{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T11:28:56Z","timestamp":1763724536317,"version":"3.41.0"},"reference-count":46,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,7,17]],"date-time":"2021-07-17T00:00:00Z","timestamp":1626480000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2021,12,31]]},"abstract":"<jats:p>Logarithmic number systems (LNS) are used to represent real numbers in many applications using a constant base raised to a fixed-point exponent making its distribution exponential. This greatly simplifies hardware multiply, divide, and square root. LNS with base-2 is most common, but in this article, we show that for low-precision LNS the choice of base has a significant impact.<\/jats:p>\n          <jats:p>We make four main contributions. First, LNS is not closed under addition and subtraction, so the result is approximate. We show that choosing a suitable base can manipulate the distribution to reduce the average error. Second, we show that low-precision LNS addition and subtraction can be implemented efficiently in logic rather than commonly used ROM lookup tables, the complexity of which can be reduced by an appropriate choice of base. A similar effect is shown where the result of arithmetic has greater precision than the input. Third, where input data from external sources is not expected to be in LNS, we can reduce the conversion error by selecting a LNS base to match the expected distribution of the input. Thus, there is no one base that gives the global optimum, and base selection is a trade-off between different factors. Fourth, we show that circuits realized in LNS require lower area and power consumption for short word lengths.<\/jats:p>","DOI":"10.1145\/3461699","type":"journal-article","created":{"date-parts":[[2021,7,17]],"date-time":"2021-07-17T10:05:22Z","timestamp":1626516322000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Low-precision Logarithmic Number Systems"],"prefix":"10.1145","volume":"18","author":[{"given":"Syed Asad","family":"Alam","sequence":"first","affiliation":[{"name":"Lero, Trinity College Dublin, Ireland"}]},{"given":"James","family":"Garland","sequence":"additional","affiliation":[{"name":"Lero, Trinity College Dublin, Ireland"}]},{"given":"David","family":"Gregg","sequence":"additional","affiliation":[{"name":"Lero, Trinity College Dublin, Ireland"}]}],"member":"320","published-online":{"date-parts":[[2021,7,17]]},"reference":[{"volume-title":"Proceedings of the ACM SIGPLAN\/SIGBED International Conference on Language, Compilers, and Tools for Embedded Systems. ACM.","author":"Alam S. A.","key":"e_1_2_1_1_1","unstructured":"S. A. Alam and D. Gregg . 2020. Beyond base-2 logarithmic number systems (WiP Paper) . In Proceedings of the ACM SIGPLAN\/SIGBED International Conference on Language, Compilers, and Tools for Embedded Systems. ACM. S. A. Alam and D. Gregg. 2020. Beyond base-2 logarithmic number systems (WiP Paper). In Proceedings of the ACM SIGPLAN\/SIGBED International Conference on Language, Compilers, and Tools for Embedded Systems. ACM."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/217495"},{"volume-title":"Proceedings of the IEEE International Application-Specific System Architecture Processors Conference. 69\u201372","author":"Arnold M.","key":"e_1_2_1_3_1","unstructured":"M. Arnold , E. Chester , and C. Johnson . 2020. Training neural nets using only an approximate tableless LNS ALU . In Proceedings of the IEEE International Application-Specific System Architecture Processors Conference. 69\u201372 . M. Arnold, E. Chester, and C. Johnson. 2020. Training neural nets using only an approximate tableless LNS ALU. In Proceedings of the IEEE International Application-Specific System Architecture Processors Conference. 69\u201372."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/784895.785090"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.709377"},{"key":"e_1_2_1_6_1","volume-title":"Proceedings of the International Workshop on Power Timing Modeling Optimization Simulation.","volume":"4644","author":"Basetas C.","unstructured":"C. Basetas , I. Kouretas , and V. Paliouras . 2007. Low-power digital filtering based on the logarithmic number system . In Proceedings of the International Workshop on Power Timing Modeling Optimization Simulation. Vol. 4644 . 546\u2013555. C. Basetas, I. Kouretas, and V. Paliouras. 2007. Low-power digital filtering based on the logarithmic number system. In Proceedings of the International Workshop on Power Timing Modeling Optimization Simulation. Vol. 4644. 