Abstract: During a replacement gate approach, the inverse tapering of the opening obtained after removal of the polysilicon material may be reduced by depositing a spacer layer and forming corresponding spacer elements on inner sidewalls of the opening. Consequently, the metal-containing gate electrode material and the high-k dielectric material may be deposited with enhanced reliability.

Abstract: A method and apparatus are disclosed for implementing early release of speculatively read data in a hardware transactional memory system. A processing core comprises a hardware transactional memory system configured to receive an early release indication for a specified word of a group of words in a read set of an active transaction. The early release indication comprises a request to remove the specified word from the read set. In response to the early release request, the processing core removes the group of words from the read set only after determining that no word in the group other than the specified word has been speculatively read during the active transaction.

Abstract: A device may include an oscillator to generate a clock signal based on first and second control signals. The oscillator may include a first buffer stage a second buffer stage. The first buffer stage may output a first signal that is based on an output of the second buffer stage and the first control signal. The second buffer stage may output the clock signal. The clock signal may be based on the first signal and the second control signal.

Abstract: Methods and systems are provided for graphics processing unit optimization via wavefront reforming including queuing one or more work-items of a wavefront into a plurality of queues of a compute unit. Each queue is associated with a particular processor within the compute unit. A plurality of work passes are performed. A determination is made which of the plurality of queues are below a threshold amount of work-items. Remaining one or more work-items from the queues with remaining ones of the work-items are redistributed to the below threshold queues. A subsequent work pass is performed. The, repeating of the determining, redistributing, and performing the subsequent work pass is done until all the queues are empty.

Abstract: Methods and systems are provided for graphics processing unit distributed work-item queuing. One or more work-items of a wavefront are queued into a first level queue of a compute unit. When one or more additional work-items exist, a queuing of the additional work-items into a second level queue of the compute unit is performed. The queuing of the work-items into the first and second level queue is performed based on an assignment technique.

Abstract: A method of fabricating a semiconductor device having a transistor with a metal gate electrode and a gate dielectric layer includes forming a protective layer on the gate dielectric layer and forming a metal gate electrode over the protective layer. The protective layer has a graded composition between the gate dielectric layer and the metal gate electrode.

Abstract: A method and apparatus are disclosed for determining the presence of adjacent channel interference. Received digital signals are processed to detect the existence of strong channels adjacent to the channel of interest and control signals may be generated based on the detection of strong adjacent channels. The control signals are then used to adjust the signal power of the received signals.

Abstract: According to one embodiment, an optical isolation module includes first and second linear polarizers, a Faraday rotator situated between the first and second linear polarizers and a transmissive element including a half-wave plate also situated between the first and second linear polarizers. In one embodiment, a method for performing optical isolation includes rotating an axis of polarization of a linearly polarized light beam by a first rotation in a first direction, and selectively rotating a portion of the linearly polarized light beam by a second rotation in the first direction to produce first and second linearly polarized light beam portions. As a result, the first linearly polarized light beam portion undergoes the first rotation, and the second linearly polarized light beam portion undergoes the first and second rotations. The method further includes filtering one of the first and second linearly polarized light beam portions to produce a light annulus.

Abstract: A system and method for increasing processor throughput by decreasing a loop critical path. In one embodiment, a table comprises multiple stack entries, each comprising an x87 floating-point (FP) stack specifier. The combinatorial logic for operand translation of N FP instructions per clock cycle may require N instantiated copies of a combinatorial logic block. Each instantiated copy may determine a new ordering of the stack entries. Control logic may receive necessary information from the corresponding N FP instructions and determine a corresponding combined computational effect, or stack reordering, on entries within the table based on two or more instructions. Resulting control signals are conveyed to the N instantiated copies. A resulting accumulative delay from an input of the first copy to the output of the Nth copy may be less than or equal to (N?1)*time_delay versus a longer N*time_delay.

Abstract: A method and apparatus for performing template-based classification of a circuit design are disclosed. A template file is read that defines a plurality of channel-connected-region (CCR) templates. A graph is formatted for each of the CCR templates. A plurality of CCRs are identified based on a partitioned netlist file that defines a given circuit design. A graph is generated for each of the identified CCRs. A matching CCR template graph is identified for each generated CCR graph. The template file may further defines super-CCR templates, and a graph may be formatted for each of the super-CCR templates. All possible combinations of CCRs and previously-matched super-CCRs that are candidates to match the formatted super-CCR template graph may be determined in an interative manner, for each formatted super-CCR template graph. A determination may be made as to which of the candidate combinations actually match the formatted super-CCR template graph.

Abstract: By providing a test structure for evaluating the patterning process and/or the epitaxial growth process for forming embedded semiconductor alloys in sophisticated semiconductor devices, enhanced statistical relevance in combination with reduced test time may be accomplished.

