{{Infobox software | name = CUDA | screenshot = Nvidia CUDA Logo.jpg | developer = Nvidia Corporation | released = {{Start date and age|2007|06|23}} | latest_release_version = 10.1.105 | latest_release_date = {{Start date and age|2019|02|27}} | operating_system = Windows, macOS, Linux | platform = Supported GPUs | genre = GPGPU | license = Freeware | website = {{URL|https://developer.nvidia.com/cuda-zone}} }}CUDA is a parallel computing platform and application programming interface (API) model created by Nvidia.[1] It allows software developers and software engineers to use a CUDA-enabled graphics processing unit (GPU) for general purpose processing — an approach termed GPGPU (General-Purpose computing on Graphics Processing Units). The CUDA platform is a software layer that gives direct access to the GPU's virtual instruction set and parallel computational elements, for the execution of compute kernels.[2]
The CUDA platform is designed to work with programming languages such as C, C++, and Fortran. This accessibility makes it easier for specialists in parallel programming to use GPU resources, in contrast to prior APIs like Direct3D and OpenGL, which required advanced skills in graphics programming.[3] Also, CUDA supports programming frameworks such as OpenACC and OpenCL.[2] When it was first introduced by Nvidia, the name CUDA was an acronym for Compute Unified Device Architecture,[4] but Nvidia subsequently dropped the use of the acronym.
Background
{{More information|Graphics processing unit}}
The graphics processing unit (GPU), as a specialized computer processor, addresses the demands of real-time high-resolution 3D graphics compute-intensive tasks. By 2012, GPUs had evolved into highly parallel multi-core systems allowing very efficient manipulation of large blocks of data. This design is more effective than general-purpose central processing unit (CPUs) for algorithms in situations where processing large blocks of data is done in parallel, such as:
push-relabel maximum flow algorithm
fast sort algorithms of large lists
two-dimensional fast wavelet transform
molecular dynamics simulations
Programming abilities
The CUDA platform is accessible to software developers through CUDA-accelerated libraries, compiler directives such as OpenACC, and extensions to industry-standard programming languages including C, C++ and Fortran. C/C++ programmers can use 'CUDA C/C++', compiled with nvcc, Nvidia's LLVM-based C/C++ compiler.[5] Fortran programmers can use 'CUDA Fortran', compiled with the PGI CUDA Fortran compiler from The Portland Group.
In addition to libraries, compiler directives, CUDA C/C++ and CUDA Fortran, the CUDA platform supports other computational interfaces, including the Khronos Group's OpenCL,[6] Microsoft's DirectCompute, [https://www.khronos.org/opengl/wiki/Compute_Shader OpenGL Compute Shaders] and C++ AMP.[7] Third party wrappers are also available for Python, Perl, Fortran, Java, Ruby, Lua, Common Lisp, Haskell, R, MATLAB, IDL, Julia, and native support in Mathematica.
