{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:17:33Z","timestamp":1743023853906,"version":"3.40.3"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030983468"},{"type":"electronic","value":"9783030983475"}],"license":[{"start":{"date-parts":[[2012,2,24]],"date-time":"2012-02-24T00:00:00Z","timestamp":1330041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2012,2,24]],"date-time":"2012-02-24T00:00:00Z","timestamp":1330041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-98347-5_4","type":"book-chapter","created":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T14:04:15Z","timestamp":1661177055000},"page":"77-98","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Low-Precision Floating-Point Formats: From General-Purpose to Application-Specific"],"prefix":"10.1007","author":[{"given":"Amir","family":"Sabbagh Molahosseini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonel","family":"Sousa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Azadeh Alsadat","family":"Emrani Zarandi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hans","family":"Vandierendonck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,2,24]]},"reference":[{"issue":"1","key":"4_CR1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1145\/103162.103163","volume":"23","author":"D Goldberg","year":"1991","unstructured":"Goldberg D. What every computer scientist should know about floating-point arithmetic. ACM Comput Surv. 1991;23(1):5\u201348.","journal-title":"ACM Comput Surv"},{"key":"4_CR2","volume-title":"Chang CH, editors","author":"AS Molahosseini","year":"2017","unstructured":"Molahosseini AS, Sousa L, Chang CH, editors. Embedded systems design with special arithmetic and number systems. Springer; 2017."},{"key":"4_CR3","volume-title":"Computer arithmetic: algorithms and hardware designs","author":"B Parhami","year":"2010","unstructured":"Parhami B. Computer arithmetic: algorithms and hardware designs. 2nd ed. New York: Oxford University Press; 2010.","edition":"2"},{"key":"4_CR4","unstructured":"IEEE Computer Society. IEEE standard for floating-point arithmetic. IEEE Std 754-2008:1\u201370; 2008."},{"key":"4_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-3459-7","volume-title":"Deep learning: convergence to big data analytics","author":"M Khan","year":"2019","unstructured":"Khan M, Bilal J, Haleem F. Deep learning: convergence to big data analytics. Springer; 2019."},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Alioto M, editor. Enabling the Internet of Things: from integrated circuits to integrated systems. Springer; 2017.","DOI":"10.1007\/978-3-319-51482-6"},{"key":"4_CR7","unstructured":"Mach S. Floating-point architectures for energy-efficient transprecision computing. Doctoral Thesis, ETH ZURICH, Switzerland. 2021."},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Malossi ACI, et al. The transprecision computing paradigm: Concept, design, and applications. In: Proc. of design, automation and test in Europe conference and exhibition (DATE). 2018.","DOI":"10.23919\/DATE.2018.8342176"},{"issue":"1","key":"4_CR9","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/MCAS.2020.3027425","volume":"21","author":"L Sousa","year":"2021","unstructured":"Sousa L. Nonconventional computer arithmetic circuits, systems and applications. IEEE Circ Syst Mag. 2021;21(1):6\u201340.","journal-title":"IEEE Circ Syst Mag"},{"issue":"2","key":"4_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3381039","volume":"53","author":"S Cherubin","year":"2020","unstructured":"Cherubin S, Agosta G. Tools for reduced precision computation: a survey. ACM Comput Surv. 2020;53(2):1.","journal-title":"ACM Comput Surv"},{"key":"4_CR11","doi-asserted-by":"publisher","first-page":"3446","DOI":"10.1109\/TSP.2021.3086355","volume":"69","author":"J Lee","year":"2021","unstructured":"Lee J, Vandierendonck H. Towards lower precision adaptive filters: facts from backward error analysis of RLS. IEEE Trans Signal Process. 