546\u2013555."},{"volume-title":"Berkeley logic interchange format (BLIF)","author":"BLIF","key":"e_1_2_1_7_1","unstructured":"BLIF 1992. Berkeley logic interchange format (BLIF) . University of California , Berkeley. Retrieved from http:\/\/www.cs.columbia.edu\/ cs6861\/sis\/blif\/index.html. BLIF 1992. Berkeley logic interchange format (BLIF). University of California, Berkeley. Retrieved from http:\/\/www.cs.columbia.edu\/ cs6861\/sis\/blif\/index.html."},{"volume-title":"Proceedings of the ACM International Conference on Computing Frontiers. 217\u2013220","author":"Bruschi N.","key":"e_1_2_1_8_1","unstructured":"N. Bruschi , A. Garofalo , F. Conti , G. Tagliavini , and D. Rossi . 2020. Enabling mixed-precision quantized neural networks in extreme-edge devices . In Proceedings of the ACM International Conference on Computing Frontiers. 217\u2013220 . N. Bruschi, A. Garofalo, F. Conti, G. Tagliavini, and D. Rossi. 2020. Enabling mixed-precision quantized neural networks in extreme-edge devices. In Proceedings of the ACM International Conference on Computing Frontiers. 217\u2013220."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2983648"},{"key":"e_1_2_1_10_1","first-page":"6","article-title":"Error analysis of FIR filters implemented using logarithmic arithmetic","author":"Satish Chandra D. V.","year":"1998","unstructured":"D. V. Satish Chandra . 1998 . Error analysis of FIR filters implemented using logarithmic arithmetic . IEEE Trans. Circ. Syst. II 45, 6 (June 1998), 744\u2013747. D. V. Satish Chandra. 1998. Error analysis of FIR filters implemented using logarithmic arithmetic. IEEE Trans. Circ. Syst. II 45, 6 (June 1998), 744\u2013747.","journal-title":"IEEE Trans. Circ. Syst."},{"key":"e_1_2_1_11_1","doi-asserted-by":"crossref","DOI":"10.1109\/82.686694","article-title":"Error analysis of FIR filters implemented using logarithmic arithmetic","author":"Chandra D. V. S.","year":"1998","unstructured":"D. V. S. Chandra . 1998 . Error analysis of FIR filters implemented using logarithmic arithmetic . IEEE Trans. Circ. Syst. II 45, 6 (1998), 744\u2013747. D. V. S. Chandra. 1998. Error analysis of FIR filters implemented using logarithmic arithmetic. IEEE Trans. Circ. Syst. II 45, 6 (1998), 744\u2013747.","journal-title":"IEEE Trans. Circ. Syst."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_2_1_13_1","unstructured":"Wai-Kai Chen (Ed.). 2003. Memory Microprocessor and ASIC. CRC Press Boca Raton FL.  Wai-Kai Chen (Ed.). 2003. Memory Microprocessor and ASIC. CRC Press Boca Raton FL."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"volume-title":"Proceedings of the IEEE Symposium on Computer Arithmetic. 128\u2013135","author":"de Dinechin F.","key":"e_1_2_1_15_1","unstructured":"F. de Dinechin and A. Tisserand . 2001. Some improvements on multipartite table methods . In Proceedings of the IEEE Symposium on Computer Arithmetic. 128\u2013135 . F. de Dinechin and A. Tisserand. 2001. Some improvements on multipartite table methods. In Proceedings of the IEEE Symposium on Computer Arithmetic. 128\u2013135."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.805158"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICGCS.2010.5543059"},{"key":"e_1_2_1_18_1","first-page":"2164","article-title":"PULP-NN: accelerating quantized neural networks on parallel ultra-low-power RISC-V processors","volume":"378","author":"Garofalo A.","year":"2019","unstructured":"A. Garofalo , M. Rusci , F. Conti , D. Rossi , and L. Benini . 2019 . PULP-NN: accelerating quantized neural networks on parallel ultra-low-power RISC-V processors . Philos. Trans. Royal Soc. A 378 , 2164 (Dec. 2019). DOI:https:\/\/doi.org\/10.1098\/rsta.2019.0155 A. Garofalo, M. Rusci, F. Conti, D. Rossi, and L. Benini. 2019. PULP-NN: accelerating quantized neural networks on parallel ultra-low-power RISC-V processors. Philos. Trans. Royal Soc. A 378, 2164 (Dec. 2019). DOI:https:\/\/doi.org\/10.1098\/rsta.2019.0155","journal-title":"Philos. Trans. Royal Soc. A"},{"key":"e_1_2_1_19_1","first-page":"1","article-title":"Quantized neural networks: Training neural networks with low-precision weights and activations","volume":"18","author":"Hubara I.","year":"2017","unstructured":"I. Hubara , M. Courbariaux , D. Soudry , R. El-Yaniv , and Y. Bengio . 