NVIDIA announced today it has released version 2.3 of the CUDA Toolkit and SDK for GPU Computing. This latest release supports several significant new features that deliver a major leap forward in getting the most performance out of NVIDIA’s massively parallel CUDA-enabled GPUs. This release of the CUDA Toolkit includes performance improvements and expanded support for the cuda-gdb hardware debugger.

Additional new features in CUDA Toolkit 2.3 include:

• The CUFFT Library now supports double-precision transforms and includes significant performance improvements for single-precision transforms as well.  See the CUDA Toolkit release notes for details.
• The CUDA-GDB hardware debugger and CUDA Visual Profiler are now included in the CUDA Toolkit installer, and the CUDA-GDB debugger is now available for all supported Linux distros.  (see below)
• Each GPU in an SLI group is now enumerated individually, so compute applications can now take advantage of multi-GPU performance even when SLI is enabled for graphics.
• The 64-bit versions of the CUDA Toolkit now support compiling 32-bit applications. (See the release notes for details, including changes to LD_LIBRARY_PATH on Linux)
• New support for fp16 <-> fp32 conversion intrinsics allows storage of data in fp16 format with computation in fp32.  Use of fp16 format is ideal for applications that require higher numerical range than 16-bit integer but less precision than fp32 and reduces memory space and bandwidth consumption.
• The CUDA SDK has been updated to include:
  • A new pitchLinearTexure code sample that shows how to efficiently texture from pitch linear memory.
  • A new PTXJIT code sample illustrating how to use cuModuleLoadDataEx() to load PTX source from memory instead of loading a file.
  • Two new code samples for Windows, showing how to use the NVCUVID library to decode MPEG-2, VC-1, and H.264 content and pass frames to OpenGL or Direct3D for display.
  • Updated code samples showing how to properly align CUDA kernel function parameters so the same code works on both x32 and x64 systems.
• The Visual Profiler includes several enhancements:
  • All memory transfer API calls are now reported
  • Support for profiling multiple contexts per GPU
  • Synchronized clocks for requested start time on the CPU and start/end times on the GPU for all kernel launches and memory transfers
  • Global memory load and store efficiency metrics for GPUs with compute capability 1.2 and higher
• The CUDA Driver for MacOS is now packaged separately from the CUDA Toolkit.
• Support for major Linux distros, MacOS X, and Windows:
  • MacOS X 10.5.6 and later (32-bit)
  • Windows XP/Vista/7 with Visual Studio 8 (VC2005 SP1) and 9 (VC2008)
  • Fedora 10, RHEL 4.7 & 5.3, SLED 10.2 & 11.0, OpenSUSE 11.1, and Ubuntu 8.10 & 9.04

Developers can download the latest CUDA Toolkit, SDK, and drivers now.