Patents by Inventor Thomas L. Drabenstott
Thomas L. Drabenstott has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 7146487Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: GrantFiled: November 20, 2003Date of Patent: December 5, 2006Assignee: Altera CorporationInventors: Thomas L. Drabenstott, Gerald George Pechanek, Edwin Franklin Barry, Charles W. Kurak, Jr.
-
Patent number: 7010668Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: GrantFiled: August 28, 2003Date of Patent: March 7, 2006Assignee: PTS CorporationInventors: Thomas L. Drabenstott, Gerald G. Penchanek, Edwin F. Barry, Charles W. Kurak, Jr.
-
Patent number: 6954842Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: GrantFiled: August 28, 2003Date of Patent: October 11, 2005Assignee: PTS CorporationInventors: Thomas L. Drabenstott, Gerald G. Pechanek, Edwin F. Barry, Charles W. Kurak, Jr.
-
Patent number: 6795909Abstract: Processing element to processing element switch connection control is described using a receive model that precludes communication hazards from occurring in a synchronous MIMD mode of operation. Such control allows different communication topologies and various processing effects such as an array transpose, hypercomplement or the like to be efficiently achieved utilizing architectures, such as the manifold array processing architecture. An encoded instruction method reduces the amount of state information and setup burden on the programmer taking advantage of the recognition that the majority of algorithms will use only a small fraction of all possible mux settings available. Thus, by means of transforming the PE identification based upon a communication path specified by a PE communication instruction an efficient switch control mechanism can be used.Type: GrantFiled: April 1, 2002Date of Patent: September 21, 2004Assignee: PTS CorporationInventors: Edwin F. Barry, Gerald G. Pechanek, Thomas L. Drabenstott, Edward A. Wolff, Nikos P. Pitsianis, Grayson Morris
-
Patent number: 6769056Abstract: A manifold array topology includes processing elements, nodes, memories or the like arranged in clusters. Clusters are connected by cluster switch arrangements which advantageously allow changes of organization without physical rearrangement of processing elements. A significant reduction in the typical number of interconnections for preexisting arrays is also achieved. Fast, efficient and cost effective processing and communication result with the added benefit of ready scalability.Type: GrantFiled: September 24, 2002Date of Patent: July 27, 2004Assignee: PTS CorporationInventors: Edwin F. Barry, Thomas L. Drabenstott, Gerald G. Pechanek, Nikos P. Pitsianis
-
Patent number: 6760831Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: GrantFiled: April 1, 2002Date of Patent: July 6, 2004Assignee: PTS CorporationInventors: Thomas L. Drabenstott, Gerald G. Pechanek, Edwin F. Barry, Charles W. Kurak, Jr.
-
Publication number: 20040107333Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: ApplicationFiled: November 20, 2003Publication date: June 3, 2004Applicant: PTS CorporationInventors: Thomas L. Drabenstott, Gerald G. Pechanek, Edwin F. Barry, Charles W. Kurak
-
Publication number: 20040049664Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: ApplicationFiled: August 28, 2003Publication date: March 11, 2004Applicant: PTS CorporationInventors: Thomas L. Drabenstott, Gerald G. Pechanek, Edwin F. Barry, Charles W. Kurak
-
Publication number: 20040039899Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: ApplicationFiled: August 28, 2003Publication date: February 26, 2004Applicant: PTS CorporationInventors: Thomas L. Drabenstott, Gerald G. Pechanek, Edwin F. Barry, Charles W. Kurak
-
Publication number: 20030088754Abstract: A manifold array topology includes processing elements, nodes, memories or the like arranged in clusters. Clusters are connected by cluster switch arrangements which advantageously allow changes of organization without physical rearrangement of processing elements. A significant reduction in the typical number of interconnections for preexisting arrays is also achieved. Fast, efficient and cost effective processing and communication result with the added benefit of ready scalability.Type: ApplicationFiled: September 24, 2002Publication date: May 8, 2003Inventors: Edwin F. Barry, Thomas L. Drabenstott, Gerald G. Pechanek, Nikos P. Pitsianis
-
Publication number: 20020178345Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: ApplicationFiled: April 1, 2002Publication date: November 28, 2002Applicant: BOPS, Inc.Inventors: Thomas L. Drabenstott, Gerald George Pechanek, Edwin Franklin Barry, Charles W. Kurak,
-
