Abstract: A static RAM cell may be formed on the basis of two double channel transistors and a select transistor, wherein a body contact may be positioned laterally between the two double channel transistors in the form of a dummy gate electrode structure, while a further rectangular contact may connect the gate electrodes, the source regions and the body contact, thereby establishing a conductive path to the body regions of the transistors. Hence, compared to conventional body contacts, a very space-efficient configuration may be established so that bit density in static RAM cells may be significantly increased.

Abstract: Embodiments include a video data encoding method comprising receiving video input frames, and performing motion estimation on the video received frames. The motion estimation comprises performing a hierarchical motion search to find motion vectors with optimum sum of absolute difference (SAD) values, and performing spatial filtering of the motion vectors, wherein spatial filtering comprises making some pairs of motion vectors the same to achieve a zero differential.

Abstract: The drain and source regions of a multiple gate transistor may be formed without an epitaxial growth process by using a placeholder structure for forming the drain and source dopant profiles and subsequently masking the drain and source areas and removing the placeholder structures so as to expose the channel area of the transistor. Thereafter, corresponding fins may be patterned and a gate electrode structure may be formed. Consequently, reduced cycle times may be accomplished due to the avoidance of the epitaxial growth process.

Abstract: In an embodiment, a system comprises a memory system and a guest interrupt manager. The guest interrupt manager is configured to receive an interrupt message corresponding to an interrupt that is targeted at a guest executable on the system. The guest interrupt manager is configured to record the interrupt in a data structure in the memory system to ensure that the interrupt is delivered to the guest even if the guest is not active in the system at a time that the interrupt message is received.

Abstract: A USB (Universal Serial Bus) controller technique for implementing OTG (On-The-Go) functionality is provided. The device may have an EHCI (Enhanced Host Controller Interface) compliant host control unit, and an OTG control unit to implement an OTG state machine partly in hardware and partly in software. The OTG control unit may have an OTG control register and an OTG status register which are accessible by software. Further, the USB controller device may have a device control unit to implement device functionality and a port multiplexer to assign a physical port to either the host or the device control unit. The OTG control unit may be comprised in the port multiplexer. Further, a software driver may read the OTG status register in response to receiving an interrupt from the USB controller device, and write to the OTG control register to force the USB controller device to change its OTG state.

Abstract: A system and method for branch prediction in a microprocessor. A hybrid device stores branch prediction information in a sparse cache for no more than a common smaller number of branches within each entry of the instruction cache. For the less common case wherein an i-cache line comprises additional branches, the device stores the corresponding branch prediction information in a dense cache. Each entry of the sparse cache stores a bit vector indicating whether or not a corresponding instruction cache line includes additional branch instructions. This indication may also be used to select an entry in the dense cache for storage. A second sparse cache stores entire evicted entries from the first sparse cache.

Abstract: By providing a surface modification process prior to or during a self-limiting deposition process, the per se highly conformal deposition behavior may be selectively changed so as to obtain reliable coverage at specific surface areas, while significantly reducing or suppressing a deposition above unwanted surface areas, such as the bottom of a via in advanced metallization structures of highly scaled semiconductor devices.

Abstract: Methods, systems, and computer readable media for improved transfer of processing data outputs to memory are disclosed. According to an embodiment, a method for transferring outputs of a plurality of threads concurrently executing in one or more processing units to a memory includes: forming, based upon one or more of the outputs, a combined memory export instruction comprising one or more data elements and one or more control elements; and sending the combined memory export instruction to the memory. The combined memory export instruction can be sent to memory in a single clock cycle. Another method includes: forming, based upon outputs from two or more of the threads, a memory export instruction comprising two or more data elements; embedding at least one address representative of the two or more of the outputs in a second memory instruction; and sending the memory export instruction and the second memory instruction to the memory.

Abstract: An integrated circuit includes a feedback controlled clock generating circuit, such as a DLL, PLL or other suitable circuit, that is operative to provide a feedback reference frequency signal based on a generated output clock signal. The integrated circuit also includes a programmable fine lock/unlock detection circuit that includes programmable static phase error sensitivity logic that senses phase error. The programmable static phase error sensitivity logic sets a phase lock sensitivity window used to determine a fine lock/unlock condition of the generated output clock signal. The programmable fine lock/unlock detection logic is also operative to generate a fine phase lock/unlock signal based on the set phase lock sensitivity window. The integrated circuit may also include a coarse lock detection circuit that generates a coarse lock signal based on a frequency unlock condition.

