Abstract: A method and apparatus implement redundant memory access using multiple controllers on the same bank of memory, and a design structure on which the subject circuit resides is provided. A first memory controller uses the memory as its primary address space, for storage and fetches. A second redundant controller is also connected to the same memory. System control logic is used to notify the redundant controller of the need to take over the memory interface. The redundant controller initializes if required and takes control of the memory. The memory only needs to be initialized if the system has to be brought down and restarted in the redundant mode. This invention allows the system to continue to stay up and continue running during a memory controller or link failure.

Abstract: A finFET structure and a method of fabricating the finFET structure. The method includes: forming a silicon fin on a top surface of a silicon substrate; forming a gate dielectric on opposite sidewalls of the fin; forming a gate electrode over a channel region of the fin, the gate electrode in direct physical contact with the gate dielectric layer on the opposite sidewalls of the fin; forming a first source/drain in the fin on a first side of the channel region and forming a second source/drain in the fin on a second side of the channel region; removing a portion of the substrate from under at least a portion of the first and second source/drains to create a void; and filling the void with a dielectric material. The structure includes a body contact between the silicon body of the finFET and the substrate.

Abstract: A diagnostic interface architecture for a memory device supports in one aspect one or more dynamically reconfigurable functional interconnects normally utilized in connection with reading data from the memory device and/or writing data to the memory device. The dynamically reconfigurable functional interconnects are capable of being configured to operate in either functional or diagnostic modes, whereby in the diagnostic mode, such interconnects may be used to communicate diagnostic information to support one or more diagnostic operations. The diagnostic interface architecture may also support multiple diagnostic interfaces in a given memory device, with at least one such diagnostic interface being capable of being selectively enabled in response to a failure in another diagnostic interface.

Abstract: A memory controller provides page copy logic that assures data coherency when a DMA operation to a page occurs during the copying of the page by the memory controller. The page copy logic compares the page index of the DMA operation to a copy address pointer that indicates the location currently being copied. If the page index of the DMA operation is less than the copy address pointer, the portion of the page that would be written to by the DMA operation has already been copied, so the DMA operation is performed to the physical address of the new page. If the page index of the DMA operation is greater than the copy address pointer, the portion of the page that would be written to by the DMA operation has not yet been copied, so the DMA operation is performed to the physical address of the old page.

Abstract: A communications architecture utilizes modules arranged in a daisy-chain, each module supporting multiple input and output ports. Point-to-point links are arranged so that a first output link of each of multiple modules connects to the next module in the chain, and a second output link connects to a module after it, and inputs arranged similarly, so that any single module can be by-passed in the event of malfunction. Multiple chains may be cross-linked and/or serviced by hubs or chains of hubs. Preferably, the redundant links are used in a non-degraded operating mode to provide higher bandwidth and/or reduced latency of communication. The exemplary embodiment is a memory subsystem in which the modules are buffered memory chips.

Abstract: An apparatus includes a virtual memory manager that moves data from a first block to second block in memory. When the virtual memory manager is ready to transfer data from the first block to the second block, a third, temporary block of memory is defined. The translation table in a DMA controller is changed to point DMA transfers that target the first block to instead target the temporary block. The virtual memory manager then transfers data from the first block to the second block. When the transfer is complete, a check is made to see if the DMA transferred data to the temporary block while the data from the first block was being written to the second block. If so, the data written to the temporary block is written to the second block. A hardware register is preferably used to efficiently detect changes to the temporary block.

Abstract: A method and apparatus implement redundant memory access using multiple controllers on the same bank of memory. A first memory controller uses the memory as its primary address space, for storage and fetches. A second redundant controller is also connected to the same memory. System control logic is used to notify the redundant controller of the need to take over the memory interface. The redundant controller initializes if required and takes control of the memory. The memory only needs to be initialized if the system has to be brought down and restarted in the redundant mode. This invention allows the system to continue to stay up and continue running during a memory controller or link failure.

Abstract: A method, and apparatus are provided for implementing a directory organization to selectively optimize performance or reliability in a computer system. A directory includes a user selected operational modes including a performance mode and a reliability mode. In the reliability mode, more directory bits are used for error correction and detection. In the performance mode, reclaimed directory bits not used for error correction and detection are used for more associativity.

Abstract: A method and data receiver apparatus implement a high speed, such as double data rate (DDR), memory read data eye stretcher. Altering the reference level is performed to increase the size of the data eye. Knowledge of the previous data state is used to adjust the reference level for the current data being latched so that the data eye is maximized.

Abstract: A FinFET body contact structure and a method for creating the FinFET body contact structure are disclosed. The body contact structure comprises a wide fin portion of a semiconductor fin, the wide fin portion having a polysilicon polygon shape formed on a top surface of the wide fin portion. The polysilicon polygon shape has a center area having no polysilicon. FinFETs are formed on two vertical surfaces of the wide fin portion and gates of the FinFETs are coupled to the polysilicon polygon shape. Top surfaces of the wide fin portion and the polysilicon polygon shape are silicided. Silicide bridging is prevented by sidewall spacers. All convex angles on the polysilicon polygon shape are obtuse enough to prevent creation of bridging vertices. The center area is doped of an opposite type from a source and a drain of an associated FinFET.