2021;69:3446\u20133458.","journal-title":"IEEE Trans Signal Process."},{"issue":"10","key":"4_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1029\/2020MS002246","volume":"12","author":"M Kl\u00f6wer","year":"2020","unstructured":"Kl\u00f6wer M, D\u00fcben PD, Palmer TN. Number formats, error mitigation, and scope for 16-bit arithmetics in weather and climate modeling analyzed with a shallow water model. J Adv Model Earth Syst. 2020;12(10):1\u201317.","journal-title":"J Adv Model Earth Syst"},{"key":"4_CR13","unstructured":"Micikevicius P, Narang S, Alben J, Diamos G, Elsen E, Garcia D, Ginsburg B, Houston M, Kuchaiev O, Venkatesh G, Wu H, Mixed precision training. Preprint. arXiv:1710.03740. 2017."},{"key":"4_CR14","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. Preprint. arXiv:1603.04467. 2016."},{"issue":"2","key":"4_CR15","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MM.2021.3058217","volume":"41","author":"T Norrie","year":"2021","unstructured":"Norrie T, et al. The design process for Google\u2019s training chips: TPUv2 and TPUv3. IEEE Micro. 2021;41(2):56\u201363.","journal-title":"IEEE Micro"},{"key":"4_CR16","unstructured":"Ying C, Kumar S, Chen D, Wang T, Cheng Y. Image classification at supercomputer scale. CoRR, abs\/1811.06992. 2018."},{"key":"4_CR17","unstructured":"Kalamkar D, et al. A study of BFLOAT16 for deep learning training. Preprint. arXiv:1905.12322. 2019."},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Burgess N, Milanovic J, Stephens N, Monachopoulos K, Mansell D. Bfloat16 processing for neural networks. In: Proc. of IEEE 26th symposium on computer arithmetic (ARITH). 2019. pp. 88\u201391.","DOI":"10.1109\/ARITH.2019.00022"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Jouppi NP, et al. Ten lessons from three generations shaped Google\u2019s TPUv4i: industrial product. In: Proc. of ACM\/IEEE 48th annual international symposium on computer architecture (ISCA). 2021. pp. 1\u201314.","DOI":"10.1109\/ISCA52012.2021.00010"},{"issue":"2","key":"4_CR20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MM.2021.3061394","volume":"41","author":"J Choquette","year":"2021","unstructured":"Choquette J, Gandhi W, Giroux O, Stam N, Krashinsky R. NVIDIA A100 Tensor Core GPU: performance and innovation. IEEE Micro. 2021;41(2):29\u201335.","journal-title":"IEEE Micro"},{"key":"4_CR21","unstructured":"Ozturk ME, Wang W, Szankin M, Shao L. Distributed BERT pre-training & fine-tuning with intel optimized TensorFlow on Intel Xeon scalable processors. In: Proc. of the ACM\/IEEE international conference for high performance computing networking, storage, and analysis. 2020."},{"key":"4_CR22","unstructured":"Daghaghi S, Nicholas M, Mengnan Z, Shrivastava A. Accelerating slide deep learning on modern CPUs: Vectorization, quantizations, memory optimizations, and more. In: Proc. of machine learning and systems conference. 2021."},{"key":"4_CR23","unstructured":"bfloat16 \u2013 Hardware Numerics Definition. White Paper, Intel Corporation, USA, Nov. 2018."},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Chromczak J, Wheeler M, Chiasson C, How D, Langhammer M, Vanderhoek T, Zgheib G, Ganusov I. Architectural enhancements in Intel Agilex FPGAs. In: Proc. of the ACM\/SIGDA international symposium on field-programmable gate arrays (FPGA \u201920), New York, NY, USA. 2020. pp. 140\u2013149.","DOI":"10.1145\/3373087.3375308"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Agrawal A, et al. DLFloat: A 16-b floating point format designed for deep learning training and inference. In Proc. of IEEE symposium on computer arithmetic (ARITH), Kyoto, Japan. 2019. pp. 92\u20135.","DOI":"10.1109\/ARITH.2019.00023"},{"key":"4_CR26","unstructured":"Bordawekar R, Abali B, Chen MH. EFloat: Entropy-coded floating point format for deep learning. arXiv:2102.02705. 2021."},{"key":"4_CR27","unstructured":"Krashinsky R, Giroux O, Jones S, Stam N, Ramaswamy S. NVIDIA ampere architecture in-depth, NVidia Blog. https:\/\/developer.nvidia.com\/blog\/nvidia-ampere-architecture-in-depth\/. Last Accessed: 30 Aug 2021."