Megjelent az NVIDIA CUDA 5.5 Release Candidate, benne a következő újdonságokkal:
- Multi-process MPI debugging & profiling
- Single GPU debugging for Linux
- Step-by-step guided performance analysis
- Static CUDA runtime library
- RPM/DEB packaging & new NVIDIA repo
- Many documentation updates. For example, the Runtime and Driver APIs are now split into separate docs. Lots of NVVM details.
- CUDA MPS: "CUDA MPS is a feature that allows multiple CUDA processes to share a single GPU context."
- A new utility "nvdisasm". See CUDA Binary Utilities.
- CUDA-GDB can now be used to debug a CUDA application on the same GPU that is rendering the desktop GUI. This feature is available on Linux with devices of compute capability 3.5.
- Debugging of long-running or indefinite CUDA kernels that would otherwise encounter a launch timeout is now possible. This feature is available on Linux with devices of compute capability 3.5
- Multiple CUDA-GDB sessions can simultaneously debug CUDA applications on the same GPU. This feature is available on Linux with devices of compute capability 3.5
- Nsight Eclipse Edition now provides remote debugging of CUDA applications for Linux targets.
- The Nsight Eclipse Edition debugger now provides a memory viewer for both host and device memory.
- Nsight Eclipse Edition is updated to use Eclipse Platform 3.8.2 and Eclipse CDT 8.1.2
Ahogy nézem, bekerült a GCC 4.7.2 támogatása, de C++11 nélkül (-std=gnu++11-gyel már nem fordul).
Figyeljetek arra, hogy külön bánásmódot igényel mind a telepítő, mind pedig a CUDA GDB, ha a /tmp noexec-kel lett csatolva.