{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T13:38:20Z","timestamp":1758893900142,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2010,3,12]],"date-time":"2010-03-12T00:00:00Z","timestamp":1268352000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2011,9]]},"DOI":"10.1007\/s11227-010-0409-z","type":"journal-article","created":{"date-parts":[[2010,3,12]],"date-time":"2010-03-12T18:57:06Z","timestamp":1268420226000},"page":"314-338","source":"Crossref","is-referenced-by-count":3,"title":["Natural instruction level parallelism-aware compiler for\u00a0high-performance QueueCore processor architecture"],"prefix":"10.1007","volume":"57","author":[{"given":"Ben Abdallah","family":"Abderazek","sequence":"first","affiliation":[]},{"given":"Masashi","family":"Masuda","sequence":"additional","affiliation":[]},{"given":"Arquimedes","family":"Canedo","sequence":"additional","affiliation":[]},{"given":"Kenichi","family":"Kuroda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,3,12]]},"reference":[{"issue":"2","key":"409_CR1","doi-asserted-by":"crossref","first-page":"191","DOI":"10.3233\/EMC-2006-00028","volume":"2","author":"BA Abderazek","year":"2006","unstructured":"Abderazek BA, Kawata S, Sowa M (2006) Design and architecture for an embedded 32-bit QueueCore. J Embed Comput 2(2):191\u2013205","journal-title":"J Embed Comput"},{"issue":"1","key":"409_CR2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s11227-006-6719-5","volume":"38","author":"BA Abderazek","year":"2006","unstructured":"Abderazek BA, Yoshinaga T, Sowa M (2006) High-level modeling and FPGA prototyping of produced order parallel queue processor core. J Supercomput 38(1):3\u201315","journal-title":"J Supercomput"},{"issue":"2","key":"409_CR3","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.jpdc.2007.08.004","volume":"68","author":"BA Abderazek","year":"2008","unstructured":"Abderazek BA, Canedo A, Yoshinga T, Sowa M (2008) The QC-2 parallel queue processor architecture. J Parallel Distrib Comput 68(2):235\u2013245","journal-title":"J Parallel Distrib Comput"},{"key":"409_CR4","volume-title":"Compilers principles, techniques, and tools","author":"AV Aho","year":"1986","unstructured":"Aho AV, Sethi R, Ullman JD (1986) Compilers principles, techniques, and tools. Addison-Wesley, Reading"},{"key":"409_CR5","volume-title":"Optimizing compilers for modern architectures","author":"R Allen","year":"2002","unstructured":"Allen R, Kennedy K (2002) Optimizing compilers for modern architectures. Morgan Kaufman, San Mateo"},{"key":"409_CR6","unstructured":"Canedo A (2006) Code generation algorithms for consumed and produced order queue machines. Master\u2019s thesis, University of Electro-Communications, Tokyo, Japan, September 2006"},{"key":"409_CR7","unstructured":"Canedo A, Abderazek BA, Sowa M (2006) A GCC-based compiler for the queue register processor. In Proceedings of international workshop on modern science and technology, May 2006, pp\u00a0250\u2013255"},{"issue":"3","key":"409_CR8","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1145\/306225.306228","volume":"26","author":"JJ Dujmovic","year":"1998","unstructured":"Dujmovic JJ, Dujmovic I (1998) Evolution and evaluation of SPEC benchmarks. ACM SIGMETRICS Perform Eval Rev 26(3):2\u20139","journal-title":"ACM SIGMETRICS Perform Eval Rev"},{"key":"409_CR9","unstructured":"Fernandes M (1997) Using queues for register file organization in VLIW architectures. Technical Report ECS-CSG-29-97, University of Edinburgh"},{"key":"409_CR10","doi-asserted-by":"crossref","unstructured":"Goudge L, Segars S (1996) Thumb: Reducing the cost of 32-bit RISC performance in portable and consumer applications. In Proceedings of COMPCON \u201996, pp\u00a0176\u2013181","DOI":"10.1109\/CMPCON.1996.501765"},{"issue":"4","key":"409_CR11","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1137\/S0097539795280287","volume":"28","author":"LS