Abstract
The microprogrammed implementation of associative instructions on conventional microprogrammable computers with address-based memory-access is introduced as "vertical processing". The implementation on the processors of the EGPA-multiprocessor project is reported as well as runtime comparisons of the microprograms with equivalent HLL-programs. The contribution of the factors vertical migration and associativity to the observed overall speedup is described. Finally, a detailed analysis of the underlying microarchitecture and the handcoded microprograms is given in view of local and global compaction techniques.
- AEG-TELEFUNKEN, "SYNFOBASE, the Mini-Datenbankmaschine", AEG-TELEFUNKEN, 1983]]Google Scholar
- T. Agerwala, "Microprogram Optimization: A Survey", IEEE Transactions on Computers, Vol. C-25, 10, 962--973, 1976]]Google Scholar
- B. Albert, A. Bode, W. Händler, "A case study in vertical migration: the implementation of a dedicated associative instruction set", Microprocessing and Microprogramming 8, 257--262, 1981]]Google Scholar
Cross Ref
- T. Baba, H. Hagiwara, "The MPG-System: A Machine-Independent efficient Microprogram-Generator", IEEE Transactions on Computers, Vol. C-30, 6, 373--395, 1981]]Google Scholar
- K. E. Batcher, "STARAN - Series E", Proc. of the 1977 International Conference on Parallel Processing, J. L. Baer (ed.), 140--143, 1977]]Google Scholar
- A. Bird, "Technical description of the distributed array processor", National Research Region, ICL, Doc. No. AP2, 1975]]Google Scholar
- A. Bode, "Vertical processing: the emulation of associative and parallel behavior on conventional hardware", Proc. EUROMICRO'80, 215--220, North Holland, 1980]]Google Scholar
- A. Bode, W. Händler, "Some results on associative processing by extending a microprogrammed general purpose processor", Proc. 6th workshop on Computer Architecture for Non Numeric Processing, INRIA, 1981]]Google Scholar
- S. Dasgupta, J. Tartar, "The Identification of Maximal Parallelism in Straight-Line Microprograms", IEEE Trans. on Comp., Vol. C-25, 10, 986--992, 1976]]Google Scholar
- S. Davidson, B. D. Shriver, "Specifying target resources in a machine independent higher level language", Proc. NCC, 81--85, 1981]]Google Scholar
Digital Library
- J. A. Fisher, "Trace Scheduling: A Technique for Global Microcode Compaction", IEEE, Transactions on Computers, Vol. C-30, 7, 478--490, 1981]]Google Scholar
- J. A. Fisher, D. Landskov, B. D. Shriver, "Microcode compaction: The State of the Art", Technical Report TR 82-3-3 University of Southwestern Louisiana, 1982]]Google Scholar
- H. J. Fromm, U. Hercksen, U. Herzog, K.-H. John, R. Klar, W. Kleinöder, "Experiences with performance measurement and modelling of a processor array", IEEE Transactions on Computers, Vol. C-32, 1, 15--31, 1983]]Google Scholar
- J. Grosch, "A language for set-theoretic concepts implemented by microprogrammed associative memory instructions", Wössner (ed.), IFB. Vol. 53, 221--236, Springer, 1982]] Google Scholar
Digital Library
- W. Händler, "Prozessor mit Mikroprogramm-steuerung einer digitalen Rechenanlage", Patent Nr. 2419241, 4/22/1974]]Google Scholar
- W. Händler, F. Hofmann, H. J. Schneider, "A general purpose array with a broad spectrum of applications", W. Händler (ed.), Computer Architecture, IFB, Vol. 4, 311--335, 1974]] Google Scholar
Digital Library
- W. Händler, R. Klar, "Fitting processors to the needs of a general purpose array (EGPA)", Proc. MICRO-8, 87--97, 1975]] Google Scholar
Digital Library
- H. Hessenauer, "Support of vertical dataprocessing by additional hardware", Feilmeier (ed.): Parallel Computers-Parallel Mathematics, Proc. of the IMACS (AICA)-Symposium, 83--86, North Holland, 1977]]Google Scholar
- S. Lamb, "An add-in recognition memory for S-100 bus microcomputers, part 1-3", Computer Design, 8/78: 140--142, 9/78: 162--168, 10/78: 182--186, 1978]]Google Scholar
- D. Landskov, S. Davidson, B. D. Shriver, P. W. Mallet, "Local microcode compaction techniques", Computing Surveys, Vol. 12, 3, 261--294, 1980]] Google Scholar
Digital Library
- H. J. Schneider, "Set theoretic concepts in programming languages and their implementation", Noltemeier (ed.): Graphtheoretic concepts in computer Science, LNCS, Vol. 100, 42--54, Springer, 1981]] Google Scholar
Digital Library
- R. J. Sheraga, J. L. Gieser, "Automatic Microcode Generation for Horizontally Microprogrammed Processors", Proc. Micro 14, SIGMICRO newsletter, Vol. 12, 4, 154--168, 1981]] Google Scholar
Digital Library
- M. Sint, "MIDL - A Microinstruction Description Language", Proc. Micro 14, SIGMICRO newsletter, Vol. 12, 4, 95--106, 1981]] Google Scholar
- M. Tokoro, E. Tamura, K. Takase, K. Tamaru, "An Approach to Microprogram Optimization considering Resource Occupancy and Instruction Formats", Proc. Micro 10, Vol. 8, 3, 92--108, 1977]] Google Scholar
Digital Library
- S. R. Vegdahl, "Phase Coupling and Constant Generation in an Optimizing Microcode Compiler", Proc. Micro 15, Vol. 13, 4, 125--133, 1982]] Google Scholar
Digital Library
Recommendations
Dynamic coalescing for 16-bit instructions
In the embedded domain, memory usage and energy consumption are critical constraints.Embedded processors such as the ARM and MIPS provide a 16-bit instruction set, (called Thumb in the case of the ARM family of processors), in addition to the 32-bit ...
Dynamically Scheduling VLIW Instructions
Very long instruction word (VLIW) machines potentially provide the most direct way to exploit instruction-level parallelism; however, they cannot be used to emulate current general-purpose instruction set architectures. In addition, programs scheduled ...
Enhancing the performance of 16-bit code using augmenting instructions
Special Issue: Proceedings of the 2003 ACM SIGPLAN conference on Language, compiler, and tool support for embedded systems (San Diego, CA).In the embedded domain, memory usage and energy consumption are critical constraints. Dual width instruction set embedded processors such as the ARM provide a 16-bit instruction set in addition to the 32-bit instruction set to address these concerns. ...






Comments