-
公开(公告)号：US10354733B1
公开(公告)日：2019-07-16
申请号：US15786321
申请日：2017-10-17
Applicant: Xilinx, Inc.
Inventor： Jindrich Zejda , Elliott Delaye , Ashish Sirasao , Yongjun Wu , Aaron Ng
Abstract: Methods and apparatus are described for partitioning and reordering block-based matrix multiplications for high-speed data streaming in general matrix multiplication (GEMM), which may be implemented by a programmable integrated circuit (IC). By preloading and hierarchically caching the blocks, examples of the present disclosure reduce the double data rate (DDR) memory intake bandwidth for software-defined GEMM accelerators.
-
公开(公告)号：US12105716B2
公开(公告)日：2024-10-01
申请号：US15632082
申请日：2017-06-23
Applicant: Xilinx, Inc.
Inventor： Hare K. Verma , Sonal Santan , Yongjun Wu
IPC: G06F16/00 , G06F3/06 , G06F9/38 , G06F16/245 , G06F16/2453 , G06F16/2455
CPC classification number: G06F16/24557 , G06F3/064 , G06F9/3885 , G06F16/2453 , G06F16/24532 , G06F16/24569
Abstract: Embodiments herein describe techniques for preparing and executing tasks related to a database query in a database accelerator. In one embodiment, the database accelerator is separate from a host CPU. A database management system (DBMS) can offload tasks corresponding to a database query to the database accelerator. The DBMS can request data from the database relevant to the query and then convert that data into one or more data blocks that are suitable for processing by the database accelerator. In one embodiment, the database accelerator contains individual hardware processing units (PUs) that can process data in parallel or concurrently. In order to process the data concurrently, the data block includes individual PU data blocks that are each intended for a respective PU in the database accelerator.
-
公开(公告)号：US20180373760A1
公开(公告)日：2018-12-27
申请号：US15632082
申请日：2017-06-23
Applicant: Xilinx, Inc.
Inventor： Hare K. Verma , Sonal Santan , Yongjun Wu
Abstract: Embodiments herein describe techniques for preparing and executing tasks related to a database query in a database accelerator. In one embodiment, the database accelerator is separate from a host CPU. A database management system (DBMS) can offload tasks corresponding to a database query to the database accelerator. The DBMS can request data from the database relevant to the query and then convert that data into one or more data blocks that are suitable for processing by the database accelerator. In one embodiment, the database accelerator contains individual hardware processing units (PUs) that can process data in parallel or concurrently. In order to process the data concurrently, the data block includes individual PU data blocks that are each intended for a respective PU in the database accelerator.
-
公开(公告)号：US11386644B2
公开(公告)日：2022-07-12
申请号：US15786267
申请日：2017-10-17
Applicant: Xilinx, Inc.
Inventor： Elliott Delaye , Ashish Sirasao , Aaron Ng , Yongjun Wu , Jindrich Zejda
Abstract: An example preprocessor circuit includes: a first buffer configured to store rows of image data and output a row thereof; a second buffer, coupled to the first buffer, including storage locations to store respective image samples of the row output by the first buffer; shift registers; an interconnect network including connections, each connection coupling a respective one of the shift registers to more than one of the storage locations, one or more of the storage locations being coupled to more than one of the connections; and a control circuit configured to load the shift registers with the image samples based on the connections and shift the shift registers to output streams of image samples.
-
公开(公告)号：US11204747B1
公开(公告)日：2021-12-21
申请号：US15786395
申请日：2017-10-17
Applicant: Xilinx, Inc.
Inventor： Jindrich Zejda , Elliott Delaye , Yongjun Wu , Aaron Ng , Ashish Sirasao , Khang K. Dao , Christopher J. Case
Abstract: Embodiments herein describe techniques for interfacing a neural network application with a neural network accelerator that operate on two heterogeneous computing systems. For example, the neural network application may execute on a central processing unit (CPU) in a computing system while the neural network accelerator executes on a FPGA. As a result, when moving a software-hardware boundary between the two heterogeneous systems, changes may be made to both the neural network application (using software code) and to the accelerator (using RTL). The embodiments herein describe a software defined approach where shared interface code is used to express both sides of the interface between the two heterogeneous systems in a single abstraction (e.g., a software class).
-
Patent Agency Ranking
公开(公告)号：US20190114499A1
公开(公告)日：2019-04-18
申请号：US15786267
申请日：2017-10-17
Applicant: Xilinx, Inc.
