Abstract: According to one embodiment, a memory system includes a first chip and a second chip. The second chip is bonded with the first chip. The memory system includes a semiconductor memory device and a memory controller. The semiconductor memory device includes a memory cell array, a peripheral circuit, and an input/output module. The memory controller is configured to receive an instruction from an external host device and control the semiconductor memory device via the input/output module. The first chip includes the memory cell array. The second chip includes the peripheral circuit, the input/output module, and the memory controller.

Abstract: Methods, systems, and devices for edgeless memory clusters are described. Systems, devices, and techniques are described for eliminating gaps between clusters by creating groups (e.g., domains) of clusters that are active at a given time, and using drivers within inactive clusters to perform array termination functions for abutting active clusters. Tiles on the edges of a cluster may have drivers that operate both for the cluster, and for a neighboring cluster, with circuits (e.g., a multiplexers) on the drivers to enable operations for both clusters.

Abstract: An SoC maintains the full flexibility of a general-purpose microprocessor while providing energy efficiency similar to an ASIC by implementing software-controlled virtual hardware architectures that enable the SoC to function as a virtual ASIC. The SoC comprises a plurality of “Stella” Reconfigurable Multiprocessors (SRMs) supported by a Network-on-a-Chip that provides efficient data transfer during program execution. A hierarchy of programmable switches interconnects the programmable elements of each of the SRMs at different levels to form their virtual architectures. Arithmetic, data flow, and interconnect operations are also rendered programmable. An architecture index” points to a storage location where pre-determined hardware architectures are stored and extracted during program execution. The programmed architectures are able to mimic ASIC properties such as variable computation types, bit-resolutions, data flows, and amount and proportions of compute and data flow operations and sizes.

Abstract: Systems and methods of propagating data within an integrated circuit includes: identifying a coarse data propagation path for distinct subsets of data of an input dataset that includes: setting inter-core data movements for the distinct subsets of data, the inter-core data movements defining a predetermined propagation of a given subset of data between two or more of a plurality of cores of an integrated circuit array of the integrated circuit; identifying a granular data propagation path for each distinct subset of data that includes: setting intra-core data movements for each distinct subset of data, the intra-core data movements defining a predetermined propagation of the given subset of data within one or more of the plurality of cores of the integrated circuit array of the integrated circuit; enabling a flow of the input dataset within the integrated circuit based on the coarse data propagation path and the granular propagation path.

Abstract: A tile including circuitry for use with machine learning models, the tile including: a first computational array of cells, in which the computational array of cells is a sub-array of a larger second computational array of cells; local memory coupled to the first computational array of cells; and multiple controllable bus lines, in which a first subset of the multiple controllable bus lines include multiple general purpose controllable bus lines couplable to the local memory.

Abstract: To program a first programmable gate array, for example a first FPGA, in a distributed computer system, a configuration of a first configuration logic on the first programmable gate array is provided. The first configuration logic is configured to receive a first user bitstream from a configuration software for configuring a first user logic on the first programmable gate array and to store the first user bitstream on a non-volatile memory of the first programmable gate array for the purpose of subsequently configuring a first user logic on the first programmable gate array according to the specifications from the first user bitstream. In an expansion stage of the invention, a configuration of a programming logic on the first programmable gate array is also provided for programming a second programmable gate array, which is connected to the first programmable gate array to form a daisy chain.

Abstract: A method is described for identifying communication-ready data bus subscribers connected to a local bus. The method comprises receiving, at a local bus master, at least one data packet transmitted via the local bus, wherein the at least one data packet received at the local bus master comprises an address of a communication-ready data bus subscriber among a plurality of communication-ready data bus subscribers in the local bus, wherein the communication-ready data bus subscriber is in a sequence of communication-ready data bus subscribers, and mapping of the received address by the local bus master to a relative position of the communication-ready data bus subscriber in the sequence of communication-ready data bus subscribers in the local bus. In addition, a local bus master of the local bus is described.

Abstract: A method for executing program components on a control unit includes receiving a first program unit and a second program unit; producing a first proxy definition and a second proxy definition, wherein a proxy definition stipulates access to at least one function and/or a memory area of a program unit, wherein the first proxy definition is associated with the first program unit and the second proxy definition is associated with the second program unit; compiling the first program unit and the second program unit to produce a first program component, a second program component, a first proxy component and a second proxy component; and executing the first program component and the second program component on a control unit, wherein the first program component calls and/or uses at least one function of the second program component by using the first proxy component and the second proxy component.

