摘要:
A Planar Memory Module (PAMM) device comprising a generally planar card comprising a first side and a second side, the first side having a plurality of couplings and the second side having a plurality of connectors, a plurality of memory devices coupled to the card via a first portion of the plurality of couplings, and at least one hub chip coupled to the card via a second portion of the plurality of couplings. Each of the plurality of couplings is connected to an associated one of the plurality of connectors.
摘要:
LGA connectors are fabricated with buttons or spring contacts preformed to different heights to accommodate the initial topography of a typical module or PCB of a particular product type. This is accomplished during fabrication by measuring topographies of mating surfaces of a first electronic device and of a second electronic device; fabricating interposer contacts to form opposing non-planar sides having respective inverse topographies for contacting the mating surfaces; and sandwiching the interposer between the first and second electronic devices with the opposing sides in contact with respective mating surfaces. For those LGA types made by molding techniques such as the metal-in-polymer type (eg. Tyco Electronics MPI, or Shin Etsu RP) or the Metal-on-Elastomer type (IBM), using molds with the desired topography provides the desired LGA topography. For those LGAs made of metal springs, cantilevers, armatures and the like, the desired topography is imposed by shaping of the buttons during or after fabrication using a sizing die with the desired topography.
摘要:
A 3D chip having at least one I/O layer connected to other 3D chip layers by a vertical bus such that the I/O layer(s) may accommodate protection and off-chip device drive circuits, customization circuits, translation circuits, conversions circuits and/or built-in self-test circuits capable of comprehensive chip or wafer level testing wherein the I/O layers function as a testhead. Substitution of I/O circuits or structures may be performed using E-fuses or the like responsive to such testing.
摘要:
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 2 m 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.
摘要:
A design structure comprising an integrated circuit architecture, circuit structure, and/or instructions for fabrication thereof. The circuit structure includes at least one logic device layer and at least two additional separate memory array layers. Each of the logic device layer and the at least two memory array layers is independently optimized for a particular type of logic device or memory device disposed therein. Preferably also disposed within the logic device layer are array sense amplifiers, memory array output drivers and like higher performance circuitry otherwise generally disposed within memory array layer substrates. All layers may be independently powered to provide additional performance enhancement.
摘要:
A Planar Memory Module (PAMM) device comprising a generally planar card comprising a first side and a second side, the first side having a plurality of couplings and the second side having a plurality of connectors, a plurality of memory devices coupled to the card via a first portion of the plurality of couplings, and at least one hub chip coupled to the card via a second portion of the plurality of couplings. Each of the plurality of couplings is connected to an associated one of the plurality of connectors.
摘要:
A method and system for providing indeterminate read data latency in a memory system. The method includes determining if a local data packet has been received. If a local data packet has been received, then the local data packet is stored into a buffer device. The method also includes determining if the buffer device contains a data packet and determining if an upstream driver for transmitting data packets to a memory controller via an upstream channel is idle. If the buffer contains a data packet and the upstream driver is idle, then the data packet is transmitted to the upstream driver. The method further includes determining if an upstream data packet has been received. The upstream data packet is in a frame format that includes a frame start indicator and an identification tag for use by the memory controller in associating the upstream data packet with its corresponding read instruction. If an upstream data packet has been received and the upstream driver is not idle, then the upstream data packet is stored into the buffer device. If an upstream data packet has been received and the buffer device does not contain a data packet and the upstream driver is idle, then the upstream data packet is transmitted to the upstream driver. If the upstream driver is not idle, then any data packets in progress are continued being transmitted to the upstream driver.
摘要:
The present invention concerns methods and apparatus for performing fault isolation in multiple node computing systems using commutative error detection values—for example, checksums—to identify and to isolate faulty nodes. In the present invention nodes forming the multiple node computing system are networked together and during program execution communicate with one another by transmitting information through the network. When information associated with a reproducible portion of a computer program is injected into the network by a node, a commutative error detection value is calculated and stored in commutative error detection apparatus associated with the node. At intervals, node fault detection apparatus associated with the multiple node computer system retrieve commutative error detection values saved in the commutative error detection apparatus associated with the node and stores them in memory. When the computer program is executed again by the multiple node computer system, new commutative error detection values are created; the node fault detection apparatus retrieves them and stores them in memory. The node fault detection apparatus identifies faulty nodes by comparing commutative error detection values associated with reproducible portions of the application program generated by a particular node from different runs of the application program. Differences in commutative error detection values indicate that the node may be faulty.
摘要:
A selectable function is provided that permits the impedance of an output driver or an addressable memory device to be configured without adding extra signal connections. The output driver impedance control function of the invention is achieved through the use of the data bus of a memory array for control. The data lines thus serve two purposes one for normal use and the other for control of the impedance. In the invention, the output impedance of each DRAM in a subassembly array that drives a common data bus is individually separately adjusted.
摘要:
A method and apparatus are disclosed for communicating between a master and slave device. A sequence of data sets and a clock signal (“Bus clock”) are sent from the master to the slave, wherein the successive sets are asserted by the master at a certain frequency, each set being asserted for a certain time interval. The data and Bus clock are received by the slave, including capturing the data by the slave, responsive to the received Bus clock. The slave generates, from the received Bus clock, a clock (“Local clock”) for clocking operations on the slave. The sequence of the received data sets is held in a sequence of latches in the slave, each set being held for a time interval that is longer than the certain time interval for which the set was asserted by the master. The data sets are read in their respective sequence from the latches, responsive to the Local clock, so that the holding of respective data sets for the relatively longer time intervals in multiple latches and the reading of the data in sequence increases allowable skew of the Local clock relative to the received Bus clock.