303 lines
8.8 KiB
BibTeX
303 lines
8.8 KiB
BibTeX
@misc{blas1979,
|
||
title = {{{BLAS}} ({{Basic Linear Algebra Subprograms}})},
|
||
author = {{Netlib}},
|
||
year = {1979},
|
||
urldate = {2024-01-08},
|
||
howpublished = {https://www.netlib.org/blas/},
|
||
}
|
||
|
||
@inproceedings{he2020,
|
||
title = {Newton: {{A DRAM-maker}}'s {{Accelerator-in-Memory}} ({{AiM}}) {{
|
||
Architecture}} for {{Machine Learning}}},
|
||
shorttitle = {Newton},
|
||
booktitle = {2020 53rd {{Annual IEEE}}/{{ACM International Symposium}} on {{
|
||
Microarchitecture}} ({{MICRO}})},
|
||
author = {He, Mingxuan and others},
|
||
year = {2020},
|
||
month = oct,
|
||
pages = {372--385},
|
||
publisher = {IEEE},
|
||
address = {Athens, Greece},
|
||
doi = {10.1109/MICRO50266.2020.00040},
|
||
urldate = {2024-01-09},
|
||
isbn = {978-1-72817-383-2},
|
||
keywords = {reviewed},
|
||
}
|
||
|
||
@inproceedings{kang2022,
|
||
title = {An {{FPGA-based RNN-T Inference Accelerator}} with {{PIM-HBM}}},
|
||
booktitle = {Proceedings of the 2022 {{ACM}}/{{SIGDA International Symposium
|
||
}} on {{Field-Programmable Gate Arrays}}},
|
||
author = {Kang, Shinhaeng and others},
|
||
year = {2022},
|
||
month = feb,
|
||
pages = {146--152},
|
||
publisher = {ACM},
|
||
address = {Virtual Event USA},
|
||
doi = {10.1145/3490422.3502355},
|
||
urldate = {2024-01-08},
|
||
isbn = {978-1-4503-9149-8},
|
||
langid = {english},
|
||
keywords = {reviewed},
|
||
}
|
||
|
||
@inproceedings{kwon2021,
|
||
title = {25.4 {{A}} 20nm {{6GB Function-In-Memory DRAM}}, {{Based}} on {{
|
||
HBM2}} with a 1.{{2TFLOPS Programmable Computing Unit Using
|
||
Bank-Level Parallelism}}, for {{Machine Learning Applications}}},
|
||
booktitle = {2021 {{IEEE International Solid- State Circuits Conference}} ({
|
||
{ISSCC}})},
|
||
author = {Kwon, Young-Cheon and others},
|
||
year = {2021},
|
||
month = feb,
|
||
pages = {350--352},
|
||
publisher = {IEEE},
|
||
address = {San Francisco, CA, USA},
|
||
doi = {10.1109/ISSCC42613.2021.9365862},
|
||
urldate = {2024-01-08},
|
||
isbn = {978-1-72819-549-0},
|
||
langid = {english},
|
||
keywords = {reviewed},
|
||
}
|
||
|
||
@inproceedings{lee2021,
|
||
title = {Hardware {{Architecture}} and {{Software Stack}} for {{PIM Based}}
|
||
on {{Commercial DRAM Technology}} : {{Industrial Product}}},
|
||
shorttitle = {Hardware {{Architecture}} and {{Software Stack}} for {{PIM
|
||
Based}} on {{Commercial DRAM Technology}}},
|
||
booktitle = {2021 {{ACM}}/{{IEEE}} 48th {{Annual International Symposium}}
|
||
on {{Computer Architecture}} ({{ISCA}})},
|
||
author = {Lee, Sukhan and others},
|
||
year = {2021},
|
||
month = jun,
|
||
pages = {43--56},
|
||
publisher = {IEEE},
|
||
address = {Valencia, Spain},
|
||
doi = {10.1109/ISCA52012.2021.00013},
|
||
urldate = {2024-01-08},
|
||
isbn = {978-1-66543-333-4},
|
||
langid = {english},
|
||
keywords = {reviewed},
|
||
}
|
||
|
||
@article{rosenfeld2011,
|
||
title = {{{DRAMSim2}}: {{A Cycle Accurate Memory System Simulator}}},
|
||
shorttitle = {{{DRAMSim2}}},
|
||
author = {Rosenfeld, P and others},
|
||
year = {2011},
|
||
month = jan,
|
||
journal = {IEEE Computer Architecture Letters},
|
||
volume = {10},
|
||
number = {1},
|
||
pages = {16--19},
|
||
issn = {1556-6056},
|
||
doi = {10.1109/L-CA.2011.4},
|
||
urldate = {2024-03-11},
|
||
langid = {english},