Abstract: A device architecture includes a spatially reconfigurable array of processors, such as configurable units of a CGRA, having spare elements, and a parameter store on the device which stores parameters that tag one or more elements as unusable. Technologies are described which change the pattern of placement of configuration data, in dependence on the tagged elements. As a result, a spatially reconfigurable array having unusable elements can be repaired.

Abstract: A processor includes: a memory; an execution pipeline having a plurality of pipeline stages for executing an operation on data provided to the execution pipeline and storing a result of the operation into the memory; a receive pipeline having a plurality of pipeline stages for handling incoming data to the processor and storing the incoming data into memory; context status storage for holding an exception indicator of an exception encountered by the receive pipeline whilst it is handling incoming data; the receive pipeline being configured to determine that an exception has been encountered in one of its pipeline stages and to delay committing the exception indicator to the context status storage until a final one of its pipeline stages and to continue to receive and store incoming data into the memory until the exception indicator has been committed.

Abstract: Fault injection testing for field programmable gate array (FPGA) devices including: interfacing with a FPGA device under test (DUT); imaging a configuration RAM (CRAM) of the FPGA DUT with a first configuration image to define a first operational function of the FPGA DUT where the CRAM includes a plurality of CRAM bits, injecting a plurality of single event upsets into a portion of the plurality of the CRAM bits while the FPGA DUT is operating; concurrently monitoring operations of the FPGA DUT and a reference FPGA device; comparing outputs of the FPGA DUT with outputs of the reference FPGA device during concurrent operations, and if there is a mismatch between the outputs of the FPGA DUT and the reference FPGA, determining that error events have occurred within the FPGA DUT; and storing the error events and CRAM location data associated with corresponding single event upsets in an error log.

Abstract: Illustrative embodiments provide a mixed programmable and application-specific integrated circuit, a method of using the mixed programmable and application-specific integrated circuit and a method of making the mixed programmable and application-specific integrated circuit. The mixed programmable and application-specific integrated circuit includes at least a portion of a programmable transistor array that is programed after fabrication. The programmable transistor array can include at least another portion that is mask programed during fabrication.

Abstract: Switchboxes are especially used in integrated circuits with programmable logic (e.g. FPGAs). They are used to establish configurable signal paths between logic blocks. It is especially important to use an efficient structure, i.e. a structure whose chip area is as small as possible and which is able to realize short and fast signal paths. The task of the present invention is to significantly reduce the effort for the interconnection structures while still maintaining good routeability. This is achieved by the fact that there is no longer a switchbox (SB) on each coordinate position. It is particularly advantageous to arrange the SBs in a chessboard-like manner and also to use two SBs of different sizes which are arranged in a superordinate chessboard structure.

Abstract: An integrated circuit device may cache configuration data to enable rapid configuration from fabric cache memory. The integrated circuit device may include programmable logic fabric having configuration memory and programmable logic elements controlled by the configuration memory, and sector-aligned memory apart from the programmable logic fabric. A first sector of the configuration memory may be programmed with first configuration data. The sector-aligned memory may include a first sector of sector-aligned memory that may cache the first configuration data while the configuration memory is programmed with the first configuration data a first time. A second sector of sector-aligned memory may cache second configuration data for a second sector of the configuration memory in parallel while the first sector of sector-aligned memory caches the first configuration data for the first sector of the configuration memory.

Abstract: Methods and apparatus for implementing a bus in a resource constrained system. In embodiments, a first FPGA is to a parallel bus and a second FPGA is connected to the first FPGA via a serial interface but not the parallel bus. The first FPGA processes a transaction request, which has a parallel bus protocol format, to the second FPGA by an initiator and converts the transaction request to the second FPGA into a transaction on the serial interface between the first and second FPGAs. The first FPGA responds to the initiator via the parallel bus indicating that the transaction request in the format for the parallel bus to the second FPGA is complete.

Abstract: A reconfigurable logic circuit comprises first, second and third switching circuits arranged for receiving first, second and third input bits, respectively, and each arranged for being configured in a mode wherein the corresponding input bit is passed on or in a mode; a first exclusive OR logic block operable on the outputs of the first, second and third switching circuits and arranged to output a sum bit; fourth, fifth and sixth switching circuits arranged for receiving a fourth, fifth and sixth input bits and arranged for being configured in a mode; first, second and third AND logic blocks, each arranged for receiving a different pair of the outputs of certain switching circuits; a second exclusive OR logic block operable on the outputs of certain AND logic blocks and arranged to produce a carry output bit.

