From a819050e30bb6906858165796655c0c726843a3f Mon Sep 17 00:00:00 2001
From: "Suren A. Chilingaryan" <csa@suren.me>
Date: Sun, 7 Mar 2021 05:57:02 +0100
Subject: Collect all relevant references from the latest publications

---
 wp.bib | 180 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 180 insertions(+)
 create mode 100644 wp.bib

(limited to 'wp.bib')

diff --git a/wp.bib b/wp.bib
new file mode 100644
index 0000000..97273fe
--- /dev/null
+++ b/wp.bib
@@ -0,0 +1,180 @@
+@misc{nvidia2017cudapg,
+  howpublished = {Manual},
+  organization = {NVIDIA},
+  title        = {CUDA C Programming Guide},
+  year         = {2017}
+}
+
+@misc{nvidia2017gpudirect,
+  howpublished = {Manual},
+  organization = {NVIDIA},
+  title        = {Developing a Linux kernel module using RDMA for GPUDirect},
+  year         = {2017}
+}
+
+@misc{ryan2016gpuboost,
+ author    = {Ryan Smith},
+ title     = {The NVIDIA GeForce GTX 1080 \& GTX 1070 Founders Editions Review: Kicking Off the FinFET Generation},
+ publisher = {Anandtech},
+ url       = {https://www.anandtech.com/show/10325/},
+ year      = {2016}
+}
+
+
+@misc{nvidia2013mpi,
+  howpublished = {Blog post},
+  author       = {Jiri Kraus},
+  organization = {NVIDIA},
+  type         = {Blog},
+  title        = {An Introduction to CUDA-Aware MPI},
+  year         = {2013},
+  url          = {https://devblogs.nvidia.com/parallelforall/introduction-cuda-aware-mpi/}
+}
+
+@misc{amd2013openclpg,
+  howpublished = {Manual},
+  organization = {AMD},
+  title        = {AMD Accelerated Parallel Processing OpenCL Programming Guide},
+  year         = {2013}
+}
+
+@misc{amd2011directgma,
+  howpublished = {Manual},
+  author       = {Brian Sumner},
+  organization = {AMD},
+  title        = {OpenCL Extension: AMD Bus Addressable Memory},
+  year         = {2011},
+  url          = {https://www.khronos.org/registry/OpenCL/extensions/amd/cl_amd_bus_addressable_memory.txt}
+}
+
+@misc{intel2011openclpg,
+  howpublished = {Manual},
+  organization = {Intel},
+  title        = {Writing Optimal OpenCL Code with Intel OpenCL SDK: Performance Guide},
+  year         = {2011}
+}
+
+@misc{nvidia2014transpose,
+  howpublished = {Manual},
+  organization = {NVIDIA},
+  author       = {Ruetsch, G. and Micikevicius, P. and Scudiero, T.},
+  title        = {Optimizing Matrix Transpose in CUDA},
+  year         = {2014}
+}
+
+@article{nvidia2008gt200,
+   title        = {NVIDIA Tesla: A Unified Graphics and Computing Architecture},
+   author       = {Lindholm, Erik and Nickolls, John and Oberman, Stuart and Montrym, John},
+   journal      = {Hot Chips},
+   volume       = {19},
+   pages        = {39--55},
+   year         = {2008}
+}
+
+@misc{nvidia2009gf110,
+  howpublished  = {White Paper},
+  organization  = {NVIDIA},
+  title         = {NVIDIA's next generation CUDA compute architecture: Fermi},
+  year          = {2009}
+}
+
+@misc{nvidia2012gk104,
+  howpublished  = {White Paper},
+  organization  = {NVIDIA},
+  title         = {NVIDIA GeForce GTX 680},
+  year          = {2012}
+}
+
+@misc{nvidia2012gk110,
+  howpublished  = {White Paper},
+  organization  = {NVIDIA},
+  title         = {NVIDIA's next generation CUDA compute architecture: Kepler GK110},
+  year          = {2012}
+}
+
+@misc{nvidia2014gm204,
+  howpublished  = {White Paper},
+  organization  = {NVIDIA},
+  title         = {NVIDIA GeForce GTX 980},
+  year          = {2014}
+}
+
+
+@misc{nvidia2016gp104,
+  howpublished  = {White Paper},
+  organization  = {NVIDIA},
+  title         = {NVIDIA GeForce GTX 1080},
+  year          = {2016}
+}
+
+@misc{nvidia2016gp100,
+  howpublished  = {White Paper},
+  organization  = {NVIDIA},
+  title         = {NVIDIA Tesla P100},
+  year          = {2016}
+}
+
+@misc{nvidia2017v100,
+  howpublished  = {White Paper},
+  organization  = {NVIDIA},
+  title         = {NVIDIA Tesla V100 GPU Architecture},
+  year          = {2017}
+}
+
+@misc{amd2012gcn,
+  howpublished  = {White Paper},
+  organization  = {AMD},
+  title         = {AMD Graphics Core Next (GCN) Architecture},
+  year          = {2012}
+}
+
+@misc{amd2008vliw,
+  howpublished  = {White Paper},
+  organization  = {AMD},
+  title         = {Anatomy of AMD’s TeraScale Graphics Engine},
+  year          = {2008}
+}
+
+@online{opencl,
+  author    = {Khronos},
+  title     = {OpenCL: The open standard for parallel programming of heterogeneous systems},
+  year      = {2014},
+  url       = {http://www.khronos.org/opencl}
+}
+
+@misc{khronos:opencl1.2,
+  title     = {The {OpenCL} Specification},
+  author    = {Khronos},
+  editor    = {Munshi, Aaftab},
+  number    = {Version 1.2, Revision 19},
+  year      = {2012},
+  url       = {http://www.khronos.org/opencl},
+}
+
+@online{pco,
+ author     = {PCO},
+ title      = {CCD and CMOS camera systems},
+ url        = {http://www.pco.de},
+ year       = {2014}
+}
+
+@misc{pco2014dimax,
+  howpublished  = {User Manual},
+  organization  = {PCO AG},
+  title         = {PCO.dimax family},
+  year          = {2014},
+  url          = {https://www.pco.de/fileadmin/user_upload/pco-manuals/pco.dimax_CW3_manual.pdf}
+}
+
+@book{ieee754,
+  author   = {IEEE Task P754},
+  title    = {IEEE standard for binary floating-point arithmetic},
+  publisher= {Institute of Electrical and Electronics Engineers},
+  address  = {New York},
+  note     = {Note: Standard 754--1985},
+  pages    = {20},
+  ISBN     = {1-55937-653-8},
+  year     = {1985},
+  url      = {http://ieeexplore.ieee.org/iel1/2355/1316/00030711.pd}
+}
+
-- 
cgit v1.2.1