In the computer game industry, GPUs are used for graphics rendering, and for game physics calculations (physical effects such as debris, smoke, fire, fluids); examples include PhysX and Bullet. CUDA has also been used to accelerate non-graphical applications in computational biology, cryptography and other fields by an order of magnitude or more.[8][9][10][11][12]
CUDA provides both a low level API (CUDA Driver API, non single-source) and a higher level API (CUDA Runtime API, single-source). The initial CUDA SDK was made public on 15 February 2007, for Microsoft Windows and Linux. Mac OS X support was later added in version 2.0,[13] which supersedes the beta released February 14, 2008.[14] CUDA works with all Nvidia GPUs from the G8x series onwards, including GeForce, Quadro and the Tesla line. CUDA is compatible with most standard operating systems. Nvidia states that programs developed for the G8x series will also work without modification on all future Nvidia video cards, due to binary compatibility.{{Citation needed|date=January 2014}}
CUDA 8.0 comes with the following libraries (for compilation & runtime, in alphabetical order):
CUBLAS - CUDA Basic Linear Algebra Subroutines library, see [https://developer.nvidia.com/cublas main] and docs
CUDART - CUDA RunTime library, see docs
CUFFT - CUDA Fast Fourier Transform library, see [https://developer.nvidia.com/cufft main] and docs
CURAND - CUDA Random Number Generation library, see [https://developer.nvidia.com/curand main] and docs
CUSOLVER - CUDA based collection of dense and sparse direct solvers, see [https://developer.nvidia.com/cusolver main] and docs
CUSPARSE - CUDA Sparse Matrix library, see [https://developer.nvidia.com/cusparse main] and docs
NPP - NVIDIA Performance Primitives library, see [https://developer.nvidia.com/npp main] and docs
NVGRAPH - NVIDIA Graph Analytics library, see [https://developer.nvidia.com/nvgraph main] and docs
NVML - NVIDIA Management Library, see [https://developer.nvidia.com/nvidia-management-library-nvml main] and docs
NVRTC - NVIDIA RunTime Compilation library for CUDA C++, see docs
CUDA 8.0 comes with these other software components:
nView - NVIDIA nView Desktop Management Software, see main and docs (pdf)
NVWMI - NVIDIA Enterprise Management Toolkit, see [https://developer.nvidia.com/nvwmi-sdk main] and [https://developer.nvidia.com/designworks/nvwmi/downloads/2.27.3/api-reference docs] (chm)
PhysX - GameWorks PhysX is a multi-platform game physics engine, see [https://developer.nvidia.com/gameworks-physx-overview main] and docs
CUDA 9.0-9.2 comes with these other components:
CUTLASS 1.0 - custom linear algebra algorithms, see [https://news.developer.nvidia.com/cuda-9-2-now-available/ CUDA 9.2 News], [https://news.developer.nvidia.com/cutlass-fast-linear-algebra-in-cuda-c/ Developer News] and [https://devblogs.nvidia.com/cutlass-linear-algebra-cuda/ dev blog ]
NVCUVID - NVIDIA Video Decoder got deprecated in CUDA 9.2; it is now available in NVIDIA Video Codec SDK
CUDA 10 comes with these other components:
nvJPEG - Hybrid JPEG Processing, see [https://developer.nvidia.com/announcing-cuda-toolkit-10 CUDA 10 News] and [https://developer.nvidia.com/nvjpeg main] and [https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html actual Release Notes]
Advantages
CUDA has several advantages over traditional general-purpose computation on GPUs (GPGPU) using graphics APIs:
Scattered reads{{snd}} code can read from arbitrary addresses in memory
Unified virtual memory (CUDA 4.0 and above)
Unified memory (CUDA 6.0 and above)
Shared memory{{snd}} CUDA exposes a fast shared memory region that can be shared among threads. This can be used as a user-managed cache, enabling higher bandwidth than is possible using texture lookups.[15]
Faster downloads and readbacks to and from the GPU
Full support for integer and bitwise operations, including integer texture lookups
Limitations
Whether for the host computer or the GPU device, all CUDA source code is now processed according to C++ syntax rules.[16] This was not always the case. Earlier versions of CUDA were based on C syntax rules.[17] As with the more general case of compiling C code with a C++ compiler, it is therefore possible that old C-style CUDA source code will either fail to compile or will not behave as originally intended.
Interoperability with rendering languages such as OpenGL is one-way, with OpenGL having access to registered CUDA memory but CUDA not having access to OpenGL memory.
Copying between host and device memory may incur a performance hit due to system bus bandwidth and latency (this can be partly alleviated with asynchronous memory transfers, handled by the GPU's DMA engine)
Threads should be running in groups of at least 32 for best performance, with total number of threads numbering in the thousands. Branches in the program code do not affect performance significantly, provided that each of 32 threads takes the same execution path; the SIMD execution model becomes a significant limitation for any inherently divergent task (e.g. traversing a space partitioning data structure during ray tracing).
Unlike OpenCL, CUDA-enabled GPUs are only available from Nvidia.[18]
No emulator or fallback functionality is available for modern revisions.
Valid C++ may sometimes be flagged and prevent compilation due to the way the compiler approaches optimization for target GPU device limitations.{{citation needed|date=May 2016}}
C++ run-time type information (RTTI) and C++-style exception handling are only supported in host code, not in device code.