2017 . Quantized neural networks: Training neural networks with low-precision weights and activations . ACM J. Mach. Learn. Res. 18 , 1 (Jan. 2017), 6869\u20136898. I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio. 2017. Quantized neural networks: Training neural networks with low-precision weights and activations. ACM J. Mach. Learn. Res. 18, 1 (Jan. 2017), 6869\u20136898.","journal-title":"ACM J. Mach. Learn. Res."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cdt:20070080"},{"key":"e_1_2_1_21_1","first-page":"2","article-title":"Digital filtering using logarithmic arithmetic","volume":"7","author":"Kingsbury N. G.","year":"1971","unstructured":"N. G. Kingsbury and P. J. W. Rayner . 1971 . Digital filtering using logarithmic arithmetic . Electron. Lett. 7 , 2 (Jan. 1971), 56\u201358. N. G. Kingsbury and P. J. W. Rayner. 1971. Digital filtering using logarithmic arithmetic. Electron. Lett. 7, 2 (Jan. 1971), 56\u201358.","journal-title":"Electron. Lett."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.111"},{"volume-title":"Proceedings of the International Conference on Modern Circuits and Systems Technologies. 1\u20134.","author":"Kouretas I.","key":"e_1_2_1_23_1","unstructured":"I. Kouretas and V. Paliouras . 2018. Logarithmic number system for deep learning . In Proceedings of the International Conference on Modern Circuits and Systems Technologies. 1\u20134. I. Kouretas and V. Paliouras. 2018. Logarithmic number system for deep learning. In Proceedings of the International Conference on Modern Circuits and Systems Technologies. 1\u20134."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1980.tb03051.x"},{"volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing.5900\u20135904","author":"Lee E. H.","key":"e_1_2_1_25_1","unstructured":"E. H. Lee , D. Miyashita , E. Chai , B. Murmann , and S. S. Wong . 2017. LogNet: Energy-efficient neural networks using logarithmic computation . In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing.5900\u20135904 . E. H. Lee, D. Miyashita, E. Chai, B. Murmann, and S. S. Wong. 2017. LogNet: Energy-efficient neural networks using logarithmic computation. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing.5900\u20135904."},{"key":"e_1_2_1_26_1","first-page":"171","article-title":"A new hardware implementation of base 2 logarithm for FPGA","volume":"3","author":"Mansour A. M.","year":"2015","unstructured":"A. M. Mansour , A. M. El-Sawy , M. S. Aziz , and A. T. Sayed . 2015 . A new hardware implementation of base 2 logarithm for FPGA . Int. J. Signal Proc. Syst. 3 , 2 (2015), 171 \u2013 181 . A. M. Mansour, A. M. El-Sawy, M. S. Aziz, and A. T. Sayed. 2015. A new hardware implementation of base 2 logarithm for FPGA. Int. J. Signal Proc. Syst. 3, 2 (2015), 171\u2013181.","journal-title":"Int. J. Signal Proc. Syst."},{"key":"e_1_2_1_27_1","volume-title":"ABC: A System for Sequential Synthesis and Verification.","author":"Mishchenko Alan","year":"2005","unstructured":"Alan Mishchenko . 2005 . ABC: A System for Sequential Synthesis and Verification. Retrieved from https:\/\/people.eecs.berkeley.edu\/ alanmi\/abc\/. Alan Mishchenko. 2005. ABC: A System for Sequential Synthesis and Verification. Retrieved from https:\/\/people.eecs.berkeley.edu\/ alanmi\/abc\/."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1962.5219391"},{"volume-title":"Digital Signal Processing","author":"Mitra Sanjit K.","key":"e_1_2_1_29_1","unstructured":"Sanjit K. Mitra . 2006. Digital Signal Processing . TATA McGraw-Hill , University of California, Santa Barbara, CA. Sanjit K. Mitra. 2006. Digital Signal Processing. TATA McGraw-Hill, University of California, Santa Barbara, CA."},{"key":"e_1_2_1_30_1","unstructured":"D. Miyashita E. H. Lee and B. Murmann. 2016. Convolutional neural networks using logarithmic data representation. Retrieved from https:\/\/arXiv:cs.NE\/1603.01025v2.  D. Miyashita E. H. Lee and B. Murmann. 2016. Convolutional neural networks using logarithmic data representation. Retrieved from https:\/\/arXiv:cs.NE\/1603.01025v2."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2008.12"},{"key":"e_1_2_1_32_1","volume-title":"Proceedings of the International Workshop on Power Timing Modeling Optimization Simulation","volume":"1918","author":"Paliouras V.","unstructured":"V. Paliouras and T. Stouraitis . 2000. Logarithmic number system for low-power arithmetic . In Proceedings of the International Workshop on Power Timing Modeling Optimization Simulation , Vol. 1918 . 285\u2013294. V. Paliouras and T. Stouraitis. 2000. Logarithmic number system for low-power arithmetic. In Proceedings of the International Workshop on Power Timing Modeling Optimization Simulation, Vol. 1918. 