Hewlett-packard Development Company, L.p.

Steve Lang

Richard Eugene Kessler

David A J Webb, Jr

Samuel Hammond Duncan

Aaron T Spink

David W Hartwell

David Arthur James Webb, Jr

Shubhendu Sekhar Mukherjee

David Asher

Michael S Bertone

Dilip K Bhavsar

A system that supports a high performance, scalable, and efficient I/O port protocol to connect to I/O devices is disclosed. A distributed multiprocessing computer system contains a number of processors each coupled to an I/O bridge ASIC implementing the I/O port protocol. One or more I/O devices are coupled to the I/O bridge ASIC, each I/O device capable of accessing machine resources in the computer system by transmitting and receiving message packets. Machine resources in the computer system include data blocks, registers and interrupt queues. Each processor in the computer system is coupled to a memory module capable of storing data blocks shared between the processors. Coherence of the shared data blocks in this shared memory system is maintained using a directory based coherence protocol. Coherence of data blocks transferred during I/O device read and write accesses is maintained using the same coherence protocol as for the memory system. Data blocks transferred during an I/O device read or write access may be buffered in a cache by the I/O bridge ASIC only if the I/O bridge ASIC has exclusive copies of the data blocks. The I/O bridge ASIC includes a DMA device that supports both in-order and out-of-order DMA read and write streams of data blocks. An in-order stream of reads of data blocks performed by the DMA device always results in the DMA device receiving coherent data blocks that do not have to be written back to the memory module.

Scalable efficient I/O port protocol

A method and apparatus for ensuring fair and efficient use of a shared memory buffer. A preferred embodiment comprises a shared memory buffer in a multi-processor computer system. Memory requests from a local processor are delivered to a local memory controller by a cache control unit and memory requests from other processors are delivered to the memory controller by an interprocessor router. The memory controller allocates the memory requests in a shared buffer using a credit-based allocation scheme. The cache control unit and the interprocessor router are each assigned a number of credits. Each must pay a credit to the memory controller when a request is allocated to the shared buffer. If the number of filled spaces in the shared buffer is below a threshold, the buffer immediately returns the credits to the source from which the credit and memory request arrived. If the number of filled spaces in the shared buffer is above a threshold, the buffer holds the credits and returns the credits in a round-robin manner only when a space in the shared buffer becomes free. The number of credits assigned to each source is sufficient to enable each source to deliver an uninterrupted burst of memory requests to the buffer without having to wait for credits to return from the buffer. The threshold is the point when the number of free spaces available in the buffer is equal to the total number of credits assigned to the cache control unit and the interprocessor router.

Mechanism to control the allocation of an N-source shared buffer

A multi-processor system in which each processor receives a message from another processor in the system. The message may contain corrupted data that was corrupted during transmission from the preceding processor. Upon receiving the message, the processor detects that a portion of the message contains corrupted data. The processor then replaces the corrupted portion with a predetermined bit pattern known or otherwise programmed into all other processors in the system. The predetermined bit pattern indicates that the associated portion of data was corrupted. The processor that detects the error in the message preferably alerts the system that an error has been detected. The message now containing the predetermined bit pattern in place of the corrupted data is retransmitted to another processor. The predetermined bit pattern will indicate that an error in the message was detected by the previous processor. In response, the processor detecting the predetermined bit pattern preferably will not alert the system of the existence of an error. The same message with the predetermined bit pattern can be retransmitted to other processors which also will detect the presence of the predetermined bit pattern and in response not alert the system of the presence of an error. As such, because only the first processor to detect an error alerts the system of the error and because messages containing uncorrectable errors still are transmitted through the system, fault isolation is improved and the system is less likely to fall into a deadlock condition.

Special encoding of known bad data

A directory-based multiprocessor cache control scheme for distributing invalidate messages to change the state of shared data in a computer system. The plurality of processors are grouped into a plurality of clusters. A directory controller tracks copies of shared data sent to processors in the clusters. Upon receiving an exclusive request from a processor requesting permission to modify a shared copy of the data, the directory controller generates invalidate messages requesting that other processors sharing the same data invalidate that data. These invalidate messages are sent via a point-to-point transmission only to master processors in clusters actually containing a shared copy of the data. Upon receiving the invalidate message, the master processors broadcast the invalidate message in an ordered fan-in/fan-out process to each processor in the cluster. All processors within the cluster invalidate a local copy of the shared data if it exists and once the master processor receives acknowledgements from all processors in the cluster, the master processor sends an invalidate acknowledgment message to the processor that originally requested the exclusive rights to the shared data. The cache coherency is scalable and may be implemented using the hybrid point-to-point/broadcast scheme or a conventional point-to-point only directory-based invalidate scheme.

Broadcast invalidate scheme

A system and method is disclosed for reducing network message passing latency in a distributed multiprocessing computer system that contains a plurality of microprocessors in a computer network, each microprocessor including router logic to route message packets prioritized in importance by the type of message packet, age of the message packet, and the source of the message packet. The microprocessors each include a plurality of network input ports connected to corresponding local arbiters in the router. The local arbiters are each able to select a message packet from the message packets waiting at the associated network input port. Microprocessor input ports and microprocessor output ports in the microprocessor allow the exchange of message packets between hardware functional units in the microprocessor and between the microprocessors. The microprocessor input ports are similarly each coupled to corresponding local arbiters in the router. Each of the local arbiters is able to select a message packet among the message packets waiting at the microprocessor input port. Global arbiters in the router connected to the network output ports and microprocessor output ports select a message packet from message packets nominated by the local arbiters of the network input ports and microprocessor input ports. The local arbiters connected to each network input port or microprocessor input port will request service from a output port global arbiter for a message packet based on the message packet type if the message packet is ready to be dispatched.

Priority rules for reducing network message routing latency

A system for scan testing a device under test (&ldquo;DUT&rdquo;) in which the clock speed of the DUT differs from test equipment. A plurality of scan-flops in the DUT form a scan-wheel, which defines a closed scan path. The Data bits in the scan path are shifted through a scan-wheel controller based on the DUT clock speed, so that a different bit passes through the scan-wheel controller on each clock cycle of the DUT. Test data is only loaded by replacing the data bit as it passes through the controller. The different clock rates of the DUT and the test equipment define a scan wheel ratio, which is used to determine the number of times that the scan-wheel must rotate before all old data bits are unloaded and replaced by newly loaded bits, and which also determines when data bits passing through the controller will be unloaded and replaced.

Growing community of inventors

Stow, MA, United States of America

Steve Lang