NVIDIA Parallel Nsight

来源：互联网发布：app 网络错误编辑：程序博客网时间：2024/05/19 06:48

历史编辑

NVIDIA于2010年7月22日正式发布了全新GPU开发工具“Parallel Nsight 1.0”(版本号1.0.10200)，这也是业界第一个针对微软Visual Studio的GPU加速应用开发环境，可以配合不久前发布的新版CUDA 3.1使用

Visual Studio用户可以在GPU上利用Parallel Nsight来调试CUDA C/C++、DirectCompute应用程序，所使用的工具和技术也都和CPU上类似

简介编辑

Parallel Nsight同时带有分析工具，可为开发人员提供相关信息，从而最大化地提高GPGPU通用计算程序的性能Parallel Nsight为图形开发人员提供了DX11工具，能够帮助他们快速、高效地开发顶级游戏和视觉计算应用，并有多项专用特性：

Graphics Debugger可以直接在GPU上调试所有的HLSL(高级着色器语言)图形着色器；Graphics Inspector能够实时检查DirectX渲染调用和GPU管线状态，以获得优化的GPU代码；Pixel History允许所有操作影响一个特定像素，从而快速查找渲染错误，创建优化渲染代码；Parallel Nsight Analyzer通过与其他GPU、CPU事件关联的时间线呈现OpenGL API追踪信息，来让开发人员优化OpenGL应用程序。

支持的运行环境编辑

NVIDIA Parallel Nsight 1.0支持32/64位版的Windows Vista、Windows 7、Windows HPC Server 2008等操作系统，支持SQL Server 2008 SP1专业版，分为两个版本：标准版免费，专业版第一年要349美元，随后每年299美元。

NVIDIA Nsight

Develop for GPUs in your favorite IDE

NVIDIA® Nsight™ is the ultimate development platform for heterogeneous computing. Work with powerful debugging and profiling tools that enable you to fully optimize the performance of the CPU and GPU. Not only do these feature-rich tools optimize performance, they help you gain a better understanding of your code - identify and analyze bottlenecks and observe the behavior of all system activities.

Experience the ease of developing code for GPUs using NVIDIA® Nsight™ Visual Studio Edition for Windows or Nsight™ Eclipse Edition for Linux and Mac OS.

Download Nsight Visual Studio Edition

Download Nsight Eclipse Edition

Editor screenshot from Nsight, Eclipse Edition

Develop

New project templates and integration with CUDA SDK samples make getting started quick and easy
CUDA code highlighting makes it easy to navigate heterogeneous CUDA code
Dynamic HLSL shader editing

Debugger screenshot from Nsight, Visual Studio Edition

Debug

Debug CPU and GPU code simultaneously and seamlessly
Debug shaders as they are being executed on the GPU
Real-time inspection of Direct3D 9/10/11 API calls
View contributing fragments with Pixel History

Profiler screenshot from Nsight, Eclipse EditionProfile

Easily identify performance bottlenecks using a unified CPU and GPU trace of application activity
In-session kernel replay mode for more accurate profiling
Profile frames and automatically measure GPU bottlenecks
Frame drawcall timing page for visualizing concurrency of execution

- See more at: http://www.nvidia.com/object/nsight.html#sthash.lQzbNuX0.dpuf

0 0