公开(公告)号：US20230084985A1

公开(公告)日：2023-03-16

申请号：US18056937

申请日：2022-11-18

Applicant: STMICROELECTRONICS S.r.l. ,  STMicroelectronics International N.V.

Inventor： Thomas BOESCH ,  Giuseppe DESOLI ,  Surinder Pal SINGH ,  Carmine CAPPETTA

IPC: G06N3/063 ,  G06F9/50 ,  H03M7/30

Abstract: Techniques and systems are provided for implementing a convolutional neural network. One or more convolution accelerators are provided that each include a feature line buffer memory, a kernel buffer memory, and a plurality of multiply-accumulate (MAC) circuits arranged to multiply and accumulate data. In a first operational mode the convolutional accelerator stores feature data in the feature line buffer memory and stores kernel data in the kernel data buffer memory. In a second mode of operation, the convolutional accelerator stores kernel decompression tables in the feature line buffer memory.

公开(公告)号：US20230062910A1

公开(公告)日：2023-03-02

申请号：US17461626

申请日：2021-08-30

Applicant: STMicroelectronics S.r.l. ,  STMicroelectronics International N.V.

Inventor： Giuseppe DESOLI ,  Surinder Pal SINGH ,  Thomas BOESCH

IPC: G06N3/063 ,  G06N3/04 ,  G06F9/50

Abstract: A convolutional neural network includes convolution circuitry. The convolution circuitry performs convolution operations on input tensor values. The convolutional neural network includes requantization circuitry that requantizes convolution values output from the convolution circuitry.

公开(公告)号：US20220101086A1

公开(公告)日：2022-03-31

申请号：US17039653

申请日：2020-09-30

Applicant: STMICROELECTRONICS S.r.l. ,  STMicroelectronics International N.V.

Inventor： Carmine CAPPETTA ,  Thomas BOESCH ,  Giuseppe DESOLI

IPC: G06N3/04 ,  G06N3/063 ,  G06F9/38 ,  G06T7/11

Abstract: A convolutional accelerator framework (CAF) has a plurality of processing circuits including one or more convolution accelerators, a reconfigurable hardware buffer configurable to store data of a variable number of input data channels, and a stream switch coupled to the plurality of processing circuits. The reconfigurable hardware buffer has a memory and control circuitry. A number of the variable number of input data channels is associated with an execution epoch. The stream switch streams data of the variable number of input data channels between processing circuits of the plurality of processing circuits and the reconfigurable hardware buffer during processing of the execution epoch. The control circuitry of the reconfigurable hardware buffer configures the memory to store data of the variable number of input data channels, the configuring including allocating a portion of the memory to each of the variable number of input data channels.

公开(公告)号：US20210397933A1

公开(公告)日：2021-12-23

申请号：US16909673

申请日：2020-06-23

Applicant: STMICROELECTRONICS S.r.l. ,  STMicroelectronics International N.V.

Inventor： Thomas BOESCH ,  Giuseppe DESOLI ,  Surinder Pal SINGH ,  Carmine CAPPETTA

IPC: G06N3/063 ,  G06F9/50 ,  H03M7/30

Abstract: Techniques and systems are provided for implementing a convolutional neural network. One or more convolution accelerators are provided that each include a feature line buffer memory, a kernel buffer memory, and a plurality of multiply-accumulate (MAC) circuits arranged to multiply and accumulate data. In a first operational mode the convolutional accelerator stores feature data in the feature line buffer memory and stores kernel data in the kernel data buffer memory. In a second mode of operation, the convolutional accelerator stores kernel decompression tables in the feature line buffer memory.

公开(公告)号：US20210256346A1

公开(公告)日：2021-08-19

申请号：US16794062

申请日：2020-02-18

Applicant: STMICROELECTRONICS S.R.L. ,  STMICROELECTRONICS INTERNATIONAL N.V.

Inventor： Giuseppe DESOLI ,  Carmine CAPPETTA ,  Thomas BOESCH ,  Surinder Pal SINGH ,  Saumya SUNEJA

IPC: G06N3/04 ,  G06N3/063 ,  G06F16/22 ,  G06N3/08 ,  G06K9/62

Abstract: Embodiments of an electronic device include an integrated circuit, a reconfigurable stream switch formed in the integrated circuit along with a plurality of convolution accelerators and a decompression unit coupled to the reconfigurable stream switch. The decompression unit decompresses encoded kernel data in real time during operation of convolutional neural network.

公开(公告)号：US20210192833A1

公开(公告)日：2021-06-24

申请号：US17194055

申请日：2021-03-05

Applicant: STMICROELECTRONICS S.R.L. ,  STMICROELECTRONICS INTERNATIONAL N.V.