Heath","year":"1999","unstructured":"Heath LS, Pemmaraju SV (1999) Stack and queue layouts of directed acyclic graphs: Part I. SIAM J Comput 28(4):1510\u20131539","journal-title":"SIAM J Comput"},{"key":"409_CR12","volume-title":"Computer architecture: a quantitative approach","author":"J Hennessy","year":"1990","unstructured":"Hennessy J, Patterson D (1990) Computer architecture: a quantitative approach. Morgan Kaufman, San Mateo"},{"key":"409_CR13","doi-asserted-by":"crossref","unstructured":"Huang X, Carr S, Sweany P (2001) Loop transformations for architectures with partitioned register banks. In Proceedings of the ACM SIGPLAN workshop on languages, compilers and tools for embedded systems, pp\u00a048\u201355","DOI":"10.1145\/384197.384206"},{"key":"409_CR14","unstructured":"Jang S, Carr S, Sweany P, Kuras D (1998) A code generation framework for VLIW architectures with partitioned register banks. In: Proceedings of the 3rd international conference on massively parallel computing systems"},{"key":"409_CR15","doi-asserted-by":"crossref","unstructured":"Janssen J, Corporaal H (1995) Partitioned register file for TTAs. In: Proceedings of the 28th annual international symposium on microarchitecture, pp\u00a0303\u2013312","DOI":"10.1109\/MICRO.1995.476840"},{"key":"409_CR16","volume-title":"MIPS RISC architecture","author":"G Kane","year":"1992","unstructured":"Kane G, Heinrich J (1992) MIPS RISC architecture. Prentice Hall, New York"},{"issue":"2","key":"409_CR17","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/40.755465","volume":"19","author":"R Kessler","year":"1999","unstructured":"Kessler R (1999) The alpha 21264 microprocessor. IEEE Micro 19(2):24\u201336","journal-title":"IEEE Micro"},{"key":"409_CR18","unstructured":"Kissel K (1997) MIPS16: high-density MIPS for the embedded market. Technical report, Silicon Graphics MIPS Group"},{"key":"409_CR19","first-page":"219","volume-title":"Lecture notes in computer science","author":"G Kucuk","year":"2003","unstructured":"Kucuk G, Ergin O, Ponomarev D, Ghose K (2003) Energy efficient register renaming. In: Lecture notes in computer science, vol 2799. Springer, Berlin, pp 219\u2013228"},{"key":"409_CR20","doi-asserted-by":"crossref","unstructured":"Lam M (1988) Software pipelining: an effective scheduling technique for VLIW machines. In: Proceedings of the ACM SIGPLAN 1988 conference on programming language design and implementation, pp\u00a0318\u2013328","DOI":"10.1145\/53990.54022"},{"issue":"2","key":"409_CR21","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1023\/A:1018743102645","volume":"26","author":"J Losa","year":"1998","unstructured":"Losa J, Ayguade E, Valero M (1998) Quantitative evaluation of register pressure on software pipelined loops. Int J Parallel Program 26(2):121\u2013142","journal-title":"Int J Parallel Program"},{"key":"409_CR22","doi-asserted-by":"crossref","unstructured":"Mahlke SA, Chen WY, Chang P, Hwu WW (1992) Scalar program performance on multiple-instruction-issue processors with a limited number of registers. In: Proceedings of the 25th annual Hawaii int\u2019l conference on system sciences, pp\u00a034\u201344","DOI":"10.1109\/HICSS.1992.183141"},{"key":"409_CR23","volume-title":"Advanced compiler design and implementation","author":"SS Muchnick","year":"1997","unstructured":"Muchnick SS (1997) Advanced compiler design and implementation. Morgan Kaufman, San Mateo"},{"key":"409_CR24","unstructured":"Novillo D (2004) Design and implementation of tree SSA. In: Proceedings of GCC developers summit, pp\u00a0119\u2013130"},{"key":"409_CR25","doi-asserted-by":"crossref","unstructured":"Okamoto S, Suzuki H, Maeda A, Sowa M (1999) Design of a superscalar processor based on queue machine computation model. In: IEEE pacific rim conference on communications, computers and signal