Abstract: Methods and apparatus for creating a physically unclonable function for SRAM are disclosed. An example method includes after applying a voltage to a memory array: determining a first duration between the applying of the voltage and a first output of a first bit cell, the first output corresponding to a first value stored in the first bit cell, and determining a second duration between the applying of the voltage and a second output of a second bit cell, the second output corresponding to a second value stored in the second bit cell. The example method further includes determining a function based on a comparison of the first duration and the second duration, the function to establish an identification of a circuit that includes the memory array.

Abstract: Various aspects may include methods, computing devices implementing such methods, and non-transitory processor-readable media storing processor-executable instructions implementing such methods for improving battery life with performance provisioning using machine learning based automated workload classification. Various aspects may include creating a machine learning model based at least in part on computing device metrics, training the machine learning model using performance provisioning rules for work groups; classifying a new work item for a software application into a work group using the trained machine learning model, and applying resource provisioning rules for the work group to the new work item.

Abstract: Various aspects may include methods, computing devices implementing such methods, and non-transitory processor-readable media storing processor-executable instructions implementing such methods for improving battery life with performance provisioning using machine learning based automated workload classification. Various aspects may include creating a machine learning model based at least in part on computing device metrics, training the machine learning model using performance provisioning rules for work groups; classifying a new work item for a software application into a work group using the trained machine learning model, and applying resource provisioning rules for the work group to the new work item.

Abstract: Methods and apparatus for a low energy accelerator processor architecture with short parallel instruction word. An integrated circuit includes a system bus having a data width N, where N is a positive integer; a central processor unit coupled to the system bus and configured to execute instructions retrieved from a memory coupled to the system bus; and a low energy accelerator processor coupled to the system bus and configured to execute instruction words retrieved from a low energy accelerator code memory, the low energy accelerator processor having a plurality of execution units including a load store unit, a load coefficient unit, a multiply unit, and a butterfly/adder ALU unit, each of the execution units configured to perform operations responsive to op-codes decoded from the retrieved instruction words, wherein the width of the instruction words is equal to the data width N. Additional methods and apparatus are disclosed.

Abstract: Disclosed embodiments include a memory device having a memory array that includes a first memory cell coupled to a first bit line and a second memory cell coupled to a second bit line and a sense amplifier that includes first and second transistors arranged in a cross-coupled configuration with third and fourth transistors, the first and second transistors being of a first conductivity type and the third and fourth transistors being of a second conductivity type, a first inverter having an input coupled to a first common drain terminal of the first and third transistors and an output coupled to the first bit line, and a second inverter having an input coupled to a second common drain terminal of the second and fourth transistors and an output coupled to the second bit line.

Abstract: Methods, apparatus, systems and articles of manufacture to determine and apply polarity-based error correction code are disclosed. In some examples, the methods and apparatus create an array by setting a first set of bit locations of a code word to have a first value and setting a second set of bit locations of the code word to have a second value different from the first value. In some examples, when the array satisfies a parity check, the methods and apparatus determine that bit locations having the first value from the array form a polarity-based error correction code.

Abstract: Methods and apparatus for a low energy accelerator processor architecture with short parallel instruction word. An integrated circuit includes a system bus having a data width N, where N is a positive integer; a central processor unit coupled to the system bus and configured to execute instructions retrieved from a memory coupled to the system bus; and a low energy accelerator processor coupled to the system bus and configured to execute instruction words retrieved from a low energy accelerator code memory, the low energy accelerator processor having a plurality of execution units including a load store unit, a load coefficient unit, a multiply unit, and a butterfly/adder ALU unit, each of the execution units configured to perform operations responsive to op-codes decoded from the retrieved instruction words, wherein the width of the instruction words is equal to the data width N. Additional methods and apparatus are disclosed.

Abstract: A method of enabling processing of a video stream is described. The method comprises establishing a slice width for frames of the video stream; receiving the video stream; dividing, for each frame of the video stream, the frame into vertical slices having the slice width; storing a frame of the video stream in a re-ordered slice based format.

Abstract: A method of operating a memory circuit (FIGS. 8A and 8B) is disclosed. The method includes writing true data (01) to a plurality of bits (B0, B1). A first data state (0) is written to a signal bit (Bi) indicating the true data. The true data is read and complementary data (10) is written to the plurality of bits. A second data state (1) is written to the signal bit indicating the complementary data.

Abstract: A system for write-once memory (WOM) code emulation of EEPROM-type devices includes, for example, a host processor for sending data words for storing in a WOM (Write-Only Memory) device. A host interface receives the data words for encoding by a WOM controller. An emulator programs the WOM-encoded data and an address identifier as an entry of the WOM device. The emulator overwrites previously programmed WOM-encoded data by searching entries of a current active page of a WOM device to locate a programmed WOM entry that includes the searched-for address identifier and the previously written WOM-encoded data word. When the previously written WOM-encoded word cannot be correctly overwritten, the contents of the second WOM-encoded word are stored in a new entry. When the current active page is substantially full, the new entry is stored a new page and the current active page is block-erased.

