@book{tuomanen2018hands,
  title={Hands-On GPU Programming with Python and CUDA: Explore high-performance parallel computing with CUDA},
  author={Tuomanen, Brian},
  year={2018},
  publisher={Packt Publishing Ltd}
}
@misc{blog_2020, 
    title={Cooperative groups: Flexible cuda thread programming}, 
    url={https://developer.nvidia.com/blog/cooperative-groups/}, 
    journal={NVIDIA Technical Blog}, year={2020}, month={Aug}
}
@misc{center, 
    title={Cuda C++ Programming Guide}, 
    url={https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#programming-model},
journal={NVIDIA Documentation Center}} 

@misc{MemoryAlignment,
    title={Fang's Notebook. Nichijou.co},
    url={https://nichijou.co/cudaRandom-memAlign/},
    month={May}, year={2022}
}

@misc{atomics, 
    title={What are atomic operations for newbies?}, 
    url={https://stackoverflow.com/questions/52196678/what-are-atomic-operations-for-newbies}, 
    journal={Stack Overflow}, author={Brijendar BakchodiaBrijendar Bakchodia1 and AmadanAmadan}, 
    year={2018}, 
    month={Apr}
} 

 @misc{habr_car_vs_bus, title={Paraljeljnoje programmirovanije s cuda. chastj 1: Vvedenije}, url={https://habr.com/ru/company/epam_systems/blog/245503/}, journal={Habr}, publisher={Habr}, year={2015}, month={Apr}}

 @misc{memory_model, 
   title={Cuda\ -\ memory model},
   url={https://medium.com/analytics-vidhya/cuda-memory-model-823f02cef0bf#:~:text=Pageable\%20memory,-The\%20memory\%20allocated\&text=The\%20data\%20at\%20this\%20memory,allocation\%20and\%20transfer\%20is\%20slow}, 
  journal={Medium}, 
  publisher={Analytics Vidhya}, 
  author={Ponnuraj, Raj Prasanna}, 
  year={2020}, 
  month={Oct}
 }

@misc{async_memcpy,
  title={How to Overlap Data Transfers in CUDA C/C++},
  url={https://developer.nvidia.com/blog/how-overlap-data-transfers-cuda-cc/},
  journal={Nvidia Developer blog},
  year={2013},
  month={Dec},
  author={Mark Harris}
}
@misc{chinese_sync, 
  title={Cuda \_\_shfl\_xor \_\_shfl \_\_shfl\_up() \_\_shfl\_down()}, 
  url={https://blog.csdn.net/jqw11/article/details/103071556}, 
  journal={cuda \_\_shfl\_xor \_\_shfl \_\_shfl\_up() \_\_shfl\_down()\_8BitCat-CSDN\_cuda}
}
@misc{conference_gpu,
    title={Kepler's SHUFFLE (SHFL): Tips and Tricks | GTC 2013},
    url={http://on-demand.gputechconf.com/gtc/2013/presentations/S3174-Kepler-Shuffle-Tips-Tricks.pdf}
}


@misc{cuda_events, 
  title={Introduction to stream and event}, 
  url={https://www.programmerall.com/article/4005578780/}, 
  journal={CUDA ---- Stream and Event - Programmer All}
} 

@misc{cuda_performance_metrics,
    title={How to Implement Performance Metrics in CUDA C/C++ | NVIDIA ...},
    url={https://developer.nvidia.com/blog/how-implement-performance-metrics-cuda-cc}
}

@misc{streams_best_practices,
   title={CUDA Streams: Best Practices and Common Pitfalls},
   url={https://on-demand.gputechconf.com/gtc/2014/presentations/S4158-cuda-streams-best-practices-common-pitfalls.pdf}
}


@misc{ptx_nvidia, 
  title={Parallel thread execution ISA version 7.7}, 
  url={https://docs.nvidia.com/cuda/parallel-thread-execution/index.html}, 
  journal={NVIDIA Documentation Center}
}

@misc{ptx_wiki, 
 title={Parallel thread execution}, 
 url={https://en.wikipedia.org/wiki/Parallel_Thread_Execution}, 
 journal={Wikipedia}, 
 publisher={Wikimedia Foundation}, 
 year={2022}, 
 month={May}
} 

