Engineering Papers⌕ Search

Engineering topics

Chen, Dong

Publications and source records attributed to Chen, Dong.

At least 109 records · Page 6

Optimized collectives using a DMA on a parallel computer

Optimizing collective operations using direct memory access controller on a parallel computer, in one aspect, may comprise establishing a byte counter associated with a direct memory access controller for each submessage in a message. The byte counter includes at least a base address of memory and a byte count associated with a submessage. A byte counter associated with a submessage is monitored to determine whether at least a block of data of the submessage has been received. The block of data has a predetermined size, for example, a number of bytes. The block is processed when the block has been fully received, for example, when the byte count indicates all bytes of the block have been received. The monitoring and processing may continue for all blocks in all submessages in the message.

97 MATHEMATICS AND COMPUTING↗

Support for non-locking parallel reception of packets belonging to a single memory reception FIFO

A method and apparatus for distributed parallel messaging in a parallel computing system. A plurality of DMA engine units are configured in a multiprocessor system to operate in parallel, one DMA engine unit for transferring a current packet received at a network reception queue to a memory location in a memory FIFO (rmFIFO) region of a memory. A control unit implements logic to determine whether any prior received packet destined for that rmFIFO is still in a process of being stored in the associated memory by another DMA engine unit of the plurality, and prevent the one DMA engine unit from indicating completion of storing the current received packet in the reception memory FIFO (rmFIFO) until all prior received packets destined for that rmFIFO are completely stored by the other DMA engine units. Thus, there is provided non-locking support so that multiple packets destined for a single rmFIFO are transferred and stored in parallel to predetermined locations in a memory.

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↗

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↗

DMA engine for repeating communication patterns

A parallel computer system is constructed as a network of interconnected compute nodes to operate a global message-passing application for performing communications across the network. Each of the compute nodes includes one or more individual processors with memories which run local instances of the global message-passing application operating at each compute node to carry out local processing operations independent of processing operations carried out at other compute nodes. Each compute node also includes a DMA engine constructed to interact with the application via Injection FIFO Metadata describing multiple Injection FIFOs where each Injection FIFO may containing an arbitrary number of message descriptors in order to process messages with a fixed processing overhead irrespective of the number of message descriptors included in the Injection FIFO.

Chen, Dong↗

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↗

Direct memory access transfer completion notification

Methods, compute nodes, and computer program products are provided for direct memory access (`DMA`) transfer completion notification. Embodiments include determining, by an origin DMA engine on an origin compute node, whether a data descriptor for an application message to be sent to a target compute node is currently in an injection first-in-first-out (`FIFO`) buffer in dependence upon a sequence number previously associated with the data descriptor, the total number of descriptors currently in the injection FIFO buffer, and the current sequence number for the newest data descriptor stored in the injection FIFO buffer; and notifying a processor core on the origin DMA engine that the message has been sent if the data descriptor for the message is not currently in the injection FIFO buffer.

Chen, Dong↗

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↗

Energy Dissipation and Defect Generation for Nanocrystalline Silicon Carbide

Large-scale molecular dynamics simulations have been employed to study defect generation and primary damage state in nano crystalline (NC) SiC of average grain diameters from 5 to 21 nm. Primary knock-on atom (PKA) kinetic energies of 10 keV are simulated, and cascade structures in NC SiC with a grain size smaller than 12 nm are generally different from those generated in single crystalline SiC. It is found that the local stresses near the grain boundaries (GBs) strongly affect the behavior of the PKA and secondary recoil atoms (SRAs), and the GBs act as sinks for deposition of kinetic energy. A striking feature is that the PKA and SRAs preferentially deposit energy along the GBs for grains with average size less 12 nm, which results in atomic displacements primarily within the GBs; whereas for larger grain sizes, most defects are produced within the grains. There exists a crossover in defect production, which is manifested in switching from grain boundary damage to grain damage. The most common defects created in NC SiC are antisite defects, following by vacancies and interstitials, in contrast to those produced in a single crystalline SiC, where the dominate defects are Frenkel pairs. Defect production efficiency increases with increasing the grain size, with a typical value of 0.18 for small grains and rising to 0.5 for larger grains.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Bad data packet capture device

An apparatus and method for capturing data packets for analysis on a network computing system includes a sending node and a receiving node connected by a bi-directional communication link. The sending node sends a data transmission to the receiving node on the bi-directional communication link, and the receiving node receives the data transmission and verifies the data transmission to determine valid data and invalid data and verify retransmissions of invalid data as corresponding valid data. A memory device communicates with the receiving node for storing the invalid data and the corresponding valid data. A computing node communicates with the memory device and receives and performs an analysis of the invalid data and the corresponding valid data received from the memory device.

