Abstract: One or more measurements of processor utilization are taken. A utilization ceiling is calculated. One or more processing units (PUs) are added automatically if it is determined that the utilization ceiling is greater than an available PU capacity. One or more PUs are removed automatically responsive to determining that the utilization ceiling is at least one PU less than the available PU capacity.

Abstract: In one exemplary embodiment, a program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine for performing operations, said operations including: depositing a first layer having a first metal on a surface of a semiconductor structure, where depositing the first layer creates a first intermix region at an interface of the first layer and the semiconductor structure; removing a portion of the deposited first layer to expose the first intermix region; depositing a second layer having a second metal on the first intermix region, where depositing the second layer creates a second intermix region at an interface of the second layer and the first intermix region; removing a portion of the deposited second layer to expose the second intermix region; and performing at least one anneal on the semiconductor structure.

Abstract: A method receives a complex instruction comprising a first portion and a second portion. The method sets a single issue queue slot and allocates an execution unit for the complex instruction, and identifies dependencies in the first and second portions. The method sets a dependency matrix slot and a consumers table slot for the first and section portion. In the event the first portion dependencies have been satisfied, the method issues the first portion and then issues the second portion from the single issue queue slot. In the event the second portion dependencies have not been satisfied, the method places the second portion into a side issue queue. The method issues the second portion when the side issue queue indicates that the second portion is eligible for issue.

Abstract: Methods and systems are provided for solving an optimization problem using a model expressed in a mixed integer programming (MIP) language. The problem is constrained within a space of valid solutions by a plurality of MIP variables. A skeleton set of the variables are designated as eligible for fixed value assignments. An initial solution for the problem is obtained, which forms the basis for refinement. New versions of the problem are prepared and solved iteratively by fixing a proportion of the skeleton set to their best known values, as found in a previous problem-solving iteration.

Abstract: A method (500) or a diagnostic recording device (400) having transactional memory and a processor coupled to the transactional memory can store (502) contents of a transaction log (40) of the transactional memory, detect (504) an exception event, and replay (506) last instructions that led up to the exception event using a debugger tool (80). The transactional memory can be hardware or software based transactional memory. The processor can also store the transaction log by storing the contents of the transaction log in a core file (302) which can include a stack (60), a register dump (70), a memory dump (75), and the transactional log. The debugger tool can be used to load up the core file, an executable file (95), and a library (90) to enable the diagnostic recording device to retrace transactions occurring at the diagnostic recording device up to the exception event.

Abstract: A method and structure is disclosed for dispatching appropriate data to a network processing system comprising an improved technique for extracting protocol header fields for use by the network processor. This technique includes basic classification of a packet according to the types of protocol headers present in the packet. Based on the results of the classification, specific parameter fields are extracted from corresponding headers. All such parameter fields from one or more protocol headers in the packet are concatenated into a compressed dispatch message. Multiple of such dispatch messages are bundled into a single composite dispatch message. Thus selected header fields from N packets are passed to the network processor in a single composite dispatch message, increasing the network processor's packet forwarding capacity by a factor of N. Likewise, multiple enqueue messages are bundled into a single composite enqueue message to direct enqueue and frame alterations to be taken on the bundle of N packets.

Abstract: A method and structure are disclosed for dispatching appropriate data to a network processing system comprising an improved technique for extracting protocol header fields for use by the network processor. This technique includes basic classification of a packet according to the types of protocol headers present in the packet. Based on the results of the classification, specific parameter fields are extracted from corresponding headers. All such parameter fields from one or more protocol headers in the packet are concatenated into a compressed dispatch message. Multiples of such dispatch messages are bundled into a single composite dispatch message. Thus, selected header fields from N packets are passed to the network processor in a single composite dispatch message, increasing the network processor's packet forwarding capacity by a factor of N.

Abstract: The present invention relates generally to a new structure and a method for reducing the cost of producing known good die (KGD). More particularly, the invention encompasses a structure and a method that uses a substrate having solder wettable pads, a chip with attached solder balls, and a thin non-conductive interposer that is assembled between the chip and the substrate. The interposer reduces the cross section of the solder connections from the chip to the substrate where the solder passes through (the holes in) the interposer. This reduced cross-sectional area of the solder connection creates a weak point which allows the chip to be easily sheared off of the substrate after a burn-in and test process. The preferred chips for this invention are flip chips.