Abstract: Ultrafine patterns with dimensions smaller than the chemical and optical limits of lithography are formed by superimposing two photoresist patterns using a double exposure technique. Embodiments include forming a first resist pattern over a target layer to be patterned, forming a protective cover layer over the first resist pattern, forming a second resist pattern on the cover layer superimposed over the first resist pattern while the cover layer protects the first resist pattern, selectively etching the cover layer with high selectivity with respect to the first and second resist patterns leaving an ultrafine target pattern defined by the first and second resist patterns, and etching the underlying target layer using the superimposed first and second resist patterns as a mask.

Abstract: Disclosed herein are a processing unit and a multi-processing unit system that implement a cache-coherency method. Such a multi-processing unit system includes a main memory, a first processing unit, and a second processing unit. The first processing unit and the second processing unit are coupled to the main memory. The first processing unit includes a cache and logic. The cache is configured to store data from the main memory. The logic is configured to maintain an entry in a directory of the cache. The entry indicates whether either of the first processing unit and the second processing unit accesses a data object of a cache line for which the first processing unit is a home node.

Abstract: A semiconductor device has a substrate, a gate dielectric layer, and a metal gate electrode on the gate dielectric layer. The gate dielectric layer includes an oxide layer having a dielectric constant (k) greater than 4, and silicon concentrated at interfaces of the oxide layer with the substrate and with the metal gate electrode. A method of fabricating a semiconductor device includes forming a removable gate over a substrate with a gate dielectric layer between the removable gate and the substrate, forming a dielectric layer over the substrate and exposing an upper surface of the removable gate, removing the removable gate leaving an opening in the dielectric layer, forming a protective layer on the gate dielectric layer and lining the opening, and forming a metal gate electrode in the opening. The protective layer has a graded composition between the gate dielectric layer and the metal gate electrode.

Abstract: Different threshold voltages of transistors of the same conductivity type in a complex integrated circuit may be adjusted on the basis of different Miller capacitances, which may be accomplished by appropriately adapting a spacer width and/or performing a tilted extension implantation. Thus, efficient process strategies may be available to controllably adjust the Miller capacitance, thereby providing enhanced transistor performance of low threshold transistors while not unduly contributing to process complexity compared to conventional approaches in which threshold voltage values may be adjusted on the basis of complex halo and well doping regimes.

Abstract: A system and method for efficient reporting of power usage. A power reporting unit within a processor receives a power consumption number once every sample interval from a power monitor. The power monitor determines a power consumption number based on sampled signals within one or more functional blocks in the processor, rather than based on temperature. An average power consumption number is computed based on received power consumption numbers for a running time interval, wherein the running time interval is larger than the sample interval. This value is conveyed to an external agent. Responsive to receiving and processing the average power consumption number, the external agent may cause changes in a cooling system.

Abstract: A system includes multiple TAP controllers that can be independently powered up and down. When a first TAP controller is powered up from a powered-down state while a second TAP controller is already in a powered-up state, the first TAP controller is reset causing the first TAP controller to enter a reset state in response to the power-up of a module on which the first TAP controller is disposed. The first TAP controller enters an idle state and its control signal is gated to hold the first TAP controller in the idle state until the second TAP controller enters the idle state. Subsequently, the first TAP controller is released such that the control signal supplied to the first and second TAP controllers are equal, thereby synchronizing the first TAP controller and the second TAP controller.

Abstract: A method of forming a field effect transistor comprises providing a substrate comprising a biaxially strained layer of a semiconductor material. A gate electrode is formed on the biaxially strained layer of semiconductor material. A raised source region and a raised drain region are formed adjacent the gate electrode. Ions of a dopant material are implanted into the raised source region and the raised drain region to form an extended source region and an extended drain region. Moreover, in methods of forming a field effect transistor according to embodiments of the present invention, a gate electrode can be formed in a recess of a layer of semiconductor material. Thus, a field effect transistor wherein a source side channel contact region and a drain side channel contact region located adjacent a channel region are subject to biaxial strain can be obtained.

Abstract: Embodiments described herein include a method and system for synchronizing clocks between coupled integrated circuits (ICs) in a computer system. According to an embodiment, a dedicated timing pin is provided on a first IC. The first IC configures a second IC to change a pin assignment, so that the second IC interprets a signal sent on the timing pin by the first IC and received on the reassigned pin as a request to transmit a return signal. The return signal is received on the timing pin. The return signal is used to determine whether timing should be adjusted by the first IC. In an embodiment a clock and data recover (CDR) circuit compares the signal sent to the signal received in order to make the determination. In an embodiment the first IC is a processor-based device, and the second IC is a memory device controlled by the first device.

Abstract: A power allocation strategy limits performance of a subset of a plurality of computational units in a computer system according to performance sensitivity of each of the plurality of computational units to a change performance capability, e.g., frequency change. The performance of the subset of computational units may be limited by setting a power state in which the subset may be operated and/or reducing a current power state of the subset to a lower power state. The subset whose performance is limited includes computational units that are least performance sensitive according to stored sensitivity data. The subset may include one or more processing cores and performance of the one or more processing cores may be limited in response to a CPU-bounded application or graphics processing unit (GPU)-bounded application being executed.

Abstract: Method, system, and computer program product embodiments for synchronizing workitems on one or more processors are disclosed. The embodiments include executing a barrier skip instruction by a first workitem from the group, and responsive to the executed barrier skip instruction, reconfiguring a barrier to synchronize other workitems from the group in a plurality of points in a sequence without requiring the first workitem to reach the barrier in any of the plurality of points.