Inventor： Surinder Pal SINGH ,  Thomas BOESCH ,  Giuseppe DESOLI

IPC: G06T15/08 ,  G06T7/62 ,  G06T7/11 ,  G06F16/901 ,  G06F9/38 ,  G06K9/00 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06N3/063

Abstract: A device include on-board memory, an applications processor, a digital signal processor (DSP) cluster, a configurable accelerator framework (CAF), and at least one communication bus architecture. The communication bus communicatively couples the applications processor, the DSP cluster, and the CAF to the on-board memory. The CAF includes a reconfigurable stream switch and data volume sculpting circuitry, which has an input and an output coupled to the reconfigurable stream switch. The data volume sculpting circuitry receives a series of frames, each frame formed as a two dimensional (2D) data structure, and determines a first dimension and a second dimension of each frame of the series of frames. Based on the first and second dimensions, the data volume sculpting circuitry determines for each frame a position and a size of a region-of-interest to be extracted from the respective frame, and extracts from each frame, data in the frame that is within the region-of-interest.

公开(公告)号：US20210072894A1

公开(公告)日：2021-03-11

申请号：US17012501

申请日：2020-09-04

Applicant: STMICROELECTRONICS S.r.l. ,  STMicroelectronics International N.V.

Inventor： Nitin CHAWLA ,  Giuseppe DESOLI ,  Anuj GROVER ,  Thomas BOESCH ,  Surinder Pal SINGH ,  Manuj AYODHYAWASI

IPC: G06F3/06 ,  G06N3/08

Abstract: A memory array arranged as a plurality of memory cells. The memory cells are configured to operate at a determined voltage. A memory management circuitry coupled to the plurality of memory cells tags a first set of the plurality of memory cells as low-voltage cells and tags a second set of the plurality of memory cells as high-voltage cells. A power source provides a low voltage to the first set of memory cells and provides a high voltage to the second set of memory cells based on the tags.

公开(公告)号：US20200310761A1

公开(公告)日：2020-10-01

申请号：US16833340

申请日：2020-03-27

Applicant: STMICROELECTRONICS S.R.L. ,  STMicroelectronics International N.V.

Inventor： Michele ROSSI ,  Giuseppe DESOLI ,  Thomas BOESCH ,  Carmine CAPPETTA

IPC: G06F7/72 ,  H03M7/18

Abstract: A system includes an addressable memory array, one or more processing cores, and an accelerator framework coupled to the addressable memory. The accelerator framework includes a Multiply ACcumulate (MAC) hardware accelerator cluster. The MAC hardware accelerator cluster has a binary-to-residual converter, which, in operation, converts binary inputs to a residual number system. Converting a binary input to the residual number system includes a reduction modulo 2m and a reduction modulo 2m−1, where m is a positive integer. A plurality of MAC hardware accelerators perform modulo 2m multiply-and-accumulate operations and modulo 2m−1 multiply-and-accumulate operations using the converted binary input. A residual-to-binary converter generates a binary output based on the output of the MAC hardware accelerators.

公开(公告)号：US20190266479A1

公开(公告)日：2019-08-29

申请号：US16280991

申请日：2019-02-20

Applicant: STMICROELECTRONICS S.R.L. ,  STMICROELECTRONICS INTERNATIONAL N.V.

Inventor： Surinder Pal SINGH ,  Thomas BOESCH ,  Giuseppe DESOLI

IPC: G06N3/063 ,  G06F17/17 ,  G06N20/00 ,  G06F1/26 ,  G06F17/16

Abstract: Embodiments of a device include an integrated circuit, a reconfigurable stream switch formed in the integrated circuit along with a plurality of convolution accelerators and an arithmetic unit coupled to the reconfigurable stream switch. The arithmetic unit has at least one input and at least one output. The at least one input is arranged to receive streaming data passed through the reconfigurable stream switch, and the at least one output is arranged to stream resultant data through the reconfigurable stream switch. The arithmetic unit also has a plurality of data paths. At least one of the plurality of data paths is solely dedicated to performance of operations that accelerate an activation function represented in the form of a piece-wise second order polynomial approximation.

公开(公告)号：US20180189641A1

公开(公告)日：2018-07-05

申请号：US15423279

申请日：2017-02-02

Applicant: STMICROELECTRONICS S.R.L. ,  STMICROELECTRONICS INTERNATIONAL N.V.

Inventor： Thomas BOESCH ,  Giuseppe DESOLI

IPC: G06N3/063 ,  G06N3/04

Abstract: Embodiments are directed towards a hardware accelerator engine that supports efficient mapping of convolutional stages of deep neural network algorithms. The hardware accelerator engine includes a plurality of convolution accelerators, and each one of the plurality of convolution accelerators includes a kernel buffer, a feature line buffer, and a plurality of multiply-accumulate (MAC) units. The MAC units are arranged to multiply and accumulate data received from both the kernel buffer and the feature line buffer. The hardware accelerator engine also includes at least one input bus coupled to an output bus port of a stream switch, at least one output bus coupled to an input bus port of the stream switch, or at least one input bus and at least one output bus hard wired to respective output bus and input bus ports of the stream switch.