Patents by Inventor Alessio ANTOLINI

Alessio ANTOLINI 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).

  • Patent number: 11942144
    Abstract: A circuit includes a memory array with memory cells arranged in a matrix of rows and columns, where each row includes a word line connected to the memory cells of the row, and each column includes a bit line connected to the memory cells of the column. Computational weights for an in-memory compute operation (IMCO) are stored in the memory cells. A word line control circuit simultaneously actuates word lines in response to input signals providing coefficient data for the IMCO by applying word line signal pulses. A column processing circuit connected to the bit lines processes analog signals developed on the bit lines in response to the simultaneous actuation of the word lines to generate multiply and accumulate output signals for the IMCO. Pulse widths of the signal pulses are modulated to compensate for cell drift. The IMCO further handles positive/negative calculation for the coefficient data and computational weights.
    Type: Grant
    Filed: January 24, 2022
    Date of Patent: March 26, 2024
    Assignees: STMicroelectronics S.r.l., Alma Mater Studiorum—Universita' Di Bologna
    Inventors: Marco Pasotti, Marcella Carissimi, Antonio Gnudi, Eleonora Franchi Scarselli, Alessio Antolini, Andrea Lico
  • Patent number: 11894052
    Abstract: An in-memory computation (IMC) circuit includes a memory array formed by memory cells arranged in row-by-column matrix. Computational weights for an IMC operation are stored in the memory cells. Each column includes a bit line connected to the memory cells. A biasing circuit is connected between each bit line and a corresponding column output. A column combining circuit combines and integrates analog signals at the column outputs of the biasing circuits. Each biasing circuit operates to apply a fixed reference voltage level to its bit line. Each biasing circuit further includes a switching circuit that is controlled to turn on for a time duration controlled by asps comparison of a coefficient data signal to a ramp signal to generate the analog signal dependent on the computational weight. The ramp signal is generated using a reference current derived from a reference memory cell.
    Type: Grant
    Filed: April 12, 2022
    Date of Patent: February 6, 2024
    Assignees: STMicroelectronics S.r.l., Alma Mater Studiorum—Universita' Di Bologna
    Inventors: Marco Pasotti, Marcella Carissimi, Alessio Antolini, Eleonora Franchi Scarselli, Antonio Gnudi, Andrea Lico, Paolo Romele
  • Publication number: 20230326524
    Abstract: An in-memory computation (IMC) circuit includes a memory array formed by memory cells arranged in row-by-column matrix. Computational weights for an IMC operation are stored in the memory cells. Each column includes a bit line connected to the memory cells. A biasing circuit is connected between each bit line and a corresponding column output. A column combining circuit combines and integrates analog signals at the column outputs of the biasing circuits. Each biasing circuit operates to apply a fixed reference voltage level to its bit line. Each biasing circuit further includes a switching circuit that is controlled to turn on for a time duration controlled by asps comparison of a coefficient data signal to a ramp signal to generate the analog signal dependent on the computational weight. The ramp signal is generated using a reference current derived from a reference memory cell.
    Type: Application
    Filed: April 12, 2022
    Publication date: October 12, 2023
    Applicants: STMicroelectronics S.r.l., Alma Mater Studiorum - Universita' Di Bologna
    Inventors: Marco PASOTTI, Marcella CARISSIMI, Alessio ANTOLINI, Eleonora FRANCHI SCARSELLI, Antonio GNUDI, Andrea LICO, Paolo ROMELE
  • Publication number: 20230326499
    Abstract: An in-memory computation (IMC) circuit includes a memory array formed by memory cells arranged in row-by-column matrix. Computational weights for an IMC operation are stored in the memory cells. Each column includes a bit line connected to the memory cells. A switching circuit is connected between each bit line and a corresponding column output. The switching circuit is controlled to turn on to generate the analog signal dependent on the computational weight and for a time duration controlled by the coefficient data signal. A column combining circuit combines (by addition and/or subtraction) and integrates analog signals at the column outputs of the biasing circuits. The addition/subtraction is dependent on one or more a sign of the coefficient data and a sign of the computational weight and may further implement a binary weighting function.
    Type: Application
    Filed: April 12, 2022
    Publication date: October 12, 2023
    Applicants: STMicroelectronics S.r.l., Alma Mater Studiorum - Universita' Di Bologna
    Inventors: Marco PASOTTI, Marcella CARISSIMI, Alessio ANTOLINI, Eleonora FRANCHI SCARSELLI, Antonio GNUDI, Andrea LICO
  • Publication number: 20230238055
    Abstract: A circuit includes a memory array with memory cells arranged in a matrix of rows and columns, where each row includes a word line connected to the memory cells of the row, and each column includes a bit line connected to the memory cells of the column. Computational weights for an in-memory compute operation (IMCO) are stored in the memory cells. A word line control circuit simultaneously actuates word lines in response to input signals providing coefficient data for the IMCO by applying word line signal pulses. A column processing circuit connected to the bit lines processes analog signals developed on the bit lines in response to the simultaneous actuation of the word lines to generate multiply and accumulate output signals for the IMCO. Pulse widths of the signal pulses are modulated to compensate for cell drift. The IMCO further handles positive/negative calculation for the coefficient data and computational weights.
    Type: Application
    Filed: January 24, 2022
    Publication date: July 27, 2023
    Applicants: STMicroelectronics S.r.l., Alma Mater Studiorum - Universita' Di Bologna
    Inventors: Marco PASOTTI, Marcella CARISSIMI, Antonio GNUDI, Eleonora FRANCHI SCARSELLI, Alessio ANTOLINI, Andrea LICO