Intel Corporation

Joe Salmon

Hing Yan To

Kuljit Singh Bains

Aaron K Martin

Mamun Ur Rashid

George Vergis

Navneet Dour

James A McCall

Andrew M Volk

Ying Zhou

Dawson Kesling

Ravindran Mohanavelu

Derek M Conrow

Hon Mo Law

A method and apparatus for transceiver clock architecture with transmit PLL and receive slave delay lines. In one embodiment, the method includes the generation of a transmitter (Tx) clock signal by adjusting a control voltage of a voltage controlled oscillator to lock a phase and frequency of Tx clock signal to a reference clock signal. In one embodiment, a frequency of the Tx clock signal is a multiple of a frequency of the reference clock signal. In one embodiment, a slave delay line may be used, including a plurality of variable delay buffers that are configured according to the control voltage to generate a receiver (Rx) clock signal in response to a received clock signal that is synchronized with the reference clock signal. The Rx clock signal may be provided to data recovery logic to sample data. Other embodiments are described and claimed.

Transceiver clock architecture with transmit PLL and receive slave delay lines

Described herein is a method and apparatus to interface a processor with a heterogeneous dual in-line memory module (DIMM). The method comprises determining an identity of a DIMM having data lanes; mapping the data lanes based on the determining of the identity of the DIMM; training input-output (I/O) transceivers in response to the mapping of the data lanes; and transferring data to and from the DIMM after training the I/O transceivers.

Method and apparatus for interfacing with heterogeneous dual in-line memory modules

Embodiments of the invention are generally directed to systems, methods, and apparatuses for optimizing the size of memory devices used for error correction code storage. An apparatus (such as a memory module) may include a number of memory devices to store data and a memory device to store error correction (ECC) bits. In some embodiments, the memory devices to store data may have a density of N and the memory device to store ECC bits has a density of &#xbd; N.

Optimizing the size of memory devices used for error correction code storage

A clock divider circuitry and method for use in a dynamic random access memory device. The method may include receiving a clock input signal having a first frequency from a clock input receiver at clock divider circuitry, the clock divider circuitry including a flip-flop configured to generate an output signal, based at least in part, on an inverted output signal and the clock input signal. The output signal may have a second frequency that is a fraction of the first frequency. The method may further include receiving the clock input signal and the output signal at a multiplexer and generating a multiplexed output. The method may additionally include receiving the multiplexed output at a first bus configured to receive the multiplexed output and to reduce an operational frequency of the first bus in response to an increase in an operational frequency of a second bus associated with the memory device.

Bus frequency adjustment circuitry for use in a dynamic random access memory device

Systems, methods, and apparatuses for optimizing the size of memory devices used for error correction code storage. An apparatus (such as a memory module) may include a number of memory devices to store data and a memory device to store error correction (ECC) bits. The memory devices to store data may have a density of N and the memory device to store ECC bits has a density of &#xbd; N.

De-skew is performed on a nibble-by-nibble basis where a nibble is not limited to four bits.

Nibble de-skew method, apparatus, and system

Some embodiments are directed to circuits comprising first and second PLLs. The first PLL generates a first clock signal based on a reference clock signal. The second PLL generates a second clock signal based on the reference clock signal and is synchronized with the first clock signal.

Extended synchronized clock

Embodiments of the invention are generally directed to systems, methods, and apparatuses for a clocking architecture using a bidirectional clock. In an embodiment, a chip includes a bidirectional clock port capable of being statically configured to receive or to transmit a reference clock. In one embodiment, the chip includes a first port to receive data and a second port, wherein the chip repeats at least a portion of the data that it receives on the first port to a transmitter at the second port. Other embodiments are described and claimed.

Clocking architecture using a bidirectional clock port

Transmission of digital signals across a bus between an electronic device having a transmitter and another electronic device having a receiver with termination for both the transmitter and receiver being referenced to ground, such that the electronic device having the transmitter and the other electronic device having the receiver are able to be powered with differing decoupled voltages, such that the voltage employed by the electronic device having the transmitter is able to be lower than the voltage employed by the other electronic device having the receiver, and wherein the electronic device having the transmitter may transmit addresses and/or commands to the other device having the receiver using single-ended signaling, while both electronic devices may exchange data using differential signaling.

Method and apparatus for power efficient and scalable memory interface

An embodiment may comprise a counter to provide a count value, enable logic coupled with the counter, and circuitry coupled with the enable logic, the circuitry to be powered up or down if the counter value is outside of a resonance bandwidth for the circuitry to be powered up or down. An embodiment may comprise a method of initializing a counter while circuitry is placed in a standby mode, reading the counter, and powering up the circuitry if the counter does not indicate a resonance bandwidth. An embodiment may be a system comprising a device including a power delivery network to deliver power, a link coupled with the device, the link to electrically communicate with the device, and control circuitry coupled with the link, the control circuitry to limit the link from powering up or down at a resonant frequency of the power delivery network.

Countering power resonance

A method, apparatus, and system are disclosed. In one embodiment the method comprises inputting an early clock signal and a late clock signal to a memory device and generating an average clock signal for the memory device by averaging the early clock signal and the late clock signal.

Latency normalization by balancing early and late clocks

To allow a memory controller to synchronize strobe to clock relationship for a DRAM, a register, such as, a flip flop, is incorporated within the DRAM to facilitate the sampling of SCLK with DQS. Likewise, while the DRAM is in a test mode of operation, the memory controller advances or retards the clock to DQS at the memory controller hub (MCH) to achieve the proper DRAM relationship. In one embodiment, the memory controller advances DQS if a binary zero value is read. In contrast, the memory controller retards DQS if a binary one value is read.

Method and apparatus for optimizing strobe to clock relationship

A system having several clock domains must have domain clocks properly aligned before powering up from a low-power or power-down mode. The domain clocks can be quickly aligned to enable fast system start-up if the clocks are forced into a rough alignment before a fine alignment process begins. Initially, a phase offset between the domain clocks is determined using a sync pulse, which indicates a location of one of the domain clocks relative to the other domain clock. Next, the domain clocks are forced into a minimum phase offset configuration by phase stalling one of the domain clocks. The phase stalling includes adjusting the pulse width of one of the domain clocks to force the clock into a rough alignment with the other domain clock. Finally, the domain clocks are fine aligned, and the system is placed into a normal power mode.

Growing community of inventors

Placerville, CA, United States of America

Joe Salmon