Abstract: A method for measuring physician efficiency and patient health risk stratification is disclosed. Episodes of care are formed from medical claims data and an output process is performed. Physicians are assigned to report groups, and eligible physicians and episode assignments are determined. Condition-specific episode statistics and weighted episode statistics are calculated, from which physician efficiency scores are determined.

Abstract: A method and system for producing statistical analysis of medical care information comprises: aggregating medical care providers to a peer group level; aggregating medical care information at the peer group level and at the medical care provider level; computing a statistical analysis, such as performing Pearson's correlation analysis; and generating peer group level and medical care provider level results utilizing the computed statistical analysis.

Abstract: A system for the insertion of microthreads in transmitted data is provided. The system includes a digital content system providing carrier data, such as sampled audio data. A microthread insertion system coupled to the digital content system generates a composite data sequence that includes the carrier data and microthread data, such as broadcast verification data. The microthread data is camouflaged using the carrier data, such as by including in the audio signal in a manner that allows it to be detected but which does not noticeably affect the audio signal for listeners.

Abstract: Bulk data is read or written by an application on a first computer system to a file on a second heterogeneous computer system. Alternatively it is read or written as bulk data directly between applications on these heterogeneous systems. Jobs or tasks are started from one system to execute on a second heterogeneous system. Results are then returned to the first system. Checkpointing and later restarting is also initiated from a first system for execution on the second heterogeneous system.

Abstract: Atomic multiple word reads are provided when emulating a target system that supports atomic multiple word reads on a host system that does not. For each except the last word to be read, a gate flag is read using an advanced speculative load, and tested, until found unlocked. Check speculation instructions are utilized after the gate flag tests to verify that the corresponding cache lines have not been invalidated through a write by another processor since the speculative loads were issued. In a host system with a longer word size than the target system, the gate flags can be stored in otherwise unused bits in the host system words containing the target system words to be written.

Abstract: In an emulation of a multiprocessor Target computer system on a Host computer system, Host virtual memory addresses are mapped and utilized as Target virtual memory addresses. Target virtual memory control tables are setup accordingly. Each Target processor is mapped to a Host thread. When a page fault is detected by the Host operating system, it is checked to see if it belongs to the Target system, and if it does, the executing thread transfers its processor identity to a free thread, and then completes processing the page fault. Upon completion, it marks the processes that had been executing on that thread and processor as available for execution, then blocks until activated. Another thread, upon dispatching that process, wakes up the blocked thread and transfers its processor identity to that thread, which continues to execute the interrupted process.

Abstract: A plurality of processors in a data processing system share a common memory through which they communicate and share resources. When sharing resources, one processor needs to wait for another processor to modify a specified location in memory, such as unlocking a lock. Memory and bus traffic are minimized during this waiting by first reading and testing the memory location. Then, the memory location is not read and tested again until the local copy of the cache line containing that memory location is invalidated by another processor. This feature is utilized both for a Lock instruction and a Wait for Change instruction, both of which utilize a timer parameter for specifying a maximum number of cycles to wait for another processor to modify the specified location in memory.

Abstract: Atomic multiple word writes are provided when emulating a target system that supports atomic multiple word writes on a host system that does not. For each except the last word to be written, a gate flag is read, tested, and locked when it is found unlocked. The words are then written to memory in reverse order, unlocking the gate flags as they are written. In a host system with a longer word size than the target system, the gate flags can be stored in otherwise unused bits in the host system words containing the target system words to be written.

Abstract: A fault number is utilized by microcode fault handling to index into a fault array pointer table containing a plurality of pointers to entry descriptors describing fault handling routines. The pointer resulting from the indexing is utilized to retrieve an entry descriptor. The entry descriptor is verified and if valid, is utilized to setup the environment for the appropriate fault handling routine and to enter such. The fault array pointer table is located in a reserved memory that cannot be overwritten by I/O. During the boot process, the fault array pointer table entries, along with a fault-on-fault pointer are updated to point at entry descriptors stored in the reserved memory. Additionally, the fault-on-fault entry descriptor that rebuilds the processor environment if necessary from information in reserved memory.

Abstract: A fault number is utilized by microcode fault handling to index into a fault array pointer table containing a plurality of pointers to entry descriptors describing fault handling routines. The pointer resulting from the indexing is utilized to retrieve an entry descriptor. The entry descriptor is verified and if valid, is utilized to setup the environment for the appropriate fault handling routine and to enter such. The fault array pointer table is located in a reserved memory that cannot be overwritten by I/O. During the boot process, the fault array pointer table entries, along with a fault-on-fault pointer are updated to point at entry descriptors stored in the reserved memory. Additionally, the fault-on-fault entry descriptor that rebuilds the processor environment if necessary from information in reserved memory.

Abstract: Bulk data is read or written by an application on a first computer system to a file on a second heterogeneous computer system. Alternatively it is read or written as bulk data directly between applications on these heterogeneous systems. Jobs or tasks are started from one system to execute on a second heterogeneous system. Results are then returned to the first system. Checkpointing and later restarting is also initiated from a first system for execution on the second heterogeneous system.

