International Business Machines Corporation

Charles Porter Geer

Steven John Baumgartner

David W Siljenberg

Anthony Richard Bonaccio

Anthony Gus Aipperspach

Timothy Clyde Buchholtz

Richard G Eikill

Daniel Mark Dreps

David Paul Paulsen

Sergey Vladimirovich Rylov

Mounir Meghelli

Alan P Wagstaff

Dana Marie Woeste

Quentin G Schmierer

Robert Allen Shearer

John Michael Borkenhagen

Sheldon Bernard Levenstein

Ronald Nick Kalla

Shmuel Ur

Daniel Guy Young

Frank G Soltis

Merle E Houdek

David W Marquart

Eugene R Jones

Thomas M Walker

Jerome Martin Meyer

Steven J Finnes

Lam Q Dang

John A Soyring

A level-shifting latch circuit for coupling a first circuit in a first voltage domain with a second circuit in a second voltage domain, includes an input node to receive an input signal provided by the first circuit, and an output node to output a level-shifted signal, corresponding with the input signal. The level-shifting latch circuit also includes a first latch, having a first node and a second node, for storing the input signal in the first voltage domain, and a second latch, having a third node and a fourth node, for storing the input signal in the second voltage domain. In addition, the level-shifting circuit also includes a first switching element which provides a path to transfer a low voltage at the first node to the third node, and a second switching element which provides a path to transfer a low voltage at the second node to the fourth node.

Level-shifting latch

A design structure for a high speed computer processor system includes a high speed interface for a graphics processor. In a preferred embodiment, the high speed interface includes a front side bus (FSB) that interfaces to a similar high speed interface on the graphics processor.

Architecture for a physical interface of a high speed front side bus

A design structure is described for dynamically aligning clocks in independent clock domains with minimal latency. In the preferred embodiments, a reference clock in the destination clock domain that is some multiple times the data clock of the destination clock domain is used to sample a data sample signal from the source domain. The sampled data is used to determine at what time slice of the reference clock the data sample signal is changing and therefore at what phase of time slice or phase of the data clock the clocks can be aligned to ensure valid data will be transferred between clock domains.

Dynamic clock phase alignment between independent clock domains

An apparatus and method is described for dynamically aligning clocks in independent clock domains with minimal latency. In the preferred embodiments, a reference clock in the destination clock domain that is some multiple times the data clock of the destination clock domain is used to sample a data sample signal from the source domain. The sampled data is used to determine at what time slice of the reference clock the data sample signal is changing and therefore at what phase of time slice or phase of the data clock the clocks can be aligned to ensure valid data will be transferred between clock domains.

A high speed computer processor system includes a high speed interface for a graphics processor. In a preferred embodiment, the high speed interface includes a front side bus (FSB) that interfaces to a similar high speed interface on the graphics processor.

Techniques and apparatus for testing phase rotators for detecting defective tap weights are provided. Phase rotator test logic may include a master phase rotator to cycle the phase of a clock signal distributed to operational phase rotators through an entire cycle of phases (e.g., an entire 360 degree rotation). Each operational phase rotator should respond with an equal but opposite phase shift in order to maintain phase lock. Thus, after sweeping, each tap weight is exercised, which may help ensure defective tap weights in any (e.g., quadrant) are detected during testing.

Phase rotator control test scheme

A system, method and apparatus for aligning data sequentially received on multiple single-byte data paths are provided. A sufficient number of bytes received in each channel may be stored (e.g., buffered) and examined to properly match data from each single-byte path. Once matched, the data may be output in a proper order on the multi-byte interface, for example, via some type of multiplexor arrangement. Furthermore, alignment operations may be performed in such a way so as to reduce the latencies involved in aligning data.

Latency optimized data alignment racheting scheme

An apparatus and method is disclosed for programmable determination of frequency, phase, and jitter relationship of a first clock and a second clock in an electronic system. In a first, initialization, mode, a first register and a second register are initialized with a first bit pattern and a second bit pattern, respectively. In a second, normal, mode, the first clock is coupled to the first register and the second clock is coupled to the second register. A compare unit observes the bit patterns of the first and second registers and reports when one or more predetermined relationships between the first clock and the second clock occur.

