-
公开(公告)号:US11630800B2
公开(公告)日:2023-04-18
申请号:US15141703
申请日:2016-04-28
申请人: NVIDIA Corporation
摘要: In one embodiment of the present invention, a programmable vision accelerator enables applications to collapse multi-dimensional loops into one dimensional loops. In general, configurable components included in the programmable vision accelerator work together to facilitate such loop collapsing. The configurable elements include multi-dimensional address generators, vector units, and load/store units. Each multi-dimensional address generator generates a different address pattern. Each address pattern represents an overall addressing sequence associated with an object accessed within the collapsed loop. The vector units and the load store units provide execution functionality typically associated with multi-dimensional loops based on the address pattern. Advantageously, collapsing multi-dimensional loops in a flexible manner dramatically reduces the overhead associated with implementing a wide range of computer vision algorithms. Consequently, the overall performance of many computer vision applications may be optimized.
-
公开(公告)号:US20230050062A1
公开(公告)日:2023-02-16
申请号:US17391395
申请日:2021-08-02
申请人: NVIDIA Corporation
发明人: Ching-Yu Hung , Ravi P. Singh , Jagadeesh Sankaran , Yen-Te Shih , Ahmad Itani
摘要: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
-
公开(公告)号:US20230048836A1
公开(公告)日:2023-02-16
申请号:US17391875
申请日:2021-08-02
申请人: NVIDIA Corporation
发明人: Ahmad Itani , Yen-Te Shih , Jagadeesh Sankaran , Ravi P Singh , Ching-Yu Hung
摘要: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
-
公开(公告)号:US20230042226A1
公开(公告)日:2023-02-09
申请号:US17391867
申请日:2021-08-02
申请人: NVIDIA Corporation
发明人: Ahmad Itani , Yen-Te Shih , Jagadeesh Sankaran , Ravi P. Singh , Ching-Yu Hung
IPC分类号: G06F13/28
摘要: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
-
公开(公告)号:US20230124604A1
公开(公告)日:2023-04-20
申请号:US18069722
申请日:2022-12-21
申请人: NVIDIA Corporation
发明人: Ching-Yu Hung , Ravi P Singh , Jagadeesh Sankaran , Yen-Te Shih , Ahmad Itani
IPC分类号: G06F3/06 , G06F12/0802
摘要: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
-
6.
公开(公告)号:US20230049442A1
公开(公告)日:2023-02-16
申请号:US17391374
申请日:2021-08-02
申请人: NVIDIA Corporation
发明人: Ching-Yu Hung , Ravi P. Singh , Jagadeesh Sankaran , Yen-Te Shih , Ahmad Itani
摘要: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
-
公开(公告)号:US20230037738A1
公开(公告)日:2023-02-09
申请号:US17391891
申请日:2021-08-02
申请人: NVIDIA Corporation
发明人: Ahmad Itani , Yen-Te Shih , Jagadeesh Sankaran , Ravi P. Singh , Ching-Yu Hung
摘要: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
-
公开(公告)号:US11573795B1
公开(公告)日:2023-02-07
申请号:US17391875
申请日:2021-08-02
申请人: NVIDIA Corporation
发明人: Ahmad Itani , Yen-Te Shih , Jagadeesh Sankaran , Ravi P Singh , Ching-Yu Hung
摘要: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
-
公开(公告)号:US20230130478A1
公开(公告)日:2023-04-27
申请号:US17798232
申请日:2020-06-22
申请人: Nvidia Corporation
发明人: Dong Zhang , Eric Viscito , Frans Sijstermans , Jagadeesh Sankaran , Ching Hung , Yen-Te Shih , Ravi Singh
IPC分类号: G06T7/593
摘要: A hybrid matching approach can be used for computer vision that balances accuracy with speed and resource consumption. Stereoscopic image data can be rectified and downsampled, then analyzed using a semi-global matching (SGM) process. The use of downsampled images greatly reduces time and bandwidth requirements, while providing high accuracy disparity results. These disparity results can be provided as external hints to a fast module that can perform a robust matching process in the time needed for applications such as real time navigation. The external hints can be used, along with potentially other hints, to define a search space for use by the fast module, which can result in higher quality disparity results obtained within specified timing constraints and with limited resources. The disparity results can be used to determine distances to various objects, as may be important for vehicle navigation or robotic task performance.
-
公开(公告)号:US11593001B1
公开(公告)日:2023-02-28
申请号:US17391861
申请日:2021-08-02
申请人: NVIDIA Corporation
发明人: Ching-Yu Hung , Ravi P Singh , Jagadeesh Sankaran , Yen-Te Shih , Ahmad Itani
IPC分类号: G06F12/00 , G06F3/06 , G06F12/0802
摘要: A VPU and associated components include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators are used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer is included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU executes a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.
-
-
-
-
-
-
-
-
-