Patents by Inventor Yi-Jung Su
Yi-Jung Su 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).
-
Publication number: 20240154015Abstract: A method includes forming a first fin and a second fin protruding from a frontside of a substrate, forming a gate stack over the first and second fins, forming a dielectric feature dividing the gate stack into a first segment engaging the first fin and a second segment engaging the second fin, and growing a first epitaxial feature on the first fin and a second epitaxial feature on the second fin. The dielectric feature is disposed between the first and second epitaxial features. The method also includes performing an etching process on a backside of the substrate to form a backside trench, and forming a backside via in the backside trench. The backside trench exposes the dielectric feature and the first and second epitaxial features. The backside via straddles the dielectric feature and is in electrical connection with the first and second epitaxial features.Type: ApplicationFiled: March 22, 2023Publication date: May 9, 2024Inventors: Jui-Lin CHEN, Hsin-Wen SU, Chih-Ching WANG, Chen-Ming LEE, Chung-I YANG, Yi-Feng TING, Jon-Hsu HO, Lien-Jung HUNG, Ping-Wei WANG
-
Patent number: 11663446Abstract: The present disclosure relates to a device for executing a convolutional neural network operation. The device comprises a first memory, a processing array comprising a plurality of processing strings, and a controller. The controller can be configured to fetch one or more batches of data into the first memory, regroup the one or more batches of data into multiple work items, wherein a first work item partially overlaps one or more work items among the multiple work items, and broadcast the multiple work items to the processing array, wherein the first work item is transferred to two or more processing strings of the processing array.Type: GrantFiled: January 6, 2020Date of Patent: May 30, 2023Assignee: Alibaba Group Holding LimitedInventors: Yang Jiao, Long Chen, Yi Jung Su
-
Publication number: 20210209442Abstract: The present disclosure relates to a device for executing a convolutional neural network operation. The device comprises a first memory, a processing array comprising a plurality of processing strings, and a controller. The controller can be configured to fetch one or more batches of data into the first memory, regroup the one or more batches of data into multiple work items, wherein a first work item partially overlaps one or more work items among the multiple work items, and broadcast the multiple work items to the processing array, wherein the first work item is transferred to two or more processing strings of the processing array.Type: ApplicationFiled: January 6, 2020Publication date: July 8, 2021Inventors: Yang JIAO, Long CHEN, Yi Jung SU
-
Patent number: 8681162Abstract: A programmable graphics processing unit (GPU) includes a first shader stage configured to receive slice data from a frame buffer and perform variable length decoding (VLD), wherein the first shader stage outputs data to a first buffer within the frame buffer; a second shader stage configured to receive the output data from the first shader stage and perform transformation and motion compensation on the slice data, wherein the second shader stage outputs decoded slice data to a second buffer within the frame buffer; a third shader stage configured to receive the decoded slice data and perform in-loop deblocking filtering (IDF) on the frame buffer; a fourth shader stage configured to perform post-processing on the frame buffer; and a scheduler configured to schedule execution of the shader stages, the scheduler comprising a plurality of counter registers; wherein execution of the shader stages is synchronized utilizing the counter registers.Type: GrantFiled: October 15, 2010Date of Patent: March 25, 2014Assignee: VIA Technologies, Inc.Inventors: Timour Paltashev, John Brothers, Yi-Jung Su, Yang (Jeff) Jiao
-
Publication number: 20120092353Abstract: A multi-shader system in a programmable graphics processing unit (GPU) for processing video data, includes a first shader stage configured to receive slice data from a frame buffer and perform variable length decoding (VLD), wherein the first shader stage outputs data to a first buffer within the frame buffer; a second shader stage configured to receive the output data from the first shader stage and perform transformation and motion compensation on the slice data, wherein the second shader stage outputs decoded slice data to a second buffer within the frame buffer; a third shader stage configured to receive the decoded slice data and perform in-loop deblocking filtering (IDF) on the frame buffer; a fourth shader stage configured to perform post-processing on the frame buffer; and a scheduler configured to schedule execution of the shader stages, the scheduler comprising a plurality of counter registers; wherein execution of the shader stages is synchronized utilizing the counter registers.Type: ApplicationFiled: October 15, 2010Publication date: April 19, 2012Applicant: VIA TECHNOLOGIES, INC.Inventors: Timour Paltashev, John Brothers, Yi-Jung Su, Yang (Jeff) Jiao