Inventor： Elliott Delaye , Ashish Sirasao , Aaron Ng , Yongjun Wu , Jindrich Zejda
Abstract: An example preprocessor circuit for formatting image data into a plurality of streams of image samples includes: a first buffer configured to store a plurality of rows of the image data and output a row of the plurality of rows; a second buffer, coupled to the first buffer, including a plurality of storage locations to store a respective plurality of image samples of the row output by the first buffer; a plurality of shift registers; an interconnect network including a plurality of connections, each connection coupling a respective one of the plurality of shift registers to more than one of the plurality of storage locations, one or more of the plurality of storage locations being coupled to more than one of the plurality of connections; and a control circuit configured to load the plurality of shift registers with the plurality of image samples based on the plurality of connections and shift the plurality of shift registers to output the plurality of streams of image samples.
-
公开(公告)号：US12086572B1
公开(公告)日：2024-09-10
申请号：US15786452
申请日：2017-10-17
Applicant: Xilinx, Inc.
Inventor： Yongjun Wu , Jindrich Zejda , Elliott Delaye , Ashish Sirasao
CPC classification number: G06F8/313 , G06F8/47 , G06F12/0646 , G06N3/04 , G06N20/00
Abstract: Embodiments herein describe techniques for expressing the layers of a neural network in a software model. In one embodiment, the software model includes a class that describes the various functional blocks (e.g., convolution units, max-pooling units, rectified linear units (ReLU), and scaling functions) used to execute the neural network layers. In turn, other classes in the software model can describe the operation of each of the functional blocks. In addition, the software model can include conditional logic for expressing how the data flows between the functional blocks since different layers in the neural network can process the data differently. A compiler can convert the high-level code in the software model (e.g., C++) into a hardware description language (e.g., register transfer level (RTL)) which is used to configure a hardware system to implement a neural network accelerator.
-
公开(公告)号：US12061990B2
公开(公告)日：2024-08-13
申请号：US15786434
申请日：2017-10-17
Applicant: Xilinx, Inc.
Inventor： Yongjun Wu , Jindrich Zejda , Elliott Delaye , Ashish Sirasao
Abstract: Embodiments herein describe techniques for static scheduling a neural network implemented in a massively parallel hardware system. The neural network may be scheduled using three different scheduling levels referred to herein as an upper level, an intermediate level, and a lower level. In one embodiment, the upper level includes a hardware or software model of the layers in the neural network that establishes a sequential order of functions that operate concurrently in the hardware system. In the intermediate level, identical processes in the functions defined in the upper level are connected to form a systolic array or mesh and balanced data flow channels are used to minimize latency. In the lower level, a compiler can assign the operations performed by the processing elements in the systolic array to different portions of the hardware system to provide a static schedule for the neural network.
-
9.发明授权公开(公告)号：US11036827B1
公开(公告)日：2021-06-15
申请号：US15786346
申请日：2017-10-17
Applicant: Xilinx, Inc.
Inventor： Jindrich Zejda , Elliott Delaye , Yongjun Wu , Aaron Ng , Ashish Sirasao , Khang K. Dao
Abstract: Methods and apparatus are described for simultaneously buffering and reformatting (e.g., transposing) a matrix for high-speed data streaming in general matrix multiplication (GEMM), which may be implemented by a programmable integrated circuit (IC). Examples of the present disclosure increase the effective double data rate (DDR) memory throughput for streaming data into GEMM digital signal processing (DSP) engine multifold, as well as eliminate slow data reformatting on a host central processing unit (CPU). This may be accomplished through software-defined (e.g., C++) data structures and access patterns that result in hardware logic that simultaneously buffers and reorganizes the data to achieve linear DDR addressing.
-
公开(公告)号：US20190114529A1
公开(公告)日：2019-04-18
申请号：US15785800
申请日：2017-10-17
Applicant: Xilinx, Inc.
Inventor： Aaron Ng , Elliott Delaye , Ehsan Ghasemi , Xiao Teng , Jindrich Zejda , Yongjun Wu , Sean Settle , Ashish Sirasao
IPC: G06N3/04
Abstract: In the disclosed methods and systems for processing in a neural network system, a host computer system writes a plurality of weight matrices associated with a plurality of layers of a neural network to a memory shared with a neural network accelerator. The host computer system further assembles a plurality of per-layer instructions into an instruction package. Each per-layer instruction specifies processing of a respective layer of the plurality of layers of the neural network, and respective offsets of weight matrices in a shared memory. The host computer system writes input data and the instruction package to the shared memory. The neural network accelerator reads the instruction package from the shared memory and processes the plurality of per-layer instructions of the instruction package.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.021 seconds)
