{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/52631"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/52631","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"On the Complexity of Robust Source-to-Source Translation from CUDA to OpenCL","abstract":"The use of hardware accelerators in high-performance computing has grown increasingly prevalent, particularly due to the growth of graphics processing units (GPUs) as general-purpose (GPGPU) accelerators. Much of this growth has been driven by NVIDIA's CUDA ecosystem for developing GPGPU applications on NVIDIA hardware. However, with the increasing diversity of GPUs (including those from AMD, ARM, and Qualcomm), OpenCL has emerged as an open and vendor-agnostic environment for programming GPUs as well as other parallel computing devices such as the CPU (central processing unit), APU (accelerated processing unit), FPGA (field programmable gate array), and DSP (digital signal processor). The above, coupled with the broader array of devices supporting OpenCL and the significant conceptual and syntactic overlap between CUDA and OpenCL, motivated the creation of a CUDA-to-OpenCL source-to-source translator. However, there exist sufficient differences that make the translation non-trivial, providing practical limitations to both manual and automatic translation efforts. In this thesis, the performance, coverage, and reliability of a prototype CUDA-to-OpenCL source translator are addressed via extensive profiling of a large body of sample CUDA applications. An analysis of the sample body of applications is provided, which identifies and characterizes general CUDA source constructs and programming practices that obstruct our translation efforts. This characterization then led to more robust support for the translator, followed by an evaluation that demonstrated the performance of our automatically-translated OpenCL is on par with the original CUDA for a subset of sample applications when executed on the same NVIDIA device.","abstract_html":"The use of hardware accelerators in high-performance computing has grown increasingly prevalent, particularly due to the growth of graphics processing units (GPUs) as general-purpose (GPGPU) accelerators. Much of this growth has been driven by NVIDIA's CUDA ecosystem for developing GPGPU applications on NVIDIA hardware. However, with the increasing diversity of GPUs (including those from AMD, ARM, and Qualcomm), OpenCL has emerged as an open and vendor-agnostic environment for programming GPUs as well as other parallel computing devices such as the CPU (central processing unit), APU (accelerated processing unit), FPGA (field programmable gate array), and DSP (digital signal processor). The above, coupled with the broader array of devices supporting OpenCL and the significant conceptual and syntactic overlap between CUDA and OpenCL, motivated the creation of a CUDA-to-OpenCL source-to-source translator. However, there exist sufficient differences that make the translation non-trivial, providing practical limitations to both manual and automatic translation efforts. In this thesis, the performance, coverage, and reliability of a prototype CUDA-to-OpenCL source translator are addressed via extensive profiling of a large body of sample CUDA applications. An analysis of the sample body of applications is provided, which identifies and characterizes general CUDA source constructs and programming practices that obstruct our translation efforts. This characterization then led to more robust support for the translator, followed by an evaluation that demonstrated the performance of our automatically-translated OpenCL is on par with the original CUDA for a subset of sample applications when executed on the same NVIDIA device.","abstract_has_math":false,"creators":["Sathre, Paul Daniel"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science and Applications","degree_department":"Computer Science","school":null,"contributors":[],"advisors":[],"committee_chairs":["Feng, Wu-chun"],"committee_members":["Gardner, Mark K.","Tilevich, Eli"],"year":2013,"date_issued":"2013-06-12","date_published":"2013-06-12","updated_at":"2026-07-22T22:18:44Z","subjects":["Source Translation","Clang","CUDA","OpenCL","GPU","GPGPU","Compilers"],"languages":[],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:808"],"render_values":[{"text":"vt_gsexam:808","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/52631","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Feng, Wu-chun"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Gardner, Mark K.","Tilevich, Eli"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science"]},{"key":"dc:creator","label":"Author","values":["Sathre, Paul Daniel"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2015-05-27T08:04:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2015-05-27T08:04:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2013-06-12"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Applications"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Source Translation","Clang","CUDA","OpenCL","GPU","GPGPU","Compilers"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:808"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/52631"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The use of hardware accelerators in high-performance computing has grown increasingly prevalent, particularly due to the growth of graphics processing units (GPUs) as general-purpose (GPGPU) accelerators. Much of this growth has been driven by NVIDIA's CUDA ecosystem for developing GPGPU applications on NVIDIA hardware. However, with the increasing diversity of GPUs (including those from AMD, ARM, and Qualcomm), OpenCL has emerged as an open and vendor-agnostic environment for programming GPUs as well as other parallel computing devices such as the CPU (central processing unit), APU (accelerated processing unit), FPGA (field programmable gate array), and DSP (digital signal processor). The above, coupled with the broader array of devices supporting OpenCL and the significant conceptual and syntactic overlap between CUDA and OpenCL, motivated the creation of a CUDA-to-OpenCL source-to-source translator. However, there exist sufficient differences that make the translation non-trivial, providing practical limitations to both manual and automatic translation efforts. In this thesis, the performance, coverage, and reliability of a prototype CUDA-to-OpenCL source translator are addressed via extensive profiling of a large body of sample CUDA applications. An analysis of the sample body of applications is provided, which identifies and characterizes general CUDA source constructs and programming practices that obstruct our translation efforts. This characterization then led to more robust support for the translator, followed by an evaluation that demonstrated the performance of our automatically-translated OpenCL is on par with the original CUDA for a subset of sample applications when executed on the same NVIDIA device."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["On the Complexity of Robust Source-to-Source Translation from CUDA to OpenCL"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Feng, Wu-chun"],"dc:contributor.committeemember":["Gardner, Mark K.","Tilevich, Eli"],"dc:contributor.department":["Computer Science"],"dc:creator":["Sathre, Paul Daniel"],"dc:date.accessioned":["2015-05-27T08:04:17Z"],"dc:date.available":["2015-05-27T08:04:17Z"],"dc:date.issued":["2013-06-12"],"dc:description.abstract":["The use of hardware accelerators in high-performance computing has grown increasingly prevalent, particularly due to the growth of graphics processing units (GPUs) as general-purpose (GPGPU) accelerators. Much of this growth has been driven by NVIDIA's CUDA ecosystem for developing GPGPU applications on NVIDIA hardware. However, with the increasing diversity of GPUs (including those from AMD, ARM, and Qualcomm), OpenCL has emerged as an open and vendor-agnostic environment for programming GPUs as well as other parallel computing devices such as the CPU (central processing unit), APU (accelerated processing unit), FPGA (field programmable gate array), and DSP (digital signal processor). The above, coupled with the broader array of devices supporting OpenCL and the significant conceptual and syntactic overlap between CUDA and OpenCL, motivated the creation of a CUDA-to-OpenCL source-to-source translator. However, there exist sufficient differences that make the translation non-trivial, providing practical limitations to both manual and automatic translation efforts. In this thesis, the performance, coverage, and reliability of a prototype CUDA-to-OpenCL source translator are addressed via extensive profiling of a large body of sample CUDA applications. An analysis of the sample body of applications is provided, which identifies and characterizes general CUDA source constructs and programming practices that obstruct our translation efforts. This characterization then led to more robust support for the translator, followed by an evaluation that demonstrated the performance of our automatically-translated OpenCL is on par with the original CUDA for a subset of sample applications when executed on the same NVIDIA device."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:808"],"dc:identifier.uri":["http://hdl.handle.net/10919/52631"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Source Translation","Clang","CUDA","OpenCL","GPU","GPGPU","Compilers"],"dc:title":["On the Complexity of Robust Source-to-Source Translation from CUDA to OpenCL"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science and Applications"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:18:44Z"}