},{"issue":"2","key":"4_CR28","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MM.2018.022071131","volume":"38","author":"E Chung","year":"2018","unstructured":"Chung E, et al. Serving DNNs in real time at datacenter scale with project brainwave. IEEE Micro. 2018;38(2):8\u201320.","journal-title":"IEEE Micro"},{"key":"4_CR29","unstructured":"K\u00f6ster U, et al. Flexpoint: an adaptive numerical format for efficient training of deep neural networks. In: Proc. of the 31st international conference on neural information processing systems, Red Hook, NY, USA. 2017. pp. 1740\u201350."},{"issue":"12","key":"4_CR30","doi-asserted-by":"publisher","first-page":"2081","DOI":"10.1109\/TC.2017.2716355","volume":"66","author":"A Anderson","year":"2017","unstructured":"Anderson A, Muralidharan S, Gregg D. Efficient multibyte floating point data formats using vectorization. IEEE Trans Comput. 2017;66(12):2081\u201396.","journal-title":"IEEE Trans Comput"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Nannarelli A. Tunable floating-point for energy efficient accelerators. In: Proc. of IEEE symposium on computer arithmetic, Amherst, MA, USA. 2018. pp. 29\u201336.","DOI":"10.1109\/ARITH.2018.8464797"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Nannarelli A. Variable precision 16-bit floating-point vector unit for embedded processors. In: Proc. of IEEE symposium on computer arithmetic (ARITH), Portland, OR, USA. 2020. pp. 96\u2013102.","DOI":"10.1109\/ARITH48897.2020.00022"},{"issue":"2","key":"4_CR33","first-page":"71","volume":"4","author":"JL Gustafson","year":"2017","unstructured":"Gustafson JL, Yonemoto I. Beating floating point at its own game: posit arithmetic. Supercomput Front Innov 2017;4(2):71\u201386.","journal-title":"Supercomput Front Innov"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Carmichael Z, Langroudi HF, Khazanov C, Lillie J, Gustafson JL, Kudithipudi D. Performance-efficiency trade-off of low-precision numerical formats in deep neural networks. In: Proc. of the conference for next generation arithmetic (CoNGA\u201919), New York, NY, USA. 2019. pp. 3, 1\u20139.","DOI":"10.1145\/3316279.3316282"},{"key":"4_CR35","volume-title":"Leveraging posit arithmetic in deep neural networks","author":"R Montero","year":"2021","unstructured":"Montero RM. Leveraging posit arithmetic in deep neural networks. Master Thesis, Complutense University of Madrid. 2021."},{"issue":"2","key":"4_CR36","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1109\/TC.2020.2985971","volume":"70","author":"J Lu","year":"2021","unstructured":"Lu J, Fang C, Xu M, Lin J, Wang Z. Evaluations on deep neural networks training using posit number system. IEEE Trans Comput. 2021;70(2):174\u201387.","journal-title":"IEEE Trans Comput"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Langroudi HF, Carmichael Z, Gustafson JL, Kudithipudi D. PositNN framework: tapered precision deep learning inference for the edge. In: Proc. of IEEE space computing conference (SCC). 2019. pp. 53\u20139.","DOI":"10.1109\/SpaceComp.2019.00011"},{"issue":"1","key":"4_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3380934","volume":"7","author":"T Gr\u00fctzmacher","year":"2020","unstructured":"Gr\u00fctzmacher T, Cojean T, Flegar G, Anzt H, Quintana-Ort\u00ed ES. Acceleration of PageRank with customized precision based on mantissa segmentation. ACM Trans Parallel Comput. 2020;7(1):1.","journal-title":"ACM Trans Parallel Comput"},{"issue":"15","key":"4_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/cpe.5418","volume":"32","author":"T Gr\u00fctzmacher","year":"2020","unstructured":"Gr\u00fctzmacher T, Cojean T, Flegar G, G\u00f6bel F, Anzt H. A customized precision format based on mantissa segmentation for accelerating sparse linear algebra. Concurr Comput Pract Exp. 2020;32(15):1\u201312.","journal-title":"Concurr Comput Pract Exp"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Molahosseini AS, Vandierendonck H. Half-precision floating-point formats for PageRank: opportunities and challenges. In: Proc. of IEEE high performance extreme computing conference (HPEC). 