公开(公告)号：US20190057304A1

公开(公告)日：2019-02-21

申请号：US16160800

申请日：2018-10-15

Applicant: Amrita Mathuriya ,  Sasikanth Manipatruni ,  Victor Lee ,  Huseyin Sumbul ,  Gregory Chen ,  Raghavan Kumar ,  Phil Knag ,  Ram Krishnamurthy ,  IAN YOUNG ,  Abhishek Sharma

Inventor： Amrita Mathuriya ,  Sasikanth Manipatruni ,  Victor Lee ,  Huseyin Sumbul ,  Gregory Chen ,  Raghavan Kumar ,  Phil Knag ,  Ram Krishnamurthy ,  IAN YOUNG ,  Abhishek Sharma

IPC: G06N3/063 ,  G06N3/04

Abstract: The present disclosure is directed to systems and methods of implementing an analog neural network using a pipelined SRAM architecture (“PISA”) circuitry disposed in on-chip processor memory circuitry. The on-chip processor memory circuitry may include processor last level cache (LLC) circuitry. One or more physical parameters, such as a stored charge or voltage, may be used to permit the generation of an in-memory analog output using a SRAM array. The generation of an in-memory analog output using only word-line and bit-line capabilities beneficially increases the computational density of the PISA circuit without increasing power requirements. Thus, the systems and methods described herein beneficially leverage the existing capabilities of on-chip SRAM processor memory circuitry to perform a relatively large number of analog vector/tensor calculations associated with execution of a neural network, such as a recurrent neural network, without burdening the processor circuitry and without significant impact to the processor power requirements.

公开(公告)号：US20190103156A1

公开(公告)日：2019-04-04

申请号：US16146932

申请日：2018-09-28

Applicant: Huseyin Ekin SUMBUL ,  Gregory K. CHEN ,  Raghavan KUMAR ,  Phil Ekin KNAG ,  Abhishek SHARMA ,  Sasikanth MANIPATRUNI ,  Amrita MATHURIYA ,  Ram A. KRISHNAMURTHY ,  Ian A. YOUNG

Inventor： Huseyin Ekin SUMBUL ,  Gregory K. CHEN ,  Raghavan KUMAR ,  Phil Ekin KNAG ,  Abhishek SHARMA ,  Sasikanth MANIPATRUNI ,  Amrita MATHURIYA ,  Ram A. KRISHNAMURTHY ,  Ian A. YOUNG

IPC: G11C11/419

CPC classification number: G11C11/419 ,  G11C7/1006 ,  G11C7/12 ,  G11C11/412 ,  G11C11/418 ,  G11C27/024

Abstract: A full-rail digital-read CIM circuit enables a weighted read operation on a single row of a memory array. A weighted read operation captures a value of a weight stored in the single memory array row without having to rely on weighted row-access. Rather, using full-rail access and a weighted sampling capacitance network, the CIM circuit enables the weighted read operation even under process variation, noise and mismatch.

公开(公告)号：US20180189632A1

公开(公告)日：2018-07-05

申请号：US15395758

申请日：2016-12-30

Applicant: RAGHAVAN KUMAR ,  GREGORY K. CHEN ,  HUSEYIN EKIN SUMBUL ,  RAM K. KRISHNAMURTHY ,  PHIL KNAG

Inventor： RAGHAVAN KUMAR ,  GREGORY K. CHEN ,  HUSEYIN EKIN SUMBUL ,  RAM K. KRISHNAMURTHY ,  PHIL KNAG

IPC: G06N3/04 ,  G06N3/08 ,  G06F7/58

CPC classification number: G06N3/04 ,  G06F7/582 ,  G06N3/049 ,  G06N3/063 ,  G06N3/08

Abstract: Apparatus and method for a scalable, free running neuromorphic processor. For example, one embodiment of a neuromorphic processing apparatus comprises: a plurality of neurons; an interconnection network to communicatively couple at least a subset of the plurality of neurons; a spike controller to stochastically generate a trigger signal, the trigger signal to cause a selected neuron to perform a thresholding operation to determine whether to issue a spike signal.

公开(公告)号：US20190056885A1

公开(公告)日：2019-02-21

申请号：US16160482

申请日：2018-10-15

Applicant: Amrita Mathuriya ,  Sasikanth Manipatruni ,  Victor Lee ,  Huseyin Sumbul ,  Gregory Chen ,  Raghavan Kumar ,  Phil Knag ,  Ram Krishnamurthy ,  IAN YOUNG ,  Abhishek Sharma

Inventor： Amrita Mathuriya ,  Sasikanth Manipatruni ,  Victor Lee ,  Huseyin Sumbul ,  Gregory Chen ,  Raghavan Kumar ,  Phil Knag ,  Ram Krishnamurthy ,  IAN YOUNG ,  Abhishek Sharma

IPC: G06F3/06 ,  G06F12/0802 ,  G06F12/1081 ,  G06N3/04

Abstract: The present disclosure is directed to systems and methods of implementing a neural network using in-memory, bit-serial, mathematical operations performed by a pipelined SRAM architecture (bit-serial PISA) circuitry disposed in on-chip processor memory circuitry. The on-chip processor memory circuitry may include processor last level cache (LLC) circuitry. The bit-serial PISA circuitry is coupled to PISA memory circuitry via a relatively high-bandwidth connection to beneficially facilitate the storage and retrieval of layer weights by the bit-serial PISA circuitry during execution. Direct memory access (DMA) circuitry transfers the neural network model and input data from system memory to the bit-serial PISA memory and also transfers output data from the PISA memory circuitry to system memory circuitry. Thus, the systems and methods described herein beneficially leverage the on-chip processor memory circuitry to perform a relatively large number of vector/tensor calculations without burdening the processor circuitry.

公开(公告)号：US20190042159A1

公开(公告)日：2019-02-07

申请号：US16146878

申请日：2018-09-28

Applicant: Ian YOUNG ,  Ram KRISHNAMURTHY ,  Sasikanth MANIPATRUNI ,  Amrita MATHURIYA ,  Abhishek SHARMA ,  Raghavan KUMAR ,  Phil KNAG ,  Huseyin SUMBUL ,  Gregory CHEN

Inventor： Ian YOUNG ,  Ram KRISHNAMURTHY ,  Sasikanth MANIPATRUNI ,  Amrita MATHURIYA ,  Abhishek SHARMA ,  Raghavan KUMAR ,  Phil KNAG ,  Huseyin SUMBUL ,  Gregory CHEN

IPC: G06F3/06 ,  H03K3/03 ,  G11C7/10

Abstract: Techniques and mechanisms for a memory device to perform in-memory computing based on a logic state which is detected with a voltage-controlled oscillator (VCO). In an embodiment, a VCO circuit of the memory device receives from a memory array a first signal indicating a logic state that is based on one or more currently stored data bits. The VCO provides a conversion from the logic state being indicated by a voltage characteristic of the first signal to the logic state being indicated by a corresponding frequency characteristic of a cyclical signal. Based on the frequency characteristic, the logic state is identified and communicated for use in an in-memory computation at the memory device. In another embodiment, a result of the in-memory computation is written back to the memory array.