|
||
}
|
||
|
||
@misc{shin-haengkang2023,
|
||
title = {{{PIMSimulator}}},
|
||
author = {{Shin-haeng Kang} and others},
|
||
year = {2023},
|
||
month = nov,
|
||
urldate = {2024-02-08},
|
||
abstract = {Processing-In-Memory (PIM) Simulator},
|
||
howpublished = {https://github.com/SAITPublic/PIMSimulator},
|
||
}
|
||
|
||
@article{steiner2022a,
|
||
title = {{{DRAMSys4}}.0: {{An Open-Source Simulation Framework}} for {{
|
||
In-depth DRAM Analyses}}},
|
||
shorttitle = {{{DRAMSys4}}.0},
|
||
author = {Steiner, Lukas and others},
|
||
year = {2022},
|
||
month = apr,
|
||
journal = {International Journal of Parallel Programming},
|
||
volume = {50},
|
||
number = {2},
|
||
pages = {217--242},
|
||
issn = {0885-7458, 1573-7640},
|
||
doi = {10.1007/s10766-022-00727-4},
|
||
urldate = {2024-01-08},
|
||
langid = {english},
|
||
}
|
||
|
||
@incollection{sudarshan2022,
|
||
title = {A {{Critical Assessment}} of {{DRAM-PIM Architectures}} - {{Trends}
|
||
}, {{Challenges}} and {{Solutions}}},
|
||
booktitle = {Embedded {{Computer Systems}}: {{Architectures}}, {{Modeling}},
|
||
and {{Simulation}}},
|
||
author = {Sudarshan, Chirag and others},
|
||
editor = {Orailoglu, Alex and Reichenbach, Marc and Jung, Matthias},
|
||
year = {2022},
|
||
volume = {13511},
|
||
pages = {362--379},
|
||
publisher = {Springer International Publishing},
|
||
address = {Cham},
|
||
doi = {10.1007/978-3-031-15074-6_23},
|
||
urldate = {2024-01-21},
|
||
isbn = {978-3-031-15073-9 978-3-031-15074-6},
|
||
langid = {english},
|
||
}
|
||
|
||
@inproceedings{jouhyu_21,
|
||
author = {Jouppi, Norman P. and others},
|
||
booktitle = {2021 ACM/IEEE 48th Annual International Symposium on Computer
|
||
Architecture (ISCA)},
|
||
title = {Ten Lessons From Three Generations Shaped Google’s TPUv4i :
|
||
Industrial Product},
|
||
doi = {10.1109/ISCA52012.2021.00010},
|
||
pages = {1-14},
|
||
keywords = {Training;Program processors;Quantization (signal);Wires;Random
|
||
access memory;Throughput;Software},
|
||
owner = {MJ},
|
||
year = {2021},
|
||
}
|
||
|
||
@article{sto_70,
|
||
author = {Stone, Harold S.},
|
||
title = {A Logic-in-Memory Computer},
|
||
doi = {10.1109/TC.1970.5008902},
|
||
number = {1},
|
||
pages = {73-78},
|
||
volume = {C-19},
|
||
journal = {IEEE Transactions on Computers},
|
||
keywords = {Computers;Logic arrays;Microelectronics;Memory
|
||
management;Adders;Magnetic memory;Complexity theory;Cache
|
||
memories;computer architecture;logic-in-memory;microelectronic
|
||
memories;unconventional computer systems},
|
||
owner = {MJ},
|
||
year = {1970},
|
||
}
|
||
|
||
@article{gomhaj_21,
|
||
author = {Juan G{\'{o}}mez{-}Luna and others},
|
||
title = {Benchmarking a New Paradigm: An Experimental Analysis of a Real
|
||
Processing-in-Memory Architecture},
|
||
eprint = {2105.03814},
|
||
eprinttype = {arXiv},
|
||
url = {https://arxiv.org/abs/2105.03814},
|
||
volume = {abs/2105.03814},
|
||
bibsource = {dblp computer science bibliography, https://dblp.org},
|
||
biburl = {https://dblp.org/rec/journals/corr/abs-2105-03814.bib},
|
||
journal = {CoRR},
|
||
owner = {MJ},
|
||
timestamp = {Fri, 14 May 2021 12:13:30 +0200},
|
||
year = {2021},
|
||
}
|
||
|
||
@misc{lowahm_20,
|
||
author = {Jason Lowe-Power and others},
|
||
title = {{T}he gem5 {S}imulator: {V}ersion 20.0+},
|
||
