{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T12:51:53Z","timestamp":1725627113025},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2009,10,14]],"date-time":"2009-10-14T00:00:00Z","timestamp":1255478400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2010,11]]},"DOI":"10.1007\/s11265-009-0412-x","type":"journal-article","created":{"date-parts":[[2009,10,13]],"date-time":"2009-10-13T10:46:16Z","timestamp":1255430776000},"page":"157-179","source":"Crossref","is-referenced-by-count":7,"title":["An Efficient Memory Organization for High-ILP Inner Modem Baseband SDR Processors"],"prefix":"10.1007","volume":"61","author":[{"given":"Bjorn","family":"De Sutter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osman","family":"Allam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Praveen","family":"Raghavan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roeland","family":"Vandebriel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hans","family":"Cappelle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Vander Aa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingfeng","family":"Mei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,10,14]]},"reference":[{"key":"412_CR1","doi-asserted-by":"crossref","unstructured":"Baert, R., de Greef, E., & Brockmeyer, E. (2008). An automatic scratch pad memory management tool and MPEG-4 encoder case study. In DAC \u201908: Proceedings of the 45th annual Design Automation Conference (201\u2013204). Anaheim, California:ACM. doi: 10.1145\/1391469.1391520","DOI":"10.1145\/1391469.1391520"},{"key":"412_CR2","unstructured":"Barua, R. (2000). Maps: A compiler-managed memory system for software-exposed architectures. Ph.D. thesis, Massachusetss Institute of Technology."},{"key":"412_CR3","unstructured":"Bastoul, C., Cohen, A., Girbal, S., Sharma, S., & Temam, O. (2003). Putting polyhedral loop transformations to work. In Proc. workshop on languages and compilers for parallel computing (LCPC\u201903) (pp. 23\u201330)."},{"key":"412_CR4","doi-asserted-by":"crossref","unstructured":"Bougard, B., De\u00a0Sutter, B., Rabou, S., Dupont, S., Allam, O., Novo, D., et al. (2008). A coarse-grained array based baseband processor for 100MBPS+ software defined radio. In Proc. of design, automation, and test in Europe (DATE 2008).","DOI":"10.1109\/DATE.2008.4484763"},{"issue":"4","key":"412_CR5","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/MM.2008.49","volume":"28","author":"B Bougard","year":"2008","unstructured":"Bougard, B., De Sutter, R., Verkest, D., Van der Perre, L., & Lauwereins, R. (2008). A coarse-grained array accelerator for software-defined radio baseband processing. IEEE Micro, 28(4), 41\u201350.","journal-title":"IEEE Micro"},{"key":"412_CR6","unstructured":"Castro, F., Chaver, D., Pinuel, L., Prieto, M., Tirado, F., & Huang, M. (2005). Load-store queue management: An energy-efficient design based on a state-filtering mechanism. In Proceedings. 2005 IEEE international conference on computer design: VLSI in computers and processors, 2005. ICCD 2005, (pp. 617\u2013624), 2\u20135 Oct. 2005."},{"key":"412_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-4903-8","volume-title":"Data access and storage management for embedded programmable processors","author":"F Catthoor","year":"2002","unstructured":"Catthoor, F., Danckaert, K., Kulkarni, C., Brockmeyer, E., Kjeldsberg, P., Van\u00a0Achteren, T., et al. (2002). Data access and storage management for embedded programmable processors. Boston: Kluwer."},{"issue":"1","key":"412_CR8","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1109\/92.820763","volume":"8","author":"S Chen","year":"2000","unstructured":"Chen, S., & Postula, A. (2000). Synthesis of custom interleaved memory systems. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 8(1), 74\u201383.","journal-title":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems"},{"key":"412_CR9","doi-asserted-by":"crossref","unstructured":"Delaluz, V., Kandemir, M. T., Vijaykrishnan, N., Irwin, M. J., Sivasubramaniam, A., & Kolcu, I. (2002). Compiler-directed array interleaving for reducing energy in multi-bank memories. In VLSI design (pp. 288\u2013293).","DOI":"10.1109\/ASPDAC.2002.994936"},{"key":"412_CR10","unstructured":"Derudder, V., Bougard, B., Couvreur, A., Dewilde, A., Dupont, S., Folens, A., et al. (2009). A 200\u00a0Mbps + 2.14\u00a0nJ\/b digital baseband multi processor system-on-chip for SDRs. In Proc of VLSI symposum."},{"key":"412_CR11","doi-asserted-by":"crossref","unstructured":"De\u00a0Sutter, B., Coene, P., Vander\u00a0Aa, T., & Mei, B.