Digital sinusoid generator
    232.
    发明授权

    公开(公告)号:US11092993B2

    公开(公告)日:2021-08-17

    申请号:US16437705

    申请日:2019-06-11

    Abstract: A recursive digital sinusoid generator generates recursive values used in the production of a digital sinusoid output. The recursive values are generated at a first frequency. A sinusoid value generator generates replacement values at a second frequency, wherein the second frequency is less than the first frequency. The generated recursive values are periodically replaced with the generated replacement values without interrupting production of the digital sinusoid output at the first frequency. This periodic replacement effectively corrects for a finite precision error which accumulates in the recursive values over time.

    Charge pump regulation circuit to increase program and erase efficiency in nonvolatile memory

    公开(公告)号:US11070128B2

    公开(公告)日:2021-07-20

    申请号:US16715209

    申请日:2019-12-16

    Abstract: A charge pump circuit generates a charge pump output signal at a first node and is enabled by a charge pump control signal. A diode has first and second terminals coupled to first and second nodes. A comparator has an inverting input coupled to the second node and a non-inverting input coupled to a third node, and causes generation of the charge pump control signal. A first current mirror produces a first current at the second node, and a second current mirror produces a second current (equal in magnitude to the first current) at the third node. The first terminal and second terminals may be a cathode and an anode. The first current mirror may be a current sink sinking a first current from the second node. The second current mirror may be current source sourcing a second current (equal in magnitude to the first current) to the third node.

    Processing system, related integrated circuit, device and method

    公开(公告)号:US11048525B2

    公开(公告)日:2021-06-29

    申请号:US16273704

    申请日:2019-02-12

    Abstract: A processing system includes a plurality of configuration data clients, each associated with a respective address and including a respective register, and where a respective configuration data client is configured to receive a respective first configuration data and to store the respective first configuration data in the respective register; a hardware block coupled to at least one of the configuration data clients and configured to change operation as a function of the respective first configuration data stored in the respective registers; a non-volatile memory including second configuration data, where the second configuration data are stored as data packets including the respective first configuration data and an attribute field identifying the respective address of one of the configuration data clients; and a hardware configuration circuit configured to sequentially read the data packets from the non-volatile memory and to transmit the respective first configuration data to the respective configuration data client.

    HIERARCHICAL RANDOM SCRAMBLING OF SECURE DATA STORAGE RESULTING IN RANDOMNESS ACROSS CHIPS AND ON POWER ON RESETS OF INDIVIDUAL CHIPS

    公开(公告)号:US20210192070A1

    公开(公告)日:2021-06-24

    申请号:US16726498

    申请日:2019-12-24

    Abstract: A system includes a random number generator generating a random number in response to an event. Control logic generates hierarchical part alignment selectors from the random number. For each secure data block to be stored in volatile storage, a physical address of a first logical address for that secure data block is set based upon the hierarchical part alignment selectors. For each data word within that secure data block, a physical address of a first logical address for that data word is set based upon the hierarchical part alignment selectors. For each data byte within that data word, a physical address of a first logical address for that data byte is set based upon the hierarchical part alignment selectors. A physical address of a logical address for a first data bit within that data byte is set based upon the hierarchical part alignment selectors.

    Combinatorial serial and parallel test access port selection in a JTAG interface

    公开(公告)号:US11041905B2

    公开(公告)日:2021-06-22

    申请号:US16671933

    申请日:2019-11-01

    Abstract: A circuit includes a test data input (TDI) pin receiving a test data input signal, a test data out (TDO) pin outputting a test data output signal, and debugging test access port (TAP) having a test data input coupled to the TDI pin and a bypass register having an input coupled to the test data input of the debugging TAP. A multiplexer has inputs coupled to the TDI pin and the debugging TAP. A testing TAP has a test data input coupled to the output of the multiplexer, and a data register having an input coupled to the test data input of the testing TAP. The multiplexer switches so the test data input signal is selectively coupled to the input of the data register of the testing TAP so the output of the debugging TAP is selectively coupled to the input of the data register of the testing TAP.

    Circuit for detection of single bit upsets in generation of internal clock for memory

    公开(公告)号:US11025252B2

    公开(公告)日:2021-06-01

    申请号:US16578487

    申请日:2019-09-23

    Abstract: A failure determination circuit includes a latch circuit that receives an internal clock from a clock latch that rises in response to an external clock rising. In response to a rising edge of the external clock, the circuit generates a rising edge of a fault flag. In response to a rising edge of the internal clock if it occurs, the fault flag falls. The fault flag is then latched. The latched fault flag indicates a single bit upset in the clock latch if the falling edge of the fault flag was not generated prior to latching, if the clock latch is in an active mode, and indicates a single bit upset in the clock latch if the falling edge of the fault flag was generated prior to latching, if the clock latch is in an inactive mode.

    Data volume sculptor for deep learning acceleration

    公开(公告)号:US10977854B2

    公开(公告)日:2021-04-13

    申请号:US16280963

    申请日:2019-02-20

    Abstract: Embodiments of 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 a data volume sculpting unit, which has an input and an output coupled to the reconfigurable stream switch. The data volume sculpting unit has a counter, a comparator, and a controller. The data volume sculpting unit is arranged to receive a stream of feature map data that forms a three-dimensional (3D) feature map. The 3D feature map is formed as a plurality of two-dimensional (2D) data planes. The data volume sculpting unit is also arranged to identify a 3D volume within the 3D feature map that is dimensionally smaller than the 3D feature map and isolate data from the 3D feature map that is within the 3D volume for processing in a deep learning algorithm.

Patent Agency Ranking