerbow and Ronaldo Ramirez-Ortega and Vahl Scott Gordon}, title = {Instruction Scheduling for the GPU on the GPU}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {545-544}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p69-p (type: Full Paper (11 pages excl. references)) doi:
	Shriraman, Arrvindh	CGO '24: "TapeFlow: Streaming Gradient ..." TapeFlow: Streaming Gradient Tapes in Automatic Differentiation Milad Hakimi and Arrvindh Shriraman (Simon Fraser University, Canada) @InProceedings{CGO24p97, author = {Milad Hakimi and Arrvindh Shriraman}, title = {TapeFlow: Streaming Gradient Tapes in Automatic Differentiation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {97-96}, doi = {}, year = {2024}, } Article: cgo24main-p55-p (type: Full Paper (11 pages excl. references)) doi:
	Smith, Lee	CGO '24: "Compiler Testing with Relaxed ..." Compiler Testing with Relaxed Memory Models Luke Geeson and Lee Smith (University College London, United Kingdom; Arm, United Kingdom) @InProceedings{CGO24p417, author = {Luke Geeson and Lee Smith}, title = {Compiler Testing with Relaxed Memory Models}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {417-416}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p169-p (type: Full Paper (11 pages excl. references)) doi:
	Sommer, Lukas	CGO '24: "Experiences Building an MLIR-Based ..." Experiences Building an MLIR-Based SYCL Compiler Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, and James Brodman (Intel Corporation, Canada; Codeplay Software, United Kingdom; Intel Corporation, USA) @InProceedings{CGO24p497, author = {Ettore Tiotto and Víctor Pérez and Whitney Tsang and Lukas Sommer and Julian Oppermann and Victor Lomüller and Mehdi Goli and James Brodman}, title = {Experiences Building an MLIR-Based SYCL Compiler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {497-496}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p70-p (type: Full Paper (11 pages excl. references)) doi:
	Song, Yunfei	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Sossai, Federico	CGO '24: "Representing Data Collections ..." Representing Data Collections in an SSA Form Tommy McMichen, Nathan Greiner, Peter Zhong, Federico Sossai, Atmn Patel, and Simone Campanoni (Northwestern University, USA) @InProceedings{CGO24p385, author = {Tommy McMichen and Nathan Greiner and Peter Zhong and Federico Sossai and Atmn Patel and Simone Campanoni}, title = {Representing Data Collections in an SSA Form}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {385-384}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p148-p (type: Full Paper (11 pages excl. references)) doi:
	Steffen, Bernhard	CGO '24: "Enhancing Performance through ..." Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs Alnis Murtovi, Giorgis Georgakoudis, Konstantinos Parasyris, Chunhua Liao, Ignacio Laguna, and Bernhard Steffen (TU Dortmund, Germany; Lawrence Livermore National Laboratory, USA) @InProceedings{CGO24p129, author = {Alnis Murtovi and Giorgis Georgakoudis and Konstantinos Parasyris and Chunhua Liao and Ignacio Laguna and Bernhard Steffen}, title = {Enhancing Performance through Control-Flow Unmerging and Loop Unrolling on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {129-128}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p103-p (type: Full Paper (11 pages excl. references)) doi:
	Susungi, Adilla	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Swann, Ryan	CGO '24: "Seer: Predictive Runtime Kernel ..." Seer: Predictive Runtime Kernel Selection for Irregular Problems Ryan Swann, Muhammad Osama, Karthik Sangaiah, and Jalal Mahmud (AMD, USA) @InProceedings{CGO24p161, author = {Ryan Swann and Muhammad Osama and Karthik Sangaiah and Jalal Mahmud}, title = {Seer: Predictive Runtime Kernel Selection for Irregular Problems}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {161-160}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p238-p (type: Full Paper (11 pages excl. references)) doi:
	Tchoulak, Nassim	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Tiotto, Ettore	CGO '24: "Experiences Building an MLIR-Based ..." Experiences Building an MLIR-Based SYCL Compiler Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, and James Brodman (Intel Corporation, Canada; Codeplay Software, United Kingdom; Intel Corporation, USA) @InProceedings{CGO24p497, author = {Ettore Tiotto and Víctor Pérez and Whitney Tsang and Lukas Sommer and Julian Oppermann and Victor Lomüller and Mehdi Goli and James Brodman}, title = {Experiences Building an MLIR-Based SYCL Compiler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {497-496}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p70-p (type: Full Paper (11 pages excl. references)) doi:
	Titzer, Ben L.	CGO '24: "Whose Baseline Compiler Is ..." Whose Baseline Compiler Is It Anyway? Ben L. Titzer (Carnegie Mellon University, USA) @InProceedings{CGO24p257, author = {Ben L. Titzer}, title = {Whose Baseline Compiler Is It Anyway?}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {257-256}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p271-p (type: Full Paper (11 pages excl. references)) doi:
	Tsang, Whitney	CGO '24: "Experiences Building an MLIR-Based ..." Experiences Building an MLIR-Based SYCL Compiler Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, and James Brodman (Intel Corporation, Canada; Codeplay Software, United Kingdom; Intel Corporation, USA) @InProceedings{CGO24p497, author = {Ettore Tiotto and Víctor Pérez and Whitney Tsang and Lukas Sommer and Julian Oppermann and Victor Lomüller and Mehdi Goli and James Brodman}, title = {Experiences Building an MLIR-Based SYCL Compiler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {497-496}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p70-p (type: Full Paper (11 pages excl. references)) doi:
	Tumeo, Antonino	CGO '24: "AXI4MLIR: User-Driven Automatic ..." AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators Nicolas Bohm Agostini, Jude Haris, Perry Gibson, Malith Jayaweera, Norm Rubin, Antonino Tumeo, José L. Abellán, José Cano, and David Kaeli (Northeastern University, USA; Pacific Northwest National Laboratory, USA; University of Glasgow, United Kingdom; University of Murcia, Spain) @InProceedings{CGO24p177, author = {Nicolas Bohm Agostini and Jude Haris and Perry Gibson and Malith Jayaweera and Norm Rubin and Antonino Tumeo and José L. Abellán and José Cano and David Kaeli}, title = {AXI4MLIR: User-Driven Automatic Host Code Generation for Custom AXI-Based Accelerators}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {177-176}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p7-p (type: Full Paper (11 pages excl. references)) doi:
	Van der Cruysse, Jonathan	CGO '24: "Latent Idiom Recognition for ..." Latent Idiom Recognition for a Minimalist Functional Array Language using Equality Saturation Jonathan Van der Cruysse and Christophe Dubach (McGill University, Canada) @InProceedings{CGO24p337, author = {Jonathan Van der Cruysse and Christophe Dubach}, title = {Latent Idiom Recognition for a Minimalist Functional Array Language using Equality Saturation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {337-336}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p104-p (type: Full Paper (11 pages excl. references)) doi:
	Vougioukas, Ilias	CGO '24: "OptiWISE: Combining Sampling ..." OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis Yuxin Guo, Alex W. Chadwick, Márton Erdős, Utpal Bora, Ilias Vougioukas, Giacomo Gabrielli, and Timothy M. Jones (University of Cambridge, United Kingdom; Arm, USA; Arm, United Kingdom) @InProceedings{CGO24p465, author = {Yuxin Guo and Alex W. Chadwick and Márton Erdős and Utpal Bora and Ilias Vougioukas and Giacomo Gabrielli and Timothy M. Jones}, title = {OptiWISE: Combining Sampling and Instrumentation for Granular CPI Analysis}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {465-464}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p78-p (type: Full Paper (11 pages excl. references)) doi:
	Wang, Lei	CGO '24: "Revamping Sampling-Based PGO ..." Revamping Sampling-Based PGO with Context-Sensitivity and Pseudo-instrumentation Wenlei He, Hongtao Yu, Lei Wang, and Taewook Oh (Meta, USA) @InProceedings{CGO24p401, author = {Wenlei He and Hongtao Yu and Lei Wang and Taewook Oh}, title = {Revamping Sampling-Based PGO with Context-Sensitivity and Pseudo-instrumentation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {401-400}, doi = {}, year = {2024}, } Article: cgo24main-p138-p (type: Full Paper (11 pages excl. references)) doi:
	Wang, Wenwen	CGO '24: "A System-Level Dynamic Binary ..." A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules Jinhu Jiang, Chaoyi Liang, Rongchao Dong, Zhaohui Yang, Zhongjun Zhou, Wenwen Wang, Pen-Chung Yew, and Weihua Zhang (Fudan University, China; University of Georgia, USA; University of Minnesota at Twin Cities, USA) @InProceedings{CGO24p529, author = {Jinhu Jiang and Chaoyi Liang and Rongchao Dong and Zhaohui Yang and Zhongjun Zhou and Wenwen Wang and Pen-Chung Yew and Weihua Zhang}, title = {A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {529-528}, doi = {}, year = {2024}, } Article: cgo24main-p51-p (type: Full Paper (11 pages excl. references)) doi:
	Wang, Yanzhi	CGO '24: "Energy-Aware Tile Size Selection ..." Energy-Aware Tile Size Selection for Affine Programs on GPUs Malith Jayaweera, Martin Kong, Yanzhi Wang, and David Kaeli (Northeastern University, USA; Ohio State University, USA) @InProceedings{CGO24p17, author = {Malith Jayaweera and Martin Kong and Yanzhi Wang and David Kaeli}, title = {Energy-Aware Tile Size Selection for Affine Programs on GPUs}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {17-16}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p83-p (type: Full Paper (11 pages excl. references)) doi:
	Woodruff, Jackson	CGO '24: "SLaDe: A Portable Small Language ..." SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly Jordi Armengol-Estapé, Jackson Woodruff, Chris Cummins, and Michael F. P. O'Boyle (University of Edinburgh, United Kingdom; Meta AI Research, USA) @InProceedings{CGO24p81, author = {Jordi Armengol-Estapé and Jackson Woodruff and Chris Cummins and Michael F. P. O'Boyle}, title = {SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {81-80}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Article: cgo24main-p72-p (type: Full Paper (11 pages excl. references)) doi:
	Wu, Jun	CGO '24: "Ecmas: Efficient Circuit Mapping ..." Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code Mingzheng Zhu, Hao Fu, Jun Wu, Chi Zhang, Wei Xie, and Xiang-Yang Li (University of Science and Technology of China, China) @InProceedings{CGO24p193, author = {Mingzheng Zhu and Hao Fu and Jun Wu and Chi Zhang and Wei Xie and Xiang-Yang Li}, title = {Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {193-192}, doi = {}, year = {2024}, } Article: cgo24main-p100-p (type: Full Paper (11 pages excl. references)) doi:
	Xie, Wei	CGO '24: "Ecmas: Efficient Circuit Mapping ..." Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code Mingzheng Zhu, Hao Fu, Jun Wu, Chi Zhang, Wei Xie, and Xiang-Yang Li (University of Science and Technology of China, China) @InProceedings{CGO24p193, author = {Mingzheng Zhu and Hao Fu and Jun Wu and Chi Zhang and Wei Xie and Xiang-Yang Li}, title = {Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {193-192}, doi = {}, year = {2024}, } Article: cgo24main-p100-p (type: Full Paper (11 pages excl. references)) doi:
	Yang, Zhaohui	CGO '24: "A System-Level Dynamic Binary ..." A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules Jinhu Jiang, Chaoyi Liang, Rongchao Dong, Zhaohui Yang, Zhongjun Zhou, Wenwen Wang, Pen-Chung Yew, and Weihua Zhang (Fudan University, China; University of Georgia, USA; University of Minnesota at Twin Cities, USA) @InProceedings{CGO24p529, author = {Jinhu Jiang and Chaoyi Liang and Rongchao Dong and Zhaohui Yang and Zhongjun Zhou and Wenwen Wang and Pen-Chung Yew and Weihua Zhang}, title = {A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {529-528}, doi = {}, year = {2024}, } Article: cgo24main-p51-p (type: Full Paper (11 pages excl. references)) doi:
	Yao, Jianguo	CGO '24: "PresCount: Effective Register ..." PresCount: Effective Register Allocation for Bank Conflict Reduction Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, and Jianguo Yao (Shanghai Jiao Tong University, China; Shanghai Enflame Technology, China) @InProceedings{CGO24p209, author = {Xiaofeng Guan and Hao Zhou and Guoqing Bao and Handong Li and Liang Zhu and Jianguo Yao}, title = {PresCount: Effective Register Allocation for Bank Conflict Reduction}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {209-208}, doi = {}, year = {2024}, } Article: cgo24main-p16-p (type: Full Paper (11 pages excl. references)) doi:
	Ye, Jason	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Yew, Pen-Chung	CGO '24: "A System-Level Dynamic Binary ..." A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules Jinhu Jiang, Chaoyi Liang, Rongchao Dong, Zhaohui Yang, Zhongjun Zhou, Wenwen Wang, Pen-Chung Yew, and Weihua Zhang (Fudan University, China; University of Georgia, USA; University of Minnesota at Twin Cities, USA) @InProceedings{CGO24p529, author = {Jinhu Jiang and Chaoyi Liang and Rongchao Dong and Zhaohui Yang and Zhongjun Zhou and Wenwen Wang and Pen-Chung Yew and Weihua Zhang}, title = {A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {529-528}, doi = {}, year = {2024}, } Article: cgo24main-p51-p (type: Full Paper (11 pages excl. references)) doi:
	Yu, Hongtao	CGO '24: "Revamping Sampling-Based PGO ..." Revamping Sampling-Based PGO with Context-Sensitivity and Pseudo-instrumentation Wenlei He, Hongtao Yu, Lei Wang, and Taewook Oh (Meta, USA) @InProceedings{CGO24p401, author = {Wenlei He and Hongtao Yu and Lei Wang and Taewook Oh}, title = {Revamping Sampling-Based PGO with Context-Sensitivity and Pseudo-instrumentation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {401-400}, doi = {}, year = {2024}, } Article: cgo24main-p138-p (type: Full Paper (11 pages excl. references)) doi:
	Zhang, Chi	CGO '24: "Ecmas: Efficient Circuit Mapping ..." Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code Mingzheng Zhu, Hao Fu, Jun Wu, Chi Zhang, Wei Xie, and Xiang-Yang Li (University of Science and Technology of China, China) @InProceedings{CGO24p193, author = {Mingzheng Zhu and Hao Fu and Jun Wu and Chi Zhang and Wei Xie and Xiang-Yang Li}, title = {Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {193-192}, doi = {}, year = {2024}, } Article: cgo24main-p100-p (type: Full Paper (11 pages excl. references)) doi:
	Zhang, Renwei	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Zhang, Weihua	CGO '24: "A System-Level Dynamic Binary ..." A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules Jinhu Jiang, Chaoyi Liang, Rongchao Dong, Zhaohui Yang, Zhongjun Zhou, Wenwen Wang, Pen-Chung Yew, and Weihua Zhang (Fudan University, China; University of Georgia, USA; University of Minnesota at Twin Cities, USA) @InProceedings{CGO24p529, author = {Jinhu Jiang and Chaoyi Liang and Rongchao Dong and Zhaohui Yang and Zhongjun Zhou and Wenwen Wang and Pen-Chung Yew and Weihua Zhang}, title = {A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {529-528}, doi = {}, year = {2024}, } Article: cgo24main-p51-p (type: Full Paper (11 pages excl. references)) doi:
	Zhang, Yan	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Zhang, Yifei	CGO '24: "oneDNN Graph Compiler: A Hybrid ..." oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation Jianhui Li, Zhennan Qin, Yijie Mei, Jingze Cui, Yunfei Song, Ciyong Chen, Yifei Zhang, Longsheng Du, Xianhang Cheng, Baihui Jin, Yan Zhang, Jason Ye, Eric Lin, and Dan Lavery (Intel, USA; Intel, China) @InProceedings{CGO24p577, author = {Jianhui Li and Zhennan Qin and Yijie Mei and Jingze Cui and Yunfei Song and Ciyong Chen and Yifei Zhang and Longsheng Du and Xianhang Cheng and Baihui Jin and Yan Zhang and Jason Ye and Eric Lin and Dan Lavery}, title = {oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {577-576}, doi = {}, year = {2024}, } Artifacts Reusable Results Reproduced Article: cgo24main-p120-p (type: Full Paper (11 pages excl. references)) doi:
	Zhang, Zhen	CGO '24: "PolyTOPS: Reconfigurable and ..." PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler Gianpietro Consolaro, Zhen Zhang, Harenome Razanajato, Nelson Lossing, Nassim Tchoulak, Adilla Susungi, Artur Cesar Araujo Alves, Renwei Zhang, Denis Barthou, Corinne Ancourt, and Cédric Bastoul (Huawei Technologies, France; Mines Paris-PSL, France; Huawei Technologies, China) @InProceedings{CGO24p33, author = {Gianpietro Consolaro and Zhen Zhang and Harenome Razanajato and Nelson Lossing and Nassim Tchoulak and Adilla Susungi and Artur Cesar Araujo Alves and Renwei Zhang and Denis Barthou and Corinne Ancourt and Cédric Bastoul}, title = {PolyTOPS: Reconfigurable and Flexible Polyhedral Scheduler}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {33-32}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p143-p (type: Full Paper (11 pages excl. references)) doi:
	Zhao, Jisheng	CGO '24: "Enabling Fine-Grained Incremental ..." Enabling Fine-Grained Incremental Builds by Making Compiler Stateful Ruobing Han, Jisheng Zhao, and Hyesoon Kim (Georgia Institute of Technology, USA) @InProceedings{CGO24p273, author = {Ruobing Han and Jisheng Zhao and Hyesoon Kim}, title = {Enabling Fine-Grained Incremental Builds by Making Compiler Stateful}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {273-272}, doi = {}, year = {2024}, } Article: cgo24main-p121-p (type: Full Paper (11 pages excl. references)) doi:
	Zhao, Qidong	CGO '24: "DrPy: Pinpointing Inefficient ..." DrPy: Pinpointing Inefficient Memory Usage in Multi-Layer Python Applications Jinku Cui, Qidong Zhao, Yueming Hao, and Xu Liu (North Carolina State University, USA) @InProceedings{CGO24p305, author = {Jinku Cui and Qidong Zhao and Yueming Hao and Xu Liu}, title = {DrPy: Pinpointing Inefficient Memory Usage in Multi-Layer Python Applications}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {305-304}, doi = {}, year = {2024}, } Artifacts Functional Article: cgo24main-p141-p (type: Full Paper (11 pages excl. references)) doi: CGO '24: "EasyView: Bringing Performance ..." EasyView: Bringing Performance Profiles into Integrated Development Environments Qidong Zhao, Milind Chabbi, and Xu Liu (North Carolina State University, USA; Scalable Machines Research, USA) @InProceedings{CGO24p481, author = {Qidong Zhao and Milind Chabbi and Xu Liu}, title = {EasyView: Bringing Performance Profiles into Integrated Development Environments}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {481-480}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Functional Results Reproduced Article: cgo24main-p107-p (type: Full Paper (11 pages excl. references)) doi:
	Zhong, Peter	CGO '24: "Representing Data Collections ..." Representing Data Collections in an SSA Form Tommy McMichen, Nathan Greiner, Peter Zhong, Federico Sossai, Atmn Patel, and Simone Campanoni (Northwestern University, USA) @InProceedings{CGO24p385, author = {Tommy McMichen and Nathan Greiner and Peter Zhong and Federico Sossai and Atmn Patel and Simone Campanoni}, title = {Representing Data Collections in an SSA Form}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {385-384}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p148-p (type: Full Paper (11 pages excl. references)) doi:
	Zhou, Hao	CGO '24: "PresCount: Effective Register ..." PresCount: Effective Register Allocation for Bank Conflict Reduction Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, and Jianguo Yao (Shanghai Jiao Tong University, China; Shanghai Enflame Technology, China) @InProceedings{CGO24p209, author = {Xiaofeng Guan and Hao Zhou and Guoqing Bao and Handong Li and Liang Zhu and Jianguo Yao}, title = {PresCount: Effective Register Allocation for Bank Conflict Reduction}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {209-208}, doi = {}, year = {2024}, } Article: cgo24main-p16-p (type: Full Paper (11 pages excl. references)) doi:
	Zhou, Zhongjun	CGO '24: "A System-Level Dynamic Binary ..." A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules Jinhu Jiang, Chaoyi Liang, Rongchao Dong, Zhaohui Yang, Zhongjun Zhou, Wenwen Wang, Pen-Chung Yew, and Weihua Zhang (Fudan University, China; University of Georgia, USA; University of Minnesota at Twin Cities, USA) @InProceedings{CGO24p529, author = {Jinhu Jiang and Chaoyi Liang and Rongchao Dong and Zhaohui Yang and Zhongjun Zhou and Wenwen Wang and Pen-Chung Yew and Weihua Zhang}, title = {A System-Level Dynamic Binary Translator using Automatically-Learned Translation Rules}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {529-528}, doi = {}, year = {2024}, } Article: cgo24main-p51-p (type: Full Paper (11 pages excl. references)) doi:
	Zhu, Liang	CGO '24: "PresCount: Effective Register ..." PresCount: Effective Register Allocation for Bank Conflict Reduction Xiaofeng Guan, Hao Zhou, Guoqing Bao, Handong Li, Liang Zhu, and Jianguo Yao (Shanghai Jiao Tong University, China; Shanghai Enflame Technology, China) @InProceedings{CGO24p209, author = {Xiaofeng Guan and Hao Zhou and Guoqing Bao and Handong Li and Liang Zhu and Jianguo Yao}, title = {PresCount: Effective Register Allocation for Bank Conflict Reduction}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {209-208}, doi = {}, year = {2024}, } Article: cgo24main-p16-p (type: Full Paper (11 pages excl. references)) doi:
	Zhu, Mingzheng	CGO '24: "Ecmas: Efficient Circuit Mapping ..." Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code Mingzheng Zhu, Hao Fu, Jun Wu, Chi Zhang, Wei Xie, and Xiang-Yang Li (University of Science and Technology of China, China) @InProceedings{CGO24p193, author = {Mingzheng Zhu and Hao Fu and Jun Wu and Chi Zhang and Wei Xie and Xiang-Yang Li}, title = {Ecmas: Efficient Circuit Mapping and Scheduling for Surface Code}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {193-192}, doi = {}, year = {2024}, } Article: cgo24main-p100-p (type: Full Paper (11 pages excl. references)) doi:
	Zinenko, Oleksandr	CGO '24: "Retargeting and Respecializing ..." Retargeting and Respecializing GPU Workloads for Performance Portability Ivan R. Ivanov, Oleksandr Zinenko, Jens Domke, Toshio Endo, and William S. Moses (Tokyo Institute of Technology, Japan; RIKEN R-CCS, Japan; Google DeepMind, France; University of Illinois at Urbana-Champaign, USA; Google DeepMind, USA) @InProceedings{CGO24p145, author = {Ivan R. Ivanov and Oleksandr Zinenko and Jens Domke and Toshio Endo and William S. Moses}, title = {Retargeting and Respecializing GPU Workloads for Performance Portability}, booktitle = {Proc.\ CGO}, publisher = {IEEE}, pages = {145-144}, doi = {}, year = {2024}, } Published Artifact Artifacts Available Artifacts Reusable Results Reproduced Article: cgo24main-p19-p (type: Full Paper (11 pages excl. references)) doi:

182 authors

proc time: 0.13