Digital Equipment Corporation

Hewlett-packard Development Company, L.P.

Other

Douglas J Burns

David Martin Fenwick

Richard T Witek

Douglas D Williams

Rebecca L Stamm

Timothy J Stanley

Richard Heye

Stephen R Van Doren

Denis J Foley

Ricky C Hetherington

Barry S Katz

Roger Dame

A clock forwarding scheme for use in a system comprising a plurality of communications links, each link configured to transmit data packets and a forwarded clock from a transmitting device to a receiving device. The required delay in the forwarded clock signal is generated at the transmitting device by adding tuning etch to the signal path for the forwarded clock signal prior to transmission of the forwarded clock signal and data packets. The source device preferably has at least two clock output pins to deliver two synchronous clock signals off the device and at least two clock input pins to receive the clock signals. One of the two clock signals is delayed with respect to the other via a longer conduction path. The delayed clock signal is used to trigger logic to transmit the forwarded clock signal. The undelayed clock signal is used to trigger logic to transmit data bits.

Method for reducing tuning etch in a clock-forwarded interface

A processor system, comprising a system board on which a processor, a memory logic controller, and a clock source are installed and a memory module on which a memory device and PLL clock driver are installed. The system board is configured to accept one or more memory modules. The clock signal generated by the clock source is distributed to the various devices on the system board by a clock buffer tree via equal length etch runs. The same clock signal is also propagated via a different length etch to the memory device on the memory module. Clock skew generated by these different clock etch lengths is removed by routing a carefully tuned feedback loop of the clock driver from the memory module to the system board and back to the clock driver on the memory module. The PLL performs a clock signal voltage translation from PECL to TTL voltage.

PECL voltage DIMM with remote multi-module etch skew compensation

A method and apparatus in a computer system for handling cache memory victim data for updating main memory. The invention operates in a computer system having one or more processor modules coupled to main memory by a system bus operating in accordance with a SNOOPING bus protocol. Upon a processor executing a READ of one of the cache memory addresses, cache memory data corresponding to the cache memory address being READ is transmitted into the data interface from the cache memory data storage. The cache memory data is received accumulatively by the data interface during the execution of the READ of the cache memory address information. A determination is made as to whether the cache memory data corresponding to the cache memory address being READ is a cache memory victim. If the determination establishes that it is a cache memory victim, the processor issues a command for transmitting cache memory victim data to main memory over the system bus. In response to the command for transmitting cache memory victim data, the cache memory data which is waiting in the data interface, is transmitted from the data interface to main memory over the system bus.

System for handling cache memory victim data which transfers data from

In a computer system, digital signals are transmitted from an output register, propagated along a first signaling path, and received by an input register. The signaling path including an address buffer, a cache memory, a main memory, and an interconnect network. The effects of the intrinsic delays experienced by the digital signals are measured as a delay value relative to a reference clock signal propagated through a second signaling path duplicating the delays of the first signaling path. The delay value is used to selectively delay the digital signal to maintain a fixed relationship between the transmitted and received digital signals. Delay measuring and regulation is provided by driving the reference and digital signals through comparable tapped delay lines, the output taps of a measuring delay line controlling the output taps of a delaying line. Storage latches are provide to hold the measured delay value stable between successive samples.

Delay compensated signal propagation

A load/store pipeline in a computer processor for loading data to registers and storing data from the registers has a cache memory within the pipeline for storing data. The pipeline includes buffers which support multiple outstanding read request misses. Data from out of the pipeline is obtained independently of the operation of the pipeline, this data corresponding to the request misses. The cache memory can then be filled with the requested for data. The provision of a cache memory within the pipeline, and the buffers for supporting the cache memory, speed up loading operations for the computer processor.

Pipeline utilizing an integral cache for transferring data to and from a

A load/store pipeline in a computer processor for loading data to registers and storing data from the registers has a cache memory within the pipeline for storing data. The pipeline includes buffers which support multiple outstanding read request misses. Data from out of the pipeline is obtained independently of the operation of the pipeline, this data corresponding to the request misses. The cache memory can then be filled with the data that has been requested. The provision of a cache memory within the pipeline, and the buffers for supporting the cache memory, speed up loading operations for the computer processor.

Growing community of inventors

Westford, MA, United States of America

Douglas J Burns