Abstract: Systems and methods are provided to enable parallelized multiply-accumulate operations in a systolic array. Each row of the systolic array can include multiple busses enabling independent transmission of inputs along the respective bus. Each processing element of a given row-oriented bus can receive an input from a prior element of the given row-oriented bus, and perform arithmetic operations on the input. Each processing element can generate an output partial sum based on the arithmetic operations, provide the input to a next processing element of the given row-oriented bus, without the input being processed by a processing element of the row located between the two processing elements that uses a different row-oriented bus. Use of row-oriented busses can enable parallelization to increase speed or enable increased latency at individual processing elements.

Abstract: A tile of an FPGA provides memory, arithmetic functions, or both. Connections directly between multiple instances of the tile are available, allowing multiple tiles to be treated as larger memories or arithmetic circuits. By using these connections, referred to as cascade inputs and outputs, the input and output bandwidth of the arithmetic and memory circuits are increased, operand sizes are increased, or both. By using the cascade connections, multiple tiles can be used together as a single, larger tile. Thus, implementations that need memories of different sizes, arithmetic functions operating on different sized operands, or both, can use the same FPGA without additional programming or waste. Using cascade communications, more tiles are used when a large memory is needed and fewer tiles are used when a small memory is needed and the waste is avoided.

Abstract: An integrated circuit device may include programmable logic fabric on a first integrated circuit die and sector-aligned memory on a second integrated circuit die to enable large amounts of data to be rapidly processed by a sector of programmable logic of the programmable logic device. The programmable logic fabric may include a first and second sectors. The first sector may be programmed with a circuit design that operates on a first set of data. The sector-aligned memory may include a first sector of sector-aligned memory directly accessible by the first sector of programmable logic fabric and a second sector of sector-aligned memory directly accessible by the second sector of programmable logic fabric. The first sector of sector-aligned memory may store the first set of data.

Abstract: Some embodiments include constructions having electrically conductive bitlines within a stack of alternating electrically conductive wordline levels and electrically insulative levels. Cavities extend into the electrically conductive wordline levels, and phase change material is within the cavities. Some embodiments include methods of forming memory. An opening is formed through a stack of alternating electrically conductive levels and electrically insulative levels. Cavities are extended into the electrically conductive levels along the opening. Phase change material is formed within the cavities, and incorporated into vertically-stacked memory cells. An electrically conductive interconnect is formed within the opening, and is electrically coupled with a plurality of the vertically-stacked memory cells.

Abstract: A test apparatus for testing electrical parameters of a target chip includes: a function generator; a switch matrix module; a plurality of source measurement units (SMUs); at least one of the SMUs is configured to provide power supply for the target chip; at least one of the SMUs is coupled to the switch matrix module; and at least two of said SMUs are test SMUs coupled to ports of the target chip and the function generator.

Abstract: A reconfigurable data processor comprises a bus system, and an array of configurable units connected to the bus system, configurable units in the array including configuration data stores to store unit files comprising a plurality of sub-files of configuration data particular to the corresponding configurable units. Configurable units in the plurality of configurable units each include logic to execute a unit configuration load process, including receiving via the bus system, sub-files of a unit file particular to the configurable unit, and loading the received sub-files into the configuration store of the configurable unit. A configuration load controller connected to the bus system, including logic to execute an array configuration load process, including distributing a configuration file comprising unit files for a plurality of the configurable units in the array.

Abstract: A memory device includes a first plane defined in a second wafer stacked on a first wafer; a second plane defined in a third wafer stacked on the second wafer, and overlapping with the first plane in a vertical direction; a first page buffer circuit including a first column driver coupled to bit lines of the first plane and a first column operator; and a second page buffer circuit including a second column driver coupled to bit lines of the second plane and a second column operator. The first column driver is disposed in the second wafer, the second column driver is disposed in the third wafer and overlaps with the first column driver in the vertical direction, and the first and second column operators are disposed in a cell region of the first wafer and overlap with the first and second planes in the vertical direction.

Abstract: A method of configuring a programmable integrated circuit device. A channel source within the virtual fabric is configured to receive input data from a first kernel outside of the virtual fabric and on the programmable integrated circuit device, and a channel sink within the virtual fabric is configured to transmit output data to the first kernel. The configuring of the channel source is modified such that the channel source receives input data from a second kernel in response to detecting a change in operation of the programmable integrated circuit device.