Abstract: In an embodiment, a first instruction is defined that comprises at least a first operand from which the execution core is configured to determine a virtual address and a second operand that specifies one or more translation attributes that exist in a page table entry that defines a translation for the virtual address. A processor executing the instruction translates the virtual address, verifies whether or not the translation attributes in the page table entry match the specified translation attributes, faults the first instruction responsive to failing to locate a translation for the virtual address, and responsive to locating a translation for the virtual address in the page table entry but with the translation attributes in the entry failing to match the specified translation attributes.

Abstract: In a semiconductor device, a through hole via extending through the substrate of the device may be formed on the basis of a carbon-containing material, thereby providing excellent compatibility with high temperature processes, while also providing superior electrical performance compared to doped semiconductor materials and the like. Thus, in some illustrative embodiments, the through hole vias may be formed prior to any process steps used for forming critical circuit elements, thereby substantially avoiding any interference of the through hole via structure with a device level of the corresponding semiconductor device. Consequently, highly efficient three-dimensional integration schemes may be realized.

Abstract: For providing control of two-step or a multi-step deposition process, a method and a corresponding deposition system is provided comprising providing a deposition process having at least two sub-processes employing different sets of process parameters, wherein each set of process parameters comprises at least one process parameter. The method comprises controllably generating an actual value for at least one first process parameter by taking into account at least one previous value of the respective first process parameter, wherein each first process parameter is a process parameter of said at least two sets of process parameters.

Abstract: Disclosed is an electrochemical etching system with localized etching capability. The system allows multiple different porous semiconductor regions to be formed on a single semiconductor wafer. Localized etching is achieved through the use of one or more stationary and/or movable computer-controlled inner containers operating within an outer container. The outer container holds the electrolyte solution and acts as an electrolyte supply source for the inner container(s). The inner container(s) limit the size of the etched region of the semiconductor wafer by confining the electric field. Additionally, the current amount passing through each inner container during the electrochemical etching process can be selectively adjusted to achieve a desired result within the etched region. Localized etching of sub-regions within each etched region can also be achieved through the use of different stationary and/or moveable electrode structures and shields within each inner container.

Abstract: By locally heating isolation trenches with different annealing conditions, a different magnitude of intrinsic stress may be obtained in different isolation trenches. In some illustrative embodiments, the different anneal temperature may be achieved on the basis of an appropriate mask layer, which may provide a patterned optical response for a lamp-based or laser-based anneal process. Consequently, the intrinsic stress of isolation trenches may be specifically adapted to the requirements of circuit elements, such as N-channel transistors and P-channel transistors.

Abstract: A peer-to-peer special purpose processor architecture and method is described. Embodiments include a plurality of special purpose processors coupled to a central processing unit via a host bridge bus, a direct bus directly coupling each of the plurality of special purpose processors to at least one other of the plurality of special purpose processors and a memory controller coupled to the plurality of special purpose processors, wherein the at least one memory controller determines whether to transmit data via the host bus or the direct bus, and whether to receive data via the host bus or the direct bus.

Abstract: The present invention facilitates network throughput by dynamically generating IPG values, which are employed when recovering from network collisions. Testing a number of IPG values and tracking collisions that occur as a result for each value generate the IPG value. The IPG value that yielded the lowest collisions is then programmed as the IPG value for a network device. This value remains in use by the network device for a stable state time period. After this period, another dynamically generated IPG value is obtained.

Abstract: By providing a tool internal sensor device in a process tool in a semiconductor facility, metal contamination may be monitored in situ, thereby avoiding or at least significantly reducing the requirement for sophisticated sample preparation techniques, such as vapor phase decomposition tests in combination with subsequent analysis procedures. Thus, a full time inspection of process tools may be accomplished.

Abstract: A controller/driver is composed of a work memory, a graphic engine, a display memory, and a driver circuit. The graphic engine converts externally received image data into first bitmap data, and stores the first bitmap data in the work memory. The display memory receives and stores second bitmap data developed from the first bitmap data stored in the work memory. The driver circuit drives a display panel in response to the second bitmap data received from the display memory.

Abstract: A microprocessor includes a cache memory, a prefetch unit, and detection logic. The prefetch unit may be configured to monitor memory accesses that miss in the cache and to determine whether to prefetch one or more blocks of memory from a system memory based upon previous memory accesses. The prefetch unit may be further configured to use addresses of the memory accesses that miss to calculate each next memory block to prefetch. The detection logic may be configured to provide a notification to the prefetch unit in response to detecting a memory access instruction including a particular hint. In response to receiving the notification, the prefetch unit may be configured to inhibit using an address associated with the memory access instruction including the particular hint, when calculating subsequent memory blocks to prefetch.