Author Topic: NVIDIA driver 260.93 and Parallel Nsight 1.5  (Read 2857 times)

0 Members and 1 Guest are viewing this topic.

Stefan

  • Global Moderator
  • Hero Member
  • *****
  • Posts: 2785
    • View Profile
NVIDIA driver 260.93 and Parallel Nsight 1.5
« on: October 17, 2010, 09:20:02 AM »
Forceware 260.93 fixes clBuildProgram and exposes a new extension WGL_NV_DX_interop (not to be confused with WGL_NVX_DX_interop)



Quote
New In The 1.5 Release (history)

    * Support for Visual Studio 2010
      The CUDA Debugger works with either Visual Studio 2008 or Visual Studio 2010. Parallel Nsight includes build customizations for Visual Studio 2010 and for versions 3.1 and 3.2 of the CUDA Toolkit. Be aware that to use Parallel Nsight CUDA Toolkit with Visual Studio 2010, you must also have Visual Studio 2008 installed.
    * CUDA Toolkit 3.2 RC
      The CUDA Debugger supports projects built with the CUDA Toolkit, version 3.2 RC. The directory structure of the CUDA Toolkit created by Parallel Nsight is compatible with the directory structure of the CUDA Toolkit 3.1. Please be aware that upgrading samples from Parallel Nsight 1.0 for use with the CUDA Toolkit 3.2 requires adjustments for build rules and project properties. See the User Guide for more information.
    * Tesla Compute Cluster (TCC)
      The CUDA Debugger can debug GPUs that use Tesla Compute Cluster (TCC) drivers with the R260 driver.
    * The CUDA Debugger supports 6GB GPUs, such as the Quadro 6000.
    * The CUDA Memory Checker now supports Fermi-based GPUs.
    * The CUDA Debugger supports debugging on the GF104-based GeForce GTX 460 GPU.
    * The CUDA Debugger now issues warnings on stack underflow.
    * Support for 64 bit pointers and expressions. The debugger now displays 64-bit integers and pointers correctly. Previous releases incorrectly displayed a value stored in memory if the value >= 2^32.
    * CUDA Debug Focus
      There is a new setting called “Unconditional breakpoints follow focus” for controlling whether the debugger automatically switches all breakpoints to the current focus. When disabled, the debugger will hit breakpoints in all warps that hit a breakpoint. When enabled, only the current focus set via the CUDA Debug Focus will hit the breakpoints.