Abstract: Techniques for improving cache latency include distributing cache lines across regions of the cache having various latencies. The latencies of the regions may vary as a function of the distance between an individual region of the cache and a cache controller. The cache controller may predict an addressable unit of interest for a next access to a data line stored in a cache line. The predicted addressable unit of interest is stored in a region of the cache having the lowest latency as compared to other regions of the cache. The addressable unit of interest may be a most-recently used addressable unit, an addressable unit sequentially following a most-recently used addressable unit, or determined by other criterion. The invention contemplates using at least one control bit to indicate which addressable unit is stored in the region having the lowest latency.

Abstract: A data processor (200) has a pipelined execution unit (120). Whether a first instruction is one of a class of instructions wherein as a result of execution of the first instruction the contents of an operand register will be stored in a destination register is determined. A second instruction that references the destination register is received before a completion of execution of the first instruction. The second instruction is executed using the contents of the operand register without stalling the second instruction in the pipelined execution unit (120).

Abstract: A method and apparatus for capturing the internal state of an integrated circuit (IC) for second and higher order speedpath-induced failures. The method includes stretching one or more cycles of an internal clock signal in order to mask a first order speedpath-induced failure (SIF), wherein the internal clock signal is restored to operating at a normal speed subsequent to masking the first order SIF. The internal clock signal may be stopped at a cycle corresponding to a higher order SIF. After stopping the internal clock signal, test output data may be loaded into a scan chain. The method may also be used in conjunction with a laser or other device for other test enhancements.

Abstract: Methods for eliminating and/or mitigating bridging and/or leakage caused by the contamination of a dielectric layer with fragments and/or residues of a conductive material are disclosed. The methods involve exposing a semiconductor substrate with a dielectric layer contaminated with fragments and/or residues of conductive materials to one or more conductor and/or dielectric etches. The disclosure by eliminating and/or mitigating metal bridging and/or leakage can provide one or more of the following advantages: high device reliability, decreased manufacturing cost, more efficient metallization, and increased performance.

Abstract: Disclosed are methods for deposition of improved memory element films for semiconductor devices. The methods involve providing a hard mask over an upper surface of a metal line of a semiconductor substrate where vias are to be placed, recess etching the mask substantially in all upper surfaces except where vias are to be placed, depositing a Ta-containing capping layer over substantially all the metal line surfaces except the surface where vias are to be placed, polishing the Ta-containing capping layer to produce a damascened Ta-containing cap while exposing the metal line at the via forming surface, depositing a dielectric layer, patterning the dielectric layer to form a via, and depositing memory element films. The improved Ta—Cu interface of the subject invention mitigates and/or eliminates lateral growth of memory element films and copper voiding under the dielectric layer at the top surface of the metal line, and thereby enhances reliability and performance of semiconductor devices.

Abstract: The present invention provides a method, an apparatus, and a system for semiconductor manufacturing. The method includes accessing information indicative of operation of at least one first processing tool. The first processing tool is configured to process at least one wafer. The method also includes determining, prior to processing the wafer by the first processing tool, a first reservation indicative of a time period for processing the wafer in at least one of the first processing tools based on the accessed information.

Abstract: Disclosed are systems and methods that employ a structural framework of cell gratings placed on a wafer surface during an immersion lithography process to restrict motion of the immersion fluid. Thus, when the stepper lens comes in contact with the immersion fluid, a typically stable immersion fluid dynamics can be maintained with the cells during the immersion lithography process. In addition, various monitoring and control systems are employed to regulate stability of the immersion fluid.

Abstract: The system includes a plurality of process modules and an independent module controller for each of the plurality of process modules that is adapted to control the process tools within each of the process modules. Each of the independent module controllers performs at least run-to-run control of the processing tools, yield management analysis, scheduling of materials provided to and sent from the process module, and movement of wafers within the process module. One method of the present invention involves providing a plurality of process modules, each of which has an independent module controller that is adapted to perform at least run-to-run control of the processing tools within the process module, yield management analysis, scheduling of materials, and movement of wafers within the process module. The independent module controller for each of the process modules controls the process tools within its respective process module that are employed in forming a portion of the integrated circuit device.

Abstract: A method includes forming a group of first structures on a semiconductor device and forming spacers adjacent side surfaces of each of the first structures to form a group of second structures. The method further includes using the group of second structures to form at least one sub-lithographic opening in a material layer located below the group of second structures.

