International Business Machines Corporation

Michel Henri Theodore Hack

Li Feng Zhang

Scott M Carlson

Peter Anthony Franaszek

Vincenzo Condorelli

Charles Otto Schulz

Elaine Rivette Palmer

Sean William Smith

Thomas Basil Smith, Iii

Steve Harris Weingart

Mark John Lindemann

Jeffrey Kenneth Kravitz

Gianluca Pedrina

Mario Bizzaro

A system/method for profiling a sequence of values from a range to determine a frequency of occurrence of a subrange includes, for a current block, determining whether cells of the current block include a count cell or a pointer cell. If the cell includes a pointer cell, follow an address that the pointer makes reference to and designate a new block as the current block and repeat the determining step for the new block. If the cell includes a count cell, increment the count cell and compare the incremented count cell to a threshold. If the count exceeds the threshold, convert the count cell to a pointer cell, which points to a newly allocated block. The newly allocated block is made the current block, and the steps are repeated until count cells do not exceed the threshold or a limit resolution is achieved.

Adaptive profiling by progressive refinement

A system and method for converting bases of floating point numbers using fixed-point computation includes tables having different related spacings of exponent indices. The tables are adapted to cross-reference conversion ratios between exponent bases. The tables are characterized by bi-uniform spacings of source and target exponents and including near-unity table entries representing the conversion ratios. A source number is converted into a target number in a different radix by a sequence of reduction operations using a sequence of the tables. The reduction operations include reducing a source number exponent magnitude and accumulating a target exponent and multiplying a source number mantissa by a selected conversion ratio including a near-unity ratio of powers. A final mantissa is normalized and rounded to produce the target number in a new radix.

Fast correctly-rounding floating-point conversion

A system and method for converting bases of floating point numbers with improved rounding over an entire exponent range includes identifying exceptional conversions for a given source precision to target precision. A representation of the exceptions is stored in a bit vector for use during conversion execution.

Fast correctly rounding floating point conversion and identifying exceptional conversion

Disclosed are a method and system for estimating the skew and offset between two clocks in a computer system. The method comprises the steps of obtaining a first set of data values representing a forward delay between the first and second clocks, and obtaining a second set of data values representing a negative backward delay between the first and second clocks. The method comprises the further steps of forming a lower convex hull for said first set of data values, and forming an upper convex hull, above the lower convex hull, for said second set of data values. The clock offset and the skew between said first and second clocks are estimated using those convex hulls. In a preferred embodiment, this estimation is made by identifying a best clock line between the first and second convex hulls.

Method and system for clock skew and offset estimation

Disclosed is a method for calculating clock offset and skew between two clocks in a computer system. The method comprises the steps of sending data packets from a first processing unit in the computer system to a second processing unit in the computer system, and sending the data packets from the second processing unit to the first processing unit. First, second, third and fourth time stamps are provided to indicate, respectively, when the packets leave the first processing unit, arrive at the second processing unit, leave the second processing unit, and arrive at the first processing unit. The method comprises the further steps of defining a set of backward delay points using the fourth time stamps, and calculating a clock offset between clocks on the first and second processing units and clock skews of said clocks using said set of backward delay points.

Method for calculating clock offset and skew

Memory is managed by controlling the expansion of memory contents, especially in those computing environments in which the memory contents are compressed. Control is provided by imposing some restrictions to memory references outside a specified subset of the memory contents, and by controlling the transfer of items into the subset. In one example, the transfer of items into the subset is based on a function of parameters, including an estimate of the amount of free space in the memory.

Space management in compressed main memory

An apparatus for permitting access to protected code, protected data or protected devices only when a computer system is in a trusted state, where said trusted state occurs only when said system is executing trusted code under a set of preselected conditions. This apparatus also has a device for exiting the trusted state and for preventing access to protected code, data and devices when the trusted state is exited. The computer system is also programmed to automatically generate a disabling signal upon the completion of execution of trusted code, and this disabling signal will result in the prevention of access to protected devices or code.

Growing community of inventors

Cortlandt Manor, NY, United States of America

Michel Henri Theodore Hack