{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T21:06:39Z","timestamp":1726002399819},"publisher-location":"Cham","reference-count":55,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319993218"},{"type":"electronic","value":"9783319993225"}],"license":[{"start":{"date-parts":[[2018,12,6]],"date-time":"2018-12-06T00:00:00Z","timestamp":1544054400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-319-99322-5_21","type":"book-chapter","created":{"date-parts":[[2018,12,5]],"date-time":"2018-12-05T17:56:24Z","timestamp":1544032584000},"page":"417-441","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards Breaking the Memory Bandwidth Wall Using Approximate Value Prediction"],"prefix":"10.1007","author":[{"given":"Amir","family":"Yazdanbakhsh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gennady","family":"Pekhimenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hadi","family":"Esmaeilzadeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todd C.","family":"Mowry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,6]]},"reference":[{"issue":"7","key":"21_CR1","doi-asserted-by":"publisher","first-page":"922","DOI":"10.1109\/TC.2005.119","volume":"54","author":"C Alvarez","year":"2005","unstructured":"Alvarez C, Corbal J, Valero M (2005) Fuzzy memoization for floating-point multimedia applications. IEEE Trans Comput 54.7:922\u2013927","journal-title":"IEEE Trans Comput"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Amant RS, Yazdanbakhsh A, Park J, Thwaites B, Esmaeilzadeh H et al (2014) General-purpose code acceleration with limited-precision analog computation. In: ISCA, pp 505\u2013516","DOI":"10.1109\/ISCA.2014.6853213"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Arnau J-M, Parcerisa J-M, Xekalakis P (2014) Eliminating redundant fragment shader executions on a mobile GPU via hardware memoization. In: ISCA, pp 529\u2013540","DOI":"10.1109\/ISCA.2014.6853207"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Baek W, Chilimbi TM (2010) Green: a framework for supporting energy-conscious programming using controlled approximation. In: PLDI, pp 198\u2013209","DOI":"10.1145\/1806596.1806620"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Bakhoda A, Yuan G, Fung W, Wong H, Aamodt T (2009) Analyzing CUDA workloads using a detailed GPU simulator. In: ISPASS, pp 163\u2013174","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Carbin M, Misailovic S, Rinard MC (2013) Verifying quantitative reliability for programs that execute on unreliable hardware. In: OOPSLA, pp 33\u201352","DOI":"10.1145\/2509136.2509546"},{"issue":"2","key":"21_CR7","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1145\/1138035.1138038","volume":"3","author":"Luis Ceze","year":"2006","unstructured":"Ceze L, Strauss K, Tuck J, Torrellas J, Renau J (2006) CAVA: using checkpoint-assisted value prediction to hide L2 misses. In: ACM TACO 3.2:182\u2013208","journal-title":"ACM Transactions on Architecture and Code Optimization"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Chakrapani LN, Akgul BES, Cheemalavagu S, Korkmaz P, Palem KV et al (2006) Ultra-efficient (embedded) SoC architectures based on probabilistic CMOS (PCMOS) technology. In: DATE, pp 1\u20136","DOI":"10.1109\/DATE.2006.243978"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Che S, Boyer M, Meng J, Tarjan D, Sheaffer JW et al (2009) Rodinia: a benchmark suite for heterogeneous computing. In: IISWC, pp 44\u201354","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Chung ES, Milder PA, Hoe JC, Mai K (2010) Single-chip heterogeneous computing: does the future include custom logic, FPGAs, and GPUs? In: MICRO, pp 225\u2013236","DOI":"10.1109\/MICRO.2010.36"},{"key":"21_CR11","first-page":"46","volume-title":"Lecture Notes in Computer Science","author":"Sylvain Collange","year":"2010","unstructured":"Collange S, Defour D, Zhang Y (2010) Dynamic detection of uniform and affine vectors in GPGPU computations. In: Euro-Par (Parallel Processing Workshops), pp 46\u201355"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Collins JD, Wang H, Tullsen DM, Hughes C, Lee Y-F et al (2001) Speculative precomputation: long-range prefetching of delinquent loads. In: ISCA, pp 14\u201325","DOI":"10.1145\/379240.379248"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"de Kruijf M, Nomura S, Sankaralingam K (2010) Relax: an architectural framework for software recovery of hardware faults. In: ISCA, pp 497\u2013508","DOI":"10.1145\/1815961.1816026"},{"issue":"4","key":"21_CR14","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1147\/rd.374.0547","volume":"37","author":"RJ Eickemeyer","year":"1993","unstructured":"Eickemeyer RJ, Vassiliadis S (1993) A load-instruction unit for pipelined processors. IBM J Res Dev 37.4:547\u2013564","journal-title":"IBM J Res Dev"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Esmaeilzadeh H, Sampson A, Ceze L, Burger D (2012) Architecture support for disciplined approximate programming. In: ASPLOS, pp 301\u2013312","DOI":"10.1145\/2150976.2151008"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Esmaeilzadeh