285\u2013294."},{"key":"e_1_2_1_33_1","doi-asserted-by":"crossref","unstructured":"M. Rastegari V. Ordonez J. Redmon and A. Farhadi. 2016. XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. Retrieved from https:\/\/arXiv:cs.CV\/1603.05279v4.  M. Rastegari V. Ordonez J. Redmon and A. Farhadi. 2016. XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. Retrieved from https:\/\/arXiv:cs.CV\/1603.05279v4.","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.4451215"},{"key":"e_1_2_1_35_1","unstructured":"A. S. Sedra K. C. Smith T. C. Carusone and V. Gaudet. 2019. Microelectronic Circuits (8th ed.). Oxford University Press.  A. S. Sedra K. C. Smith T. C. Carusone and V. Gaudet. 2019. Microelectronic Circuits (8th ed.). Oxford University Press."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171386"},{"key":"e_1_2_1_38_1","first-page":"4","article-title":"Considering the alternatives in low-power design","volume":"17","author":"Stouraitis T.","year":"2002","unstructured":"T. Stouraitis and V. Paliouras . 2002 . Considering the alternatives in low-power design . IEEE Circ. Syst. Mag. 17 , 4 (Aug. 2002), 22\u201329. T. Stouraitis and V. Paliouras. 2002. Considering the alternatives in low-power design. IEEE Circ. Syst. Mag. 17, 4 (Aug. 2002), 22\u201329.","journal-title":"IEEE Circ. Syst. Mag."},{"volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems.4901\u20134910","author":"Sun X.","key":"e_1_2_1_39_1","unstructured":"X. Sun , J. Choi , C. Y Chen , N. Wang , S. Venkataramani , V. Srinivasan , X. Cui , W. Zhang , and K. Gopalakrishnan . 2019. Hybrid 8-bit floating point (HFP8) training and inference for deep neural networks . In Proceedings of the Conference on Advances in Neural Information Processing Systems.4901\u20134910 . X. Sun, J. Choi, C. Y Chen, N. Wang, S. Venkataramani, V. Srinivasan, X. Cui, W. Zhang, and K. Gopalakrishnan. 2019. Hybrid 8-bit floating point (HFP8) training and inference for deep neural networks. In Proceedings of the Conference on Advances in Neural Information Processing Systems.4901\u20134910."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1975.224172"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2007.70791"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240803"},{"volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems.7675\u20137684","author":"Wang N.","key":"e_1_2_1_43_1","unstructured":"N. Wang , J. Choi , D. Brand , C.-Y. Chen , and K. Gopalakrishnan . 2018. Training deep neural networks with 8-bit floating point numbers . In Proceedings of the Conference on Advances in Neural Information Processing Systems.7675\u20137684 . N. Wang, J. Choi, D. Brand, C.-Y. Chen, and K. Gopalakrishnan. 2018. Training deep neural networks with 8-bit floating point numbers. In Proceedings of the Conference on Advances in Neural Information Processing Systems.7675\u20137684."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2767624"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2003.816138"},{"key":"e_1_2_1_46_1","first-page":"848","article-title":"An optimized logarithmic converter with equal distribution of relative errors","volume":"63","author":"Zhu M.","year":"2016","unstructured":"M. Zhu , Y. Ha , C. Gu , and L. Gao . 2016 . An optimized logarithmic converter with equal distribution of relative errors . IEEE Trans. Circ. Syst. II: Express Briefs 63 , 9 (2016), 848 \u2013 852 . M. Zhu, Y. Ha, C. Gu, and L. Gao. 2016. An optimized logarithmic converter with equal distribution of relative errors. IEEE Trans. Circ. Syst. II: Express Briefs 63, 9 (2016), 848\u2013852.","journal-title":"IEEE Trans. Circ. Syst. II: Express Briefs"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3461699","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3461699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:05Z","timestamp":1750193345000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3461699"}},"subtitle":["Beyond Base-2"],"short-title":[],"issued":{"date-parts":[[2021,7,17]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,12,31]]}},"alternative-id":["10.1145\/3461699"],"URL":"https:\/\/doi.org\/10.1145\/3461699","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"type":"print","value":"1544-3566"},{"type":"electronic","value":"1544-3973"}],"subject":[],"published":{"date-parts":[[2021,7,17]]},"assertion":[{"value":"2020-09-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}