eprint = {2007.03152},
|
||
archiveprefix = {arXiv},
|
||
groups = {MJ:1},
|
||
owner = {MJ},
|
||
primaryclass = {cs.AR},
|
||
timestamp = {2020-07-08},
|
||
year = {2020},
|
||
}
|
||
|
||
@inproceedings{stejun_20,
|
||
author = {Steiner, Lukas and others},
|
||
booktitle = {International Conference on Embedded Computer Systems
|
||
Architectures Modeling and Simulation (SAMOS)},
|
||
title = {{DRAMS}ys4.0: {A} {F}ast and {C}ycle-{A}ccurate {S}ystem{C}/{TLM}-{
|
||
B}ased {DRAM} {S}imulator},
|
||
publisher = {Springer},
|
||
groups = {MJ:1},
|
||
month = {July},
|
||
owner = {MJ},
|
||
timestamp = {2020-07-14},
|
||
year = {2020},
|
||
}
|
||
|
||
@misc{corda2021,
|
||
title = {{{NMPO}}: {{Near-Memory Computing Profiling}} and {{Offloading}}},
|
||
shorttitle = {{{NMPO}}},
|
||
author = {Corda, Stefano and others},
|
||
year = {2021},
|
||
month = jun,
|
||
number = {arXiv:2106.15284},
|
||
eprint = {2106.15284},
|
||
primaryclass = {cs},
|
||
publisher = {arXiv},
|
||
urldate = {2024-03-20},
|
||
archiveprefix = {arxiv},
|
||
langid = {english},
|
||
keywords = {Computer Science - Hardware Architecture,Computer Science -
|
||
Performance},
|
||
}
|
||
|
||
@inproceedings{singh2019,
|
||
title = {{{NAPEL}}: {{Near-Memory Computing Application Performance
|
||
Prediction}} via {{Ensemble Learning}}},
|
||
shorttitle = {{{NAPEL}}},
|
||
booktitle = {Proceedings of the 56th {{Annual Design Automation Conference}}
|
||
2019},
|
||
author = {Singh, Gagandeep and others},
|
||
year = {2019},
|
||
month = jun,
|
||
pages = {1--6},
|
||
publisher = {ACM},
|
||
address = {Las Vegas NV USA},
|
||
doi = {10.1145/3316781.3317867},
|
||
urldate = {2024-03-20},
|
||
isbn = {978-1-4503-6725-7},
|
||
langid = {english},
|
||
}
|
||
|
||
@article{yu2021,
|
||
title = {{{MultiPIM}}: {{A Detailed}} and {{Configurable Multi-Stack
|
||
Processing-In-Memory Simulator}}},
|
||
shorttitle = {{{MultiPIM}}},
|
||
author = {Yu, Chao and others},
|
||
year = {2021},
|
||
month = jan,
|
||
journal = {IEEE Computer Architecture Letters},
|
||
volume = {20},
|
||
number = {1},
|
||
pages = {54--57},
|
||
issn = {1556-6056, 1556-6064, 2473-2575},
|
||
doi = {10.1109/LCA.2021.3061905},
|
||
urldate = {2024-03-20},
|
||
langid = {english},
|
||
}
|
||
|
||
@article{sanchez2013,
|
||
title = {{{ZSim}}: Fast and Accurate Microarchitectural Simulation of
|
||
Thousand-Core Systems},
|
||
shorttitle = {{{ZSim}}},
|
||
author = {Sanchez, Daniel and others},
|
||
year = {2013},
|
||
month = jun,
|
||
journal = {ACM SIGARCH Computer Architecture News},
|
||
volume = {41},
|
||
number = {3},
|
||
pages = {475--486},
|
||
issn = {0163-5964},
|
||
doi = {10.1145/2508148.2485963},
|
||
urldate = {2024-03-20},
|
||
langid = {english},
|
||
}
|
||
@article{kim2016a,
|
||
title = {Ramulator: {{A Fast}} and {{Extensible DRAM Simulator}}},
|
||
shorttitle = {Ramulator},
|
||
author = {Kim, Yoongu and others},
|
||
year = {2016},
|
||
month = jan,
|
||
journal = {IEEE Computer Architecture Letters},
|
||
volume = {15},
|
||
number = {1},
|
||
pages = {45--49},
|
||
issn = {1556-6056},
|
||
doi = {10.1109/LCA.2015.2414456},
|
||
urldate = {2024-03-20},
|
||
langid = {english},
|
||
}
|
||
@misc{rust,
|
||
title = {The {{Rust Programming Language}}},
|
||
author = {{Rust Foundation}},
|
||
howpublished = {https://www.rust-lang.org/}
|
||
} |