H, Sampson A, Ceze L, Burger D (2012) Neural acceleration for general-purpose approximate programs. In: MICRO, pp 449\u2013460","DOI":"10.1109\/MICRO.2012.48"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Garcia P, Emambakhsh M, Wallace A (2017) Learning to approximate computing at run-time. In: International conference on intelligent signal processing (ISP), pp 1\u20136","DOI":"10.1049\/cp.2017.0361"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Goeman B, Vandierendonck H, De Bosschere K (2001) Differential FCM: increasing value prediction accuracy by improving table usage efficiency. In: HPCA, pp 207\u2013216","DOI":"10.1109\/HPCA.2001.903264"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"He B, Fang W, Luo Q, Govindaraju NK, Wang T (2008) Mars: a MapReduce framework on graphics processors. In: PACT, pp 260\u2013269","DOI":"10.1145\/1454115.1454152"},{"issue":"5","key":"21_CR20","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/MM.2011.89","volume":"31","author":"Stephen W. Keckler","year":"2011","unstructured":"Keckler SW, Dally WJ, Khailany B, Garland M, Glasco D (2011) GPUs and the future of parallel computing. In: IEEE Micro 5:7\u201317","journal-title":"IEEE Micro"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Kim Y, Venkataramani S, Roy K, Raghunathan A (2016) Designing approximate circuits using clock overgating. In: DAC. IEEE, Piscataway, pp 1\u20136","DOI":"10.1145\/2897937.2898005"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Leng J, Hetherington T, ElTantawy A, Gilani S, Kim NS et al (2013) GPUWattch: enabling energy optimizations in GPGPUs. In: ISCA, pp 487\u2013498","DOI":"10.1145\/2485922.2485964"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Li X, Yeung D (2007) Application-level correctness and its impact on fault tolerance. In: HPCA, pp 181\u2013192","DOI":"10.1109\/HPCA.2007.346196"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Li S, Ahn JH, Strong RD, Brockman JB, Tullsen DM et al (2009) McPAT: an integrated power, area, and timing modeling framework for multicore and manycore architectures. In: MICRO, pp 469\u2013480","DOI":"10.1145\/1669112.1669172"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Li A, Song SL, Wijtvliet M, Kumar A, Corporaal H (2016) SFU-driven transparent approximation acceleration on GPUs. In Proceedings of the international conference on supercomputing. ACM, New York, pp 15:1\u201315:14","DOI":"10.1145\/2925426.2926255"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Lipasti MH, Shen JP (1996) Exceeding the dataflow limit via value prediction. In: MICRO, pp 226\u2013237","DOI":"10.1109\/MICRO.1996.566464"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Lipasti MH, Wilkerson CB, Shen JP (1996) Value locality and load value prediction. In: ASPLOS, pp 138\u2013147","DOI":"10.1145\/237090.237173"},{"key":"21_CR28","unstructured":"Liu S, Pattabiraman K, Moscibroda T, Zorn BG (2011) Flikker: saving refresh-power in mobile devices through critical data partitioning. In: ASPLOS, pp 213\u2013224"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Luo Y, Govindan S, Sharma BP, Santaniello M, Meza J et al (2014) Characterizing application memory error vulnerability to optimize datacenter cost via heterogeneous-reliability memory. In: DSN, pp 467\u2013478","DOI":"10.1109\/DSN.2014.50"},{"issue":"5","key":"21_CR30","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MM.2015.108","volume":"35","author":"Divya Mahajan","year":"2015","unstructured":"Mahajan D, Ramkrishnan K, Jariwala R, Yazdanbakhsh A, Park J et al (2015) Axilog: abstractions for approximate hardware design and reuse. In: IEEE Micro 35.5:16\u201330","journal-title":"IEEE Micro"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Maier D, Cosenza B, Juurlink B (2018) Local memory-aware kernel perforation. In: CGO, pp 278\u2013287","DOI":"10.1145\/3168814"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Muralimanohar N, Balasubramonian R, Jouppi N (2007) Optimizing NUCA organizations and wiring alternatives for large caches with CACTI 6.0. In: MICRO, pp 3\u201314","DOI":"10.1109\/MICRO.2007.33"},{"key":"21_CR33","unstructured":"Murase M (1992) Linear feedback shift register. In: US Patent"},{"issue":"6","key":"21_CR34","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MM.2003.1261383","volume":"23","author":"O. Mutlu","year":"2003","unstructured":"Mutlu O, Stark J, Wilkerson C, Patt YN (2003) Runahead execution: an effective alternative to large instruction windows. In: IEEE Micro 23.6:20\u201325","journal-title":"IEEE Micro"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Mutlu O, Kim H, Patt YN (2005) Address-value delta (AVD) prediction: increasing the effectiveness of runahead execution by exploiting regular memory allocation patterns. In: MICRO, pp 233\u2013244","DOI":"10.1109\/MICRO.2005.11"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Park J, Esmaeilzadeh H, Zhang X, Naik M, Harris W (2015) FlexJava: language support for safe and modular approximate programming. In: FSE, pp 745\u2013757","DOI":"10.1145\/2786805.2786807"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Pekhimenko G, Seshadri V, Mutlu O, Gibbons PB, Kozuch MA et al (2012) Base-delta-immediate compression: practical data compression for on-chip caches. In: PACT, pp 377\u2013388","DOI":"10.1145\/2370816.2370870"},{"issue":"2","key":"21_CR38","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/LCA.2015.2430853","volume":"14","author":"G Pekhimenko","year":"2015","unstructured":"Pekhimenko G, Bolotin E, O\u2019Connor M, Mutlu O, Mowry T et al (2015) Toggle-aware compression for GPUs. Comput. Archit. Lett. 14.2:164\u2013168","journal-title":"Comput. Archit. Lett."