Abstract: By querying a set of fabrics to determine an initiator logged into a fabric in the set of fabrics, a set of accessible fabrics is discovered, an accessible fabric in the set of accessible fabrics accessible to the initiator, an initiator comprising a transceiver connecting a server to a switch, a fabric in the set of fabrics comprising a switch connecting a server to a storage device, the storage device comprising a storage volume. Using a fabric usage policy, a set of allowed fabrics within the set of accessible fabrics is determined. Using the set of allowed fabrics, a storage volume is mapped to a server, the mapping enabling the server to access the storage volume via a fabric in the set of allowed fabrics.

Abstract: Secure updating of programmable integrated circuits includes receiving, within the programmable integrated circuit, a configuration bitstream, inserting, using a processor of the programmable integrated circuit, a key into the configuration bitstream resulting in a modified configuration bitstream, encrypting, using the programmable integrated circuit, the modified configuration bitstream using the key resulting in an encrypted configuration bitstream, and storing the encrypted configuration bitstream in a boot memory for the programmable integrated circuit.

Abstract: A 3D semiconductor device, including: a first level including a single crystal layer, a plurality of first transistors, and a first metal layer, forming memory control circuits; a second level overlaying the single crystal layer, and including a plurality of second transistors and a plurality of first memory cells; a third level overlaying the second level, and including a plurality of third transistors and a plurality of second memory cells; where the second transistors are aligned to the first transistors with less than 40 nm alignment error, where the memory cells include a NAND non-volatile memory type, where some of the memory control circuits can control at least one of the memory cells, and where some of the memory control circuits are designed to perform a verify read after a write pulse so to detect if the at least one of the memory cells has been successfully written.

Abstract: Examples described herein generally relate to a Peripheral Connect Interconnect Express (PCIe) device. An example is a non-transitory memory storing a representation of a design that is to be implemented on a programmable integrated circuit. The design includes a classifier module (CM), a message trap engine module (MTEM), and a configuration space. The CM is capable of receiving a PCIe message and is configured to determine whether the PCIe message is a PCIe Type 1 configuration transaction. The CM is configured to forward the PCIe message to an endpoint device and to the MTEM when the PCIe message is a non-PCIe Type 1 configuration transaction and the PCIe Type 1 configuration transaction, respectively. The MTEM is configured to virtualize a downstream port(s) of a virtual switch and maintain the configuration space. The MTEM is capable of accessing the configuration space in response to the PCIe message.

Abstract: An expandable logic scheme based on a chip package, includes: an interconnection substrate comprising a set of data buses for use in an expandable interconnection scheme, wherein the set of data buses is divided into a plurality of data bus subsets; and a first field-programmable-gate-array (FPGA) integrated-circuit (IC) chip comprising a plurality of first I/O ports coupling to the set of data buses and at least one first I/O-port selection pad configured to select a first port from the plurality of first I/O ports in a first clock cycle to pass a first data between a first data bus subset of the plurality of data bus subsets and the first field-programmable-gate-array (FPGA) integrated-circuit (IC) chip.

Abstract: A method for mapping a Boolean function to a configurable logic block (CLB). The CLB includes a first plurality of programmable logic cells (PLCs). The Boolean function includes a plurality of digits. Each of the plurality of digits includes a respective hexadecimal value. The method includes mapping the Boolean function to a first PLC of the first plurality of PLCs responsive to the plurality of digits satisfying a first condition. In an exemplary embodiment, the first condition includes at least two digits of the plurality of digits being different and each of the plurality of digits including one of a first hexadecimal digit, a second hexadecimal digit different from the first hexadecimal digit, a bitwise complement of the first hexadecimal digit, and a bitwise complement of the second hexadecimal digit.

Abstract: Embodiments detailed herein relate to matrix (tile) operations. For example, decode circuitry to decode an instruction having fields for an opcode and a memory address; and execution circuitry to execute the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers are discussed.

Abstract: An image acceleration processing device including a field programmable gate array (FPGA) processing platform; and a personal computer (PC). The FPGA processing platform includes: a first fiber interface configured to receive configuration parameters and test commands, and to output test results; a second fiber interface configured to exchange data with the PC; a third fiber interface configured to receive image data and output the configuration parameters and the test commands; a fourth fiber interface configured to control the generation of a screen lighting signal; and a fifth fiber interface configured to control an input/output (IO) light source.

