-
1.
公开(公告)号:US20240362471A1
公开(公告)日:2024-10-31
申请号:US18764864
申请日:2024-07-05
发明人: Sehwan LEE , Namjoon KIM , Joonho SONG , Junwoo JANG
摘要: Provided are a method and apparatus for processing a convolution operation in a neural network, the method includes determining a precision of feature map operands and a precision of weight operands, respectively, on which the convolution operation is to be performed in parallel, decomposing a multiplier included in a convolution operator into sub-multipliers based on the precision of the feature map operands and the precision of the weight operands, performing the convolution operation between the feature map operands and the weight operands by using the decomposed sub-multipliers, each operand being processed in a sub-multiplier corresponding to a precision of the operand, and obtaining output feature maps corresponding to results of the convolution operation.
-
公开(公告)号:US20240362389A1
公开(公告)日:2024-10-31
申请号:US18650648
申请日:2024-04-30
发明人: Tijmen Spreij
IPC分类号: G06F30/392 , G06T1/20 , G06T1/60 , G06T15/04
CPC分类号: G06F30/392 , G06T1/20 , G06T1/60 , G06T15/04
摘要: A circuit for mapping N coordinates to a 1D space receives N input bit-strings representing respective coordinates, which can be of different sizes; produces a grouped bit-string therefrom, in which the bits, including non-data bits, are grouped into groups of bits originating from the same bit position per group; and demultiplexes this into n=1 . . . N demultiplexed bit-strings, and sends each to a respective n-coordinate channel. The nth demultiplexed bit-string includes a respective part of the grouped bit-string that has n coordinate data bits and N-n non-data bits per group, and all other groups filled with null bits. Each but the N-coordinate channel includes bit-packing circuitry which packs down the respective demultiplexed bit-string by removing the non-data bits, and removing the same number of bits per group from the null bit.
-
公开(公告)号:US20240354894A1
公开(公告)日:2024-10-24
申请号:US18437298
申请日:2024-02-09
摘要: A filter system can effectively filter images with low computation cost by, instead of using large 2D filters, applying a series of smaller filters that require less compute and memory. In some implementations, the larger filter function, ƒ, is replaced by ƒ1, ƒ2, . . . , ƒN where ƒ(x)≈ƒ1(x)+ƒ2(x)+ . . . +ƒN(x). The filter system can apply these filters sequentially across multiple frames in time. The time integration of information by the human visual system results in the perception of a single higher quality filtering result, while using only the compute and memory footprint necessary to implement the filters. The number of frames across which a filter can be split without introducing flicker artifacts is dependent on the refresh rate of the display.
-
公开(公告)号:US20240354887A1
公开(公告)日:2024-10-24
申请号:US18637735
申请日:2024-04-17
申请人: MEDIATEK INC.
发明人: Yu-Hua WU , Yong-Guan LIAO , Kuan-Yu CHEN
IPC分类号: G06T1/20
CPC分类号: G06T1/20
摘要: A graphics system is provided. The graphics system includes a frame buffer, a timing controller, and a processing unit. The processing unit generating an output video frame based on a raw video frame. The output video frame includes the main window and a picture-in-picture window overlaid on the main window, and the picture-in-picture window is generated by zooming in a target region of the main window. The timing controller is configured to generates a first vertical synchronization signals to control the input timing for the processing unit to write the raw video frame into the frame buffer, and generate a second vertical synchronization signal to control an output timing for the processing unit to read the raw video frame from the frame buffer and generating the output video frame, such that specific timing conditions are met.
-
公开(公告)号:US12125134B2
公开(公告)日:2024-10-22
申请号:US18130448
申请日:2023-04-04
申请人: Stratasys Ltd.