Patent number: 6470441Abstract: A manifold array topology includes processing elements, nodes, memories or the like arranged in clusters. Clusters are connected by cluster switch arrangements which advantageously allow changes of organization without physical rearrangement of processing elements. A significant reduction in the typical number of interconnections for preexisting arrays is also achieved. Fast, efficient and cost effective processing and communication result with the added benefit of ready scalability.Type: GrantFiled: November 6, 2000Date of Patent: October 22, 2002Assignee: BOPS, Inc.Inventors: Gerald G. Pechanek, Nikos P. Pitsianis, Edwin F. Barry, Thomas L. Drabenstott
-
Publication number: 20020144082Abstract: Processing element to processing element switch connection control is described using a receive model that precludes communication hazards from occurring in a synchronous MIMD mode of operation. Such control allows different communication topologies and various processing effects such as an array transpose, hypercomplement or the like to be efficiently achieved utilizing architectures, such as the manifold array processing architecture. An encoded instruction method reduces the amount of state information and setup burden on the programmer taking advantage of the recognition that the majority of algorithms will use only a small fraction of all possible mux settings available. Thus, by means of transforming the PE identification based upon a communication path specified by a PE communication instruction an efficient switch control mechanism can be used.Type: ApplicationFiled: April 1, 2002Publication date: October 3, 2002Applicant: BOPS, Inc.Inventors: Edwin Franklin Barry, Gerald George Pechanek, Thomas L. Drabenstott, Edward A. Wolff, Nikos P. Pitsianis, Grayson Morris
-
Patent number: 6446191Abstract: A SIMD machine employing a plurality of parallel processor (PEs) in which communications hazards are eliminated in an efficient manner. An indirect Very Long Instruction Word instruction memory (VIM) is employed along with execute and delimiter instructions. A masking mechanism may be employed to control which PEs have their VIMs loaded. Further, a receive model of operation is preferably employed. In one aspect, each PE operates to control a switch that selects from which PE it receives. The present invention addresses a better machine organization for execution of parallel algorithms that reduces hardware cost and complexity while maintaining the best characteristics of both SIMD and MIMD machines and minimizing communication latency. This invention brings a level of MIMD computational autonomy to SIMD indirect Very Long Instruction Word (iVLIW) processing elements while maintaining the single thread of control used in the SIMD machine organization.Type: GrantFiled: October 2, 2000Date of Patent: September 3, 2002Assignee: BOPS, Inc.Inventors: Gerald G. Pechanek, Thomas L. Drabenstott, Juan Guillermo Revilla, David Carl Strube, Grayson Morris
-
Patent number: 6366997Abstract: Processing element to processing element switch connection control is described using a receive model that precludes communication hazards from occurring in a synchronous MIMD mode of operation. Such control allows different communication topologies and various processing effects such as an array transpose, hypercomplement or the like to be efficiently achieved utilizing architectures, such as the manifold array processing architecture. An encoded instruction method reduces the amount of state information and setup burden on the programmer taking advantage of the recognition that the majority of algorithms will use only a small fraction of all possible mux settings available. Thus, by means of transforming the PE identification based upon a communication path specified by a PE communication instruction an efficient switch control mechanism can be used.Type: GrantFiled: August 29, 2000Date of Patent: April 2, 2002Assignee: BOPS, Inc.Inventors: Edwin F. Barry, Gerald G. Pechanek, Thomas L. Drabenstott, Edward A. Wolff, Nikos P. Pitsianis, Grayson Morris
-
Patent number: 6366999Abstract: General purpose flags (ACFs) are defined and encoded utilizing a hierarchical one-, two- or three-bit encoding. Each added bit provides a superset of the previous functionality. With condition combination, a sequential series of conditional branches based on complex conditions may be avoided and complex conditions can then be used for conditional execution. ACF generation and use can be specified by the programmer. By varying the number of flags affected, conditional operation parallelism can be widely varied, for example, from mono-processing to octal-processing in VLIW execution, and across an array of processing elements (PE)s. Multiple PEs can generate condition information at the same time with the programmer being able to specify a conditional execution in one processor based upon a condition generated in a different processor using the communications interface between the processing elements to transfer the conditions.Type: GrantFiled: January 28, 1999Date of Patent: April 2, 2002Assignee: BOPS, Inc.Inventors: Thomas L. Drabenstott, Gerald G. Pechanek, Edwin F. Barry, Charles W. Kurak, Jr.