Abstract: A decoder in an integrated circuit memory device having: a positive section having a first input line; a negative section having a second input line; and an output line connected from both the positive section and the negative section to a voltage driver connected to a memory cell. The positive section and the negative sections are controlled by a polarity control signal. When the polarity control signal indicates positive polarity, the positive section drives the output line according to signals received in the first input line; and when the polarity control signal indicates negative polarity, the negative section drives the output line according to signals received in the second input line.

Abstract: A processor including a memory controller for interfacing an external memory and a programmable functional unit (PFU). The PFU is programmed by a PFU program to modify operation of the memory controller, in which the PFU includes programmable logic elements and programmable interconnectors. For example, the PFU is programmed by the PFU program to add a function or otherwise to modify an existing function of the memory controller enhance its functionality during operation of the processor. In this manner, the functionality and/or operation of the memory controller is not fixed once the processor is manufactured, but instead the memory controller may be modified after manufacture to improve efficiency and/or enhance performance of the processor, such as when executing a corresponding process.

Abstract: A 3D semiconductor device, the device including: a first level including a first single crystal layer and first transistors, where the first transistors each include a single crystal channel; first metal layers interconnecting at least the first transistors; and a second level including a second single crystal layer and second transistors, where the second level overlays the first level, where the second transistors are horizontally oriented and include replacement gate, where the second level is bonded to the first level, and where the bonded includes oxide to oxide bonds.

Abstract: A device includes a platform implemented, at least in part, in a static region of programmable circuitry and a dynamic region of programmable circuitry configured to implement user-specified circuitry in communication with the platform. The platform is configured to establish and maintain a first communication link with a host data processing system and a second communication link with a network while at least a portion of the dynamic region of programmable circuitry is dynamically reconfigured.

Abstract: A secure one-way network gateway for transmitting data from a source network to a destination network is disclosed. An input circuit is for coupling to a source network and an output circuit is for coupling to an output network. A memory stores configuration data. Either a single field-programmable device or a pair of field-programmable devices coupled via a one-way link are inserted between the input circuit and the output circuit. The configuration data is loaded into the device(s) to program the device(s) to pass data from the input circuit to the output circuit, to optionally filter the data, and to prevent any data from passing from the output circuit to the input circuit. A processor is coupled to only the memory and a separate management interface. The processor receives updated configuration data via the management interface and replaces the configuration data in the memory with the updated configuration memory.

Abstract: Systems and methods provide an extensible, multi-stage, realtime application program processing load adaptive, manycore data processing architecture shared dynamically among instances of parallelized and pipelined application software programs, according to processing load variations of said programs and their tasks and instances, as well as contractual policies. The invented techniques provide, at the same time, both application software development productivity, through presenting for software a simple, virtual static view of the actually dynamically allocated and assigned processing hardware resources, together with high program runtime performance, through scalable pipelined and parallelized program execution with minimized overhead, as well as high resource efficiency, through adaptively optimized processing resource allocation.

Abstract: A microcontroller has a central processing unit, memory, I/O ports and a plurality of peripheral units, wherein one of the peripheral units is a configurable logic cell. The configurable logic cell is formed by a look-up table formed by a plurality of memory cells receiving a predefined number of input address signals selectable from internal signals provided by the peripheral units and at least one external signal provided by at least one external pin and generating an output signal. The central processing unit is configured to directly provide input address signals for the look-up table.

Abstract: Techniques are described herein for a reconfigurable memory device that is configurable based on the type of interposer used to couple the memory device with a host device. The reconfigurable memory device may include a plurality components for a plurality of configurations. Various components of the reconfigurable memory die may be activated/deactivated based on what type of interposer is used in the memory device. For example, if a first type of interposer is used (e.g., a high-density interposer), the data channel may be eight data pins wide. In contrast, if second type of interposer is used (e.g., an organic-based interposer), the data channel may be four data pins wide. As such, a reconfigurable memory device may include data pins and related drivers that are inactive in some configurations.

Abstract: Methods, systems, and apparatus, including a system that includes a first integrated circuit chip configured to store application logic for one or more executable applications; and a second integrated circuit chip communicatively coupled to the first integrated circuit chip, the second integrated circuit chip including an instruction decoder configured to decode instructions for executing the one or more executable applications; and a communication interface configured to transmit the decoded instructions to the first integrated circuit chip to execute the one or more executable applications on the first integrated circuit chip.

