Abstract: Techniques are disclosed relating to scheduling graphics instructions for execution on different types of execution units based on characteristics of decoded and cached graphics instruction. In some embodiments, a graphics unit includes multiple different types of execution units that are configured to execute different types of instructions (e.g., different units for datapath, sample, load/store, etc.). In some embodiments, the graphics unit stores decoded instructions in an instruction cache in at least one cache level, along with information specifying characteristics of the instructions. The characteristics may be stored at clause granularity and may indicate the type of instructions in each clause (e.g., corresponding to which type of execution unit is configured to execute the instructions).

Abstract: Instructions may require one or more operands to be executed, which may be provided from a register file. In the context of a GPU, however, a register file may be a relatively large structure, and reading from the register file may be energy and/or time intensive An operand cache may be used to store a subset of operands, and may use less power and have quicker access times than the register file. Hint values may be used in some embodiments to suggest that a particular operand should be stored in the operand cache (so that is available for current or future use). In one embodiment, a hint value indicates that an operand should be cached whenever possible. Hint values may be determined by software, such as a compiler, in some embodiments. One or more criteria may be used to determine hint values, such as how soon in the future or how frequently an operand will be used again.

Abstract: Techniques are disclosed relating to predication. In one embodiment, a graphics processing unit is disclosed that includes a first set of architecturally-defined registers configured to store predication information. The graphics processing unit further includes a second set of registers configured to mirror the first set of registers and an execution pipeline configured to discontinue execution of an instruction sequence based on predication information in the second set of registers. In one embodiment, the second set of registers includes one or more registers proximal to an output of the execution pipeline. In some embodiments, the execution pipeline writes back a predicate value determined for a predicate writer to the second set of registers. The first set of architecturally-defined registers is then updated with the predicate value written back to the second set of registers. In some embodiments, the execution pipeline discontinues execution of the instruction sequence without stalling.

Abstract: Embodiments of a unified shading controller are disclosed. The embodiments may provide a first functional unit configured to send a write request to a second functional unit. The write request may include data and the data may include one or more control bits. Upon receiving the write request, the second functional unit may check the one or more control bits, and hold the data in a given queue dependent upon the control bits.

Abstract: Embodiments of a unified shading controller are disclosed. The embodiments may provide a first functional unit configured to send a write request to a second functional unit. The write request may include data and the data may include one or more control bits. Upon receiving the write request, the second functional unit may check the one or more control bits, and hold the data in a given queue dependent upon the control bits.

Abstract: Instructions may require one or more operands to be executed, which may be provided from a register file. In the context of a GPU, however, a register file may be a relatively large structure, and reading from the register file may be energy and/or time intensive An operand cache may be used to store a subset of operands, and may use less power and have quicker access times than the register file. Hint values may be used in some embodiments to suggest that a particular operand should be stored in the operand cache (so that is available for current or future use). In one embodiment, a hint value indicates that an operand should be cached whenever possible. Hint values may be determined by software, such as a compiler, in some embodiments. One or more criteria may be used to determine hint values, such as how soon in the future or how frequently an operand will be used again.

Abstract: Techniques are disclosed relating to predication. In one embodiment, a graphics processing unit is disclosed that includes a first set of architecturally-defined registers configured to store predication information. The graphics processing unit further includes a second set of registers configured to mirror the first set of registers and an execution pipeline configured to discontinue execution of an instruction sequence based on predication information in the second set of registers. In one embodiment, the second set of registers includes one or more registers proximal to an output of the execution pipeline. In some embodiments, the execution pipeline writes back a predicate value determined for a predicate writer to the second set of registers. The first set of architecturally-defined registers is then updated with the predicate value written back to the second set of registers. In some embodiments, the execution pipeline discontinues execution of the instruction sequence without stalling.

Abstract: The exemplary embodiments are related to systems and methods for prioritizing risk models and suggesting services tailored to a patient profile according to an exemplary embodiment described herein. One embodiment relates to a method comprising retrieving risk model and parameter data from a risk database, retrieving hospital profile data from a records database, determining a recommendation value for the model and parameter data based on the hospital profile data, determining at least one recommended service for a patient based on the recommendation value, and outputting the at least one recommended service to a user.

Abstract: A method of selecting a solution, comprises identifying a set of performance indicators that are correlated with a quality indicator. A target value is set for at least one of the performance indicators, based on a target in respect of the quality indicator. A plurality of solutions is selected, wherein a solution is associated with an effect on said at least one of the performance indicators for which a target value was set. At least one solution is selected of the plurality of solutions based on the target value of said at least one of the performance indicators and the effect of the selected at least one solution on said at least one of the performance indicators. A scenario is simulated with a particular value of at least one of the performance indicators, to obtain a predicted value of the quality indicator.

Abstract: An optical modulator includes first and second modulator segments. The first and second modulator segments form an optical signal path for an optical signal. The optical modulator also includes an electrical signal path capable of receiving and carrying a modulation signal, which is applied to the optical signal at the first and second modulation segments to generate a modulated optical signal. An inductive element may be disposed between electrical inputs to the first and second modulator segments. The optical modulator may be an electro-absorption modulator (EAM). The inductive element may be an inductor or a transmission line segment.

