Search NASA⌕ Search

Engineering topics

Blumrich, Matthias A

Publications and source records attributed to Blumrich, Matthias A.

At least 19 records

Conditional load and store in a shared memory

A method, system and computer program product for implementing load-reserve and store-conditional instructions in a multi-processor computing system. The computing system includes a multitude of processor units and a shared memory cache, and each of the processor units has access to the memory cache. In one embodiment, the method comprises providing the memory cache with a series of reservation registers, and storing in these registers addresses reserved in the memory cache for the processor units as a result of issuing load-reserve requests. In this embodiment, when one of the processor units makes a request to store data in the memory cache using a store-conditional request, the reservation registers are checked to determine if an address in the memory cache is reserved for that processor unit. If an address in the memory cache is reserved for that processor, the data are stored at this address.

97 MATHEMATICS AND COMPUTING↗

Collective network for computer structures

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices are included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to the needs of a processing algorithm.

97 MATHEMATICS AND COMPUTING↗

Simplifying and speeding the management of intra-node cache coherence

A method and apparatus for managing coherence between two processors of a two processor node of a multi-processor computer system. Generally the present invention relates to a software algorithm that simplifies and significantly speeds the management of cache coherence in a message passing parallel computer, and to hardware apparatus that assists this cache coherence algorithm. The software algorithm uses the opening and closing of put/get windows to coordinate the activated required to achieve cache coherence. The hardware apparatus may be an extension to the hardware address decode, that creates, in the physical memory address space of the node, an area of virtual memory that (a) does not actually exist, and (b) is therefore able to respond instantly to read and write requests from the processing elements.

97 MATHEMATICS AND COMPUTING↗

Managing coherence via put/get windows

A method and apparatus for managing coherence between two processors of a two processor node of a multi-processor computer system. Generally the present invention relates to a software algorithm that simplifies and significantly speeds the management of cache coherence in a message passing parallel computer, and to hardware apparatus that assists this cache coherence algorithm. The software algorithm uses the opening and closing of put/get windows to coordinate the activated required to achieve cache coherence. The hardware apparatus may be an extension to the hardware address decode, that creates, in the physical memory address space of the node, an area of virtual memory that (a) does not actually exist, and (b) is therefore able to respond instantly to read and write requests from the processing elements.

97 MATHEMATICS AND COMPUTING↗

Local rollback for fault-tolerance in parallel computing systems

A control logic device performs a local rollback in a parallel super computing system. The super computing system includes at least one cache memory device. The control logic device determines a local rollback interval. The control logic device runs at least one instruction in the local rollback interval. The control logic device evaluates whether an unrecoverable condition occurs while running the at least one instruction during the local rollback interval. The control logic device checks whether an error occurs during the local rollback. The control logic device restarts the local rollback interval if the error occurs and the unrecoverable condition does not occur during the local rollback interval.

97 MATHEMATICS AND COMPUTING↗

Collective network for computer structures

A system and method for enabling high-speed, low-latency global collective communications among interconnected processing nodes. The global collective network optimally enables collective reduction operations to be performed during parallel algorithm operations executing in a computer structure having a plurality of the interconnected processing nodes. Router devices ate included that interconnect the nodes of the network via links to facilitate performance of low-latency global processing operations at nodes of the virtual network and class structures. The global collective network may be configured to provide global barrier and interrupt functionality in asynchronous or synchronized manner. When implemented in a massively-parallel supercomputing structure, the global collective network is physically and logically partitionable according to needs of a processing algorithm.

97 MATHEMATICS AND COMPUTING↗

Programmable partitioning for high-performance coherence domains in a multiprocessor system

A multiprocessor computing system and a method of logically partitioning a multiprocessor computing system are disclosed. The multiprocessor computing system comprises a multitude of processing units, and a multitude of snoop units. Each of the processing units includes a local cache, and the snoop units are provided for supporting cache coherency in the multiprocessor system. Each of the snoop units is connected to a respective one of the processing units and to all of the other snoop units. The multiprocessor computing system further includes a partitioning system for using the snoop units to partition the multitude of processing units into a plurality of independent, memory-consistent, adjustable-size processing groups. Preferably, when the processor units are partitioned into these processing groups, the partitioning system also configures the snoop units to maintain cache coherency within each of said groups.