\u00a0B. (2008). Placement-and-routing-based register allocation for coarse-grained reconfigurable arrays. In Proceedings of the 2008 ACM SIGPLAN-SIGBED conference on languages, compilers, and tools for embedded systems (pp. 151\u2013160).","DOI":"10.1145\/1375657.1375678"},{"key":"412_CR12","unstructured":"Friedman, S., Carroll, A., Van\u00a0Essen, B., Ylvisaker, B., Ebeling, C., & Hauck, S. S. (2009). SPR: An architecture-adaptive CGRA mapping tool. In FPGA \u201909: Proceeding of the ACM\/SIGDA international symposium on field programmable gate arrays (pp. 191\u2013200)."},{"issue":"1","key":"412_CR13","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/71.80188","volume":"2","author":"D Harper","year":"1991","unstructured":"Harper, D. (1991). Block, multistride vectorm and FFT accesses in parallel memory systems. IEEE Transactions on Parallel and Distributed Systems, 2(1), 43\u201351.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"issue":"3","key":"412_CR14","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/12.76404","volume":"40","author":"D Harper","year":"1991","unstructured":"Harper, D., & Linebarger, D. (1991). Conflict-free vector access using a dynamic storage scheme. IEEE Transactions on Computers, 40(3), 276\u2013283.","journal-title":"IEEE Transactions on Computers"},{"key":"412_CR15","unstructured":"Hive. HiveFlex CSP2000 series, programmable OFDM communication signal processor. http:\/\/www.siliconhive.com ."},{"issue":"4","key":"412_CR16","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1314299.1314301","volume":"25","author":"I Hur","year":"2007","unstructured":"Hur, I., & Lin, C. (2007). Memory scheduling for modern microprocessors. ACM Transactions on Computer Systems, 25(4), 10.","journal-title":"ACM Transactions on Computer Systems"},{"issue":"2","key":"412_CR17","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1109\/12.752657","volume":"48","author":"M Kandemir","year":"1999","unstructured":"Kandemir, M., Ramanujam, J., & Choudhary, A. (1999). Improving cache locality by a combination of loop and data transformations. IEEE Transactions on Computers, 48(2), 159\u2013167.","journal-title":"IEEE Transactions on Computers"},{"key":"412_CR18","doi-asserted-by":"crossref","unstructured":"Lam, M. S. (1988). Software pipelining: An effecive scheduling technique for VLIW machines. In Proc. PLDI (pp. 318\u2013327).","DOI":"10.1145\/53990.54022"},{"key":"412_CR19","unstructured":"Mahlke, S., Lin, D., Chen, W. Y., Hank, R., & Bringmann, R. (1992). Effective compiler support for predicated execution using the hyperblock. In MICRO 25: Proceedings of the 25th annual international symposium on microarchitecture (pp. 45\u201354)."},{"key":"412_CR20","unstructured":"Mei, B., Vernalde, S., Verkest, D., & Lauwereins, R. (2004). Design methodology for a tightly coupled VLIW\/reconfigurable matrix arcchitecture: A case study. In Proc. of design, automation and test in Europe (DATE 2004) (pp. 1224\u20131229)."},{"key":"412_CR21","doi-asserted-by":"crossref","unstructured":"Mei, B., Vernalde, S., Verkest, D., Man, H. D., & Lauwereins, R. (2003). Exploiting loop-level parallelism for coarse-grained reconfigurable architecture using modulo scheduling. IEE Proceedings: Computer and Digital Techniques, 150(5).","DOI":"10.1049\/ip-cdt:20030833"},{"key":"412_CR22","unstructured":"Novo, D., Schuster, T., Bougard, B., Lambrechts, A., Van der Perre, L., & Catthoor, F. (2008). Energy-performance exploration of a CGA-based SDR processor. Journal of Signal Processing Systems."},{"key":"412_CR23","doi-asserted-by":"crossref","unstructured":"Oh, T., Egger, B., Park, H., & Mahlke, S. (2009). Recurrence cycle aware modulo scheduling for coarse-grained reconfiguralbe architectures. In Proceedings of the 2009 ACM SIGPLAN-SIGBED conference on languages, compilers, and tools for embedded systems (pp. 21\u201330).","DOI":"10.1145\/1542452.1542456"},{"key":"412_CR24","unstructured":"PACT (2006). PACT XPP technologies. http:\/\/www.pactcorp.com ."},{"key":"412_CR25","doi-asserted-by":"crossref","unstructured":"Park, I., Ooi, C. L., & Vijaykumar, T. N. (2003). Reducing design complexity of the load\/store queue. In Proc. of the 36th international symposium on microarchitecture (MICRO-36).","DOI":"10.1109\/MICRO.2003.1253245"},{"key":"412_CR26","doi-asserted-by":"crossref","unstructured":"Park, H., Fan, K., Mahlke, S. A. , Oh, T., Kim, H., & Kim, H.-S. (2008). Edge-centric modulo scheduling for coarse-grained reconfigurable architectures. In PACT \u201908: Proceedings of the 17th international conference on parallel architectures and compilation techniques (pp.\u00a0166\u2013176).","DOI":"10.1145\/1454115.1454140"},{"key":"412_CR27","unstructured":"Pitk\u00e4nen, T., Tanskanen, J., M\u00e4kinen, R., & Takala, J. (2008). Parallel memory architecture for application-specific instruction-set processors. Journal of Signal Processing Systems."},{"key":"412_CR28","doi-asserted-by":"crossref","unstructured":"Rau, B. R. (1991). Pseudo-randomly interleaved memory. In ISCA \u201991: Proceedings of the 18th annual international symposium on computer architecture (pp. 74\u201383).","DOI":"10.1145\/115952.115961"},{"key":"412_CR29","unstructured":"Rau, B. R. (1995). Iterative modulo scheduling. Technical report, Hewlett-Packard Lab: HPL-94-115."