Abstract: The present invention is an electronic device including a submount for mounting a component thereon. The submount includes a first high speed transmission line electrically coupled to a contact for providing electrical contact to the component. At least two load resistors are also formed on the submount and electrically coupled to the contact. A second high speed transmission line is coupled between the two resistors to a ground electrode. The impedance and inductance of the second transmission line is desirably such as to provide a loss v. frequency characteristic that is essentially opposite to that of the first transmission line so as to produce a combined characteristic which is essentially flat.

Abstract: Optical alignment between a communication optical fiber and an optical device is achieved by using a substrate including a fiber-holding channel formed in the top surface of the substrate. The channel is particularly formed to include a central fulcrum region, against which the fiber is pressed into as the fiber-to-device alignment is performed. In particular, the fulcrum functions as a pivot point to allow for the free endface of the fiber nearest the optical device to be adjusted (performing a “fine” adjustment) by manipulating the opposing end of the fiber (using a “gross” movement) until alignment with the optical device is achieved. A reduction of, for example, 14:1 between the gross movement and the fine adjustment can be achieved by using the inventive fulcrum structure.

Abstract: A device, such as an optoelectronic device, including a submount and a cover, and a method of manufacture of such a device. The submount includes a substrate with a groove formed in the substrate. The substrate further includes at least one cavity formed in the substrate displaced from but in sufficiently close proximity to the groove so that a controlled amount of liquid adhesive, such as epoxy, in the cavity wicks into the groove when the cover is placed over the cavity and groove.

Abstract: The present invention is an electronic device including a submount for mounting a component thereon. The submount includes a first high speed transmission line electrically coupled to a contact for providing electrical contact to the component. At least two load resistors are also formed on the submount and electrically coupled to the contact. A second high speed transmission line is coupled between the two resistors to a ground electrode. The impedance and inductance of the second transmission line is desirably such as to provide a loss v. frequency characteristic that is essentially opposite to that of the first transmission line so as to produce a combined characteristic which is essentially flat.

Abstract: A device, such as an optoelectronic device, including a submount and a cover, and a method of manufacture of such a device. The submount includes a substrate with a groove formed in the substrate. The substrate further includes at least one cavity formed in the substrate displaced from but in sufficiently close proximity to the groove so that a controlled amount of liquid adhesive, such as epoxy, in the cavity wicks into the groove when the cover is placed over the cavity and groove.

Abstract: Optical alignment between a communication optical fiber and an optical device is achieved by using a substrate including a fiber-holding channel formed in the top surface of the substrate. The channel is particularly formed to include a central fulcrum region, against which the fiber is pressed into as the fiber-to-device alignment is performed. In particular, the fulcrum functions as a pivot point to allow for the free endface of the fiber nearest the optical device to be adjusted (performing a “fine” adjustment) by manipulating the opposing end of the fiber (using a “gross” movement) until alignment with the optical device is achieved. A reduction of, for example, 14:1 between the gross movement and the fine adjustment can be achieved by using the inventive fulcrum structure.

Abstract: An optical modulator includes first and second modulator segments. The first and second modulator segments form an optical signal path for an optical signal. The optical modulator also includes an electrical signal path capable of receiving and carrying a modulation signal, which is applied to the optical signal at the first and second modulation segments to generate a modulated optical signal. An inductive element may be disposed between electrical inputs to the first and second modulator segments. The optical modulator may be an electro-absorption modulator (EAM). The inductive element may be an inductor or a transmission line segment.

Abstract: A process for attaching one or more optoelectronic components to an optical submount uses an epoxy to first tack each component to its associated bondpad site. The epoxy has a sufficient strength to temporarily hold each component in place as various ones of the components are positioned, moved, etc. Once all of the components are “tacked” into position, the arrangement is heated to the solder reflow temperature, where the molten solder will displace the epoxy and form the final physical and electrical connection between the components and the submount. Preferably, the solder reflow temperature is sufficient to cure the epoxy, which then forms an inert substance that will not interfere with the performance of the final system.

Abstract: A cleaving apparatus, system and method which inhibit damage to cleave edges of laser bars are described. The cleaving apparatus includes a cleaving device having a first and a second slope meeting at a solitary cleave line. The slopes are angled to provide a solitary cleave point at the cleave line. Preferably, the first slope is between zero and four degrees and the second slope is about twenty degrees above a support structure upon which the cleaving device is mounted. A source of air may optionally provide air directed at the cleave line to assist in cleaving the laser bars.

Abstract: An apparatus and method for performing tests on laser chips that are not labor intensive and will not result in wasted parts should the laser chip fail the test is disclosed. A “bare” laser chip is subjected to a test in accordance with one embodiment by placing the laser chip on an insulating material with an embedded conducting contact through which the current to power the laser chip is passed. A cover plate provides a channel around the laser chip through which a jet of high pressure inert gas is passed to dissipate the self-heating of the laser chip that occurs during the test process. The laser chip is kept in place by physical pressure. In accordance with another embodiment, the temperature of the laser chip is measured and a thermoelectric cooler is used to cool the laser chip. The test on the “bare” laser chip eliminates the need to solder bond the laser chip to a carrier and attach wire bonds to the laser chip, thus reducing associated labor and parts costs.