97 MATHEMATICS AND COMPUTING↗

DMA shared byte counters in a parallel computer

A parallel computer system is constructed as a network of interconnected compute nodes. Each of the compute nodes includes at least one processor, a memory and a DMA engine. The DMA engine includes a processor interface for interfacing with the at least one processor, DMA logic, a memory interface for interfacing with the memory, a DMA network interface for interfacing with the network, injection and reception byte counters, injection and reception FIFO metadata, and status registers and control registers. The injection FIFOs maintain memory locations of the injection FIFO metadata memory locations including its current head and tail, and the reception FIFOs maintain the reception FIFO metadata memory locations including its current head and tail. The injection byte counters and reception byte counters may be shared between messages.

97 MATHEMATICS AND COMPUTING↗

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↗

Migration of Cr-Vacancy Clusters and Interstitial Cr in Alpha-Fe using the Dimer Method

The migration mechanisms and the corresponding activation energies of Cr-vacancy (Cr-V) clusters and Cr interstitials in α-Fe have been investigated using the dimer and the nudged elastic band methods. Dimer searches are employed to find the possible transition states of these defects, and the lowest energy paths are used to determine the energy barriers for migration. A substitutional Cr atom can migrate to a nearest neighbor vacancy through an energy barrier of 0.56 eV, but this simple mechanism alone is unlikely to lead to the long-distance migration of Cr unless there is a supersaturated concentration of vacancies in the system. The Cr-vacancy clusters can lead to long-distance migration of a Cr atom that is accomplished by Fe and Cr atoms successively jumping to nearest neighbor vacancy positions, defined as a self-vacancy-assisted migration mechanism, with the migration energies ranging from 0.64 to 0.89 eV. In addition, a mixed Cr-Fe dumbbell interstitial can easily migrate through Fe lattices, with the migration energy barrier of 0.17, which is lower than that of the Fe-Fe interstitial. The on-site rotation of the Cr-Fe interstitial and Cr atom hopping from one site to another are believed to comprise the dominant migration mechanism. The calculated binding energies of Cr-V clusters are strongly dependent on the size of clusters and the concentration of Cr atoms in clusters.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Global tree network for computing structures enabling global processing operations

A system and method for enabling high-speed, low-latency global tree network communications among processing nodes interconnected according to a tree network structure. The global tree network 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 tree via links to facilitate performance of low-latency global processing operations at nodes of the virtual tree and sub-tree structures. The global operations performed include one or more of: broadcast operations downstream from a root node to leaf nodes of a virtual tree, reduction operations upstream from leaf nodes to the root node in the virtual tree, and point-to-point message passing from any node to the root node. The global tree network is configurable to provide global barrier and interrupt functionality in asynchronous or synchronized manner, and, is physically and logically partitionable.

Blumrich↗

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↗

Diffusion of tungsten clusters on tungsten (110) surface

Using molecular dynamics simulation and modified analytic embedded-atom method, we have investigated the self-diffusion of clusters on a tungsten (110) surface. As compared to the linear-chain configuration, the close-packed islands for tungsten clusters containing more than nine adatoms have been predicted to be more stable with the relatively lower binding energies. The migration energies show an interesting and oscillating behavior with increasing cluster size. The tetramer, hexamer and octamer have obviously higher migration energies than the others. The different atomic configurations and diffusion mechanisms have been determined during the diffusion processes. It is clear that the dimer-shearing mechanism occurs inside the hexamer, while it occurs at the periphery of heptamer. The successive hopping mechanism of individual atom is of critical importance in the migration of the clusters containing five or fewer adatoms. In addition, the diffusion of a cluster with nine adatoms is achieved through the changes of the cluster shape.

36 MATERIALS SCIENCE↗