97 MATHEMATICS AND COMPUTING↗

Managing coherence via put/get windows

A method and apparatus for managing coherence between two processors of a two processor node of a multi-processor computer system. Generally the present invention relates to a software algorithm that simplifies and significantly speeds the management of cache coherence in a message passing parallel computer, and to hardware apparatus that assists this cache coherence algorithm. The software algorithm uses the opening and closing of put/get windows to coordinate the activated required to achieve cache coherence. The hardware apparatus may be an extension to the hardware address decode, that creates, in the physical memory address space of the node, an area of virtual memory that (a) does not actually exist, and (b) is therefore able to respond instantly to read and write requests from the processing elements.

97 MATHEMATICS AND COMPUTING↗

Method and apparatus for single-stepping coherence events in a multiprocessor system under software control

An apparatus and method are disclosed for single-stepping coherence events in a multiprocessor system under software control in order to monitor the behavior of a memory coherence mechanism. Single-stepping coherence events in a multiprocessor system is made possible by adding one or more step registers. By accessing these step registers, one or more coherence requests are processed by the multiprocessor system. The step registers determine if the snoop unit will operate by proceeding in a normal execution mode, or operate in a single-step mode.

Blumrich, Matthias A↗

Low latency memory access and synchronization

A low latency memory system access is provided in association with a weakly-ordered multiprocessor system. Bach processor in the multiprocessor shares resources, and each shared resource has an associated lock within a locking device that provides support for synchronization between the multiple processors in the multiprocessor and the orderly sharing of the resources. A processor only has permission to access a resource when it owns the lock associated with that resource, and an attempt by a processor to own a lock requires only a single load operation, rather than a traditional atomic load followed by store, such that the processor only performs a read operation and the hardware locking device performs a subsequent write operation rather than the processor. A simple prefetching for non-contiguous data structures is also disclosed. A memory line is redefined so that in addition to the normal physical memory data, every line includes a pointer that is large enough to point to any other line in the memory, wherein the pointers to determine which memory line to prefetch rather than some other predictive algorithm. This enables hardware to effectively prefetch memory access patterns that are non-contiguous, but repetitive.

Blumrich, Matthias A↗

System and method for programmable bank selection for banked memory subsystems

A programmable memory system and method for enabling one or more processor devices access to shared memory in a computing environment, the shared memory including one or more memory storage structures having addressable locations for storing data. The system comprises: one or more first logic devices associated with a respective one or more processor devices, each first logic device for receiving physical memory address signals and programmable for generating a respective memory storage structure select signal upon receipt of pre-determined address bit values at selected physical memory address bit locations; and, a second logic device responsive to each of the respective select signal for generating an address signal used for selecting a memory storage structure for processor access. The system thus enables each processor device of a computing environment memory storage access distributed across the one or more memory storage structures.

Blumrich, Matthias A↗

Multiple node remote messaging

A method for passing remote messages in a parallel computer system formed as a network of interconnected compute nodes includes that a first compute node (A) sends a single remote message to a remote second compute node (B) in order to control the remote second compute node (B) to send at least one remote message. The method includes various steps including controlling a DMA engine at first compute node (A) to prepare the single remote message to include a first message descriptor and at least one remote message descriptor for controlling the remote second compute node (B) to send at least one remote message, including putting the first message descriptor into an injection FIFO at the first compute node (A) and sending the single remote message and the at least one remote message descriptor to the second compute node (B).

Blumrich, Matthias A↗

Ultrascalable petaflop parallel supercomputer

A massively parallel supercomputer of petaOPS-scale includes node architectures based upon System-On-a-Chip technology, where each processing node comprises a single Application Specific Integrated Circuit (ASIC) having up to four processing elements. The ASIC nodes are interconnected by multiple independent networks that optimally maximize the throughput of packet communications between nodes with minimal latency. The multiple networks may include three high-speed networks for parallel algorithm message passing including a Torus, collective network, and a Global Asynchronous network that provides global barrier and notification functions. These multiple independent networks may be collaboratively or independently utilized according to the needs or phases of an algorithm for optimizing algorithm processing performance. The use of a DMA engine is provided to facilitate message passing among the nodes without the expenditure of processing resources at the node.