},{"key":"412_CR30","doi-asserted-by":"crossref","unstructured":"Rivers, J. A., Tyson, G. S., Davidson, E. S., & Austin, T. M. (1997) On high-bandwidth data cache design for multi-issue processors. In Proc. of the 30th international symposium on microarchitecture (MICRO-30).","DOI":"10.1109\/MICRO.1997.645796"},{"key":"412_CR31","doi-asserted-by":"crossref","unstructured":"Sethumadhavan, S., Roesner, F., Emer, J. S., Burger, D., & Keckler, S. W. (2007). Late-binding: Enabling unordered load-store queues. In D. M. Tullsen & B. Calder (Eds.), ISCA (pp. 347\u2013357). ACM.","DOI":"10.1145\/1250662.1250705"},{"issue":"5","key":"412_CR32","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/12.859540","volume":"49","author":"H Singh","year":"2000","unstructured":"Singh, H., Lee, M.-H., Lu, G., Kurdahi, F. J., Bagherzadeh, N., & Filho, E. M.\u00a0C. (2000). MorphoSys: An integrated reconfigurable system for data-parallel and computation-intensive applications. IEEE Transactions on Computers, 49(5), 465\u2013481.","journal-title":"IEEE Transactions on Computers"},{"key":"412_CR33","unstructured":"So, B., Hall, M. W., & Ziegler, H. E. (2004) Custom data layout for memory parallelism. In Proc. of international symposium on code generation and optimization (CGO)."},{"key":"412_CR34","doi-asserted-by":"crossref","unstructured":"Subramaniam, S., & Loh, G. H. (2006). Fire-and-forget: Load\/store scheduling with no store queue at all. In Proceedings of the 39th annual IEEE\/ACM international symposium on microarchitecture (pp. 273\u2013284).","DOI":"10.1109\/MICRO.2006.26"},{"key":"412_CR35","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s11265-005-4962-2","volume":"40","author":"J Tanskanen","year":"2005","unstructured":"Tanskanen, J., & Creutzburg, a. J.\u00a0N. R. (2005). On design of parallel memory access schemes for video coding. Journal of VLSI Signal Processing Systems, 40, 215\u2013237.","journal-title":"Journal of VLSI Signal Processing Systems"},{"issue":"2","key":"412_CR36","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1109\/MM.2002.997877","volume":"22","author":"M Taylor","year":"2002","unstructured":"Taylor, M., Kim, J., Miller, J., Wentzla, D., Ghodrat, F., Greenwald, B., et al. (2002). The raw microprocessor: A computational fabric for software circuits and general purpose programs. IEEE Micro, 22(2), 25\u201335.","journal-title":"IEEE Micro"},{"issue":"5","key":"412_CR37","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1109\/12.381949","volume":"44","author":"L Valero","year":"1995","unstructured":"Valero, L., Lang, T., Peiron, M., & Ayguad\u00e9, E. (1995). Conflict-free access for streams in multimodule memories. IEEE Transactions on Computers, 44(5), 634\u2013646.","journal-title":"IEEE Transactions on Computers"},{"key":"412_CR38","first-page":"2613","volume":"2005","author":"K Berkel van","year":"2005","unstructured":"van Berkel, K., Heinle, F., Meuwissen, P., Moerman, K., & Weiss, M. (2005). Vector processing as an enabler for software-defined radio in handheld devices. EURASIP Journal on Applied Signal Processing, 2005, 2613\u20132625.","journal-title":"EURASIP Journal on Applied Signal Processing"},{"key":"412_CR39","volume-title":"Fast, efficient, and predictable memory accesses","author":"L Wehmeyer","year":"2006","unstructured":"Wehmeyer, L., & Marwedel, P. (2006). Fast, efficient, and predictable memory accesses. New York: Springer."},{"key":"412_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhu, Z., & Zhang, X. (2000). A permutation-based page interleaving scheme to reduce row-buffer conflicts and exploit data locality. In International symposium on microarchitecture (pp. 32\u201341).","DOI":"10.1145\/360128.360134"},{"key":"412_CR41","doi-asserted-by":"crossref","unstructured":"Zhuang, X., Pande, S., & J. S.\u00a0G. Jr. (2002). A Framework for parallelizing load\/stores on embedded processors. In Proc. of international conference on parallel architectures and compilation techniques (PACT 2002).","DOI":"10.1109\/PACT.2002.1106005"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-009-0412-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-009-0412-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-009-0412-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,12]],"date-time":"2021-10-12T05:44:27Z","timestamp":1634017467000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-009-0412-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,10,14]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2010,11]]}},"alternative-id":["412"],"URL":"https:\/\/doi.org\/10.1007\/s11265-009-0412-x","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,10,14]]}}}