Abstract: Introduced here is an artificial intelligence system designed for machine learning. The system may be based on a neuromorphic computational model that learns spatial patterns in inputs using data structures called Sparse Distributed Representations (SDRs) to represent the inputs. Moreover, the system can generate signatures for these SDRs, and these signatures may be used to create definitions of classes or subclasses for classification purposes.

Abstract: A memory is organized into blocks. In a bit-flipping operation, a memory block is read, the read bit data values are inverted, and the inverted data is written back to the memory block. Inverted memory blocks are tracked by setting a flag bit in the memory block, or by storing a pointer to a memory block. In a read operation, a memory block is read and, if the tracking method indicates the memory block is inverted, the read data values are reverted before being returned. In a write operation, a memory block is read and, if the tracking method indicates the memory block is inverted, the write data values are inverted before being written. Inversion of data values and tracking of inverted memory blocks may be performed by a specialized memory controller or by a processor executing secure memory code. Data remanence is thus prevented in the memory.

Abstract: A delay-locked loop (DLL) involves a pulse generating circuit that generates first and second pulses from an input clock signal. The second pulse is generated one clock signal period later than the first pulse. The first pulse is supplied to the input of a delay line. An edge of a delayed version of the first pulse as output from the delay line is phase-aligned with respect to a corresponding edge of the undelayed second pulse such that the DLL locks. The sending of pulses through the delay line of the DLL rather than clock signals having more edges per unit time helps reduce DLL aliasing problems and reduces the amount of switching in the delay line, thereby reducing power. consumption. A compact segmented delay line construction allows an input signal of arbitrary wave shape to be delayed by a fraction of the clock signal period.

Abstract: The present invention provides a memory architecture allowing for instructions of variable length to be stored without wasted memory spaces. Instructions of one, two, and three bytes can all be retrieved in a single fetch. The exemplary embodiment divides the memory block into two ×16 memories having some special addressing circuitry. This structure logically arranges the memory into a number of rows, each of four byte-wide columns. To the first of these ×16 memories, the full address is provided. If the address is within the two columns of the second ×16 memory, the full address is also provided to the second ×16 memory. If the address is to the first of the ×16 memories, the second ×16 memory instead receives the portion of the address specifying the row with one added to it. This results in a dual row access with the last one or two bytes of 3-byte instruction being supplied by the row above the first byte.

Abstract: The present invention provides a memory architecture allowing for instructions of variable length to be stored without wasted memory spaces. Instructions of one, two, and three bytes can all be retrieved in a single fetch. The exemplary embodiment divides the memory block into two ×16 memories having some special addressing circuitry. This structure logically arranges the memory into a number of rows, each of four byte-wide columns. To the first of these ×16 memories, the full address is provided. If the address is within the two columns of the second ×16 memory, the full address is also provided to the second ×16 memory. If the address is to the first of the ×16 memories, the second ×16 memory instead receives the portion of the address specifying the row with one added to it. This results in a dual row access with the last one or two bytes of 3-byte instruction being supplied by the row above the first byte.

Abstract: The present invention provides a memory architecture allowing for instructions of variable length to be stored without wasted memory spaces. Instructions of one, two, and three bytes can all be retrieved in a single fetch. The exemplary embodiment divides the memory block into two ×16 memories having some special addressing circuitry. This structure logically arranges the memory into a number of rows, each of four byte-wide columns. To the first of these ×16 memories, the full address is provided. If the address is within the two columns of the second ×16 memory, the full address is also provided to the second ×16 memory. If the address is to the first of the ×16 memories, the second ×16 memory instead receives the portion of the address specifying the row with one added to it. This results in a dual row access with the last one or two bytes of 3-byte instruction being supplied by the row above the first byte.

Abstract: The present invention provides a memory architecture allowing for instructions of variable length to be stored without wasted memory spaces. Instructions of one, two, and three bytes can all be retrieved in a single fetch. The exemplary embodiment divides the memory block into two x16 memories having some special addressing circuitry. This structure logically arranges the memory into a number of rows, each of four byte-wide columns. To the first of these x16 memories, the full address is provided. If the address is within the two columns of the second x16 memory; the full address is also provided to the second x16 memory. If the address is to the first of the x16 memories, the second x16 memory instead receives the portion of the address specifying the row with one added to it. This results in a dual row access with the last one or two bytes of 3-byte instruction being supplied by the row above the first byte.