International Business Machines Corporation

John Stephen Liptay

Charles Franklin Webb

Mark Anthony Check

Mark S Farrell

Barry Watson Krumm

Timothy John Slegel

Steven T Comfort

Eric M Schwarz

Bruce C Giamei

Chung-Lung K Shum

Jennifer A Navarro

Ronald M Smith

James Walter Rymarczyk

Clifford O Hayden

Susan B Stillman

Steven QiHong Ying

Brian Robert Prasky

Christopher A Krygowski

Dean G Bair

Jin Song Ji

Patrick M Gannon

Jennifer Serena Navarro

Richard N Gustafson

David Man Wong

Steven B Risch

Stanley E Stone

Jeffrey F Hughes

A method of supporting programs that include instructions that modify subsequent instructions in a multi-processor system with a central processing unit including an execution unit, and instruction unit and a plurality of caches including a separate instruction and operand cache.

Program store compare handling between instruction and operand caches

A method is disclosed for instructing a computing system to ensure that a line is present in an instruction cache that includes selecting a line-touch instruction, recognizing the line-touch instruction as a type of branch instruction where the branch is not taken, executing the line-touch instruction to fetch a target line from a target address into the instruction cache, and interlocking the execution of the line-touch instruction with the completion of the fetch of the target line in order to prevent execution of the instruction following the line-touch instruction until after the target line has reached the cache.

Method for ensuring that a line is present in an instruction cache

A method is disclosed for selecting data in a computer system having a cache memory and a branch history table, where the method includes predicting an address corresponding to the data, selecting data at the predicted address in the cache memory, translating an address corresponding to the data, comparing the translated address with the predicted address, and if they are different, re-selecting data at the translated address in the cache memory and appending the translated address to the branch history table.

Absolute address bits kept in branch history table

A method and system for detecting address generation interlock in a pipelined data processor is disclosed. The method comprises accumulating a plurality of vectors over a predefined number of processor clock cycles, with subsequent vectors corresponding to subsequent clock cycles; accumulating the status of one or more general registers in the plurality of vectors with the same bit location in each vector of the plurality of vectors corresponding to a particular general register; generating a list of pending general register updates from a logical combination of the plurality of vectors; and determining the existence of address generation interlock from the list of pending general register updates.

Address generation interlock detection

An exemplary embodiment of the present invention is a method and system for reducing the number of branch instructions required to test combinations of millicode branch points. The method is implemented via a pipe-lined computer processor executing a millicode routine. The processor interrogates a millicode condition code; interrogates a first field of the TMBP instruction, the results of which determine a logical function to be performed on the millicode condition code; interrogates a second field of the TMBP instruction which specifies a first millicode branch point; interrogates a third field of the TMBP instruction, which specifies a second millicode branch point; and sets a millicode condition code based upon the results of the interrogating and used for executing subsequent TMBP instructions or conditional branch instructions.

Method and system for testing millicode branch points

A computer processor that uses an AAHT to provide a guess at the real (absolute) address bits used to access the cache and directories that is more accurate in a high-frequency design which prevents any sort of full or large partial adds of ranges of base, index, or displacement has two index values generated and two AAHT arrays, one each for instruction and operand logical requests. It handles cases in which the data is not directly from the GPR array. For designs that aim at improving performance data for some operations that update GPR's may be used for address generation prior to the execution and write to the GPR array, these include data bypass for Load Address (LA) and Load (L). The system handles instruction fetches, relative branches, other special instruction address instruction fetch requests, and those started as a result of a branch history table (BHT) predicted instruction fetch. A method for AAHT synonym resolution improves the accuracy of the index value for an Absolute Address History Table buffer.

Absolute address history table index generation for predicting

A millimode capable computer system provides control to millicode to allow the BHT operations to continue except when the these special situations occur that require control of instruction fetch operations must be provided and the BHT can be turned off for some sections of code execution, but not disabled for all. A single free running BHT functions for both a normal mode and a millimode for the central processor which can execute in millimode with a branch history table directing instruction fetch for which both a global BHT disable and millicode disables exist. Hit detection logic receives input from the global BHT disable, as well as from an initialized control register bit and a processor control register bit to select the correct set target information and generate a 'branch history table hit detected' control signal.

Millimode capable computer system providing global branch history table

Globally or selectively disabling branch history table operations during

A computer processor floating point processor six cycle pipeline system where instruction text is fetched prior to the first cycle and decoded during the first cycle for the fetched particular instruction and the base (B) and index (X) register values are read for use in address generation. RXE Instructions are of the RX-type but extended by placing the extension of the operation code beyond the first four bytes of the instruction format and to assign the operation codes in such a way that the machine may determine the exact format from the first 8 bits of the operation code alone. ESA/390 instructions SS, RR; RX; S; RRE; RI; and the new RXE instructions have a format which can be used for fixed point processing as well as floating point processing where instructions of the RXE format have their R1, X2, B2, and D2 fields in the identical positions in said instruction register as in the RX format to enable the processor to determine from the first 8 bits of the operation code alone that an instruction being decoded is an RXE format instruction and the register indexed extensions of the RXE format instruction, after which it gates the correct information to said X-B-D adder. During the second cycle the address add of B+X+Displacement is performed and sent to the cache processor's, and during the third and fourth cycles the cache is respectively accessed and data is returned, and during a fifth cycle execution of the fetched instruction occurs with the result putaway in a sixth cycle.