2020. pp. 1\u20137.","DOI":"10.1109\/HPEC43674.2020.9286179"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Markidis S, Chien SWD, Laure E, Peng IB, Vetter JS. Nvidia Tensor Core programmability, performance & precision. In Proc. of IEEE international parallel and distributed processing symposium workshops (IPDPSW). 2018. pp. 522\u2013531.","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Mach S, Rossi D, Tagliavini G, Marongiu A, Benini L. A transprecision floating-point architecture for energy-efficient embedded computing. In Proc. of IEEE international symposium on circuits and systems (ISCAS). 2018. pp. 1\u20135.","DOI":"10.1109\/ISCAS.2018.8351816"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Ho N, Wong W. Exploiting half precision arithmetic in Nvidia GPUs. In: Proc. of IEEE high performance extreme computing conference (HPEC). 2017. pp. 1\u20137.","DOI":"10.1109\/HPEC.2017.8091072"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Haidar A, Tomov S, Dongarra J, Higham NJ. Harnessing GPU tensor cores for fast FP16 arithmetic to speed up mixed-precision iterative refinement solvers. In: Proc. of international conference for high performance computing, networking, storage and analysis. 2018. pp. 603\u201313.","DOI":"10.1109\/SC.2018.00050"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Zambelli C, Ranhel J. Half-precision floating point on spiking neural networks simulations in FPGA. In: Proc. of international joint conference on neural networks (IJCNN). 2018. pp. 1\u20136.","DOI":"10.1109\/IJCNN.2018.8489438"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Brennan J, Bonner S, Atapour-Abarghouei A, Jackson PT, Obara B, McGough AS. Not half bad: exploring half-precision in graph convolutional neural networks. In: Proc. of IEEE international conference on big data (Big Data). 2020. pp. 2725\u201334.","DOI":"10.1109\/BigData50022.2020.9378263"},{"key":"4_CR47","unstructured":"Bj\u00f6rck J, Chen X, De Sa C, Gomes CP, Weinberger K. Low-precision reinforcement learning: running soft actor-critic in half precision. In: Proc. of the 38th international conference on machine learning. 2021. pp. 980\u201391."},{"issue":"12","key":"4_CR48","doi-asserted-by":"publisher","first-page":"2232","DOI":"10.1109\/JPROC.2020.3029453","volume":"108","author":"S Venkataramani","year":"2020","unstructured":"Venkataramani S, et al. Efficient AI system design with cross-layer approximate computing. Proc IEEE. 2020;108(12):2232\u201350.","journal-title":"Proc IEEE"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Firoz JS, Li A, Li J, Barker K. On the feasibility of using reduced-precision tensor core operations for graph analytics. In: Proc. of IEEE high performance extreme computing conference (HPEC), Waltham, MA, USA. 2020. pp. 1\u20137.","DOI":"10.1109\/HPEC43674.2020.9286152"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Carvalho A, Azevedo R. Towards a transprecision polymorphic floating-point unit for mixed-precision computing. In: Proc. of 31st international symposium on computer architecture and high performance computing (SBAC-PAD). 2019. pp. 56\u201363.","DOI":"10.1109\/SBAC-PAD.2019.00022"},{"issue":"1","key":"4_CR51","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1145\/3273982.3273991","volume":"52","author":"S Xie","year":"2018","unstructured":"Xie S, Davidson S, Magaki I, Khazraee M, Vega L, Zhang L, Taylor MB. Extreme datacenter specialization for planet-scale computing: ASIC clouds. ACM SIGOPS Oper Syst Rev. 2018;52(1):96\u2013108","journal-title":"ACM SIGOPS Oper Syst Rev"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Yang K, Chen YF, Roumpos G, Colby C, Anderson JR. High performance Monte Carlo simulation of Ising model on TPU clusters. CoRR, abs\/1903.11714. 