-
Patent number: 6167502Abstract: A manifold array topology includes processing elements, nodes, memories or the like arranged in clusters. Clusters are connected by cluster switch arrangements which advantageously allow changes of organization without physical rearrangement of processing elements. A significant reduction in the typical number of interconnections for preexisting arrays is also achieved. Fast, efficient and cost effective processing and communication result with the added benefit of ready scalability.Type: GrantFiled: October 10, 1997Date of Patent: December 26, 2000Assignee: Billions of Operations Per Second, Inc.Inventors: Gerald G. Pechanek, Nikos P. Pitsianis, Edwin F. Barry, Thomas L. Drabenstott
-
Patent number: 6167501Abstract: Processing element to processing element switch connection control is described using a receive model that precludes communication hazards from occurring in a synchronous MIMD mode of operation. Such control allows different communication topologies and various processing effects such as an array transpose, hypercomplement or the like to be efficiently achieved utilizing architectures, such as the manifold array processing architecture. An encoded instruction method reduces the amount of state information and setup burden on the programmer taking advantage of the recognition that the majority of algorithms will use only a small fraction of all possible mux settings available. Thus, by means of transforming the PE identification based upon a communication path specified by a PE communication instruction an efficient switch control mechanism can be used.Type: GrantFiled: October 9, 1998Date of Patent: December 26, 2000Assignee: Billions of Operations Per Second, Inc.Inventors: Edwin F. Barry, Gerald G. Pechanek, Thomas L. Drabenstott, Edward A. Wolff, Nikos P. Pitsianis, Grayson Morris
-
Patent number: 6151668Abstract: A SIMD machine employing a plurality of parallel processor (PEs) in which communications hazards are eliminated in an efficient manner. An indirect Very Long Instruction Word instruction memory (VIM) is employed along with execute and delimiter instructions. A masking mechanism may be employed to control which PEs have their VIMs loaded. Further, a receive model of operation is preferably employed. In one aspect, each PE operates to control a switch that selects from which PE it receives. The present invention addresses a better machine organization for execution of parallel algorithms that reduces hardware cost and complexity while maintaining the best characteristics of both SIMD and MIMD machines and minimizing communication latency. This invention brings a level of MIMD computational autonomy to SIMD indirect Very Long Instruction Word (iVLIW) processing elements while maintaining the single thread of control used in the SIMD machine organization.Type: GrantFiled: November 6, 1998Date of Patent: November 21, 2000Assignee: Billions of Operations Per Second, Inc.Inventors: Gerald G. Pechanek, Thomas L. Drabenstott, Juan Guillermo Revilla, David Carl Strube, Grayson Morris
-
Patent number: RE41703Abstract: A SIMD machine employing a plurality of parallel processor (PEs) in which communications hazards are eliminated in an efficient manner. An indirect Very Long Instruction Word instruction memory (VIM) is employed along with execute and delimiter instructions. A masking mechanism may be employed to control which PEs have their VIMs loaded. Further, a receive model of operation is preferably employed. In one aspect, each PE operates to control a switch that selects from which PE it receives. The present invention addresses a better machine organization for execution of parallel algorithms that reduces hardware cost and complexity while maintaining the best characteristics of both SIMD and MIMD machines and minimizing communication latency. This invention brings a level of MIMD computational autonomy to SIMD indirect Very Long Instruction Word (iVLIW) processing elements while maintaining the single thread of control used in the SIMD machine organization.Type: GrantFiled: June 21, 2004Date of Patent: September 14, 2010Assignee: Altera Corp.Inventors: Gerald George Pechanek, Thomas L. Drabenstott, Juan Guillermo Revilla, David Strube, Grayson Morris