Abstract: Apparatus for memory elements and related methods for performing an allocate operation are provided. An exemplary memory element includes a plurality of way memory elements and a replacement module coupled to the plurality of way memory elements. Each way memory element is configured to selectively output data bits maintained at an input address. The replacement module is configured to enable output of the data bits maintained at the input address of a way memory element of the plurality of way memory elements for replacement in response to an allocate instruction including the input address.

Abstract: An electrically programmable reticle is made using at least one electrochromatic layer that changes its optical transmissibility in response to applied voltages. Transparent conductor layers are configured to the desired patterns. The electrically programmable reticles are either patterned in continuous forms that have separately applied voltages or in a matrix of rows and columns that are addressed by row and column selects such that desired patterns are formed with the application of a first voltage level and reset with the application of a second voltage level.

Abstract: An integrated circuit comprising a plurality of functional blocks, each functional block being operative to cause one or more power consuming events, each power consuming event being associated with a respective weight. The integrated circuit also comprises at least one accumulation block for monitoring the functional blocks over a time window and generating a weighted count of the number of occurrences of each power consuming event within the time window; and a power calculation module for calculating a runtime power consumption estimate over the time window using the weighted count. The weighted count may comprise a sum of products of each one of the power consuming events by its respective weight. Calculating the runtime power consumption estimate may comprise averaging the weighted count over the time window to generate a dynamic power estimate, calculating a leakage power estimate over the time window, and summing the dynamic power estimate with the leakage power estimate.

Abstract: In the present method of implementing functioning of an encryption engine, a plurality of logic blocks are provided, each for running a function. Each function is run based on three variables, each of which may have a first or second value. The function is run with the first variable value selected as having its first value, and with the second and third variables having their actual values. The function is again run with the first variable value selected as having its second value, and again with the second and third variables having their actual values. An actual value of the first variable is determined, and the output of the logic block is determined by the actual value of the first variable.

Abstract: A performance monitor records performance information for tagged instructions being executed at an instruction pipeline. For instructions resulting in a load or store operation, a cache access analyzer can decompose the address associated with the operation to determine which cache line, if any, of a cache is accessed by the operation, and which portion of the cache line is requested by the operation. The cache access analyzer records the cache line portion in a data record, and, in response to a change in instruction being executed, stores the data record for subsequent analysis.

Abstract: A method and apparatus for dynamically controlling a cache size is disclosed. In one embodiment, a method includes changing an operating point of a processor from a first operating point to a second operating point, and selectively removing power from one or more ways of a cache memory responsive to changing the operating point. The method further includes processing one or more instructions in the processor subsequent to removing power from the one or more ways of the cache memory, wherein said processing includes accessing one or more ways of the cache memory from which power was not removed.

Abstract: A monitoring system is presented. The monitoring system may include a first chemical vessel containing a first chemical mixture and a second chemical vessel containing a second chemical mixture. The monitoring system may further include a sensor configured to selectively receive a first sample flow of the first chemical mixture from the first chemical vessel and a second sample flow of the second chemical mixture from the second chemical vessel. The sensor may be configured to measure a first sample attribute value of the first sample flow and a second sample attribute value of the second sample flow. By multiplexing multiple sample flows through a sensor, the monitoring system may monitor attributes of multiple chemical mixtures without requiring separate sensors for each chemical mixture monitored by the system. In an embodiment, the monitoring system is preferably configured to control an attribute of a chemical mixture.

Abstract: In at least one embodiment, a method includes locally scheduling a memory request requested by a thread of a plurality of threads executing on at least one processor. The memory request is locally scheduled according to a quality-of-service priority of the thread. The quality-of-service priority of the thread is based on a quality of service indicator for the thread and system-wide memory bandwidth usage information for the thread. In at least one embodiment, the method includes determining the system-wide memory bandwidth usage information for the thread based on local memory bandwidth usage information associated with the thread periodically collected from a plurality of memory controllers during a timeframe. In at least one embodiment, the method includes at each mini-timeframe of the timeframe accumulating the system-wide memory bandwidth usage information for the thread and updating the quality-of-service priority based on the accumulated system-wide memory bandwidth usage information for the thread.

Abstract: Each thread of a multi-threaded application is assigned a ranking, referred to as thread criticality, based on the amount of time the thread is expected to take to complete one or more operations associated with the thread. More resources are assigned to threads having a higher thread criticality, in order to increase the rate at which the thread completes its operations. Thread criticality is determined using a perceptron model, whereby the thread criticality for a thread is a weighted sum of a set of data processing device performance characteristics associated with the thread, such as the number of instruction cache misses and data cache misses experienced by the thread. The weights of the perceptron model can be repeatedly adjusted over time based on repeated measurements that indicate the relative speed with which each thread is completing its operations.