Clock frequency detect with programmable jitter tolerance

Testcases are run to test the design of an integrated circuit. The coverage of the testcases is evaluated and compared against one or more microarchitecture models that define the behavior of a portion of the integrated circuit. If the coverage of the testcases is not adequate, new testcases are generated to test the previously untested behavior specified in the microarchitecture models.

Integrated circuit test coverage evaluation and adjustment mechanism and method

A circuit arrangement and method of dynamically repairing a redundant memory array utilize dynamically-determined repair information, generated from a memory test performed on the redundant memory array, along with persistently-stored repair information to repair the redundant memory array. In one implementation, for example, the persistent repair information is generated during manufacture to repair manufacturing defects in the array, with the dynamic repair information generated during a power-on reset of the array to address any additional faults arising after initial manufacture and repair of the array. Furthermore, repair of dynamically-determined errors may utilize otherwise unused redundant memory cells in a redundant memory array, thus minimizing the additional circuitry required to implement dynamic repair functionality with an array.

Dynamic repair of redundant memory array

A data processing network includes multiple processing devices, multiple memory cards of main storage, and a main storage interface shared by the processors and memory cards. Each of the memory cards includes memory arrays, a hold register for retaining a data pattern stored to the arrays, a compare register and logic circuity. For a memory array diagnostic test, one of the processing devices sends a compare command (including address information) and the data pattern to one of the memory cards. In response, the logic circuity on the selected memory card stores the data pattern to its hold register and writes the data pattern into its memory arrays, then reads the data out of the memory arrays into its compare register. The contents of the compare and hold registers are compared, and an error indication provided to the processing device in the event that these registers' contents are not the same.

Memory card resident diagnostic testing

A fast store-through cache process is disclosed in connection with multiple processors sharing a main storage memory. Each processor has a cache memory including multiple cache lines, each line associated with an address in main storage. Each cache memory has a cache directory for recording main storage addresses mapped into cache memory, identifying cache lines as valid or invalid, and holding status bits of data words stored in the cache memory. According to the process, a data word is stored in the cache memory during a first clock cycle and the associated cache directory is read to determine whether the corresponding main storage address is mapped into the cache memory. If so, and if no status bits in the data word require update, the store to the cache memory is complete. If a different main storage address is mapped into the cache memory, processor logic generates a processor interrupt signal during the second clock cycle, and the processor is interrupted during the third clock cycle while the cache directory is modified to purge the corresponding cache line. If the main storage address is in the cache memory but the data includes at least one status bit requiring update, the interrupt signal is generated during the second clock cycle, with the cache directory modified to update status bits during the third clock cycle. Special logic forces modifications to the cache directory if two consecutive store or fetch operations correspond to the same location in main storage.

Fast store-through cache memory

A data processing network includes multiple processing devices, one or more memory cards in main storage, and a shared interface for processor access to main storage. Each of the memory cards includes dynamic random access memory arrays which require a periodic refresh pulse. To provide refresh pulses, each of the memory cards includes a programmable register, a counter receiving clock pulses, and a comparator. The comparator generates a request pulse each time the output from the pulse counter equals a selected value provided by the register. The register is programmable to controllably adjust the selected value, and thus select the frequency at which refresh request pulses are generated by the comparator. The memory card further includes a buffer for receiving the refresh request pulses and generating a refresh request responsive to each pulse. Responsive to the refresh request, a memory array control circuit either provides a refresh signal to the arrays, or stores the refresh request, depending on whether the arrays are busy with an external request. However, when stored requests accumulate to a predetermined threshold, the external request is interrupted and a refresh signal is provided to the arrays.

Memory card refresh buffer

A method and apparatus are provided for uniquely identifying integrated circuit chips adapted for use with scan design systems and scan testing techniques. A predetermined identification number corresponding to each LSI chip to be identified is assigned. Each predetermined identification number has a predefined format. The assigned identification number is stored in a plurality of predefined shift register latches (SRLs) in the corresponding LSI chip to be identified. Then the LSI chip is identified by selectively reading out the stored predetermined identification number.

Growing community of inventors

Rochester, MN, United States of America

Charles Porter Geer