International Business Machines Corporation

Robert Dominick Mirabella

Alexander Erik Mericas

Hung Qui Le

Michitaka Okuno

Masahiro Tokoro

Toshihiko Kurihara

Paul William Coteus

Michael Stephen Floyd

Warren Edward Maule

Dung Q Nguyen

Mark William Kellogg

John Michael Kaiser

James Wilson Bishop

Harry R Bickford

Philip Lee Vitale

David Wayne Victor

Wally Tuten

Hideki Mitsubayashi

An apparatus, system and method of integrating performance monitor data with thermal event information are provided. A thermal event, in this case, is when the temperature of a chip within which is embedded a processor exceeds a user-configurable value while the processor is processing instructions and/or using storage devices that are being monitored. In any event, when the thermal event occurs, the temperature of the chip along with the performance monitor data is stored for future uses, which include performance and diagnostic analyses.

Apparatus, system and computer program product for seamlessly integrating thermal event information data with performance monitor data

A method for pseudo-randomly, without bias, selecting instructions for marking in a microprocessor. Responsive to reading an instruction from an instruction cache, an instruction tag associated with the instruction is compared against a pseudo-randomly generated value in a linear feedback shift register (LFSR). If the instruction tag matches the value in the LFSR, a mark bit, indicating the instruction is a marked instruction, is sent with the instruction to an execution unit. Responsive to an indication from the performance monitor, the value in the LFSR is incremented prior to selecting a next instruction to mark. If the value equals a predetermined prime number of increments, the value is reset to all ones to avoid any harmonics with the code stream being executed. Upon receiving the marked instruction, the execution unit combines the marked bit with a selected event and reports the marked event to the performance monitor.

Methods to randomly or pseudo-randomly, without bias, select instruction for performance analysis in a microprocessor

Method of seamlessly integrating thermal event information data with performance monitor data

A method for determining the latency for a particular level of memory within a hierarchical memory system is disclosed. A performance monitor counter is allocated to count the number of loads (load counter) and for counting the number of cycles (cycle counter). The method begins with a processor determining which load to select for measurement. In response to the determination, the cycle counter value is stored in a rewind register. The processor issues the load and begins counting cycles. In response to the load completing, the level of memory for the load is determined. If the load was executed from the desired memory level, the load counter is incremented. Otherwise, the cycle counter is rewound to its previous value.

Method for measuring memory latency in a hierarchical memory system

A method and system for identifying instruction completion delays for a group of instructions in a computer processor. Each instruction in the group of instructions has a status indicator that identifies what is preventing that instruction from completing execution. Examples of completion delays are cache misses, data dependencies or simply the time required for an execution unit in the computer processor to process the instruction. As each instruction finishes executing, its associated status indicator is cleared to indicate that the instruction is no longer waiting to execute. The last instruction to execute is the instruction that is holding up completion of the entire group, and thus the cause for the completion delay of the last instruction is recorded as the cause of completion delay for the entire group.

Analyzing instruction completion delays in a processor

A method and system for analyzing cycles per instruction (CPI) performance in a processor. A completion table corresponds to the instructions in a group to be processed by the processor. An empty completion table indicates that there has been some type of catastrophe that caused a table flush. While the table is empty, a performance monitoring counter (PMC), located in a performance monitoring unit (PMU) in the processor, counts the number of clock cycles that the table is empty. Preferably, a separate PMC is utilized depending on the reason that the completion table is empty. A second PMC likewise counts the number of clock cycles spent re-filling the empty completion table. A third PMC counts the number of clock cycles spent actually executing the instructions in the completion table. The information in the PMC's can be used to evaluate the true cause for degradation of CPI performance.

Counting latencies of an instruction table flush, refill and instruction execution using a plurality of assigned counters

A circuit and method for maintaining a correct value in performance monitor counter within a speculative computer microprocessor is disclosed. In response to determining the begin of speculative execution within the microprocessor, the value of the performance monitor counter is stored in a rewind register. The performance monitor counter is incremented in response to predetermined events. If the microprocessor determines the speculative execution was incorrect, the value of the rewind register is loaded into the counter, restoring correct value for the counter.

Speculative counting of performance events with rewind counter

Memory cards for a computer system are placed back-to-back on an active backplane, using wiring topology where the memory address and data busses are wired to pairs of symmetrical connectors. This topology takes advantage of symmetrical memory card pinouts to improve memory bus performance while reducing backplane cost and wiring complexity. The symmetrical layout of the data and address wiring allows two memory cards to be placed back-to-back on the backplane, maintaining the same relative position of data and address pins between cards. Since the data and most of the address lines are common to each card, and any such data or (common or non-unique) address pin on one card can be wired to any other such data or address pin, respectively, on the other card, the back-to-back arrangement provides for minimal address and data bus interconnect lengths between connectors. Each data signal can be wired from a memory controller data pin on the first connector, then daisy-chained through the short printed circuit card wire to an adjacent pin on the second connector. Likewise, non-unique address pins can be connected from the memory controller to such address pins that are parallel between connectors. Those unique address and control signals which are to be connected together are placed as close as possible to the centerpoint of the edge connector.

Memory cards with symmetrical pinout for back-to-back mounting in computer system

A vital product data (VPD) detection circuit mountable on a substrate of a pluggable component. The circuit comprises a 'parallel read' circuit for generating vital product data associated with the pluggable component, a 'serial read' circuit for storing and retrieving vital product data associated with the pluggable component, and means for interconnecting the parallel and serial read circuits. The parallel read circuit preferably comprises a parallel array of transistors surface-mounted on the substrate, and the serial read circuit preferably comprises a serial EEPROM having a clock input, a set of address inputs, and a bidirectional data pin. A VPD detection mechanism may disable the parallel VPD circuitry in favor of the serial VPD detection circuitry, or vice versa, or these circuits may be enabled but activated in a mutually exclusive manner.

Pluggable electronic card presence detect scheme for use in parallel and

A method and apparatus are provided which are implemented in a chip I/O buffer-multiplexor circuit or I/O buffer cell 201. The I/O buffer portion includes a receiver circuit 205 for receiving bus input signals to the buffered chip, and a driver circuit 203 for driving output signals from the buffered chip to a data bus. An integrated multiplexor or MUX circuit 207 selectively gates one of three possible signals to chip internal logic. The three signals applied to the MUX circuit include a boundary scan test signal BS MUX for testing scan points in an integrated circuit, a bypass Data In signal DI which is generated by chip internal drive logic, and a DQ signal received by the I/O buffer receiver circuit from a data bus. The data input node of the I/O buffer is wired directly to the new multiplexor data input. Additional control signals are provided for orthogonal selection of the three multiplexor data inputs.

Bidirectional off-chip driver with receiver bypass

To present a consistent image of storage facilities to components in Bi-modal Endian PowerPC system enviromnents, provision is made for transferring data between system components in the appropriate Endian format. Endian conversion function can be incorporated into the memory controller subsystem by adding byte-lane swapping logic on the inbound and outbound I/O data paths. With this structure, inbound data from the processor and memory bus will be converted to true Little Endian order before being sent to I/O devices. Likewise, true Little Endian data from I/O devices targeted for the processor or memory is modified to reflect the PowerPC Little Endian byte ordering convention.

Growing community of inventors

Round Rock, TX, United States of America

Robert Dominick Mirabella