摘要: Traditional microprocessors have long benefited from the transistor density gains of Moore's law. Diminishing speeds and practical energy limits however created new challenges in technology, where exponential performance improvements we been accustomed to previous computing generations continue slowly cease. These factors signify that while transistors scale other technological means are researched, design faced by computer architects will only be temporarily masked before similar yet again encountered. This work addresses several conventional processors back-end issues introducing concept Reconfigurable Computing Units (RCUs). RCUs employ logical physical compilation maintain compatibility with current compilers ISAs, supporting an underlying reconfigurable processor architecture. consist a variety execution engines functional units, connected through configurable single-cycle multi-hop registerSwitch interconnect. Experimental results demonstrate can achieve up 2× improvement purely sequential applications 3× less logic utilization than CPU back-end.
sci-hub.se 参考文章(13)
Shekhar Borkar, Andrew A. Chien, The future of microprocessors Communications of The ACM. ,vol. 54, pp. 67- 77 ,(2011) , 10.1145/1941487.1941507
K. Sankaralingam, R. Nagarajan, Haiming Liu, Changkyu Kim, Jaehyuk Huh, D. Burger, S.W. Keckler, C. Moore, Exploiting ILP, TLP, and DLP with the polymorphous trips architecture IEEE Micro. ,vol. 23, pp. 46- 51 ,(2003) , 10.1109/MM.2003.1261386
H. Esmaeilzadeh, E. Blem, R. St. Amant, K. Sankaralingam, D. Burger, Dark Silicon and the End of Multicore Scaling IEEE Micro. ,vol. 32, pp. 122- 134 ,(2012) , 10.1109/MM.2012.17
Yoav Etsion, Felipe Cabarcas, Alejandro Rico, Alex Ramirez, Rosa M. Badia, Eduard Ayguade, Jesus Labarta, Mateo Valero, Task Superscalar: An Out-of-Order Task Pipeline international symposium on microarchitecture. pp. 89- 100 ,(2010) , 10.1109/MICRO.2010.13
Venkatraman Govindaraju, Chen-Han Ho, Karthikeyan Sankaralingam, Dynamically Specialized Datapaths for energy efficient computing high-performance computer architecture. pp. 503- 514 ,(2011) , 10.1109/HPCA.2011.5749755
Erika Gunadi, Mikko H. Lipasti, CRIB Proceeding of the 38th annual international symposium on Computer architecture - ISCA '11. ,vol. 39, pp. 23- 32 ,(2011) , 10.1145/2000064.2000068
Francis Tseng, Yale N. Patt, Achieving Out-of-Order Performance with Almost In-Order Complexity ACM SIGARCH Computer Architecture News. ,vol. 36, pp. 3- 12 ,(2008) , 10.1145/1394608.1382169
Hadi Esmaeilzadeh, Adrian Sampson, Luis Ceze, Doug Burger, Neural Acceleration for General-Purpose Approximate Programs international symposium on microarchitecture. ,vol. 33, pp. 449- 460 ,(2012) , 10.1109/MICRO.2012.48
Francis Tseng, Yale N. Patt, Achieving Out-of-Order Performance with Almost In-Order Complexity international symposium on computer architecture. pp. 3- 12 ,(2008) , 10.1109/ISCA.2008.23
Venkatraman Govindaraju, Chen-Han Ho, Tony Nowatzki, Jatin Chhugani, Nadathur Satish, Karthikeyan Sankaralingam, Changkyu Kim, DySER: Unifying Functionality and Parallelism Specialization for Energy-Efficient Computing IEEE Micro. ,vol. 32, pp. 38- 51 ,(2012) , 10.1109/MM.2012.51