50 results about "Datapath circuits" patented technology

A method and apparatus for design-for-low-power of register transfer level (RTL) controller/data path circuits that implement control-flow intensive specifications. The method of the invention focuses on multiplexer networks and registers which dominate the total circuit power consumption and reduces generation and propagation of glitches in both the control and data path parts of the circuit. Further the method reduces glitching power consumption by minimizing propagation of glitches in the RTL circuit through restructuring multiplexer networks (to enhance data correlations and eliminate glitchy control signals), clocking control signals, and inserting selective rising/falling delays, in order to kill the propagation of glitches from control as well as data signals. To reduce power consumption in registers, the clock inputs to registers are gated with conditions derived by an analysis of the RTL circuit, ensuring that glitches are not introduced on the clock signals.

A memory architecture and circuits for minimizing current leakage in the memory array. Subdivisions of the memory array each have local power grids that can be selectively connected to power supplies, such that only an accessed subdivision will receive power to execute the memory access operation. The memory array can further include databuses which are precharged to one voltage during idle times and a second voltage during active read cycles, which reduces leakage current in datapath circuitry connected to the databuses within the memory array blocks.

Methods and apparatus for providing a bus interface are disclosed. An example method for providing a bus interface includes operating first circuitry using a first power supply voltage in a normal operating mode, where the first circuitry includes at least a portion of datapath circuitry of the bus interface. The example method further includes powering down the first circuitry in a low power operating mode and operating second circuitry using the first power supply voltage in the normal operating mode. The example method also includes operating the second circuitry using a second power supply voltage in the low power operating mode. The second circuitry includes a power management control circuit adapted to receive a power management event indication signal. Responsive to the power management event indication signal, the control circuit provides at least one of an in-band power management indication and an out-of-band power management indication to one or more devices in a computing system. In the example method, the first and second power supply voltages may be provided by a single power supply or, alternatively, by multiple power supplies.

In one embodiment, an apparatus includes a datapath circuit to generate a data output signal in response to a data input signal and at least a first data clock signal; a shadow circuit, coupled to the datapath circuit, to generate a shadow output signal in response the data input signal and at least a second data clock signal during a functional mode of operation and to generate a scan-out signal in response to a scan-in signal and at least a first test clock signal during a test mode of operation; and an error detect circuit, coupled to the datapath and the shadow circuits, to generate an error signal in response to a mismatch between the data output signal and the shadow output signal.

A datapath circuit may include a digital multiply and accumulate circuit (MAC) and a digital hardware calculator for parallel computation. The digital hardware calculator and the MAC may be coupled to an input memory element for receipt of input operands. The MAC may include a digital multiplier structure with partial product generators coupled to an adder to multiply a first and second input operands and generate a multiplication result. The digital hardware calculator may include a first look-up table coupled between a calculator input and a calculator output register. The first look-up table may include table entry values mapped to corresponding math function results in accordance with a first predetermined mathematical function. The digital hardware calculator may be configured to calculate, based on the first look-up table, a computationally hard mathematical function such as a logarithm function, an exponential function, a division function and a square root function.

In accordance with some embodiments, a floating point number datapath circuitry, e.g., within an integrated circuit programmable logic device is provided. The datapath circuitry may be used for computing a rounded absolute value of a mantissa of a floating point number. The floating point datapath circuitry may have only a single adder stage for computing a rounded absolute value of a mantissa of the floating point number based on one or more bits of an unrounded mantissa of the floating point number. The unrounded and rounded mantissas may include a sign bit, a sticky bit, a round bit, and/or a least significant bit, and/or other bits. The unrounded mantissa may be in a format that includes negative numbers (e.g., 2's complement) and the rounded mantissa may be in a format that may include a portion of the floating point number represented as a positive number, (e.g., signed magnitude).

A processor including instruction support for implementing large-operand multiplication may issue, for execution, programmer-selectable instructions from a defined instruction set architecture (ISA). The processor may include an instruction execution unit comprising a hardware multiplier datapath circuit, where the hardware multiplier datapath circuit is configured to multiply operands having a maximum number of bits M. In response to receiving a single instance of a large-operand multiplication instruction defined within the ISA, wherein at least one of the operands of the large-operand multiplication instruction includes more than the maximum number of bits M, the instruction execution unit is configured to multiply operands of the large-operand multiplication instruction within the hardware multiplier datapath circuit to determine a result of the large-operand multiplication instruction without execution of programmer-selected instructions within the ISA other than the large-operand multiplication instruction.