IPC分类号: G06T15/08 , B29C64/386 , B29C64/393 , B33Y50/02 , G03G15/22 , G06F30/00 , G06T1/20 , G06T15/00 , G06T15/50
CPC分类号: G06T15/08 , B29C64/393 , B33Y50/02 , G06F30/00 , G06T1/20 , G06T15/005 , G06T15/503 , B29C64/386 , G03G15/224
摘要: A system for generating slice data for additive manufacturing, comprises a graphics processing unit (GPU) that receives a digital model of an object in a three-dimensional build space defined over a plurality of slices, computes a three-dimensional signed distance field over voxels in the build space, assigns a building material to each voxel based on a respective distance field value, and generates slice data output pertaining to the building material assignments for each slice. The slice data output can be used for printing the object in layers corresponding to the slices. The distance field comprises one or more vector having a vertical component with respect to the slices.
-
公开(公告)号:US12125122B2
公开(公告)日:2024-10-22
申请号:US17556161
申请日:2021-12-20
发明人: Mihir Narendra Mody , Niraj Nandan , Ankur Ankur , Mayank Mangla , Prithvi Shankar Yeyyadi Anantha
CPC分类号: G06T1/20 , G06F9/4812 , G06F11/1004 , G06T1/60
摘要: A technique including receiving an image stream for processing; processing the received image stream in a real time mode of operation; outputting an indication that an image processing pipeline has begun processing the received image stream; receiving, in response to the indication, first configuration information associated with test data for testing the image processing pipeline; switching the image processing pipeline to a non-real time mode of operation to process the test data based on the first configuration information during a vertical blanking period of the received image stream; loading the test data from an external memory; switching an input of the image processing pipeline from the image stream to the test data; determining a checksum based on the processed test data; comparing the determined checksum to an expected checksum to determine that the test data was successfully processed; and outputting an indication that the test data was successfully processed.
-
公开(公告)号:US12124852B2
公开(公告)日:2024-10-22
申请号:US18347964
申请日:2023-07-06
申请人: Intel Corporation
CPC分类号: G06F9/3802 , G06F13/28 , G06T1/20
摘要: A graphics processing device is provided that includes a set of compute units to execute a workload, a cache coupled with the set of compute units, and circuitry coupled with the cache and the set of compute units. The circuitry is configured to, in response to a cache miss for the read from a first cache, broadcast an event within the graphics processor device to identify data associated with the cache miss, receive the event at a second compute unit in the set of compute units, and prefetch the data identified by the event into a second cache that is local to the second compute unit before an attempt to read the instruction or data by the second thread.
-
公开(公告)号:US20240345888A1
公开(公告)日:2024-10-17
申请号:US18621392
申请日:2024-03-29
发明人: Ian King
CPC分类号: G06F9/5038 , G06T1/20
摘要: A method of managing task dependencies within a task queue of a GPU determines a class ID and a resource ID for a task and also for any parent task of the task and outputting the class IDs and resource IDs for both the task itself and any parent task of the task for storage associated with the task in a task queue. The class ID identifies a class of the task from a hierarchy of task classes and the resource ID of the task identifies resources allocated and/or written to by the task.
-
公开(公告)号:US12118642B2
公开(公告)日:2024-10-15
申请号:US17516479
申请日:2021-11-01
摘要: This application provides a graphics rendering method and apparatus. A service starts an application and obtains a rendering instruction sent by the application; and sends the rendering instruction to an electronic device. The electronic device performs graphics rendering according to the rendering instruction, to display an image related to the application. According to the technical solutions provided in this application, the electronic device, instead of the server, can perform graphics rendering according to the rendering instruction, thereby improving picture quality and user experience.
-
公开(公告)号:US12113946B2
公开(公告)日:2024-10-08
申请号:US17897521
申请日:2022-08-29
IPC分类号: H04N1/21 , G06F9/445 , G06T1/20 , G06T1/60 , H04N101/00
CPC分类号: H04N1/2141 , G06F9/44526 , G06T1/20 , G06T1/60 , H04N2101/00 , H04N2201/0084 , H04N2201/0087
摘要: A computer vision processing device is provided which comprises memory configured to store data and a processor. The processor is configured to store captured image data in a first buffer and acquire access to the captured image data in the first buffer when the captured image data is available for processing. The processor is also configured to execute a first group of operations in a processing pipeline, each of which processes the captured image data accessed from the first buffer and return the first buffer for storing next captured image data when a last operation of the first group of operations executes.
-
-
-
-
-
-
-
-
-