Abstract: In a Cache-Coherent Non-Uniform Memory Architecture (CC-NUMA), the time as measured in cycles that it takes for cache control signals to travel between processors (92) sharing an L2 cache (94) differs from the time it takes for those signals to travel between processors (92) not sharing the same L2 cache (94). This difference, or DELTA, is dynamically computed by computing (332) the time it takes for a invalidate cache line cache command to travel between a local processor (92) and a master processor (92). This computation (334) is then made for the time it takes the signal to travel between a remote processor (92) and the master processor (92). The difference (336) is the DELTA value in cycles. This DELTA value can then be utilized to bias delay values when exhaustively testing the interactions among multiple processors in a CC-NUMA environment (180).

Abstract: In a data processing system implementing Dynamic Object Code Translation (DOCT) for emulating Target system instructions on a Host system, each Target system instruction has an associated index/offset field and an associated code tag that identifies whether the Target instruction has been translated into Host code, and if already translated, whether it is an entry point, middle, or last instruction in a block of code. When an emulator encounters a code tag indicating an entry point into a block of code, execution control is transferred to the corresponding Host code. Upon completion of the Host code block, execution control is returned to the emulator, with an indication of the next Target system instruction to execute. One code tag value is utilized to identify self-modified code. Another code tag value is utilized to indicate how often untranslated Target instructions have been interpreted in order to determine when to perform DOCT.

Abstract: A processor (92) contains a Trace RAM (210) for tracing internal processor signals and operands. A first trace mode separately traces microcode instruction execution and cache controller execution. Selectable groups of signals are traced from both the cache controller (256) and the arithmetic (AX) processor (260). A second trace mode selectively traces full operand words that result from microcode instruction (242). Each microcode instruction word (242) has a trace enable bit (244) that when enabled causes the results of that microcode instruction (242) to be recorded in the Trace RAM (210).

Abstract: In a data processing system implementing Dynamic Object Code Translation (DOCT) for emulating Target system instructions on a Host system, each Target system instruction has an associated index/offset field and an associated code tag that identifies whether the Target instruction has been translated into Host code, and if already translated, whether it is an entry point, middle, or last instruction in a block of code. When an emulator encounters a code tag indicating an entry point into a block of code, execution control is transferred to the corresponding Host code. Upon completion of the Host code block, execution control is returned to the emulator, with an indication of the next Target system instruction to execute. One code tag value is utilized to identify self-modified code. Another code tag value is utilized to indicate how often untranslated Target instructions have been interpreted in order to determine when to perform DOCT.

Abstract: In a NUMA architecture, processors in the same CPU module with a processor opening a spin gate tend to have preferential access to a spin gate in memory when attempting to close the spin gate. This “unfair” memory access to the desired spin gate can result in starvation of processors from other CPU modules. This problem is solved by “balking” or delaying a specified period of time before attempting to close a spin gate whenever either one of the processors in the same CPU module just opened the desired spin gate, or when a processor in another CPU module is spinning trying to close the spin gate. Each processor detects when it is spinning on a spin gate. It then transmits that information to the processors in other CPU modules, allowing them to balk when opening spin gates.

Abstract: A method of addressing mass storage memory in which information is stored in Space Control Pages of physically contiguous disk segments subject to irregularities in the mapping is disclosed. Space Control Pages fall at regular intervals across the address space. An efficient hashing method is disclosed that first hashes record keys across the entire address space to form a hash index. If the hash index falls into one of the Space Control Pages, the key is rehashed across the contiguous hash space following the Space. Control Page utilizing a second hash function. The result of the second hash function is added to the start of the contiguous hash space following the Space Control Page to generate the hash index utilized for those records that initially hashed into a Space Control Page. In all cases the generated hash index is utilized to store and retrieve records in a database or hash file.

Abstract: Two instructions are provided to synchronize multiple processors (92) in a data processing system (80). A Transmit Sync instruction (TSYNC) transmits a synchronize processor interrupt (276) to all of the active processors (92) in the system (80). Processors (92) wait for receipt of the synchronize signal (278) by executing a Wait for Sync (WSYNC) instruction. Each of the processors waiting for such a signal (278) is activated at the next clock cycle after receipt of the interrupt signal (278). An optional timeout value is provided to protect against hanging a waiting processor (92) that misses the interrupt (278). Whenever the WSYNC instruction is activated by receipt of the interrupt (278), a trace is started to trace a fixed number of events to an internal Trace Cache (58).

Abstract: One way of filtering graphics images to remove pixel dropout and shot noise while preserving overall image quality is to use non-linear filters based on rank order of an M.times.N grid of pixel values surrounding a pixel to be filtered. This rank order filter method for M.times.N grids first sorts columns, then sorts rows, and finally sorts diagonals to obtain either just a median filter value, a rank-based filter value, or a complete sorted order of the M.times.N grid. All of the sort operations are control-flow-free allowing implementation on SIMD processors processing multiple overlapping M.times.N grids in parallel. Advantage is taken of columns and rows that are shared among the horizontally and vertically overlapping M.times.N grids in the digital image to reduce the total number of sort operations for the image.

Abstract: An arithmetic logic unit (30) for a digital signal processor (DSP) contains circuitry for preshifting (46, 48) and prerounding (54) the 2's-complement fractional input operands (32, 34) before they are used by a carry look-ahead adder (56). The preshifting (46, 48) provides for efficient divide-by-2 and divide-by-4 functionality and reduces early overflow. Concurrent preshifting (46, 48) and prerounding (54) improve the critical path timing in the carry look-ahead adder (56).