Blog

四月初的時候，有貼過 CUDA 2.2 Beta 正在進行「封測」，開放給有註冊的開發者下載；而在五月七號，nVidia 則是放出 CUDA 2.2 的正式版提供所有人下載了∼詳細細節可以參考官方論壇的《CUDA Toolkit and SDK v2.2 released》一文。

官方的新功能列表如下：

• Officially adds support for Windows 7, Server 2003, Server 2008, Ubuntu 8.10, RHEL 5.3, and Fedora 10
• Includes cuda-gdb (hardware GPU debugger) for RHEL5 32 and 64-bit (officially supported and tested), but it may work on more platforms than just those
• Exclusive device mode in Linux: set some GPUs as exclusive-compute (can only own a single CUDA context) and some as non-compute (no CUDA contexts allowed) for easier management of clusters/MPI applications. See the manpage for nvidia-smi for how to set this and cudaSetValidDevices in the reference manual on how to best use this from CUDART.
• Zero-copy support: transparently read from certain system memory from a kernel on GT200 or MCP79 systems. See this post for more information on how it works.
• Asynchronous memcpy support on Vista/Server 2008/Win7
• Texture from pitchlinear memory: use this to avoid an additional memcpy at times in some scenarios.
• >4GB of pinned memory in a single allocation on most OSes
• maximum pinned memory per allocation increased in Vista to ~1.5GB
• pinned memory can be shared between contexts
• Multi-device OpenGL interop performance between a Quadro display card and a separate compute card is dramatically improved.
• Visual Profiler works on Vista
• Visual Profiler supports additional counters for GT200 to measure number of memory transactions of a given size, instruction throughput, etc.
• Blocking sync support for all platforms: allows the host thread to sleep and be awoken by driver when the GPU operation the host thread is waiting on is completed.
• Quite a few additional math functions added due to forum requests (feel free to keep posting requests, we do pay attention)
• __threadfence(): ensure that a thread's pending memory writes are visible to all threads before continuing. It is explicitly not a global sync, unlike how it appears to some.
• Lots of bugfixes, of course; most importantly, killing a CUDA app should behave much, much better than it ever has before, especially when you're on a dedicated compute card

下載頁面：http://www.nvidia.com/object/cuda_get.html；或是直接下載：

• 驅動程式
  • Windows 185.85
    • for Windows XP 32bit：桌上型／工作站、筆記型
    • for Windows XP 64bit：桌上型／工作站、筆記型
    • for Windows Vista 32bit：桌上型／工作站、筆記型
    • for Windows Vista 64bit：桌上型／工作站、筆記型
    • for Windows 7 32bit：桌上型／工作站、筆記型
    • for Windows 7 64bit：桌上型／工作站、筆記型
  • Linux 185.18.08：32bit OS、64bit OS
• CUDA Toolkit 2.2
  • for Windows：32bit、64bit
  • for Fedora 9：32bit、64bit
  • for Fedora 10：32bit、64bit
  • for RHEL 4.7：32bit、64bit
  • for RHEL 5.3：32bit、64bit
  • for SLED 10 SP2：32bit、64bit
  • for SUSE 11：32bit、64bit
  • for SUSE 11.1：32bit、64bit
  • for Ubuntu 8.04：32bit、64bit
  • for Ubuntu 8.10：32bit、64bit
  • for MacOS 10.5
  • CUDA Toolkit 2.2 EULA
• SDK 2.2
  • for Windows：32bit、64bit
  • for Linux
  • for Mac
• Debugger：
  • CUDA-GDB for RHEL 5.3 32bit / 64bit
  • CUDA-GDB 2.2 User's Manual
• Visual Profiler
  • for MacOS 10.5（其他平台包含在 Toolkit 內）
  • CUDA Visual Profiler 1.2 Readme
  • CUDA Visual Profiler EULA
• Documentation
  • CUDA 2.2: Getting Started in Linux / Mac OS / Windows
  • CUDA 2.2 Release Notes for Linux / Mac OS / Windows
  • CUDA 2.2 API Reference Manual
  • CUDA 2.2 Programming Guide