In single precision on first generation CUDA compute capability 1.x devices, denormal numbers are unsupported and are instead flushed to zero, and the precisions of the division and square root operations are slightly lower than IEEE 754-compliant single precision math. Devices that support compute capability 2.0 and above support denormal numbers, and the division and square root operations are IEEE 754 compliant by default. However, users can obtain the prior faster gaming-grade math of compute capability 1.x devices if desired by setting compiler flags to disable accurate divisions and accurate square roots, and enable flushing denormal numbers to zero.[19]
GPUs supported
Supported CUDA level of GPU and card. See also at Nvidia:
CUDA SDK 1.0 support for compute capability 1.0 – 1.1 (Tesla)[20]
CUDA SDK 1.1 support for compute capability 1.0 – 1.1+x (Tesla)
CUDA SDK 2.0 support for compute capability 1.0 – 1.1+x (Tesla)
CUDA SDK 2.1 – 2.3.1 support for compute capability 1.0 – 1.3 (Tesla)[21][22][23][24]
CUDA SDK 3.0 – 3.1 support for compute capability 1.0 – 2.0 (Tesla, Fermi)[25][26]
CUDA SDK 3.2 support for compute capability 1.0 – 2.1 (Tesla, Fermi)[27]
CUDA SDK 4.0 – 4.2 support for compute capability 1.0 – 2.1+x (Tesla, Fermi, more?)
CUDA SDK 5.0/5.5 support for compute capability 1.0 – 2.1+x (Tesla, Fermi, more?)
CUDA SDK 6.0 support for compute capability 1.0 – 3.5 (Tesla, Fermi, Kepler)
CUDA SDK 6.5 support for compute capability 1.1 – 5.x (Tesla, Fermi, Kepler, Maxwell). Last version with support for compute capability 1.x (Tesla)
CUDA SDK 7.0/7.5 support for compute capability 2.0 – 5.x (Fermi, Kepler, Maxwell)
CUDA SDK 8.0 support for compute capability 2.0 – 6.x (Fermi, Kepler, Maxwell, Pascal). Last version with support for compute capability 2.x (Fermi)
CUDA SDK 9.0 – 9.2 support for compute capability 3.0 – 7.2 (Kepler, Maxwell, Pascal, Volta)
CUDA SDK 10.0/10.1 support for compute capability 3.0 – 7.5 (Kepler, Maxwell, Pascal, Volta, Turing)
Note: Any missing lines or empty entries do reflect some lack of information on that exact item.
[33]
Technical specifications
Compute capability (version)
1.0
1.1
1.2
1.3
2.x
3.0
3.2
3.5
3.7
5.0
5.2
5.3
6.0
6.1
6.2
7.0 (7.2?)
7.5
Maximum number of resident grids per device (concurrent kernel execution)
t.b.d.}}
16}}
4}}
32}}
16}}
128}}
32}}
16}}
128}}
Maximum dimensionality of grid of thread blocks
2}}
3}}
Maximum x-dimension of a grid of thread blocks
65535}}
231 − 1}}
Maximum y-, or z-dimension of a grid of thread blocks
65535}}
Maximum dimensionality of thread block
3}}
Maximum x- or y-dimension of a block
512}}
1024}}
Maximum z-dimension of a block
64}}
Maximum number of threads per block
512}}
1024}}
Warp size
32}}
Maximum number of resident blocks per multiprocessor
8}}
16}}
32}}
16}}
Maximum number of resident warps per multiprocessor
24}}
32}}
48}}
64}}
32}}
Maximum number of resident threads per multiprocessor
768}}
1024}}
1536}}
2048}}
1024}}
Number of 32-bit registers per multiprocessor
8 K}}
16 K}}
32 K}}
64 K}}
128 K}}
64 K}}
Maximum number of 32-bit registers per thread block
colspan="4" {{n/a}}
32 K}}
64 K}}
32 K}}
64 K}}