Abstract: Data words to be written to a memory location are delta encoded in multi-write avoidance (“MWA”) code words. MWA code words result in no re-writing of single-bit storage cells containing logical “0's” to a “0” state and no re-writing of logical “1's” to cells that have already been written once to a logical “1.” Potential MWA code words stored in a look-up table (“LUT”) are indexed by a difference word DELTA_D. DELTA_D represents a bitwise difference (“delta”) between a data word currently stored at the memory location and a new data word (“NEW_D”) to be stored at the memory location. Validation and selection logic chooses an MWA code word representing NEW_D to be written if the MWA code word does not violate the principle of multi-write avoidance. Some embodiments generate the MWA code words using a pattern generator rather than indexing the MWA code words from a LUT.

Abstract: Instructions for 32-bit arithmetic support using 16-bit multiply and 32-bit addition without a barrel shifter. Illustrative instructions include operations that include receiving a first 32-bit operand, receiving a second 32-bit operand, shifting the second 32-bit operand right 16 or 15 bits to obtain a shifted second 32-bit operand, and adding the shifted second 32-bit operand and the first 32-bit operand to generate a 32-bit sum.

Abstract: Computers and methods for performing mathematical functions are disclosed. An embodiment of a computer includes an operations level and a driver level. The operations level performs mathematical operations. The driver level includes a first lookup table and a second lookup table, wherein the first lookup table includes first data for calculating at least one mathematical function using a first level of accuracy. The second lookup table includes second data for calculating the at least one mathematical function using a second level of accuracy, wherein the first level of accuracy is greater than the second level of accuracy. A driver executes either the first data or the second data depending on a selected level of accuracy.

Abstract: Methods and apparatus to measure detect and correct errors in destructive read non-volatile memory are disclosed. In some examples, the method and apparatus determine, in response to stabilizing a power supply, a status signature stored in non-volatile memory. In examples wherein the status signature is not normal, the methods and apparatus decode an error correction code that is encoded in a destructive read non-volatile memory.

Abstract: Methods and a device for providing for authentication of an integrated circuit (IC) chip are shown. The IC chip contains a physically unclonable function (PUF), a processor, a non-volatile memory, and an encryption module containing first instructions that, when executed by the processor, receive the unique key from the PUF, receive a master key from an external source, encrypt the unique key using the master key and store the encrypted unique key in the non-volatile memory.

Abstract: Computers and methods for performing mathematical functions are disclosed. An embodiment of a computer includes an operations level and a driver level. The operations level performs mathematical operations. The driver level includes a first lookup table and a second lookup table, wherein the first lookup table includes first data for calculating at least one mathematical function using a first level of accuracy. The second lookup table includes second data for calculating the at least one mathematical function using a second level of accuracy, wherein the first level of accuracy is greater than the second level of accuracy. A driver executes either the first data or the second data depending on a selected level of accuracy.

Abstract: An apparatus for preventing a relay attack that includes a microcontroller, a receiver, and a transmitter. The receiver is configured to receive a challenge message from a verifier. The challenge message has a challenge message frequency at a first challenge message frequency during a first time slot. The transmitter is configured to transmit a response message to the verifier. The response message has a response message frequency at a first response message frequency during the first time slot. The first response message frequency is different than the first challenge message frequency. The challenge message frequency is at a second challenge message frequency and the response message frequency is at a second response message frequency during a second time slit. The second challenge message frequency is different than the second response message frequency.

Abstract: Data words to be written to a memory location are delta encoded in multi-write avoidance (“MWA”) code words. MWA code words result in no re-writing of single-bit storage cells containing logical “0's” to a “0” state and no re-writing of logical “1's” to cells that have already been written once to a logical “1.” Potential MWA code words stored in a look-up table (“LUT”) are indexed by a difference word DELTA_D. DELTA_D represents a bitwise difference (“delta”) between a data word currently stored at the memory location and a new data word (“NEW_D”) to be stored at the memory location. Validation and selection logic chooses an MWA code word representing NEW_D to be written if the MWA code word does not violate the principle of multi-write avoidance. Some embodiments generate the MWA code words using a pattern generator rather than indexing the MWA code words from a LUT.

Abstract: A system for write-once memory (WOM) code emulation of EEPROM-type devices includes, for example, a host processor for sending data words for storing in a WOM (Write-Only Memory) device. A host interface receives the data words for encoding by a WOM controller. An emulator programs the WOM-encoded data and an address identifier as an entry of the WOM device. The emulator overwrites previously programmed WOM-encoded data by searching entries of a current active page of a WOM device to locate a programmed WOM entry that includes the searched-for address identifier and the previously written WOM-encoded data word. When the previously written WOM-encoded word cannot be correctly overwritten, the contents of the second WOM-encoded word are stored in a new entry. When the current active page is substantially full, the new entry is stored a new page and the current active page is block-erased.

Abstract: Methods and apparatus for creating a physically unclonable function for SRAM are disclosed. An example method includes decreasing a supply voltage of a memory array to a first voltage level, the first voltage level being below a normal operating voltage associated with the memory array, reading a first value of a bit cell after the supply voltage has been at the first voltage level, and determining a function based on the first value of the bit cell and a second value, the second value stored in the bit cell when the memory array is operating at a voltage level above the first voltage level, the function to represent an identification of a circuit including the memory array.