Abstract: A method of booting a computer system using a non-volatile memory of a memory module of the computer system is disclosed. According to one embodiment, a memory controller driver of a memory module of the computer system is stored in a non-volatile memory of the memory module. A memory controller of the memory module has a register that is set to indicate a location of the memory controller driver in the non-volatile memory of the memory module. The memory controller determines the location of the memory controller driver of the memory module using the register. The memory controller driver is transferred from the non-volatile memory to a buffer of the memory controller and subsequently from the buffer of the memory controller to a main memory of the computer system. The computer system initializes the memory module using the memory controller driver.

Abstract: A system and method for implementing an object storage device is disclosed. According to one embodiment, the system includes a first controller configured to interface with a main memory controller of a computer system to receive a data object and a first request for storing the data object, the first request including a key value. The system also includes a second controller configured to: allocate memory in one or more non-volatile memory storage units for storing the data object, store the data object in the allocated memory, and maintain an association between the key value and allocated memory.

Abstract: A method of controlling a remote computer device of a remote computer system over a remote direct memory access (RDMA) is disclosed. According to one embodiment, the method includes establishing a connection for remote direct memory access (RDMA) between a local memory device of a local computer system and a remote memory device of a remote computer system. A local command is sent from a local application that is running on the local computer system to the remote memory device of the remote computer system via the RDMA. The remote computer system executes the local command on the remote computer device.

Abstract: A method is disclosed for providing memory bus timing of a load reduction dual inline memory module (LRDIMM). The method includes: determining a latency value of a dynamic random access memory (DRAM) of the LRDIMM; determining a modified latency value of the DRAM that accounts for a delay caused by a load reduction buffer (LRB) that is deployed between the DRAM and a memory bus; storing the modified latency value in a serial presence detector (SPD) of the LRDIMM; and providing memory bus timing for the LRDIMM based on the modified latency value, wherein the memory bus timing is compatible with a registered dual inline memory module (RDIMM).

Abstract: A system for interfacing with a co-processor or input/output device is disclosed. According to one embodiment, the system includes a computer processing unit, a memory module, a memory bus that connects the computer processing unit and the memory module, and a co-processing unit or input/output device, wherein the memory bus also connects the co-processing unit or input/output device to the computer processing unit.

Abstract: A system for interfacing with a co-processor or input/output device is disclosed. According to one embodiment, the system performs a maze unlock sequence by operating a memory device in a maze unlock mode. The maze unlock sequence involves writing a first data pattern of a plurality of data patterns to a memory address of the memory device, reading a first set of data from the memory address, and storing the first set of data in a validated data array. The maze unlock sequence further involves writing a second data pattern of the plurality of data patterns to the memory address, reading a second set of data from the memory address, and storing the second set of data in the validated data array. A difference vector array is generated from the validate data array and an address map of the memory device is identified based on the difference vector array.

Abstract: A system for interfacing with a co-processor or input/output device is disclosed. According to one embodiment, the system is configured to receive a command from a host memory controller of a host system and store the command in a command buffer entry. The system determines that the command is complete using a buffer check logic and provides the command to a command buffer. The command buffer comprises a first field that specifies an entry point of the command within the command buffer entry.

Abstract: A system for interfacing with a co-processor or input/output device is disclosed. According to one embodiment, the system provides a one-hot address cache comprising a plurality of one-hot addresses and a host interface to a host memory controller of a host system. Each one-hot address of the plurality of one-hot addresses has a bit width. The plurality of one-hot addresses is configured to store the data associated with a corresponding memory address in an address space of a memory system and provide the data to the host memory controller during a memory map learning process. The plurality of one-hot addresses comprises a zero address of the bit width and a plurality of non-zero addresses of the bit width, and each one-hot address of the plurality of non-zero addresses of the one-hot address cache has only one non-zero address bit of the bit width.

Abstract: A system for interfacing with a co-processor or input/output device is disclosed. According to one embodiment, the system includes a computer processing unit, a memory module, a memory bus that connects the computer processing unit and the memory module, and a co-processing unit or input/output device, wherein the memory bus also connects the co-processing unit or input/output device to the computer processing unit.

Abstract: A load reduction dual in-line memory module (LRDIMM) is similar to a registered dual inline memory module (RDIMM) in which control signals are synchronusly buffered but the LRDIMM includes a load reduction buffer (LRB) in the data path as well. To make an LRDIMM which appears compatible with RDIMMs on a system memory bus, the serial presence detector (SPD) of the LRDIMM is programmed with modified latency support and minimum delay values. When the dynamic read only memory (DRAMs) devices of the LRDIMM are subsequently set up by the host at boot time based on the parameters provided by the SPD, selected latency values are modified on the fly in an enhanced register phase look loop (RPLL) device. This has the effect of compensating for the delay introduced by the LRB without violating DRAM constraints, and provides memory bus timing for a LRDIMM that is indistinguishable from that of a RDIMM.