processing, pp\u00a0151\u2013154","DOI":"10.1109\/PACRIM.1999.799499"},{"key":"409_CR26","doi-asserted-by":"crossref","unstructured":"Pinter S (1993) Register allocation with instruction scheduling. In: Proceedings of the ACM SIGPLAN 1993 conference on programming language design and implementation, pp\u00a0248\u2013257","DOI":"10.1145\/155090.155114"},{"key":"409_CR27","doi-asserted-by":"crossref","unstructured":"Postiff M, Greene D, Mudge T (2000) The need for large register file in integer codes. Technical Report CSE-TR-434-00, University of Michigan","DOI":"10.21236\/ADA461519"},{"key":"409_CR28","doi-asserted-by":"crossref","unstructured":"Preiss B, Hamacher C (1985) Data flow on queue machines. In: 12th int IEEE symposium on computer architecture, pp\u00a0342\u2013351","DOI":"10.1145\/327070.327367"},{"key":"409_CR29","doi-asserted-by":"crossref","unstructured":"Rau R (1994) Iterative modulo scheduling: an algorithm for software pipelining loops. In: Proceedings of the 27th annual international symposium on microarchitecture, pp\u00a063\u201374","DOI":"10.1145\/192724.192731"},{"issue":"8","key":"409_CR30","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1109\/TC.2005.132","volume":"54","author":"R Ravindran","year":"2005","unstructured":"Ravindran R, Senger R, Marsman E, Dasika G, Guthaus M, Mahlke S, Brown R (2005) Partitioning variables across register windows to reduce spill code in a low-power processor. IEEE Trans Comput 54(8):998\u20131012","journal-title":"IEEE Trans Comput"},{"key":"409_CR31","unstructured":"Schmit H, Levine B, Ylvisaker B (2002) Queue machines: hardware computation in hardware. In: 10th annual IEEE symposium on field-programmable custom computing machines, p\u00a0152"},{"key":"409_CR32","volume-title":"The SPARC architecture manual, version 8","author":"Sparc International","year":"1992","unstructured":"Sparc International (1992) The SPARC architecture manual, version 8. Prentice Hall, New York"},{"issue":"8","key":"409_CR33","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1109\/12.946998","volume":"50","author":"G Tayson","year":"2001","unstructured":"Tayson G, Smelyanskiy M, Davidson E (2001) Evaluating the use of register queues in software pipelined loops. IEEE Trans Comput 50(8):769\u2013783","journal-title":"IEEE Trans Comput"},{"issue":"2","key":"409_CR34","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1145\/106975.106991","volume":"19","author":"D Wall","year":"1991","unstructured":"Wall D (1991) Limits of instruction-level parallelism. ACM SIGARCH Comput Archit News 19(2):176\u2013188","journal-title":"ACM SIGARCH Comput Archit News"},{"key":"409_CR35","volume-title":"High performance compilers for parallel computing","author":"M Wolfe","year":"1996","unstructured":"Wolfe M (1996) High performance compilers for parallel computing. Addison-Wesley, Reading"},{"issue":"6","key":"409_CR36","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1023\/B:IJPP.0000042082.31819.6d","volume":"32","author":"J Zalamea","year":"2004","unstructured":"Zalamea J, Losa J, Ayguade E, Valero M (2004) Software and hardware techniques to optimize register file utilization in VLIW architectures. Int J Parallel Program 32(6):447\u2013474","journal-title":"Int J Parallel Program"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-010-0409-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-010-0409-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-010-0409-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T12:32:54Z","timestamp":1739968374000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-010-0409-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,3,12]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2011,9]]}},"alternative-id":["409"],"URL":"https:\/\/doi.org\/10.1007\/s11227-010-0409-z","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2010,3,12]]}}}