Patents by Inventor Muthu Manikandan Baskaran
Muthu Manikandan Baskaran 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: 11907549Abstract: A system for allocation of one or more data structures used in a program across a number of processing units takes into account a memory access pattern of the data structure, and the amount of total memory available for duplication across the several processing units. Using these parameters duplication factors are determined for the one or more data structures such that the cost of remote communication is minimized when the data structures are duplicated according to the respective duplication factors while allowing parallel execution of the program.Type: GrantFiled: June 24, 2021Date of Patent: February 20, 2024Assignee: QUALCOMM IncorporatedInventors: Muthu Manikandan Baskaran, Thomas Henretty, Ann Johnson, Athanasios Konstantinidis, M. H. Langston, Janice O. Mcmahon, Benoit J. Meister, Paul D. Mountcastle, Aale Naqvi, Benoit Pradelle, Tahina Ramananandro, Sanket Tavarageri, Richard A. Lethin
-
Patent number: 11755684Abstract: In a system for improving performance of tensor-based computations and for minimizing the associated memory usage, computations associated with different non-zero tensor values are performed while exploiting an overlap between the respective index tuples of those non-zero values. While performing computations associated with a selected mode, when an index corresponding to a particular mode in a current index tuple is the same as the corresponding index from another, previously processed index tuple, the value already stored in a buffer corresponding to that particular mode is reused either wholly or in part, minimizing the processor usage and improving performance. Certain matrix operations may be iterated more than once so as to avoid the need to store a large partial result obtained from those operations. The performance overhead of the repeated operations is not significant, but the reduction in memory usage is.Type: GrantFiled: March 18, 2021Date of Patent: September 12, 2023Assignee: Reservoir Labs, Inc.Inventor: Muthu Manikandan Baskaran
-
Patent number: 11579905Abstract: A compilation system can define, at compile time, the data blocks to be managed by an Even Driven Task (EDT) based runtime/platform, and can also guide the runtime/platform on when to create and/or destroy the data blocks, so as to improve the performance of the runtime/platform. The compilation system can also guide, at compile time, how different tasks may access the data blocks they need in a manner that can improve performance of the tasks.Type: GrantFiled: October 26, 2021Date of Patent: February 14, 2023Assignee: Reservoir Labs, Inc.Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Patent number: 11573945Abstract: In a system for storing in memory a tensor that includes at least three modes, elements of the tensor are stored in a mode-based order for improving locality of references when the elements are accessed during an operation on the tensor. To facilitate efficient data reuse in a tensor transform that includes several iterations, on a tensor that includes at least three modes, a system performs a first iteration that includes a first operation on the tensor to obtain a first intermediate result, and the first intermediate result includes a first intermediate-tensor. The first intermediate result is stored in memory, and a second iteration is performed in which a second operation on the first intermediate result accessed from the memory is performed, so as to avoid a third operation, that would be required if the first intermediate result were not accessed from the memory.Type: GrantFiled: September 25, 2020Date of Patent: February 7, 2023Assignee: Qualcomm IncorporatedInventors: Muthu Manikandan Baskaran, Richard A. Lethin, Benoit J. Meister, Nicolas T. Vasilache
-
Patent number: 11537373Abstract: A system for compiling programs for execution thereof using a hierarchical processing system having two or more levels of memory hierarchy can perform memory-level-specific optimizations, without exceeding a specified maximum compilation time. To this end, the compiler system employs a polyhedral model and limits the dimensions of a polyhedral program representation that is processed by the compiler at each level using a focalization operator that temporarily reduces one or more dimensions of the polyhedral representation. Semantic correctness is provided via a defocalization operator that can restore all polyhedral dimensions that had been temporarily removed.Type: GrantFiled: September 28, 2020Date of Patent: December 27, 2022Assignee: Qualcomm Technologies, Inc.Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Publication number: 20220114000Abstract: A compilation system can define, at compile time, the data blocks to be managed by an Even Driven Task (EDT) based runtime/platform, and can also guide the runtime/platform on when to create and/or destroy the data blocks, so as to improve the performance of the runtime/platform. The compilation system can also guide, at compile time, how different tasks may access the data blocks they need in a manner that can improve performance of the tasks.Type: ApplicationFiled: October 26, 2021Publication date: April 14, 2022Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Publication number: 20220057949Abstract: A system for allocation of one or more data structures used in a program across a number of processing units takes into account a memory access pattern of the data structure, and the amount of total memory available for duplication across the several processing units. Using these parameters duplication factors are determined for the one or more data structures such that the cost of remote communication is minimized when the data structures are duplicated according to the respective duplication factors while allowing parallel execution of the program.Type: ApplicationFiled: June 24, 2021Publication date: February 24, 2022Inventors: Muthu Manikandan Baskaran, Thomas Henretty, Ann Johnson, Athanasios Konstantinidis, M. H. Langston, Janice O. Mcmahon, Benoit J. Meister, Paul D. Mountcastle, Aale Naqvi, Benoit Pradelle, Tahina Ramananandro, Sanket Tavarageri, Richard A. Lethin
-
Patent number: 11188363Abstract: A compilation system can define, at compile time, the data blocks to be managed by an Even Driven Task (EDT) based runtime/platform, and can also guide the runtime/platform on when to create and/or destroy the data blocks, so as to improve the performance of the runtime/platform. The compilation system can also guide, at compile time, how different tasks may access the data blocks they need in a manner that can improve performance of the tasks.Type: GrantFiled: February 10, 2020Date of Patent: November 30, 2021Assignee: Reservoir Labs, Inc.Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Publication number: 20210294876Abstract: A system for performing tensor decomposition in a selective expansive and/or recursive manner, a tensor is decomposed into a specified number of components, and one or more tensor components are selected for further decomposition. For each selected component, the significant elements thereof are identified, and using the indices of the significant elements a sub-tensor is formed. In a subsequent iteration, each sub-tensor is decomposed into a respective specified number of components. Additional sub-tensors corresponding to the components generated in the subsequent iteration are formed, and these additional sub-tensors may be decomposed further in yet another iteration, until no additional components are selected. The mode of a sub-tensor can be decreased or increased prior to decomposition thereof. Components likely to reveal information about the data stored in the tensor can be selected for decomposition.Type: ApplicationFiled: November 2, 2020Publication date: September 23, 2021Inventors: Muthu Manikandan Baskaran, David Bruns-Smith, James Ezick, Richard A. Lethin
-
Patent number: 11086968Abstract: In a system for improving performance of tensor-based computations and for minimizing the associated memory usage, computations associated with different non-zero tensor values are performed while exploiting an overlap between the respective index tuples of those non-zero values. While performing computations associated with a selected mode, when an index corresponding to a particular mode in a current index tuple is the same as the corresponding index from another, previously processed index tuple, the value already stored in a buffer corresponding to that particular mode is reused either wholly or in part, minimizing the processor usage and improving performance. Certain matrix operations may be iterated more than once so as to avoid the need to store a large partial result obtained from those operations. The performance overhead of the repeated operations is not significant, but the reduction in memory usage is.Type: GrantFiled: June 5, 2018Date of Patent: August 10, 2021Assignee: Reservoir Labs, Inc.Inventor: Muthu Manikandan Baskaran
-
Publication number: 20210232379Abstract: A system for compiling programs for execution thereof using a hierarchical processing system having two or more levels of memory hierarchy can perform memory-level-specific optimizations, without exceeding a specified maximum compilation time. To this end, the compiler system employs a polyhedral model and limits the dimensions of a polyhedral program representation that is processed by the compiler at each level using a focalization operator that temporarily reduces one or more dimensions of the polyhedral representation. Semantic correctness is provided via a defocalization operator that can restore all polyhedral dimensions that had been temporarily removed.Type: ApplicationFiled: September 28, 2020Publication date: July 29, 2021Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Patent number: 11068178Abstract: A system for allocation of one or more data structures used in a program across a number of processing units takes into account a memory access pattern of the data structure, and the amount of total memory available for duplication across the several processing units. Using these parameters duplication factors are determined for the one or more data structures such that the cost of remote communication is minimized when the data structures are duplicated according to the respective duplication factors while allowing parallel execution of the program.Type: GrantFiled: December 2, 2019Date of Patent: July 20, 2021Assignee: Reservoir Labs, Inc.Inventors: Muthu Manikandan Baskaran, Thomas Henretty, Ann Johnson, Athanasios Konstantinidis, M. H. Langston, Janice O. Mcmahon, Benoit J. Meister, Paul D. Mountcastle, Aale Naqvi, Benoit Pradelle, Tahina Ramananandro, Sanket Tavarageri, Richard A. Lethin