},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Perais A, Seznec A (2014) Practical data value speculation for future high-end processors. In: HPCA, pp 428\u2013439","DOI":"10.1109\/HPCA.2014.6835952"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Rogers BM, Krishna A, Bell GB, Vu K, Jiang X et al (2009) Scaling the bandwidth wall: challenges in and avenues for CMP scaling. In: ISCA, pp 371\u2013382","DOI":"10.1145\/1555754.1555801"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Rogers T, O\u2019Connor M, Aamodt T (2012) Cache-conscious wavefront scheduling. In: MICRO, pp 72\u201383","DOI":"10.1109\/MICRO.2012.16"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Samadi M, Lee J, Jamshidi DA, Hormati A, Mahlke S (2013) SAGE: self-tuning approximation for graphics engines. In: MICRO, pp 13\u201324","DOI":"10.1145\/2540708.2540711"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Samadi M, Jamshidi DA, Lee J, Mahlke S (2014) Paraprox: pattern-based approximation for data parallel applications. In: ASPLOS, pp 35\u201350","DOI":"10.1145\/2541940.2541948"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Sampson A, Dietl W, Fortuna E, Gnanapragasam D, Ceze L et al (2011) EnerJ: approximate data types for safe and general low-power computation. In: PLDI, pp 164\u2013174","DOI":"10.1145\/1993498.1993518"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Sampson A, Nelson J, Strauss K, Ceze L (2013) Approximate storage in solid-state memories. In: MICRO, pp 25\u201336","DOI":"10.1145\/2540708.2540712"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"San Miguel J, Badr M, Jerger NE (2014) Load value approximation. In: MICRO, December 2014, pp 127\u2013139","DOI":"10.1109\/MICRO.2014.22"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"San Miguel J, Albericio J, Jerger NE, Jaleel A (2016) The bunker cache for spatio-value approximation. In: MICRO, pp 1\u201312","DOI":"10.1109\/MICRO.2016.7783746"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Sazeides Y, Smith JE (1997) The predictability of data values. In: MICRO, pp 248\u2013258","DOI":"10.1109\/MICRO.1997.645815"},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Sidiroglou-Douskos S, Misailovic S, Hoffmann H, Rinard M (2011) Managing performance vs. accuracy trade-offs with loop perforation. In: FSE, pp 124\u2013134","DOI":"10.1145\/2025113.2025133"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Thomas R, Franklin M (2001) Using dataflow based context for accurate value prediction. In: PACT, pp 107\u2013117","DOI":"10.1109\/PACT.2001.953292"},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Thwaites B, Pekhimenko G, Esmaeilzadeh H, Yazdanbakhsh A, Mutlu O et al (2014) Rollback-free value prediction with approximate loads. In: PACT, August 2014, pp 493\u2013494","DOI":"10.1145\/2628071.2628110"},{"key":"21_CR52","doi-asserted-by":"crossref","unstructured":"Vijaykumar N, Pekhimenko G, Jog A, Bhowmick A, Ausavarungnirun R et al (2015) A case for core-assisted bottleneck acceleration in GPUs: enabling flexible data compression with assist warps. In: ISCA, pp 41\u201353","DOI":"10.1145\/2749469.2750399"},{"key":"21_CR53","doi-asserted-by":"crossref","unstructured":"Wong D, Kim NS, Annavaram M (2016) Approximating warps with intra-warp operand value similarity. In: HPCA, pp 176\u2013187","DOI":"10.1109\/HPCA.2016.7446063"},{"key":"21_CR54","doi-asserted-by":"crossref","unstructured":"Yazdanbakhsh A, Mahajan D, Thwaites B, Park J, Nagendrakumar A et al (2015) Axilog: language support for approximate hardware design. In: DATE, pp 812\u2013817","DOI":"10.7873\/DATE.2015.0513"},{"issue":"7","key":"21_CR55","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1109\/TC.2005.117","volume":"54","author":"H Zhou","year":"2005","unstructured":"Zhou H, Conte TM (2005) Enhancing memory-level parallelism via recovery-free value prediction. IEEE Trans Comput 54.7:897\u2013912","journal-title":"IEEE Trans Comput"}],"container-title":["Approximate Circuits"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99322-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,7]],"date-time":"2022-09-07T17:55:18Z","timestamp":1662573318000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99322-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,6]]},"ISBN":["9783319993218","9783319993225"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99322-5_21","relation":{},"subject":[],"published":{"date-parts":[[2018,12,6]]}}}