Abstract: A system for interfacing with a co-processor or input/output device is disclosed. According to one embodiment, the system includes a computer processing unit, a memory module, a memory bus that connects the computer processing unit and the memory module, and a co-processing unit or input/output device, wherein the memory bus also connects the co-processing unit or input/output device to the computer processing unit.

Abstract: A load reduction dual in-line memory module (LRDIMM) is similar to a registered dual in-line memory module (RDIMM) in which control signals are synchronously buffered but the LRDIMM includes a load reduction buffer (LRB) in the data path as well. To make an LRDIMM which appears compatible with RDIMMs on a system memory bus, the serial presence detector (SPD) of the LRDIMM is programmed with modified latency support and minimum delay values. When the dynamic read only memory (DRAMs) devices of the LRDIMM are subsequently set up by the host at boot time based on the parameters provided by the SPD, selected latency values are modified on the fly in an enhanced register phase look loop (RPLL) device. This has the effect of compensating for the delay introduced by the LRB without violating DRAM constraints, and provides memory bus timing for a LRDIMM that is indistinguishable from that of a RDIMM.

Abstract: The present invention describes methods and circuitry for a sub-rate bang-bang phase detector, in which the reference clock has frequency that is a fraction of the bit rate of the received data stream. The sub-rate bang-bang phase detector is enabled by multiple phases of the reference clock.

Abstract: A system for interfacing with a co-processor or input/output device is disclosed. According to one embodiment, the system includes a computer processing unit, a memory module, a memory bus that connects the computer processing unit and the memory module, and a co-processing unit or input/output device, wherein the memory bus also connects the co-processing unit or input/output device to the computer processing unit.

Abstract: A novel interpolating phase detector for use in a multiphase PLL is described comprising an array of individual phase comparators, all operating at essentially the same operating point which permits the circuits to be designed simultaneously for high speed and for low power consumption. Two adjacent phase outputs of a multi-phase VCO may be selected and interpolated in between, by selectively attaching a variable number of phase comparators to each phase output and summing their phase error outputs. By varying the number of phase comparators attached to each phase output, interpolation can be achieved with high linearity.

Abstract: An equalization circuit is disclosed that enables high data rate transmission over high loss communications channels. Also disclosed is a set of functional blocks and update criteria that allow for the equalization function to be adapted for a large variety of different communications channels. A fully continuous adaptive equalizer is used in conjunction with a Decision Feedback Equalizer to fully equalize a wide range of communications channels. Interoperability and Bit Error Rate performance are optimized through compensation of pre-cursor inter-symbol interference, which is performed adaptively in the receiver as opposed to the transmitter.

Abstract: An equalization circuit is disclosed that enables high data rate transmission over high loss communications channels. Also disclosed is a set of functional blocks and update criteria that allow for the equalization function to be adapted for a large variety of different communications channels. A fully continuous adaptive equalizer is used in conjunction with a Decision Feedback Equalizer to fully equalize a large number of communications channels.

Abstract: A multi reference phase locked loop (MPLL) generates a high speed clock frequency and phase locks it to a lowest common reference frequency derived from a selected one of at least two reference clocks. One of the reference clocks is a system reference clock in a FBDIMM system, another may be a forwarded clock in an AMB2. A prescaler reduces the frequency of at least the forwarded clock to the lowest common reference frequency which is the frequency of the system reference clock. A PLL at the core of the MPLL may be locked to the forwarded clock or the system reference clock for generating a high speed clock. A feedback divider generates the feedback clock for the PLL as well as other clocks required in the system. Furthermore, the MPLL provides a number of clocking modes, including modes to facilitate testing and powering down of sections of the circuitry for conserving power.

Abstract: A method and system for reducing the frequency of operation for a transversal Finite Impulse Response (FIR) filter is disclosed. In the preferred embodiment, the transversal filter operates in such a way that it has an even and odd row of data, which are latched on rising and falling edges of the clock respectively. This allows the clock frequency to be reduced by a factor of 2, and thus allows the use of more power efficient latches. A reduction in the frequency of operation causes the high speed latches within the transversal filter to hold the data bits twice as long as is required, which changes the desired impulse response of the FIR filter. A circuit is required to select the appropriate data bits from the output of the appropriate half-speed latch, and subsequently scale it to apply the co-efficient gain. Each of the subsystems is analog, and operates in accordance with a synchronous clock system.

Abstract: Where high speed communication between a host and memory devices is carried over serial bit lanes, memory buffers are required for converting buffering the serial bit lanes, and for converting between serial and parallel formats. In addition, jitter, wander, and skew between the bit lanes need to be accommodated. The invention discloses a programmable asynchronous FIFO with the integrated ability to convert blocks of bits from serial to parallel as well as inserting bits from a parallel bus into the serial bit stream. The invention provides very low latency and can be implemented in low power technologies.