Address bit decoding for same adder circuitry for RXE instruction format

A computer processor system having a floating point processor for instructions which are processed in a six cycle pipeline, in which prior to the first cycle of the pipeline an instruction text is fetched, and during the first cycle for the fetched particular instruction it is decoded and the base (B) and index (X) register values are read for use in address generation. Instructions of the RX-type are extended by placing the extension of the operation code beyond the first four bytes of the instruction format and to assign the operation codes in such a way that the machine may determine from the first 8 bits of the operation code alone, the exact format of the instruction. Instructions formats include the ESA/390 instructions SS, RR; RX; S; RRE; RI: and the new RXE instructions. where instructions of the RXE format have their R.sub.1, X.sub.2, B.sub.2, and D.sub.2 fields in the identical positions in said instruction register as in the RX format to enable the processor to determine from the first 8 bits of the operation code alone that an instruction being decoded is an RXE format instruction and the register indexed extensions of the RXE format instruction, after which it gates the correct information to said X-B-D adder. During the second cycle the address add of B+X+Displacement is performed and sent to the cache processor's, and during the third and fourth cycles the cache is respectively accessed and data is returned, and during a fifth cycle execution of the fetched instruction occurs with the result putaway in a sixth cycle.RXE instructions can be used for floating point processing and fixed point processing.

Computer processor system for executing RXE format floating point

A computer for executing programs and having a structure for fetching instructions and/or operands along a path which may not be taken by a process being executed by a computer processor having a hierarchical memory structure with data being loaded into cache lines of a cache in the structure, and having block line fetch signal selection logic and computational logic with hedge selection logic for generating line fetch block signals for control of hedging by fetching instructions and/or operands along a path which may not be taken by a process being executed and making selected hedge fetches sensitive to whether the data is in the cache so as to gain the best performance advantage with a selected hedge fetch signal which accompanies each fetch request to the cache to identify whether a line should be loaded if it misses the cache to indicate a selected hedge fetch when this signal is ON, and rejecting a fetch request in the event the selected hedge fetch signal is turned ON if the data is not in the cache, the cache will reject the fetch, and thereafter repeating the fetch request after a fetch request has been rejected when the selected hedge fetch signal was turned ON the data was not in the cache to repeat the fetch request at a later time when it is more certain that the process being executed wants the data, or never repeating the request upon determination that the process being executed does not need the data to he fetched.

Computer with optimizing hardware for conditional hedge fetching into

A computer for executing programs and having a structure for fetching instructions and/or operands along a path which may not be taken by a process being executed by a computer processor having a hierarchical memory structure with data being loaded into cache lines of a cache in the structure, and having block line fetch signal selection logic and computational logic with hedge selection logic for generating line fetch block signals for control of hedging by fetching instructions and/or operands along a path which may not be taken by a process being executed and making selected hedge fetches sensitive to whether the data is in the cache so as to gain the best performance advantage with a selected hedge fetch signal which accompanies each fetch request to the cache to identify whether a line should be loaded if it misses the cache to indicate a selected hedge fetch when this signal is ON, and rejecting a fetch request in the event the selected hedge fetch signal is turned ON if the data is not in the cache, the cache will reject the fetch, and thereafter repeating the fetch request after a fetch request has been rejected when the the selected hedge fetch signal was turned ON the data was not in the cache to repeat the fetch request at a later time when it is more certain that the process being executed wants the data, or never repeating the request upon determination that the process being executed does not need the data to be fetched.

Method for conditional hedge fetching into cache storage

A method and system for processing instructions in a floating point unit for executing denormalized numbers in floating point pipeline via serializing uses an instruction unit and having a control unit and a pipelined data flow unit, a shifter and a rounding unit. The floating point unit has an external feedback path for providing intermediate result data from said rounding unit to an input of the pipelined data flow unit to reuse the pipeline for denormalization by passing intermediate results in the pipeline which have a denormalized condition computed after the exponent calculation of the shifting circuit directly from the rounding unit to the top of the dataflow in the pipeline via an external feedback path. The pipelined has two paths which are selected based on the presence of other instructions in the pipeline. If no other instructions are in the pipeline a first path is taken which uses the external feedback path from the rounding unit back into the top of the dataflow. When there are instructions in the pipeline a shifter unit performing normalization of the fraction indicates possible underflow of the exponent, and prepares to hold the exponent and the fraction in a floating point data flow register; and upon detection of exponent underflow during the rounder stage and detection of any other instructions in pipeline; then the control unit forces an interrupt for serialization, and cancels execution of this instruction and other instructions in pipeline.

Method and system for executing denormalized numbers

A special inillicode instruction 'Load With Access Test' explicitly detects access exceptions for storage operands while retaining control in the current millicode routine to insure exceptions are handled correctly and with the right priority. The millicode Load With Access Test instruction operates similarly to the ESA/390 Load instruction except that access exception code is set, interrupts are blocked and the serialization is forced to purge the instruction pipeline and reset the pipeline control without redirection of the instruction stream.

Millicode load and test access instruction that blocks interrupts in

A special Program Status Word (PSW) millicode routine, tests the validity of the PSW with three simple millicode instructions. Testing for access exceptions is executed by a special millicode instruction 'Load With Access Test', which explicitly detects access exceptions for storage operands while retaining control in the current millicode routine. A Translate and Test (TRT) routine uses a table of 256 bytes to translate a string of bytes. Each string is used as an index into the table, and the selected table byte is fetched. For Translate and Test, the selected bytes are tested, and the first non-zero table byte selected is returned to the program in a general register along with the address of the string byte which selected it; translate and test also sets the condition code, and does not update storage. To provide reasonable performance on Translate and Translate and Test, while maintaining flexibility and simplicity of a millicoded design, a millicode instruction Translate Fetch (TRFET) is provided specifically for use in execution of the Translate and Translate and Test instructions. This Translate Fetch millicode instruction uses an RX format, but modifies the interpretation of the certain fields.

Growing community of inventors

Rhinebeck, NY, United States of America

John Stephen Liptay