 @misc{nsight_cern,
 url={https://indico.cern.ch/event/962112/contributions/4110591/attachments/2159863/3643851/CERN_Nsight_Compute.pdf}
} 

@misc{armour_warp_nodate,
	address = {Oxford e-Research centre},
	type = {Lecture},
	title = {Warp shuffles, reduction and scan operations},
	url = {https://people.maths.ox.ac.uk/gilesm/cuda/2019/lecture_04.pdf},
	abstract = {n this fourth lecture we will learn about warp shuffle instructions, reduction and scan operations.
You will learn about:
• Different types of warp shuffle instructions and why they are useful.
• How warp shuffles can be used to construct different memory access patterns.
• The reduction algorithm and implementation on a GPU.
• The scan algorithm and implementation on a GPU},
	language = {English},
	urldate = {2022-11-10},
	author = {Armour, Was},
}

@misc{giles_warp_nodate,
	address = {Oxford University Mathematical Institute},
	type = {Lecture},
	title = {Warp shuffles, reduction and scan operations},
	url = {https://people.maths.ox.ac.uk/gilesm/cuda/lecs/lec4.pdf},
	language = {English},
	urldate = {2022-11-10},
	author = {Giles, Mike},
}

@misc{talonmies_cudamemcpytosymbol_2013,
	type = {Answer},
	title = {{cudaMemcpyToSymbol} vs. {cudaMemcpy} why is it still around ({cudaMemcpyToSymbol})},
	url = {https://stackoverflow.com/questions/15984913/cudamemcpytosymbol-vs-cudamemcpy-why-is-it-still-around-cudamemcpytosymbol},
	journal = {stackoverflow.com},
	author = {talonmies},
	month = may,
	year = {2013},
}


@misc{noauthor_docsgl_nodate,
	title = {docs.gl},
	url = {https://docs.gl/},
	urldate = {2022-11-11},
	file = {docs.gl:/home/leo/Zotero/storage/KIHKSL57/docs.gl.html:text/html},
}

@misc{noauthor_steps3d_nodate,
	title = {{steps3D}\ -\ {Tutorials}\ -\ Vzaimodejstvije\ {CUDA}\ i\ {OpenGL}},
	url = {http://steps3d.narod.ru/tutorials/cuda-opengl-tutorial.html},
	urldate = {2022-11-11},
	file = {steps3D\ -\ Tutorials\ -\ Vzaimodejstvije\ CUDA\ и\ OpenGL:/home/leo/Zotero/storage/833WUXG9/cuda-opengl-tutorial.html:text/html},
}

@book{boreskov__nodate,
  edition = {Издательство Московского университета},
  series = {Moskovskij gosudarstvennij universitet imeni M. V. Lomonosova},
  title = {{Paralleljnije Vichislenija na GPU Arhitektura i programmnaja modelj CUDA}},
	isbn = {978-5-19-011058-6},
	language = {Russian},
	author = {Boreskov and Kharlamov and Markovskij and Miljnjcev and Sakharnih and Frolov},
}

@misc{reeves_ams_nodate,
	type = {Course description},
	title = {{AMS} 148: {GPU} {Programming} {For} {Scientific} {Computation} {\textbar} {AMS148}, {Spring} 18, {Section} 01},
	url = {https://ams148-spring18-01.courses.soe.ucsc.edu/},
	abstract = {This is a first course in parallel programming with GPUs in CUDA C and C++. This course covers introductory parallelism, basic hardware, parallel communication patterns, and primitive algorithms. The students will apply these topics to problems in scientific computing, image/signal processing, and linear algebra.  At the end of the course, students will complete a final project in a topic of their choosing.},
	urldate = {2022-11-13},
	author = {Reeves, Steven},
	file = {AMS 148\: GPU Programming For Scientific Computation | AMS148, Spring 18, Section 01:/home/leo/Zotero/storage/5R9APMF6/ams148-spring18-01.courses.soe.ucsc.edu.html:text/html},
}