Abstract: An integrated circuit comprising a field programmable gate array including a plurality of logic tiles, wherein, during operation, each logic tile is configurable to connect with at least one other logic tile, and wherein each logic tile includes: (1) a normal operating mode and test mode, (2) an interconnect network including a plurality of multiplexers, wherein during operation, the interconnect network of each logic tile is configurable to connect with the interconnect network of at least one other logic tile in the normal operating mode and (3) bitcells to store data. The FPGA also includes control circuitry, electrically connected to each logic tile, to configure each logic tile in a test mode and enable concurrently writing configuration test data into each logic tile of the plurality of logic tiles when the FPGA is in the test mode.

Abstract: In an embodiment, an apparatus includes an input/output (I/O) buffer to couple a logic unit to another device coupled via a pad, and a logic coupled to the I/O buffer to detect a value on the pad and to control the I/O buffer to provide the value to the pad, responsive to entry into an architectural state. Other embodiments are described and claimed.

Abstract: A tile including circuitry for use with machine learning models, the tile including: a first computational array of cells, in which the computational array of cells is a sub-array of a larger second computational array of cells; local memory coupled to the first computational array of cells; and multiple controllable bus lines, in which a first subset of the multiple controllable bus lines include multiple general purpose controllable bus lines couplable to the local memory.

Abstract: An integrated circuit device is disclosed that includes an interposer and a programmable fabric die disposed on the interposer. The programmable fabric die includes multiple sectors that each have multiple rows of logic element blocks. Each row of logic element blocks includes multiple microbumps. Each logic element block has programmable fabric circuitry and an input/output interface electrically coupled to a respective microbump. The integrated circuit device also includes a device disposed on the interposer external to the programmable fabric die and electrically coupled to the microbumps via the interposer.

Abstract: A method and system of co-packaging optoelectronics components or photonic integrated circuit (PIC) with application specific integrated circuits (ASICs) are disclosed and may include package substrate, several electronics die, passive components, socket assembly, and heat sinks. The said method converts ASIC high speed signals to optical signals by eliminating intermediary electrical interface between the ASIC and conventional optical modules. The method described provides many advantages of pluggable optical modules such as configurability, serviceability, and thermal isolation from the ASIC heat, while eliminating bandwidth bottlenecks as result of the ASIC package, host or linecard printed circuit board (PCB) traces, and the optical module connector. The high-power consumption ASIC is mounted below the package substrate, but sensitive optoelectronics and PIC components are mounted on top of the package substrate assembly for thermal isolation and serviceability.

Abstract: An memory component includes a memory bank and a command interface to receive a read-modify-write command, having an associated read address indicating a location in the memory bank and to either access read data from the location in the memory bank indicated by the read address after an adjustable delay period transpires from a time at which the read-modify-write command was received or to overlap multiple read-modify-write commands. The memory component further includes a data interface to receive write data associated with the read-modify-write command and an error correction circuit to merge the received write data with the read data to form a merged data and write the merged data to the location in the memory bank indicated by the read address.

Abstract: Illustrative embodiments provide a field-programmable transistor array and a method of making an integrated circuit comprising a field-programmable transistor array. The field-programmable transistor array comprises a plurality of logic cells. Each of the plurality of logic cells comprises a plurality of columns of transistors. Each of the plurality of columns of transistors comprises a plurality of first transistors and a plurality of second transistors. Each of the plurality of first transistors are individually programmable to be either always on, always off, or to be controlled by a logic signal to be on or off. Each of the plurality of second transistors are configured to be programmed to be always on or always off.

Abstract: Modular layout design units are provided with an internal channel for multi-directional distribution of a shared signal. In one illustrative embodiment, an integrated circuit includes: one or more modular units, each modular unit having an internal channel for signal distribution. The internal channel possesses: an edge connection on each edge of the modular unit; a hub node coupled to each edge connection by a respective bi-directional buffer having an incoming buffer and an outgoing buffer with at least one of the incoming and outgoing buffers disabled, the bi-directional buffers cooperating to steer a signal from a selectable one of the edge connections to one or more of the other edge connections; and a tap providing the signal for use by internal circuitry of the modular unit.

Abstract: A method includes programming an FPGA based controller of a master blade with a power scheme. The master blade receives a first power management signal from the master blade and slave blades. The master blade transmits a second power management signal to itself and to the slave blades responsive to the first power management signal. The master blade receives a third power management signal from itself and the slave blades. The power scheme controls an order and delay in which the second power management signal is transmitted to the first master blade and the slave blades. The power scheme controls an order and delay in which the third power management signal is received from the master blade and the slave blades. The system can be expanded by connecting the master blades to a grand master blade and multiple grand master blades to a great grand master blade.