32 K}}
64 K}}
32 K}}
64 K}}
Maximum number of 32-bit registers per thread
124}}
63}}
255}}
Maximum amount of shared memory per multiprocessor
16 KB}}
48 KB}}
112 KB}}
64 KB}}
96 KB}}
64 KB}}
96 KB}}
64 KB}}
96 KB (of 128)}}
64 KB (of 96)}}
Maximum amount of shared memory per thread block
48 KB}}
48/96 KB}}
64 KB}}
Number of shared memory banks
16}}
32}}
Amount of local memory per thread
16 KB}}
512 KB}}
Constant memory size
64 KB}}
Cache working set per multiprocessor for constant memory
8 KB}}
4 KB}}
8 KB}}
Cache working set per multiprocessor for texture memory
6 – 8 KB}}
12 KB}}
12 – 48 KB}}
24 KB}}
48 KB}}
colspan="1" {{n/a}}
24 KB}}
48 KB}}
24 KB}}
32 – 128 KB}}
32 – 64 KB}}
Maximum width for 1D texture reference bound to a CUDA array
8192}}
65536}}
Maximum width for 1D texture reference bound to linear memory
227}}
Maximum width and number of layers for a 1D layered texture reference
8192 × 512}}
16384 × 2048}}
Maximum width and height for 2D texture reference bound to a CUDA array
65536 × 32768}}
65536 × 65535}}
Maximum width and height for 2D texture reference bound to a linear memory
650002}}
Maximum width and height for 2D texture reference bound to a CUDA array supporting texture gather
colspan="4" {{n/a}}
163842}}
Maximum width, height, and number of layers for a 2D layered texture reference
8192 × 8192 × 512}}
16384 × 16384 × 2048}}
Maximum width, height and depth for a 3D texture reference bound to linear memory or a CUDA array
20483}}
40963}}
Maximum width and number of layers for a cubemap layered texture reference
colspan="4" {{n/a}}
16384 × 2046}}
Maximum number of textures that can be bound to a kernel
128}}
256}}
Maximum width for a 1D surface reference bound to a CUDA array
Not supported}}
65536}}
Maximum width and number of layers for a 1D layered surface reference
65536 × 2048}}
Maximum width and height for a 2D surface reference bound to a CUDA array
65536 × 32768}}
Maximum width, height, and number of layers for a 2D layered surface reference
65536 × 32768 × 2048}}
Maximum width, height, and depth for a 3D surface reference bound to a CUDA array
65536 × 32768 × 2048}}
Maximum width and number of layers for a cubemap layered surface reference
32768 × 2046}}
Maximum number of surfaces that can be bound to a kernel
8}}
16}}
Maximum number of instructions per kernel
2 million}}
512 million}}
[34]
Architecture specifications
Compute capability (version)
1.0
1.1
1.2
1.3
2.0
2.1
3.0
3.5
3.7
5.0
5.2
6.0
6.1, 6.2
7.0/2 (Volta)
7.5 (Turing)
Number of ALU lanes for integer and single-precision floating-point arithmetic operations
8}}[35]
32}}
48}}
192}}
128}}
64}}
128}}
64}}
Number of special function units for single-precision floating-point transcendental functions
2}}
4}}
8}}
32}}
16}}
32}}
16}}
Number of texture filtering units for every texture address unit or render output unit (ROP)
2}}
4}}
8}}
16}}
8}}[36]
Number of warp schedulers
1}}
2}}
4}}
2}}
4}}
Max number of instructions issued at once by a single scheduler
1}}
2}}[37]
1}}
Number of tensor cores
colspan="13" {{n/a}}
8}}[38]
Size in kB of unified memory for data cache and shared memory per multi processor
t.b.d.
