SYSTEM FOR PREPARING INSTRUCTIONS FOR INSTRUCTION PARALLEL PROCESSOR AND SYSTEM WITH MECHANISM FOR BRANCHING IN THE MIDDLE OF A COMPOUND INSTRUCTION.
    1.
    发明公开
    SYSTEM FOR PREPARING INSTRUCTIONS FOR INSTRUCTION PARALLEL PROCESSOR AND SYSTEM WITH MECHANISM FOR BRANCHING IN THE MIDDLE OF A COMPOUND INSTRUCTION. 失效
    设备来的命令与指令的并行处理器来准备和设备与程序到复合命令分行的中间。

    公开(公告)号:EP0545927A4

    公开(公告)日:1993-04-26

    申请号:EP91908085

    申请日:1991-03-29

    Applicant: IBM

    Abstract: An instruction processor system for decoding compound instructions created from a series of base instruction (21) of a scalar machine, the processor generating a series of compound instruction (33) with an instruction format text having appened control bits in the instruction format text enabling the execution of the compound instruction format text in said instruction processor with a compounding facility (42) which fetches and decodes compound instructions which can be executed as compounded and single instructions by the arithmetic and logic units (26) of the instruction processor while preserving intact the scalar execution of the base instructions of a scalar machine which were originally in storage. The system nullifies any execution of a member instruction unit of a compound instruction upon occurrence of possible conditions, such as branch wich would affect the correctness of recording results of execution of the member instruction unit portion based upon the interrelationship of member units of the compound instruction with other instructions. The resultant series of compounded instructions generally executes in a faster manner than the original format which is preserved due to the parallel nature of the compounded instruction stream which is executed.

    COMPOUNDED PREPROCESSOR SYSTEM FOR CACHE

    公开(公告)号:JPH0683623A

    公开(公告)日:1994-03-25

    申请号:JP9609791

    申请日:1991-04-03

    Applicant: IBM

    Abstract: PURPOSE: To provide a digital computer system in which computer instructions can be executed in parallel, and which includes a cache storage unit which temporarily stores the computer instruction in a machine level in a process from a higher level storage unit to a functional unit which processes the instruction in the computer system. CONSTITUTION: An instruction composite unit 37 arranged between a high level storage unit 36 and a cache storage unit 38 operates the analysis of an instruction, and generates composite information indicating whether or not this instruction can be processed in parallel to the adjacent instruction in an instruction stream to each instruction. Then, those instructions with a tag and the composite information are stored in the cache unit 38. Plural functional instruction processing units 39-41 which are operated in parallel are included in this computer system.

    DIGITAL COMPUTER SYSTEM
    5.
    发明专利

    公开(公告)号:JPH04230528A

    公开(公告)日:1992-08-19

    申请号:JP9609491

    申请日:1991-04-03

    Applicant: IBM

    Abstract: PURPOSE: To provide a system where more than two computer instructions are processed in parallel. CONSTITUTION: A cache storage unit temporarily storing a machine level computer instruction is provided in the midst of function units 13-15 which processes the instruction from a host storage unit 10. An instruction composite conversion unit 11 which analyzes the instruction between the host storage unit and the cache storage unit and adds a tag field indicating whether or not the respective instructions are processed in parallel with more than one adjacent instruction of an instruction stream is provided. The instruction with a tag is stored in the cache unit. Moreover, Plural function instruction processing units which are mutually operated in parallel are provided. The instruction where the tag is given for a parallel processing is transmitted to the different one of the function units 13-15 in accordance with the code of an operation code fields.

    8.
    发明专利
    未知

    公开(公告)号:DE68923262D1

    公开(公告)日:1995-08-03

    申请号:DE68923262

    申请日:1989-11-24

    Applicant: IBM

    Abstract: A multi-bit overlapped scanning multiplication system using overlapped partial products in a matrix, accepts and multiplies either sign-magnitude operands or signed binary operands without correction, conversion, or complementation of operands or results.

    VERSATILE METHOD OF LOGGING DATA AT COMMAND LEVEL WHILE PERFORMING PARALLEL PROCESSING OF DATA

    公开(公告)号:PL289723A1

    公开(公告)日:1992-05-04

    申请号:PL28972391

    申请日:1991-04-03

    Applicant: IBM

    Abstract: This is a method of compounding two or more instructions from an instruction stream without knowing the starting point or length of each individual instruction. All instructions include one OP Code at a predetermined field location which identifies the instruction and its length. Those instructions which qualify need to have appropriate tags to indicate they are candidates for compounding. In System 370 where instructions are either 2,4 or 6 bytes in length, the field positions for the OP Code are presumed based on an estimated instruction length code. The value of each tag based on a presumed OP Code is recorded, and the instruction length code in the presumed OP Code is used to locate a complete sequence of possible instructions. Once an actual instruction boundary is found, the corresponding correct tag values are used to identify the commencement of a compound instruction, and other incorrectly generated tags are ignored.

    GENERALIZED METHOD FOR GENERATING COMPUTER-INSTRUCTIONS DRAWN TOGETHER FOR PARALLEL PROCESSORS OF INSTRUCTION LEVEL

    公开(公告)号:HUT57456A

    公开(公告)日:1991-11-28

    申请号:HU110291

    申请日:1991-04-04

    Applicant: IBM

    Abstract: This is a method of compounding two or more instructions from an instruction stream without knowing the starting point or length of each individual instruction. All instructions include one OP Code at a predetermined field location which identifies the instruction and its length. Those instructions which qualify need to have appropriate tags to indicate they are candidates for compounding. In System 370 where instructions are either 2,4 or 6 bytes in length, the field positions for the OP Code are presumed based on an estimated instruction length code. The value of each tag based on a presumed OP Code is recorded, and the instruction length code in the presumed OP Code is used to locate a complete sequence of possible instructions. Once an actual instruction boundary is found, the corresponding correct tag values are used to identify the commencement of a compound instruction, and other incorrectly generated tags are ignored.

Patent Agency Ranking