2019.","DOI":"10.1145\/3295500.3356149"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Henry G, Tang PTP, Heinecke A. Leveraging the bfloat16 artificial intelligence datatype for higher-precision computations. In: Proc. of IEEE 26th symposium on computer arithmetic (ARITH), Kyoto, Japan. 2019. pp. 69\u201376.","DOI":"10.1109\/ARITH.2019.00019"},{"issue":"4","key":"4_CR54","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1109\/TVLSI.2020.3044752","volume":"29","author":"S Mach","year":"2021","unstructured":"Mach S, Schuiki F, Zaruba F, Benini L. FPnew: an open-source multiformat floating-point unit architecture for energy-proportional transprecision computing. IEEE Trans Very Large Scale Integr (VLSI) Syst. 2021;29(4):774\u201387.","journal-title":"IEEE Trans Very Large Scale Integr (VLSI) Syst"},{"issue":"1","key":"4_CR55","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/TCAD.2018.2883902","volume":"39","author":"G Tagliavini","year":"2020","unstructured":"Tagliavini G, Marongiu A, Benini L. FlexFloat: a software library for transprecision computing. IEEE Trans Comput Aided Des Integr Circ Syst. 2020;39(1):145\u201356.","journal-title":"IEEE Trans Comput Aided Des Integr Circ Syst"},{"key":"4_CR56","unstructured":"Wang N, Choi J, Brand D, Chen CY, Gopalakrishnan K. Training deep neural networks with 8-bit floating point numbers. In: Proc. of the 32nd international conference on neural information processing systems, Red Hook, NY, USA. 2018. pp. 7686\u201395."},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Xu S, Gregg D. Bitslice vectors: a software approach to customizable data precision on processors with SIMD extensions. In: Proc. of 46th international conference on parallel processing (ICPP). 2017. pp. 442\u201351.","DOI":"10.1109\/ICPP.2017.53"},{"key":"4_CR58","doi-asserted-by":"crossref","unstructured":"Tambe T, et al. Algorithm-hardware co-design of adaptive floating-point encodings for resilient deep learning inference. In: Proc. of 57th ACM\/IEEE design automation conference (DAC). 2020. pp. 1\u20136.","DOI":"10.1109\/DAC18072.2020.9218516"},{"key":"4_CR59","doi-asserted-by":"crossref","unstructured":"Franceschi M, Nannarelli A, Valle M. Tunable floating-point for embedded machine learning algorithms implementation. In: Proc. of 15th international conference on synthesis, modeling, analysis and simulation methods and applications to circuit design (SMACD). 2018. pp. 89\u201392.","DOI":"10.1109\/SMACD.2018.8434873"},{"key":"4_CR60","doi-asserted-by":"crossref","unstructured":"Franceschi M, Nannarelli A, Valle M. Tunable floating-point for artificial neural networks. In Proc. of 25th IEEE international conference on electronics, circuits and systems (ICECS). 2018. pp. 289\u201392.","DOI":"10.1109\/ICECS.2018.8617900"},{"issue":"10","key":"4_CR61","doi-asserted-by":"publisher","first-page":"1553","DOI":"10.1109\/TC.2019.2906907","volume":"68","author":"A Nannarelli","year":"2019","unstructured":"Nannarelli A. Tunable floating-point adder. IEEE Trans Comput. 2019;68(10):1553\u201360.","journal-title":"IEEE Trans Comput"},{"key":"4_CR62","unstructured":"Elam D, Iovescu C. A block floating point implementation for an N-Point FFT on the TMS320C55x DSP. Application Report, Texas Instruments. 2003."},{"key":"4_CR63","unstructured":"Drumond M, Lin T, Jaggi M, Falsafi B. Training DNNs with hybrid block floating point. In: Proc. of the 32nd international conference on neural information processing systems (NIPS\u201918), Red Hook, NY, USA. 2018. pp. 451\u201361."},{"key":"4_CR64","unstructured":"Fox S, Rasoulinezhad S, Faraone J, Leong P. A block minifloat representation for training deep neural networks. In: Proc. of international conference on learning representations. 2020."},{"key":"4_CR65","volume-title":"Google\u2019s PageRank and beyond: the science of search engine rankings","author":"A Langville","year":"2012","unstructured":"Langville AN, Meyer CD. Google\u2019s PageRank and beyond: the science of search engine rankings. Princeton University Press; 2012."