128}}
96}}[39]
[40]
For more information see the article: {{cite web|url=http://www.geeks3d.com/20100606/gpu-computing-nvidia-cuda-compute-capability-comparative-table/|title=(GPU Computing) NVIDIA CUDA Compute Capability Comparative Table|author=JeGX|publisher=Geeks3D|date=2010-06-06|access-date=2017-08-08}} and read Nvidia CUDA programming guide.[41]
Example
This example code in C++ loads a texture from an image into an array on the GPU:
// Unbind the array from the texture cudaUnbindTexture(tex);
} //end foo()
__global__ void kernel(float* odata, int height, int width)
{
unsigned int x = blockIdx.x*blockDim.x + threadIdx.x; unsigned int y = blockIdx.y*blockDim.y + threadIdx.y; if (x < width && y < height) { float c = tex2D(tex, x, y); odata[y*width+x] = c; }
}
Below is an example given in Python that computes the product of two arrays on the GPU. The unofficial Python language bindings can be obtained from PyCUDA.[42]
R – [https://github.com/gpuRcore/gpuRcuda gpuRcuda]
Current and future usages of CUDA architecture
Accelerated rendering of 3D graphics
Accelerated interconversion of video file formats
Accelerated encryption, decryption and compression
Bioinformatics, e.g. NGS DNA sequencing BarraCUDA
Distributed calculations, such as predicting the native conformation of proteins
Medical analysis simulations, for example virtual reality based on CT and MRI scan images.
Physical simulations, in particular in fluid dynamics.
Neural network training in machine learning problems
Face recognition
Distributed computing
Molecular dynamics
Mining cryptocurrencies
Structure from motion (SfM) software
See also
OpenCL – An open standard from Khronos Group for programming a variety of platforms, including GPUs, similar to lower-level CUDA Driver API (non single-source)
SYCL – An open standard from Khronos Group for programming a variety of platforms, including GPUs, with single-source modern C++, similar to higher-level CUDA Runtime API (single-source)
BrookGPU – the Stanford University graphics group's compiler
Array programming
Parallel computing
Stream processing
rCUDA – An API for computing on remote computers
Molecular modeling on GPU
Vulkan
References
1. ^{{cite web|url=http://www.nvidia.com/object/cuda_home_new.html|title=Nvidia CUDA Home Page}} 2. ^1 {{cite web|url=http://www.tomshardware.com/reviews/nvidia-cuda-gpu,1954.html|title=Nvidia's CUDA: The End of the CPU?|last=Abi-Chahla|first=Fedy|date=June 18, 2008|publisher=Tom's Hardware|accessdate=May 17, 2015}} 3. ^{{Cite news|url=https://www.videomaker.com/article/c15/19313-cuda-vs-opencl-vs-opengl|title=CUDA vs. OpenCL vs. OpenGL|last=Zunitch|first=Peter|date=2018-01-24|work=Videomaker|access-date=2018-09-16|language=en-US}} 4. ^{{cite web|url=http://www.anandtech.com/show/2116/8|title=Nvidia's GeForce 8800 (G80): GPUs Re-architected for DirectX 10|last1=Shimpi|first1=Anand Lal|last2=Wilson|first2=Derek|date=November 8, 2006|publisher=AnandTech|accessdate=May 16, 2015}} 5. ^{{cite web|url=http://developer.nvidia.com/cuda/cuda-llvm-compiler|title=CUDA LLVM Compiler}} 6. ^{{YouTube|r1sN1ELJfNo|First OpenCL demo on a GPU}} 7. ^{{YouTube|K1I4kts5mqc|DirectCompute Ocean Demo Running on Nvidia CUDA-enabled GPU}} 8. ^{{cite journal|last1=Vasiliadis |first1=Giorgos |last2=Antonatos |first2=Spiros |last3=Polychronakis |first3=Michalis |last4=Markatos |first4=Evangelos P. |last5=Ioannidis |first5=Sotiris |title= Gnort: High Performance Network Intrusion Detection Using Graphics Processors |journal= Proceedings of the 11th