@inproceedings{uica,
    author = {Abel, Andreas and Reineke, Jan},
    title = {{UiCA}: Accurate Throughput Prediction of Basic Blocks on Recent Intel Microarchitectures},
    year = {2022},
    isbn = {9781450392815},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3524059.3532396},
    doi = {10.1145/3524059.3532396},
    booktitle = {Proceedings of the 36th ACM International Conference on Supercomputing},
    articleno = {33},
    numpages = {14},
    keywords = {simulation, benchmarking, pipeline model, optimization, performance, throughput prediction},
    location = {Virtual Event},
    series = {ICS '22}
}

@article{ithemal,
    author       = {Charith Mendis and
                    Saman P. Amarasinghe and
                    Michael Carbin},
    title        = {Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation
                    using Deep Neural Networks},
    journal      = {CoRR},
    volume       = {abs/1808.07412},
    year         = {2018},
    url          = {http://arxiv.org/abs/1808.07412},
    eprinttype    = {arXiv},
    eprint       = {1808.07412},
    timestamp    = {Sun, 02 Sep 2018 15:01:55 +0200},
    biburl       = {https://dblp.org/rec/journals/corr/abs-1808-07412.bib},
    bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{bhive,
    author={Chen, Yishen and Brahmakshatriya, Ajay and Mendis, Charith and Renda, Alex and Atkinson, Eric and Sýkora, Ondřej and Amarasinghe, Saman and Carbin, Michael},
    booktitle={2019 IEEE International Symposium on Workload Characterization (IISWC)}, 
    title={BHive: A Benchmark Suite and Measurement Framework for Validating x86-64 Basic Block Performance Models}, 
    year={2019},
    volume={},
    number={},
    pages={167-177},
    doi={10.1109/IISWC47752.2019.9042166}}

@article{anica,
    author = {Ritter, Fabian and Hack, Sebastian},
    title = {AnICA: Analyzing Inconsistencies in Microarchitectural Code Analyzers},
    year = {2022},
    issue_date = {October 2022},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    volume = {6},
    number = {OOPSLA2},
    url = {https://doi.org/10.1145/3563288},
    doi = {10.1145/3563288},
    journal = {Proc. ACM Program. Lang.},
    month = {oct},
    articleno = {125},
    numpages = {29},
    keywords = {Throughput Prediction, Basic Blocks, Abstraction, Differential Testing}
}

@inproceedings{palmed,
    author={Derumigny, Nicolas and Bastian, Théophile and Gruber, Fabian and Iooss, Guillaume and Guillon, Christophe and Pouchet, Louis-Noël and Rastello, Fabrice},
    booktitle={2022 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)}, 
    title={PALMED: Throughput Characterization for Superscalar Architectures}, 
    year={2022},
    volume={},
    number={},
    pages={106-117},
    doi={10.1109/CGO53902.2022.9741289}
}


@misc{llvm-mca,
    author  = {{Sony Corporation} and {LLVM Project}},
    title   = {{LLVM} Machine Code Analyzer},
    howpublished = {\url{https://llvm.org/docs/CommandGuide/llvm-mca.html}},
}
@misc{llvm_mca_rfc,
    title={{[RFC] llvm-mca: a static performance analysis tool}},
    author={Andrea Di Biagio},
    howpublished={\url{https://lists.llvm.org/pipermail/llvm-dev/2018-March/121490.html}},
    month={March},
    year={2018},
    note={Request for comments on the llvm-dev mailing-list},
}

@misc{iaca,
    title={Intel Architecture Code Analyzer ({IACA})},
    author={{Intel Corporation}},
    howpublished={\url{https://software.intel.com/en-us/articles/intel-architecture-code-analyzer/}}
}


@INPROCEEDINGS{osaca1,
    author={Laukemann, Jan and Hammer, Julian and Hofmann, Johannes and Hager, Georg and Wellein, Gerhard},
    booktitle={2018 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)}, 
    title={Automated Instruction Stream Throughput Prediction for Intel and AMD Microarchitectures}, 
    year={2018},
    volume={},
    number={},
    pages={121-131},
    doi={10.1109/PMBS.2018.8641578}
}

@INPROCEEDINGS{osaca2,
    author={Laukemann, Jan and Hammer, Julian and Hager, Georg and Wellein, Gerhard},
    booktitle={2019 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)}, 
    title={Automatic Throughput and Critical Path Analysis of x86 and ARM Assembly Kernels}, 
    year={2019},
    volume={},
    number={},
    pages={1-6},
    doi={10.1109/PMBS49563.2019.00006}
}

@online{AgnerFog,
	author    = {Agner Fog},
	title     = {Instruction tables: Lists of instruction latencies, through-puts and micro-operation breakdowns for Intel, {AMD} and {VIA} {CPU}s},
	publisher = {Technical University of Denmark},
	year      = {2020},
	url       = {http://www.agner.org/optimize/instruction_tables.pdf},
}

@inproceedings{uopsinfo,
    title = {uops.info: Characterizing Latency, Throughput, and Port Usage of Instructions on Intel Microarchitectures},
    acmid = {3304062},
    address = {New York, NY, USA},
    author = {Abel, Andreas and Reineke, Jan},
    booktitle = {ASPLOS},
    doi = {10.1145/3297858.3304062},
    isbn = {978-1-4503-6240-5},
    location = {Providence, RI, USA},
    numpages = {14},
    pages = {673--686},
    publisher = {ACM},
    series = {ASPLOS '19},
    year = {2019},
    url = {http://doi.acm.org/10.1145/3297858.3304062}
}

@article{nanobench,
    author    = {Andreas Abel and Jan Reineke},
    title     = {nano{B}ench: A Low-Overhead Tool for Running Microbenchmarks on x86 Systems},
    journal   = {arXiv e-prints},
    volume    = {abs/1911.03282},
    year      = {2019},
    url       = {http://arxiv.org/abs/1911.03282},
    archivePrefix = {arXiv},
    eprint    = {1911.03282},
    timestamp = {Mon, 11 Nov 2019 18:38:09 +0100},
    biburl    = {https://dblp.org/rec/journals/corr/abs-1911-03282.bib},
    bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{PMEvo,
  author    = {Fabian Ritter and
               Sebastian Hack},
  editor    = {Alastair F. Donaldson and
               Emina Torlak},
  title     = {PMEvo: portable inference of port mappings for out-of-order processors
               by evolutionary optimization},
  booktitle = {Proceedings of the 41st {ACM} {SIGPLAN} International Conference on
               Programming Language Design and Implementation, {PLDI} 2020},
  pages     = {608--622},
  publisher = {{ACM}},
  address   = {New York, USA},
  location  = {London, UK},
  month     = {June},
  year      = {2020},
  url       = {https://doi.org/10.1145/3385412.3385995},
  doi       = {10.1145/3385412.3385995},
  timestamp = {Tue, 09 Jun 2020 13:52:54 +0200},
  biburl    = {https://dblp.org/rec/conf/pldi/0002H20.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}