},{"key":"4_CR66","unstructured":"Takac L, Zabovsky M. Data analysis in public social networks. In: Proc. of international scientific conference and international workshop present day trends of innovations, Lomza, Poland. 2012."},{"issue":"7","key":"4_CR67","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1145\/3360307","volume":"63","author":"NP Jouppi","year":"2020","unstructured":"Jouppi NP, Yoon DH, Kurian G, Li S, Patil N, Laudon J, Young C, Patterson D. A domain-specific supercomputer for training deep neural networks. Commun ACM. 2020;63(7):67\u201378.","journal-title":"Commun ACM"},{"key":"4_CR68","volume-title":"The SoftFloat and TestFloat validation suite for binary floating-point arithmetic","author":"J Hauser","year":"1999","unstructured":"Hauser J. The SoftFloat and TestFloat validation suite for binary floating-point arithmetic. Technical Report, University of California, Berkeley. 1999."},{"key":"4_CR69","doi-asserted-by":"crossref","unstructured":"Gerlach L, Pay\u00e1-Vay\u00e1 G, Blume H. Efficient emulation of floating-point arithmetic on fixed-point SIMD processors. In Proc. of IEEE international workshop on signal processing systems (SiPS). 2016. pp. 254\u20139.","DOI":"10.1109\/SiPS.2016.52"},{"key":"4_CR70","unstructured":"Chen B, et al. Slide: In defense of smart algorithms over hardware acceleration for large-scale deep learning systems. arXiv preprint arXiv:1903.03129. 2019."},{"key":"4_CR71","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.micpro.2019.01.009","volume":"67","author":"O Mutlu","year":"2019","unstructured":"Mutlu O, Ghose S, G\u00f3mez-Luna J, Ausavarungnirun R. Processing data where it makes sense: Enabling in-memory computation. Microprocess Microsyst 2019;67:28\u201341.","journal-title":"Microprocess Microsyst"},{"key":"4_CR72","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.parco.2020.102663","volume":"97","author":"J Lee","year":"2020","unstructured":"Lee J, Peterson GD, Nikolopoulos DS, Vandierendonck H. AIR: Iterative refinement acceleration using arbitrary dynamic precision. Parallel Comput 2020;97:1\u201313.","journal-title":"Parallel Comput"},{"key":"4_CR73","first-page":"1","volume":"29","author":"D Zoni","year":"2021","unstructured":"Zoni D, Galimberti A, Fornaciari W. An FPU design template to optimize the accuracy-efficiency-area trade-off. Sustain Comput Inform Syst. 2021;29:1\u201310.","journal-title":"Sustain Comput Inform Syst."},{"issue":"5","key":"4_CR74","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1137\/19M1251308","volume":"41","author":"NJ Higham","year":"2019","unstructured":"Higham NJ, Pranesh S. Simulating low precision floating-point arithmetic. SIAM J Sci Comput. 2019;41(5):585\u2013602.","journal-title":"SIAM J Sci Comput"},{"key":"4_CR75","volume-title":"Mikaitis M","author":"M Fasi","year":"2020","unstructured":"Fasi M, Mikaitis M. CPFloat: A C library for emulating low-precision arithmetic. Technical Report, The University of Manchester. 2020."},{"key":"4_CR76","doi-asserted-by":"publisher","first-page":"82318","DOI":"10.1109\/ACCESS.2021.3086669","volume":"9","author":"A Romanov","year":"2021","unstructured":"Romanov AY, et al. Analysis of Posit and Bfloat arithmetic of real numbers for machine learning. IEEE Access. 2021;9:82318\u201324.","journal-title":"IEEE Access."}],"container-title":["Approximate Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-98347-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T14:13:32Z","timestamp":1661177612000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-98347-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,2,24]]},"ISBN":["9783030983468","9783030983475"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-98347-5_4","relation":{},"subject":[],"published":{"date-parts":[[2012,2,24]]},"assertion":[{"value":"24 February 2012","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}