International Symposium on Recent Advances in Intrusion Detection (RAID) |date=September 2008 |url= http://www.ics.forth.gr/dcs/Activities/papers/gnort.raid08.pdf }} 9. ^{{cite journal |last1=Schatz |first1=Michael C. |last2=Trapnell |first2=Cole |last3=Delcher |first3=Arthur L. |last4=Varshney |first4=Amitabh |year= 2007 |title= High-throughput sequence alignment using Graphics Processing Units |journal= BMC Bioinformatics |volume= 8|doi= 10.1186/1471-2105-8-474 |pages= 474 |pmid= 18070356 |pmc= 2222658}} 10. ^{{cite journal|last1= Manavski |first1= Svetlin A. |last2=Giorgio |first2=Valle |title= CUDA compatible GPU cards as efficient hardware accelerators for Smith-Waterman sequence alignment |journal= BMC Bioinformatics |volume= 10 |year= 2008 |doi= 10.1186/1471-2105-9-S2-S10 |pages= S10 |pmid= 18387198 |pmc= 2323659}} 11. ^{{cite web|url=https://code.google.com/p/pyrit/|title=Pyrit – Google Code}} 12. ^{{cite web|url=http://boinc.berkeley.edu/cuda.php|title=Use your Nvidia GPU for scientific computing|archive-url=https://web.archive.org/web/20081228022142/http://boinc.berkeley.edu/cuda.php|archive-date=2008-12-28|dead-url=yes|access-date=2017-08-08|publisher=BOINC|date=2008-12-18}} 13. ^{{cite web|url=http://developer.download.nvidia.com/compute/cuda/sdk/website/doc/CUDA_SDK_release_notes_macosx.txt|title=Nvidia CUDA Software Development Kit (CUDA SDK) – Release Notes Version 2.0 for MAC OS X|deadurl=yes|archiveurl=https://web.archive.org/web/20090106020401/http://developer.download.nvidia.com/compute/cuda/sdk/website/doc/CUDA_SDK_release_notes_macosx.txt|archivedate=2009-01-06|df=}} 14. ^{{cite web|url=http://news.developer.nvidia.com/2008/02/cuda-11---now-o.html|title=CUDA 1.1 – Now on Mac OS X|date=February 14, 2008|deadurl=yes|archiveurl=https://web.archive.org/web/20081122105633/http://news.developer.nvidia.com/2008/02/cuda-11---now-o.html|archivedate=November 22, 2008|df=}} 15. ^{{cite conference|doi=10.1145/1375527.1375572|title=Efficient computation of sum-products on GPUs through software-managed cache|conference=Proceedings of the 22nd annual international conference on Supercomputing – ICS '08|year=2008|last1=Silberstein|first1=Mark|last2=Schuster|first2=Assaf|author2-link= Assaf Schuster |last3=Geiger|first3=Dan|last4=Patney|first4=Anjul|last5=Owens|first5=John D.|isbn=978-1-60558-158-3|pages=309–318}} 16. ^{{cite web|title=CUDA Toolkit Documentation|url=http://docs.nvidia.com/cuda/pdf/CUDA_C_Programming_Guide.pdf|website=nVidia Developer Zone - CUDA C Programming Guide v8.0|accessdate=22 March 2017|location=Section 3.1.5|page=19|date=January 2017}} 17. ^{{cite web|url=https://devtalk.nvidia.com/default/topic/508479/cuda-programming-and-performance/nvcc-forces-c-compilation-of-cu-files/#entry1340190|title=NVCC forces c++ compilation of .cu files}} 18. ^{{cite web |url=http://www.nvidia.com/object/cuda_learn_products.html |title=CUDA-Enabled Products |work=CUDA Zone |publisher=Nvidia Corporation |accessdate=2008-11-03}} 19. ^{{Cite web|url=https://developer.nvidia.com/sites/default/files/akamai/cuda/files/NVIDIA-CUDA-Floating-Point.pdf |first1=Nathan |last1=Whitehead |first2=Alex |last2=Fit-Florea |title=Precision & Performance: Floating Point and IEEE 754 Compliance for Nvidia GPUs |accessdate=November 18, 2014 |publisher=Nvidia}} 20. ^http://developer.download.nvidia.com/compute/cuda/1.0/NVIDIA_CUDA_Programming_Guide_1.0.pdf 21. ^http://developer.download.nvidia.com/compute/cuda/2_1/toolkit/docs/NVIDIA_CUDA_Programming_Guide_2.1.pdf 