Abstract: Methods are disclosed for improving data processing performance in a processor using on-chip local memory in multiple processing units. According to an embodiment, a method of processing data elements in a processor using a plurality of processing units, includes: launching, in each of the processing units, a first wavefront having a first type of thread followed by a second wavefront having a second type of thread, where the first wavefront reads as input a portion of the data elements from an off-chip shared memory and generates a first output; writing the first output to an on-chip local memory of the respective processing unit; and writing to the on-chip local memory a second output generated by the second wavefront, where input to the second wavefront comprises a first plurality of data elements from the first output. Corresponding system and computer program product embodiments are also disclosed.

Abstract: Embodiments of the present invention are directed to improving the performance of anti-aliased image rendering. One embodiment is a method of rendering a pixel from an anti-aliased image. The method includes: storing a first set and a second set of samples from a plurality of anti-aliased samples of the pixel respectively in a first memory and a second memory; and rendering a determined number of said samples from one of only the first set or the first and second sets. Corresponding system and computer program product embodiments are also disclosed.

Abstract: Embodiments of the present invention enable the reduction of the memory bandwidth required for graphics rendering. According to an embodiment, a method to render a pixel from a compressed anti-aliased image includes: accessing metadata for the pixel, where the metadata includes entries for respective samples generated by multisampling the pixel; and retrieving a subset of said samples based upon the metadata, wherein the subset is stored in the compressed anti-aliased image stored in a memory.

Abstract: Metallization systems on the basis of copper and low-k dielectric materials may be efficiently formed by providing an additional dielectric material of enhanced surface conditions after the patterning of the low-k dielectric material. Consequently, defects such as isolated copper voids and the like may be reduced without significantly affecting overall performance of the metallization system.

Abstract: By removing material during the formation of trench openings of isolation structures in an SOI device, the subsequent implantation process for defining the well region for a substrate diode may be performed on the basis of moderately low implantation energies, thereby increasing process uniformity and significantly reducing cycle time of the implantation process. Thus, enhanced reliability and stability of the substrate diode may be accomplished while also providing a high degree of compatibility with conventional manufacturing techniques.

Abstract: A content addressable memory (CAM) of a data processing device can operate in a normal mode or a test mode. In the normal mode, the CAM provides a match value in response to determining that a received data value matches one of a plurality of values stored at memory locations of the CAM. In a test mode of operation, a plurality of test signals are applied to the CAM, and the CAM provides a match value in response to assertion of one of the test signals. The match value is applied to a functional module associated with the CAM to determine a test result. Accordingly, the test signals applied to the CAM provide a flexible way to generate match values and apply those values to the functional module during testing of the data processing device.

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: An integrated circuit system includes an integrated circuit, forming a triode near the integrated circuit, and attaching a connector to the triode and the integrated circuit.

Abstract: One or more processor cores of a multiple-core processing device each can utilize a processing pipeline having a plurality of execution units (e.g., integer execution units or floating point units) that together share a pre-execution front-end having instruction fetch, decode and dispatch resources. Further, one or more of the processor cores each can implement dispatch resources configured to dispatch multiple instructions in parallel to multiple corresponding execution units via separate dispatch buses. The dispatch resources further can opportunistically decode and dispatch instruction operations from multiple threads in parallel so as to increase the dispatch bandwidth. Moreover, some or all of the stages of the processing pipelines of one or more of the processor cores can be configured to implement independent thread selection for the corresponding stage.

Abstract: A system and method for efficient reliable execution on a simultaneous multithreading machine. A processor is placed in a reliable execution mode (REM) to detect possible errors during execution of a software application. Only two threads may be configured to operate in this mode. Floating-point store and integer-transfer unary instructions may be converted to new instructions. Each new instruction has two source operands, each corresponding to a different thread is specified by a same logical register number as a single source operand of the original unary instruction. All other instructions are replicated, wherein the original instruction and its twin are assigned to different threads. Simultaneous multi-threaded (SMT) floating-point logic may only be able to provide lockstep execution when it communicates using the new instruction with instantiated integer independent clusters.

Abstract: In one embodiment, a processor supports an alternate address space during execution of non-guest code (such as a minivisor or a virtual machine monitor (VMM)). The alternate address space may be the guest address space. An instruction in the minivisor/VMM may specify the alternate address space for a data access, permitting the minivisor/VMM to read guest memory state via the alternate address space. In another embodiment, a processor may implement a page table base address register dedicated for the minivisor's use. In still another embodiment, the minivisor may be implemented as a specified entry point in the VMM address space.

Abstract: Methods for forming a semiconductor device comprising a silicon-comprising substrate are provided. One exemplary method comprises depositing a polysilicon layer overlying the silicon-comprising substrate, amorphizing the polysilicon layer, etching the amorphized polysilicon layer to form a gate electrode, etching recesses into the substrate using the gate electrode as an etch mask, depositing a stress-inducing layer overlying the gate electrode, annealing the silicon-comprising substrate to recrystallize the gate electrode, removing the stress-inducing layer, and epitaxially growing impurity-doped, silicon-comprising regions in the recesses.

