The user to access the computational resources of NVIDIA Graphical Processing Unit (GPU), but does not auto-parallelize across cuBLAS The cuBLAS library is an implementation of BLAS (Basic Linear Algebra Subprograms) on top of the NVIDIA CUDA runtime. The document also provides a list of some pitfalls that you mayĬUDA Runtime API The CUDA runtime API. Itĭescribes available assembler statement parameters and constraints, and Thread execution) assembly language statements into CUDA code. Inline PTX Assembly This document shows how to inline PTX (parallel PTX Interoperability This document shows how to write PTX that isĪBI-compliant and interoperable with other CUDA code. Video Decoder NVIDIA Video Decoder (NVCUVID) is deprecated. PTX exposes the GPU as aĭeveloper Guide for Optimus This document explains how CUDA APIs can be used to query for GPU capabilities in NVIDIA Optimus systems. Use of PTX, a low-level parallel thread execution virtual machine and PTX ISA This guide provides detailed instructions on the ThisĪdditional speedups by leveraging Volta architectural features. Speedups on the Volta architecture without any code changes. The best practices for the Pascal architecture should typically see Volta Tuning Guide Volta is NVIDIA's 6th-generation ThisĪdditional speedups by leveraging Pascal architectural features. Speedups on the Pascal architecture without any code changes. The best practices for the Maxwell architecture should typically see Pascal Tuning Guide Pascal is NVIDIA's 5th-generation ThisĪdditional speedups by leveraging Maxwell architectural features. Speedups on the Maxwell architecture without any code changes. The best practices for the Kepler architecture should typically see Maxwell Tuning Guide Maxwell is NVIDIA's 4th-generation Guide summarizes the ways that applications can be fine-tuned to gainĪdditional speedups by leveraging Kepler architectural features. See speedups on the Kepler architecture without any code changes. The best practices for the Fermi architecture should typically Kepler Tuning Guide Kepler is NVIDIA's 3rd-generationĪrchitecture for CUDA compute applications. Properly on GPUs based on the NVIDIA Volta Architecture. Volta Compatibility Guide This application note is intended to help Properly on GPUs based on the NVIDIA Pascal Architecture. Pascal Compatibility Guide This application note is intended to help Thisĭocument provides guidance to ensure that your software applications are Properly on GPUs based on the NVIDIA Maxwell Architecture. Maxwell Compatibility Guide This application note is intended to helpĭevelopers ensure that their NVIDIA CUDA applications will run Obtaining the best performance from NVIDIA GPUs using the CUDA Metaphors and idioms that can greatly simplify programming forĬUDA-capable GPU architectures. Parallelization and optimization techniques and explains coding Specifications of various devices, and concludes by introducing theīest Practices Guide This guide presents established Host and device code, details on texture fetching, technical Listings of supported mathematical functions, C++ features supported in The appendices include a list of all CUDA-enabledĭevices, detailed description of all extensions to the C language, The hardware implementation, and provides guidance on how to achieve The CUDA programming model and programming interface. Programming Guide This guide provides a detailed discussion of Installation Guide Linux This guide discusses how to install and check for correct operation of the CUDA Development Tools on GNU/Linux systems. Installation Guide Mac OS X This guide discusses how to install and check for correct operation of the CUDA Development Tools on Mac OS X systems. Installation Guide Windows This guide discusses how to install and check for correct operation of the CUDA Development Tools on Microsoft Windows systems. Quick Start Guide This guide provides the minimal first-steps instructions for installation and verifying CUDA on a standard system. Toolkit, the NVIDIA CUDA Samples, the NVIDIA Display Driver, and NVIDIA NSight (Visual Studio Edition). EULA The End User License Agreements for the NVIDIA CUDA Release Notes The Release Notes for the CUDA Toolkit.
0 Comments
Leave a Reply. |