In some embodiments, a computer-aided design system comprises a functional regularity extraction component, a structural regularity extraction component and a floorplanning component. The structural regularity extraction component provides a method to extract regularity for circuits (and in particular datapath circuits) based on the structural characteristics of a logic design. Some embodiments of the structural regularity extraction component automatically generate a set of vectors for the logic design. A vector is a group of template instances that are identical in function and in structure. The vectors generated by the structural regularity extraction component are used by a floorplanning component. The floorplanning component provides a method of generating a circuit layout from the set of vectors. In some embodiments, each vectors corresponds to a row in the circuit layout.

A memory device with a data path circuit having support in the sense-amp region for compression testing of the device. The data path circuit uses NOR logic compression to provide a scalable design which may be extended to large circuits.

TSV repair circuit of a semiconductor device includes a first chip, a second chip, at least two TSV, at least two data path circuits and an output logic circuit. Each data path circuit comprises an input driving circuit, a TSV detection circuit, a memory device, a protection circuit and a power control circuit. The TSV detection circuit detects a TSV status, the memory device keeps the TSV status, the protection circuit determines whether to pull a first end of the TSV to a ground voltage according to the TSV status, and the power control circuit prevents a leakage current of a power voltage from flowing through a substrate.

A write burst stop command function is provided for a semiconductor memory device, and in particular for a memory device having a write latency, such as is common in a low power double data rate (DDR) dynamic random access memory (DRAM) device. In the memory device, when a write stop command is received, pulses that are generated for a column address strobe signal are terminated so that no further data already in the memory device is transferred into a memory array. When the write stop command is received at the beginning of a write operation prior to generation of the pulses in the column address strobe signal, a first-in first-out (FIFO) circuit is reset. The FIFO circuit is used to introduce a predetermined write latency to the write operation. The column address strobe signal is supplied to a column decoder associated with the memory array and to a data path circuit that transfers data to the memory array based on pulses in the column address strobe signal. In one embodiment, the pulses for the column address strobe signal are produced by a latch circuit based on a signal derived from the output of the write latency FIFO circuit and so an input to the latch is disabled in response to the write stop command to stop producing pulses for the column address strobe signal.

A data path circuit includes a bit line sense amplifier, a local input/output line precharger connected to a local input/output line pair, a global input/output line precharger connected to a global input/output line pair, a column selector connecting a bit line pair connected to the bit line sense amplifier and the local input/output line pair to each other in response to a column selection signal, and a local input/output line selector connecting the local input/output line pair and the global input/output line pair to each other in response to a multiplexing control signal. A discharge path generator decreases the potential on the global input/output line pair down to a predetermined level in response to a data masking control signal which is activated earlier than the column selection signal during a data masking operation mode.

Embodiments of the present invention provide a system for transferring data between a receiver chip and a transmitter chip. The system includes a set of data path circuits in the transmitter chip and a set of data path circuits in the receiver chip coupled to a shared data channel. In addition, the system includes a set of asynchronous control circuits for controlling corresponding data path circuits in the transmitter chip and receiver chip. Upon detecting the transition of a control signal for an asynchronous control circuit in the transmitter chip, the asynchronous control circuit is configured to enable a transfer of data from the corresponding data path circuit in the transmitter chip across the data channel to a corresponding data path circuit in the receiver chip, and generate a control signal to cause a next asynchronous control circuit to commence the transfer of a data signal.

An element selection unit (200) and a method therein for vector element selection. The element selection unit comprises a selector control circuit (404) and a selector data path circuit (406), which data path circuit comprises a plurality of layers of multiplexers. The element selection unit further comprises a receiving circuit (401) configured to receive an instruction to perform a selection of elements from an input vector. The selector control circuit (404) is configured to generate a multiplexer control signal for each multiplexer based on a bit map and on a plurality of relative offset values. The data path circuit is configured to propagate the elements comprised in the input vector through the plurality of layers of multiplexers towards an output vector based on the generated multiplexer control signals. The data path circuit is further configured to write the propagated elements to enabled elements of the output vector.

Techniques are disclosed relating to sharing an arithmetic logic unit (ALU) between multiple threads. In some embodiments, the threads also have dedicated ALUs for other types of operations. In some embodiments, arbitration circuitry is configured to receive operations to be performed by the shared arithmetic logic unit from the set of threads and issue the received operations to the shared arithmetic logic unit. In some embodiments, the arbitration circuitry is configured to switch to a different one of the set of threads for each instruction issued to the shared arithmetic logic unit. In some embodiments, the shared ALU is configured to perform 32-bit operations and the dedicated ALUs are configured to perform the same operations using 16-bit precision. In some embodiments, the shared ALU is shared between two threads and is physically located adjacent to other datapath circuitry for the two threads.