Abstract: A strain-inducing semiconductor alloy may be formed on the basis of cavities which may have a non-rectangular shape, which may be maintained even during corresponding high temperature treatments by providing an appropriate protection layer, such as a silicon dioxide material. Consequently, a lateral offset of the strain-inducing semiconductor material may be reduced, while nevertheless providing a sufficient thickness of corresponding offset spacers during the cavity etch process, thereby preserving gate electrode integrity. For instance, P-channel transistors may have a silicon/germanium alloy with a hexagonal shape, thereby significantly enhancing the overall strain transfer efficiency.

Abstract: A compound logic flip-flop. The flip-flop includes a plurality of input stages, wherein each of the input stages is coupled to receive at least one input signal and a clock signal. Each of the plurality of input (i.e. ‘master’) stages is configured to perform a corresponding input logic function during a first phase of a clock cycle and to store a result of the corresponding input logic function. The flip-flop further includes an output (i.e. ‘slave’) stage coupled to receive the clock signal and the results of the input logic functions from each of the plurality of input stages. The output stage is configured, during a second phase of the clock cycle, to logically combine the results of the input logic functions by performing an output logic function and provide an output signal based on a result of the output logic function.

Abstract: According to one exemplary embodiment, a method for determining a power spectral density of an edge of at least one patterned feature situated over a semiconductor wafer includes measuring the edge of the at least one patterned feature at a number of points on the edge. The method further includes determining an autoregressive estimation of the edge of the at least one patterned feature using measured data corresponding to a number of points on the edge. The method further includes determining a power spectral density of the edge using autoregressive coefficients from the autoregressive estimation. The method further includes utilizing the power spectral density to characterize line edge roughness of the at least one patterned feature in a frequency domain.

Abstract: A nitrogen-containing silicon carbide material may be deposited on the basis of a single frequency or mixed frequency deposition recipe with a high internal compressive stress level up to 1.6 GPa or higher. Thus, this dielectric material may be advantageously used in the contact level of sophisticated integrated circuits, thereby providing high strain levels while not unduly contributing to signal propagation delay.

Abstract: Disclosed are methods and systems for granting an application-specific integrated circuit (ASIC) in a multi-ASIC environment controlled access to a shared resource. A system includes a first ASIC, a second ASIC, and a shared memory that stores a shared resource and a data set partitioned into fields. The first ASIC writes data to a first subset of the fields and reads data from the fields. The first ASIC includes first logic that computes a first value based on the data read from the fields. The second ASIC writes data to a second subset of the fields and reads data from the fields. The second ASIC includes second logic that computes a second value based on the data read from the fields. Based on the first and second values respectively computed by the first and second logic, only one of the first and second ASICs gains access to the shared resource.

Abstract: Disclosed are methods and systems for granting an application-specific integrated circuit (ASIC) in a multi-ASIC environment controlled access to a shared resource. A system includes a first ASIC, a second ASIC, and a shared memory that stores a shared resource and a data set partitioned into fields. The first ASIC writes data to a first subset of the fields and reads data from the fields. The first ASIC includes first logic that computes a first value based on the data read from the fields. The second ASIC writes data to a second subset of the fields and reads data from the fields. The second ASIC includes second logic that computes a second value based on the data read from the fields. Based on the first and second values respectively computed by the first and second logic, only one of the first and second ASICs gains access to the shared resource.

Abstract: A method for delayed memory access request arbitration includes dispatching a first memory access request to a memory controller and dispatching a second memory access request to the memory controller in response to an anticipated completion of a memory access operation represented by the first memory access request. Another method includes receiving a first memory access request at a bus interface unit at a first time, dispatching a second memory access request to a memory controller at a second time subsequent to the first time, receiving a third memory access request at the bus interface unit at a third time subsequent to the second time, dispatching the third memory access request to the memory controller at a fourth time subsequent to the third time and dispatching the first memory access request to the memory controller at a fifth time subsequent to the fourth time.

Abstract: In one disclosed embodiment, the present method for determining a gate-to-body current for a floating body FET comprises measuring at least three unique gate-to-body currents corresponding to at least three unique body-tied FET structures, determining at least three unique relationships between the at least three unique gate-to-body currents and at least three gate-to-body current density components for the at least three unique body-tied FET structures, and utilizing those at least three unique relationships to determine the at least three gate-to-body current density components; wherein one of the gate-to-body current density components is used to determine the gate-to-body current for the floating body FET. In one embodiment, a test structure implements a method for determining a gate-to-body current in a floating body FET. The determined gate-to-body current may be used to predict hysteresis in the floating body FET.