Abstract: A system for decoding video data includes a processing unit. The processing unit includes a plurality of processing pipelines and a driver. The driver includes a decoder configured to generate a plurality of intermediate control maps containing control information including an indication of which macro blocks or portions of macro blocks may be processed in parallel in the plurality of processing pipelines.

Abstract: A first and second plurality of gates are coupled respectively between first and second source storage elements and first and second destination storage elements. The first and second plurality of gates are slept to reduce leakage current in the plurality of gates under certain conditions by turning off respective one or more transistors between the first and second plurality of gates and power supplies. A third plurality of gates are maintained in a reduced leakage current state (sleep state) or regular state (wake state) based on conditions associated with the source and destination elements for the first and second plurality of gates.

Abstract: A system and method for dynamic function based power control is disclosed. In one embodiment, a system includes a bridge unit having a memory controller and a communication hub coupled to the memory controller. The system further includes a power management unit, wherein the power management unit is configured to clock-gate the communication hub responsive to determining that each of a plurality of processor cores are in an idle state and that an I/O interface unit has been idle for an amount of time exceeding a first threshold. The power management unit is further configured to clock-gate the memory controller responsive to clock-gating the communication hub and determining that a memory coupled to the memory controller is in a first low power state. The power management unit may also perform power-gating of functional units subsequent to clock-gating the same.

Abstract: A method of manufacturing a semiconductor device structure, such as a FinFET device structure, is provided. The method begins by providing a substrate comprising a bulk semiconductor material, a first conductive fin structure formed from the bulk semiconductor material, and a second conductive fin structure formed from the bulk semiconductor material. The first conductive fin structure and the second conductive fin structure are separated by a gap. Next, spacers are formed in the gap and adjacent to the first conductive fin structure and the second conductive fin structure. Thereafter, an etching step etches the bulk semiconductor material, using the spacers as an etch mask, to form an isolation trench in the bulk semiconductor material. A dielectric material is formed in the isolation trench, over the spacers, over the first conductive fin structure, and over the second conductive fin structure.

Abstract: Embodiments of a method and system for conserving power used in a central processing unit (CPU) are described. An embodiment uses direct memory access (DMA) fetch suspend logic to allow the CPU to stay in a sleep state indefinitely until a break event occurs. Embodiments include power management monitoring and Universal Serial Bus (USB) descriptor monitoring logic. Power management monitor logic monitors the CPU sleep state and sets a status flag to the USB descriptor monitoring logic whenever the CPU is in a predefined sleep state. The USB descriptor monitoring logic monitors the fetching of linked descriptor lists. When the CPU status flag is raised, it causes monitoring of the descriptor fetch by the USB descriptor monitoring logic. If the USB controller has completed all of the descriptor fetches while the CPU sleep flag is true, this logic sets a flag to cause the USB controller to suspend DMA fetch operations.

Abstract: Methods and apparatuses are provided for duty cycle correction of high-speed clock circuits. The apparatus includes a duty cycle interpolator receiving a clock source for providing a duty cycle corrected clock signal. The duty cycle corrected clock signal is filtered and compared to a reference signal, the result of which is clocked into a shift register. The shift register provides complementary N-bit duty cycle correction signals to the duty cycle interpolator for adjusting the duty cycle of the clock signal to provide the duty cycle corrected clock signal. The method includes filtering a duty cycle corrected clock signal to provide a filtered signal and comparing the filtered signal to a reference signal, the result of is clocked into a shift register. The shift register provides complementary N-bit duty cycle correction signals to a duty cycle interpolator for adjusting the duty cycle of a clock signal.

Abstract: A method of distributing audio and video processing tasks among devices interconnected to a display device via a local network is disclosed. In one embodiment, the display device offloads some processing tasks to a computing device on the local network to achieve improved processing performance. The computing device receives audiovisual data, decodes, processes, encodes and transmits the encoded data to the display device in a suitable data format. The processing in the computing device is complementary to any processing to be performed in the display device. In another embodiment, the display device utilizes a plurality of devices on the local network to perform particular signal processing tasks. The other devices in network perform the processing tasks indicated by the display, and send processed data back to the display device for presentation, which helps improve the overall audiovisual data processing performance.

Abstract: Various circuit board sockets and methods of manufacturing and using the same are disclosed. In one aspect, a method of manufacturing is provided that includes forming a socket operable to receive a first circuit board. The socket includes a housing and a cover slidedly coupled to the housing. The cover has an opening sized to enable the first circuit board to seat on the housing.

Abstract: By using powerful data analysis techniques, such as PCR, PLS, CLS and the like, in combination with measurement techniques providing structural information, gradually varying material characteristics may be determined during semiconductor fabrication, thereby also enabling the monitoring of complex manufacturing sequences. For instance, the material characteristics of sensitive dielectric materials, such as ULK material, may be detected, for instance with respect to an extension of a damage zone, in order to monitor the quality of metallization systems of sophisticated semiconductor devices. The inline measurement data may be obtained on the basis of infrared spectroscopy, for instance using FTIR and the like, which may even allow directly obtaining the measurement data at process chambers, substantially without affecting the overall process throughput.

Abstract: Integrated circuits with memory built-in self test (MBIST) circuitry and methods are disclosed that employ enhanced features. In one aspect of the invention, an integrated circuit is provided having MIBST circuitry configured to serially test multiple arrays of memory elements within a component of the integrated circuit and to also conduct parallel initialization of the serially tested arrays. In another aspect of the invention, the MBST circuitry is used set the memory elements of the arrays to a first state and then to an inverse state during a burn-in operation to maintain each of the two opposing states for a desired time in order to either force a failure of the integrated circuit component or produce a pre-stressed component beyond an infancy stage.