Abstract: Multiple interfaces dedicated to individual logic circuits such as memory arrays are capable of being dynamically reconfigured from operating separately and in parallel to operating in a more collective manner to ensure that data associated with all of the logic circuits will be communicated irrespective of a failure in any of the interfaces. Specifically, a plurality of interfaces, each of which being ordinarily configured to communicate data associated with an associated logic circuit in parallel with the other interfaces, may be dynamically reconfigured, e.g., in response to a detected failure in one or more of the interfaces, to communicate data associated with each of the interfaces over each of at least a subset of the interfaces in a time multiplexed and replicated manner.

Abstract: A finFET structure and a method of fabricating the finFET structure. The method includes: forming a silicon fin on a top surface of a silicon substrate; forming a gate dielectric on opposite sidewalls of the fin; forming a gate electrode over a channel region of the fin, the gate electrode in direct physical contact with the gate dielectric layer on the opposite sidewalls of the fin; forming a first source/drain in the fin on a first side of the channel region and forming a second source/drain in the fin on a second side of the channel region; removing a portion of the substrate from under at least a portion of the first and second source/drains to create a void; and filling the void with a dielectric material. The structure includes a body contact between the silicon body of the finFET and the substrate.

Abstract: An apparatus for measuring a structural characteristic between a polysilicon shape and a silicon area. The apparatus for measuring a structural characteristic between a polysilicon shape and a silicon area comprises the silicon area, and a plurality of polysilicon shapes each having a unique orientation relative to the silicon area wherein each of the polysilicon shapes is formed having an angle less than or equal to a critical angle. The critical angle is an angle at or below which a sidewall spacer no longer is formed on a polysilicon shape, thereby causing the polysilicon shape to short circuit to an underlying portion of the silicon area by way of a silicide bridge.

Abstract: A method and data receiver apparatus implement a high speed, such as double data rate (DDR), memory read data eye stretcher and a design structure on which the subject circuit resides is provided. Altering the reference level is performed to increase the size of the data eye. Knowledge of the previous data state is used to adjust the reference level for the current data being latched so that the data eye is maximized.

Abstract: A method and apparatus implement redundant memory access using multiple controllers for a memory system, and a design structure on which the subject circuit resides are provided. A first memory controller uses a first memory and a second memory controller uses the second memory as its respective primary address space, for storage and fetches. The second memory controller is also connected to the first memory. The first memory controller is also connected to the second memory. The first memory controller and the second memory controller, for example, are connected together by a processor communications bus. When one of the first memory controller or the second memory controller fails, then the other memory controller is notified. The other memory controller takes control of the memory for the failed controller, using the direct connection to that memory, and maintains coherence of both the first memory and second memory.

Abstract: A method and apparatus implement cache coherency and reduced latency using multiple controllers for a memory system, and a design structure is provided on which the subject circuit resides. A first memory controller uses a first memory as its primary address space, for storage and fetches. A second memory controller is also connected to the first memory. A second memory controller uses a second memory as its primary address space, for storage and fetches. The first memory controller is also connected to the second memory. The first memory controller and the second memory controller, for example, are connected together by a processor communications bus. A request and send sequence of the invention sends data directly to a requesting memory controller eliminating the need to re-route data back through a responding controller, and improving the latency of the data transfer.

Abstract: An apparatus and method are disclosed for an improved semiconductor interconnect scheme using a simplified process. In an embodiment of the apparatus, a polysilicon shape is formed on a silicon area. The polysilicon shape is created having a bridging vertex. When a spacer is created on the polysilicon shape, the spacer width is formed to be small enough near the bridging vertex to allow a silicide bridge to form that creates an electrical coupling between the silicon area and the bridging vertex. Semiconductor devices and circuits are created using the improved semiconductor interconnect scheme using the simplified process.

Abstract: Verification operations are utilized to effectively verify multiple associated write operations. A verification operation may be initiated after the issuance of a plurality of write operations that initiate the storage of data to a memory storage device, and may be configured to verify only a subset of the data written to the memory storage device by the plurality of write operations. As a result, verification operations are not required to be performed after each write operation, and consequently, the number of verification operations, and thus the processing and communication bandwidth consumed thereby, can be substantially reduced.

Abstract: A diagnostic interface architecture for a memory device supports in one aspect one or more dynamically reconfigurable functional interconnects normally utilized in connection with reading data from the memory device and/or writing data to the memory device. The dynamically reconfigurable functional interconnects are capable of being configured to operate in either functional or diagnostic modes, whereby in the diagnostic mode, such interconnects may be used to communicate diagnostic information to support one or more diagnostic operations. The diagnostic interface architecture may also support multiple diagnostic interfaces in a given memory device, with at least one such diagnostic interface being capable of being selectively enabled in response to a failure in another diagnostic interface.

Abstract: A memory controller provides page copy logic that assures data coherency when a DMA operation to a page occurs during the copying of the page by the memory controller. The page copy logic compares the page index of the DMA operation to a copy address pointer that indicates the location currently being copied. If the page index of the DMA operation is less than the copy address pointer, the portion of the page that would be written to by the DMA operation has already been copied, so the DMA operation is performed to the physical address of the new page. If the page index of the DMA operation is greater than the copy address pointer, the portion of the page that would be written to by the DMA operation has not yet been copied, so the DMA operation is performed to the physical address of the old page.