@misc{noauthor_prefix_2022,
	title = {Prefix sum},
	copyright = {Creative Commons Attribution-ShareAlike License},
	url = {https://en.wikipedia.org/w/index.php?title=Prefix_sum\&oldid=1120386053},
	abstract = {In computer science, the prefix sum, cumulative sum, inclusive scan, or simply scan of a sequence of numbers x0, x1, x2, ... is a second sequence of numbers y0, y1, y2, ..., the sums of prefixes (running totals) of the input sequence:

y0 = x0
y1 = x0 + x1
y2 = x0 + x1+ x2
...For instance, the prefix sums of the natural numbers are the triangular numbers:

Prefix sums are trivial to compute in sequential models of computation, by using the formula yi = yi − 1 + xi to compute each output value in sequence order. However, despite their ease of computation, prefix sums are a useful primitive in certain algorithms such as counting sort,
and they form the basis of the scan higher-order function in functional programming languages. Prefix sums have also been much studied in parallel algorithms, both as a test problem to be solved and as a useful primitive to be used as a subroutine in other parallel algorithms.Abstractly, a prefix sum requires only a binary associative operator ⊕, making it useful for many applications from calculating well-separated pair decompositions of points to string processing.Mathematically, the operation of taking prefix sums can be generalized from finite to infinite sequences; in that context, a prefix sum is known as a partial sum of a series. Prefix summation or partial summation form linear operators on the vector spaces of finite or infinite sequences; their inverses are finite difference operators.},
	language = {en},
	urldate = {2022-11-13},
	journal = {Wikipedia},
	month = nov,
	year = {2022},
	note = {Page Version ID: 1120386053},
	file = {Snapshot:/home/leo/Zotero/storage/8AHRTZXN/Prefix_sum.html:text/html},
}

@misc{harris_parallel_2007,
	title = {Parallel {Prefix} {Sum} ({Scan}) with {CUDA}},
	copyright = {2007 NVIDIA Corporation. All rights reserved.},
	url = {https://www.eecs.umich.edu/courses/eecs570/hw/parprefix.pdf},
	abstract = {Parallel prefix sum, also known as parallel Scan, is a useful building block for many
parallel algorithms including sorting and building data structures. In this document
we introduce Scan and describe step-by-step how it can be implemented efficiently
in NVIDIA CUDA. We start with a basic naïve algorithm and proceed through
more advanced techniques to obtain best performance. We then explain how to
scan arrays of arbitrary size that cannot be processed with a single block of threads.},
	language = {English},
	urldate = {2022-10-14},
	author = {Harris, Mark},
	month = apr,
	year = {2007},
}

@misc{luebke_blelloch_nodate,
	title = {Blelloch {Scan} - {Intro} to {Parallel} {Programming}},
	url = {https://www.youtube.com/watch?v=mmYv3Haj6uc},
	language = {En},
	urldate = {2022-11-18},
	publisher = {Udacity},
	author = {Luebke, David and Owens, John},
}

@misc{harris_chapter_nodate,
	title = {Chapter 39. {Parallel} {Prefix} {Sum} ({Scan}) with {CUDA}},
	url = {https://developer.nvidia.com/gpugems/gpugems3/part-vi-gpu-computing/chapter-39-parallel-prefix-sum-scan-cuda},
	language = {en-US},
	urldate = {2022-11-23},
	journal = {NVIDIA Developer},
	author = {Harris, Mark},
	file = {Snapshot:/home/leo/Zotero/storage/X372HD24/chapter-39-parallel-prefix-sum-scan-cuda.html:text/html},
}

@book{osnovi_raboti,
  title = {Osnovi paboti s tehnologijej CUDA},
  author = {Boreskov and Harlamov},
  address = {Moscow},
  year = {2010},
  publisher = {DMK PRSS Издательство},
  isbn = {978-5-94074-578-5}
}

@book{tehnologija_cuda,
  title = {CUDA by Example, An introduction to general-purpose GPU programming},
  address = {Moscow},
  author = {Jason Sanders and Edward Kandrot},
  language = {Russian},
  isbn = {978-5-94074-504-4},
  year = {2011},
  publisher = {DMK Press}
}