-
Patent number: 10936569Abstract: In a system for storing in memory a tensor that includes at least three modes, elements of the tensor are stored in a mode-based order for improving locality of references when the elements are accessed during an operation on the tensor. To facilitate efficient data reuse in a tensor transform that includes several iterations, on a tensor that includes at least three modes, a system performs a first iteration that includes a first operation on the tensor to obtain a first intermediate result, and the first intermediate result includes a first intermediate-tensor. The first intermediate result is stored in memory, and a second iteration is performed in which a second operation on the first intermediate result accessed from the memory is performed, so as to avoid a third operation, that would be required if the first intermediate result were not accessed from the memory.Type: GrantFiled: May 20, 2013Date of Patent: March 2, 2021Assignee: Reservoir Labs, Inc.Inventors: Muthu Manikandan Baskaran, Richard A. Lethin, Benoit J. Meister, Nicolas T. Vasilache
-
Publication number: 20210004249Abstract: A compilation system can define, at compile time, the data blocks to be managed by an Even Driven Task (EDT) based runtime/platform, and can also guide the runtime/platform on when to create and/or destroy the data blocks, so as to improve the performance of the runtime/platform. The compilation system can also guide, at compile time, how different tasks may access the data blocks they need in a manner that can improve performance of the tasks.Type: ApplicationFiled: February 10, 2020Publication date: January 7, 2021Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Patent number: 10789055Abstract: A system for compiling programs for execution thereof using a hierarchical processing system having two or more levels of memory hierarchy can perform memory-level-specific optimizations, without exceeding a specified maximum compilation time. To this end, the compiler system employs a polyhedral model and limits the dimensions of a polyhedral program representation that is processed by the compiler at each level using a focalization operator that temporarily reduces one or more dimensions of the polyhedral representation. Semantic correctness is provided via a defocalization operator that can restore all polyhedral dimensions that had been temporarily removed.Type: GrantFiled: October 5, 2016Date of Patent: September 29, 2020Assignee: Reservoir Labs, Inc.Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Patent number: 10558479Abstract: A compilation system can define, at compile time, the data blocks to be managed by an Even Driven Task (EDT) based runtime/platform, and can also guide the runtime/platform on when to create and/or destroy the data blocks, so as to improve the performance of the runtime/platform. The compilation system can also guide, at compile time, how different tasks may access the data blocks they need in a manner that can improve performance of the tasks.Type: GrantFiled: March 25, 2019Date of Patent: February 11, 2020Assignee: Reservoir Labs, Inc.Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Publication number: 20190220295Abstract: A compilation system can define, at compile time, the data blocks to be managed by an Even Driven Task (EDT) based runtime/platform, and can also guide the runtime/platform on when to create and/or destroy the data blocks, so as to improve the performance of the runtime/platform. The compilation system can also guide, at compile time, how different tasks may access the data blocks they need in a manner that can improve performance of the tasks.Type: ApplicationFiled: March 25, 2019Publication date: July 18, 2019Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle
-
Publication number: 20170097815Abstract: A system for compiling programs for execution thereof using a hierarchical processing system having two or more levels of memory hierarchy can perform memory-level-specific optimizations, without exceeding a specified maximum compilation time. To this end, the compiler system employs a polyhedral model and limits the dimensions of a polyhedral program representation that is processed by the compiler at each level using a focalization operator that temporarily reduces one or more dimensions of the polyhedral representation. Semantic correctness is provided via a defocalization operator that can restore all polyhedral dimensions that had been temporarily removed.Type: ApplicationFiled: October 5, 2016Publication date: April 6, 2017Inventors: Muthu Manikandan Baskaran, Benoit J. Meister, Benoit Pradelle