Abstract: A basic input/output system (BIOS) evaluates a plurality of performance state data that is stored in a disposable memory to determine if one of the plurality matches a set of processor criteria, which correspond to a processor of the computer system. Each of the plurality of performance state data corresponds to one or more processors. The BIOS selects the one of the plurality that matches the criteria to some degree (e.g., exactly, nearly, etc.) and stores it in BIOS runtime memory. If there are no matches, then the BIOS may select a default performance state table or dynamically generate a performance state table.

Abstract: Precise estimation of latency is attained based on identifying that a receive clock is configured to operate only at prescribed available frequencies. A receive buffer circuit includes buffer control logic configured for reading a selected number of the buffer entries based on a detected number of receive clock edges within one local clock cycle. Valid data is identified based on the number of clock edges exceeding a selected threshold. A selected pointer offset is obtained from a lookahead table, specifying multiple pointer offsets for accommodating latency encountered at respective prescribed available frequencies, based on matching the determined frequency to one of the prescribed available frequencies. The selected pointer offset is added to a read pointer to offset the latency encountered from edge detection.

Abstract: A stacked module device and corresponding module and method are provided where at least some modules have input ports connected to receive first resource related signals and output ports connected to provide second resource related signals. The first and second signals are different, and each module comprises a resource signal transformation unit for generating the second signal from the first signals. The resource signal transformation units of each module are of the same construction. Resources may be addresses. Further, a software configurable address assignment is provided.

Abstract: A method is provided for testing RAM blocks embedded in an integrated circuit. The method provides a scan circuit embedded in an integrated circuit. The scan circuit includes a RAM block, a plurality of first flip-flops each sending a read address to the RAM block, a plurality of second flip-flops each sending a write address to the RAM block, a plurality of third flip-flops each sending an enable signal to the RAM block, a plurality of fourth flip-flops, and a multiplexer receiving an output from the RAM block, the first, second, third and fourth flip-flops being connected in series. An internal scan test is performed by loading serial data into the first, second, third and fourth flip-flops.

Abstract: A semiconductor device comprises a substrate including isolation regions and active regions, and a high-k dielectric layer proximate the substrate. The high-k dielectric layer comprises a mixture formed by annealing at least one high-k material and at least one metal to oxidize the metal. The semiconductor device comprises a gate electrode proximate the high-k dielectric layer.

Abstract: The present invention provides a method and apparatus for comparing device and non-device structures. The method includes determining at least one characteristic parameter associated with at least one non-device structure on at least one workpiece and determining at least one characteristic parameter associated with at least one device structure on the at least one workpiece. The method also includes comparing the at least one characteristic parameter associated with the at least one non-device structure and the at least one characteristic parameter associated with at least one device structure.

Abstract: A processor supports a mode in which the default operand size is 32 bits, but which supports operand size overrides to 64 bits. Furthermore, the default operand size may automatically be overridden to 64 bits for instructions having an implicit stack pointer reference and for near branch instructions. The overriding of the default operand size may occur without requiring an operand size override encoding in these instructions. In one embodiment, the instruction set specifying the instructions may be a variable byte length instruction set (e.g. x86), and the operand size override encoding may be a prefix byte which increases the instruction length.

Abstract: A processor includes a prediction circuit and a floating point unit. The prediction circuit is configured to predict an execution latency of a floating point operation. The floating point unit is coupled to receive the floating point operation for execution, and is configured to detect a misprediction of the execution latency. In some embodiments, an exception may be taken in response to the misprediction. In other embodiments, the floating point operation may be rescheduled with the corrected execution latency.

Abstract: A method for making a simplified dielectric layer stack for the first metallization layer is provided in combination with an improved anisotropic etch process, wherein the etch attack at the trench perimeter is reduced for a patterning process on the basis of a 193 nm lithography. In the simplified layer stack, a bottom etch stop layer formed beneath a low-k dielectric layer may be omitted, thereby reducing production costs while enhancing product performance by lowering leakage currents in the first metallization layer.

Abstract: Aspects for performing localized diagnostics in a station of a home phoneline networking alliance (HPNA) network are described. The aspects include providing a network state and control register comprising a plurality of bits to indicate status of a network state machine of an HPNA media access controller (MAC). A test mode bit is also provided as one of the plurality of bits in the network state and control register. The test mode bit allows overriding of one or more other bits in the network state and control register to direct changes to the network state machine logic state and diagnose performance in response to the changes.

Abstract: A method for forming spacers of specific dimensions on a polysilicon gate electrode protects the sidewalls of the polysilicon gate electrode during selective epitaxial growth. The spacers, whether asymmetric or symmetric, are precisely defined by using the same specific exposure tool, such as a 193 nm wavelength step and scan exposure tool, and the same pattern reticle, in both the defining of the polysilicon gate electrode pattern and the pattern spacer, while employing tight alignment specifications.