-
Patent number: 7414900Abstract: Methods and systems consistent with this invention comprise a control circuit for reading data from a memory comprising a plurality of data channels. Such control circuits comprise at least one multiplexer, wherein the at least one multiplexer is configured to route a data strobe signal to a first number of the plurality of data channels for reading the data from the memory when the at least one multiplexer is in a first selected state, and wherein the at least one multiplexer is configured to route the data strobe signal to a second number of the plurality of data channels, wherein the second number is greater than the first number, for reading the data from the memory when the at least one multiplexer is in a second selected state. Such methods and systems may also comprise a clock for generating a data strobe signal, and a flip-flop for latching the data from the memory into the control circuit with the data strobe signal, wherein the data strobe signal does not leave the control circuit.Type: GrantFiled: May 2, 2007Date of Patent: August 19, 2008Assignee: Via Technologies, Inc.Inventors: Chen-Kuan Eric Hong, Yi-Jung Su
-
Patent number: 7304897Abstract: Methods and systems consistent with this invention comprise a control circuit for reading data from a memory comprising a plurality of data channels. Such control circuits comprise at least one multiplexer, wherein the at least one multiplexer is configured to route a data strobe signal to a first number of the plurality of data channels for reading the data from the memory when the at least one multiplexer is in a first selected state, and wherein the at least one multiplexer is configured to route the data strobe signal to a second number of the plurality of data channels, wherein the second number is greater than the first number, for reading the data from the memory when the at least one multiplexer is in a second selected state. Such methods and systems may also comprise a clock for generating a data strobe signal, and a flip-flop for latching the data from the memory into the control circuit with the data strobe signal, wherein the data strobe signal does not leave the control circuit.Type: GrantFiled: April 2, 2003Date of Patent: December 4, 2007Assignee: VIA Technologies, Inc.Inventors: Chen-Kuan Eric Hong, Yi-Jung Su
-
Publication number: 20070237010Abstract: Methods and systems consistent with this invention comprise a control circuit for reading data from a memory comprising a plurality of data channels. Such control circuits comprise at least one multiplexer, wherein the at least one multiplexer is configured to route a data strobe signal to a first number of the plurality of data channels for reading the data from the memory when the at least one multiplexer is in a first selected state, and wherein the at least one multiplexer is configured to route the data strobe signal to a second number of the plurality of data channels, wherein the second number is greater than the first number, for reading the data from the memory when the at least one multiplexer is in a second selected state. Such methods and systems may also comprise a clock for generating a data strobe signal, and a flip-flop for latching the data from the memory into the control circuit with the data strobe signal, wherein the data strobe signal does not leave the control circuit.Type: ApplicationFiled: May 2, 2007Publication date: October 11, 2007Inventors: Chen-Kuan Hong, Yi-Jung Su
-
Publication number: 20030221050Abstract: Methods and systems consistent with this invention comprise a control circuit for reading data from a memory comprising a plurality of data channels. Such control circuits comprise at least one multiplexer, wherein the at least one multiplexer is configured to route a data strobe signal to a first number of the plurality of data channels for reading the data from the memory when the at least one multiplexer is in a first selected state, and wherein the at least one multiplexer is configured to route the data strobe signal to a second number of the plurality of data channels, wherein the second number is greater than the first number, for reading the data from the memory when the at least one multiplexer is in a second selected state. Such methods and systems may also comprise a clock for generating a data strobe signal, and a flip-flop for latching the data from the memory into the control circuit with the data strobe signal, wherein the data strobe signal does not leave the control circuit.Type: ApplicationFiled: April 2, 2003Publication date: November 27, 2003Applicant: Via Technologies, Inc.Inventors: Chen-Kuan Eric Hong, Yi-Jung Su