97 MATHEMATICS AND COMPUTING↗

Method and apparatus for granting processors access to a resource

An apparatus and method for granting one or more requesting entities access to a resource in a predetermined time interval. The apparatus includes a first circuit receiving one or more request signals, and implementing logic for assigning a priority to the one or more request signals, and, generating a set of first_request signals based on the priorities assigned. One or more priority select circuits for receiving the set of first_request signals and generating corresponding one or more fixed grant signals representing one or more highest priority request signals when asserted during the predetermined time interval. A second circuit device receives the one or more fixed grant signals generates one or more grant signals associated with one or more highest priority request signals assigned, the grant signals for enabling one or more respective requesting entities access to the resource in the predetermined time interval, wherein the priority assigned to the one or more request signals changes each successive predetermined time interval. In one embodiment, the assigned priority is based on a numerical pattern, the first circuit changing the numerical pattern with respect to the first_request signals generated at each successive predetermined time interval.

Blumrich, Matthias A↗

Optimized scalable network switch

In a massively parallel computing system having a plurality of nodes configured in m multi-dimensions, each node including a computing device, a method for routing packets towards their destination nodes is provided which includes generating at least one of a 2m plurality of compact bit vectors containing information derived from downstream nodes. A multilevel arbitration process in which downstream information stored in the compact vectors, such as link status information and fullness of downstream buffers, is used to determine a preferred direction and virtual channel for packet transmission. Preferred direction ranges are encoded and virtual channels are selected by examining the plurality of compact bit vectors. This dynamic routing method eliminates the necessity of routing tables, thus enhancing scalability of the switch.

Blumrich, Matthias A↗

Insertion of coherence requests for debugging a multiprocessor

A method and system are disclosed to insert coherence events in a multiprocessor computer system, and to present those coherence events to the processors of the multiprocessor computer system for analysis and debugging purposes. The coherence events are inserted in the computer system by adding one or more special insert registers. By writing into the insert registers, coherence events are inserted in the multiprocessor system as if they were generated by the normal coherence protocol. Once these coherence events are processed, the processing of coherence events can continue in the normal operation mode.

Blumrich, Matthias A↗

Class network routing

Class network routing is implemented in a network such as a computer network comprising a plurality of parallel compute processors at nodes thereof. Class network routing allows a compute processor to broadcast a message to a range (one or more) of other compute processors in the computer network, such as processors in a column or a row. Normally this type of operation requires a separate message to be sent to each processor. With class network routing pursuant to the invention, a single message is sufficient, which generally reduces the total number of messages in the network as well as the latency to do a broadcast. Class network routing is also applied to dense matrix inversion algorithms on distributed memory parallel supercomputers with hardware class function (multicast) capability. This is achieved by exploiting the fact that the communication patterns of dense matrix inversion can be served by hardware class functions, which results in faster execution times.

97 MATHEMATICS AND COMPUTING↗

Method for prefetching non-contiguous data structures

A low latency memory system access is provided in association with a weakly-ordered multiprocessor system. Each processor in the multiprocessor shares resources, and each shared resource has an associated lock within a locking device that provides support for synchronization between the multiple processors in the multiprocessor and the orderly sharing of the resources. A processor only has permission to access a resource when it owns the lock associated with that resource, and an attempt by a processor to own a lock requires only a single load operation, rather than a traditional atomic load followed by store, such that the processor only performs a read operation and the hardware locking device performs a subsequent write operation rather than the processor. A simple perfecting for non-contiguous data structures is also disclosed. A memory line is redefined so that in addition to the normal physical memory data, every line includes a pointer that is large enough to point to any other line in the memory, wherein the pointers to determine which memory line to prefect rather than some other predictive algorithm. This enables hardware to effectively prefect memory access patterns that are non-contiguous, but repetitive.

97 MATHEMATICS AND COMPUTING↗