22. ^http://developer.download.nvidia.com/compute/cuda/2_2/toolkit/docs/NVIDIA_CUDA_Programming_Guide_2.2.pdf 23. ^http://developer.download.nvidia.com/compute/cuda/2_21/toolkit/docs/NVIDIA_CUDA_Programming_Guide_2.2.1.pdf 24. ^http://developer.download.nvidia.com/compute/cuda/2_3/toolkit/docs/NVIDIA_CUDA_Programming_Guide_2.3.pdf 25. ^http://developer.download.nvidia.com/compute/cuda/3_0/toolkit/docs/NVIDIA_CUDA_ProgrammingGuide.pdf 26. ^http://developer.download.nvidia.com/compute/cuda/3_1/toolkit/docs/NVIDIA_CUDA_C_ProgrammingGuide_3.1.pdf 27. ^http://developer.download.nvidia.com/compute/cuda/3_2_prod/toolkit/docs/CUDA_C_Programming_Guide.pdf 28. ^https://developer.nvidia.com/cuda-toolkit-archive 29. ^https://www.techpowerup.com/gpu-specs/quadro-nvs-420.c1448 30. ^{{cite web|url=http://www.phoronix.com/scan.php?page=news_item&px=Tegra-X2-Nouveau-Support|title=NVIDIA Rolls Out Tegra X2 GPU Support In Nouveau|last=Larabel|first=Michael|author-link=Michael Larabel|publisher=Phoronix|date=March 29, 2017|access-date=August 8, 2017}} 31. ^[https://www.techpowerup.com/gpudb/3232/xavier Nvidia Xavier Specs] on TechPowerUp (preliminary) 32. ^[https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#features-and-technical-specifications H.1. Features and Technical Specifications - Table 13. Feature Support per Compute Capability] 33. ^https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#features-and-technical-specifications 34. ^[https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#features-and-technical-specifications H.1. Features and Technical Specifications - Table 14. Technical Specifications per Compute Capability] 35. ^ALUs perform only single-precision floating-point arithmetics. There is 1 double-precision floating-point unit. 36. ^[https://devblogs.nvidia.com/inside-volta/ Inside Volta] on Nvidia DevBlogs 37. ^No more than one scheduler can issue 2 instructions at once. The first scheduler is in charge of warps with odd IDs. The second scheduler is in charge of warps with even IDs. 38. ^[https://devblogs.nvidia.com/inside-volta/ Inside Volta] on Nvidia DevBlogs 39. ^https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#architecture-7-x 40. ^[https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#compute-capability-7-x H.6. Compute Capability 7.x] 41. ^{{cite web|url= http://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/CUDA_C_Programming_Guide.pdf |title=Appendix F. Features and Technical Specifications }} {{small|(3.2 MiB)}}, Page 148 of 175 (Version 5.0 October 2012) 42. ^{{cite web|url=http://mathema.tician.de/software/pycuda|title=PyCUDA}} 43. ^{{cite web|url=http://kered.org/blog/2009-04-13/easy-python-numpy-cuda-cublas/|title=pycublas|archive-url=https://web.archive.org/web/20090420124748/http://kered.org/blog/2009-04-13/easy-python-numpy-cuda-cublas/|archive-date=2009-04-20|dead-url=yes|access-date=2017-08-08}} 44. ^https://devblogs.nvidia.com/gpu-computing-julia-programming-language/ 45. ^{{cite web|title=MATLAB Adds GPGPU Support|url=http://www.hpcwire.com/features/MATLAB-Adds-GPGPU-Support-103307084.html|date=2010-09-20|deadurl=yes|archiveurl=https://web.archive.org/web/20100927155948/http://www.hpcwire.com/features/MATLAB-Adds-GPGPU-Support-103307084.html|archivedate=2010-09-27|df=}}
External links
{{Official website}}
[https://plus.google.com/communities/114632076318201174454 CUDA Community] on Google+
[https://devtalk.nvidia.com/default/topic/726765/need-a-little-tool-to-adjust-the-vram-size/ A little tool to adjust the VRAM size]