NVIDIA CUDA Toolkit 5.5.20 Download

Posted at December 21, 2024 by PCI-DB Team

NVIDIA CUDA Toolkit 5.5.20 Description

New Features:

- Adds support for Linux on the ARMv7 Architecture.
- The Toolkit is using a new installer on Windows.
- The CUDA Sample projects have makefiles that are now more self-contained and robust.
- The CUDA Toolkit and the CUDA Driver are now available for installation as .rpm and .deb installation packages for all the supported Linux distributions, except Ubuntu 10.04 and RHEL 5.5.
- Installations can be updated when a new version of the CUDA Toolkit is available.
- The routines cublas{S,D,C,Z}getriBatched() and cublas{S,D,C,Z}matinvBatched() have been added to the CUBLAS Library.
- The limitation on the dimension n of the routine cublas<T>getrfbatched() has been removed.
- CUFFT 5.5 extends the existing API. The new calls allow creation of a CUFFT plan handle separate from the actual creation of the plan, allow insertion of new calls to set plan attributes before the work of plan creation is done, and allow advanced users more control over memory space allocation.
- CUFFT 5.5 provides FFTW3 interfaces that enables applications using FFTW to gain performance with NVIDIA CUFFT with minimal changes to program source code.
- CURAND 5.5 introduces support for the random number generator Philox4x32-10.
- The cublas<T>gtsv() routines have been replaced with a version that supports pivoting.
- The version of Thrust included with the current CUDA toolkit was upgraded from version 1.5.3 to version 1.7.0.
- An optimizing compiler library (libnvvm.so, nvvm.dll/nvvm.lib, libnvvm.dylib) and its header file nvvm.h are provided for compiler developers who want to generate PTX from a program written in NVVM IR, which is a compiler internal representation based on LLVM.
- A set of libraries, libdevice.bc, that implement the common math functions for devices in the LLVM bitcode format are provided.
- A set of samples that illustrate the use of the compiler SDK are provided.
- Documents for the CUDA Compiler SDK (including the specification for LLVM IR, an API document for libnvvm, and an API document for libdevice) are provided.
- The default nvcc.profile no longer includes -lcudart (on Linux and Mac OS X) and cudart.lib (on Windows), and the use of the CUDA runtime is now controlled by the option --cudart (-cudart).
- CUDA 5.5 adds support for JIT linking.
- Clang is now supported as a host compiler on Mac OS.
- CUDA-GDB can now be used to debug a CUDA application on the same GPU that is rendering the desktop GUI.
- Debugging of long-running or indefinite CUDA kernels that would otherwise encounter a launch timeout is now possible
- Multiple CUDA-GDB sessions can simultaneously debug CUDA applications on the same GPU.
- To represent the parent/child kernel information, two commands were added.
- CUDA-GDB now supports remote debugging.
- Multiple CUDA-GDB instances can be now used for debugging ranks of an MPI application that uses a separate GPU for each rank.
- The list of threads returned by the info cuda threads can now be narrowed to the threads currently at a breakpoint.
- The info cuda contexts command was added.
- Return code cudaErrorNotReady can be returned by cudaStreamQuery() and cudaEventQuery() in the case where the stream/event being waited on is still busy.
- The racecheck tool in CUDA-MEMCHECK now has support for SM 3.5 devices.
- The racecheck-report mode option of the racecheck tool can be used to enable the generation of analysis records.
- CUDA-MEMCHECK now supports displaying error information as errors occur during program execution instead of waiting for program termination to display output.
- The NVIDIA Visual Profiler now supports applications that use CUDA Dynamic Parallelism.
- The application analysis performed by the NVIDIA Visual Profiler has been enhanced.
- The NVIDIA Visual Profiler and the command-line profiler, nvprof, now support power, thermal, and clock profiling.
- The NVIDIA Visual Profiler and the command-line profiler, nvprof, now support metrics that report the floating-point operations performed by a kernel.
- The NVIDIA command-line profiler, nvprof, now supports collection of any number of events and metrics during a single run of a CUDA application.
- The NVIDIA command-line profiler, nvprof, now supports profiling of all CUDA processes executed on a system.
- Two new symbols are introduced to control the behavior of the application: CUDBG_ENABLE_LAUNCH_BLOCKING and CUDBG_ENABLE_INTEGRATED_MEMCHECK
- Software preemption is available as a BETA.
- Software preemption (BETA) enables debugging of long-running or indefinite CUDA kernels that would otherwise encounter a launch timeout.
- Software preemption (BETA) allows multiple debugger sessions can simultaneously debug CUDA applications on the same GPU.
- The parent grid information for each kernel is now available as either a new field in the kernelReady event, or as a field in the newly created CUDBGGridInfo struct, which is retrievable via the new getGridInfo() call.
- To reduce the number of times the debugger stops and resumes the application, the debugger API can be made to defer non-essential host kernel launch notifications instead of producing events in the the synchronous event queue.
- The gridId is now available as a 64-bit value.
- 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 now provides CUDA Dynamic Parallelism support for both new and existing projects.
- For applications that use CUDA Dynamic Parallelism, the Nsight Eclipse Edition debugger now shows the parent/child launch trace for device-launched kernels.
- Nsight Eclipse Edition now includes the Remote System Explorer plug-in.
- Nsight Eclipse Edition is updated to use Eclipse Platform 3.8.2 and Eclipse CDT 8.1.2, introducing a number of new features and enhancements to existing features.
- The cublas<T>trsv() routines have been significantly optimized with the work of Jonathan Hogg from The Science and Technology Facilities Council (STFC).
- The performance of the double-precision functions fmod(), remainder(), and remquo() has been significantly improved for sm_30.

Resolved Issues:

- In CUDA 5.5 the library versioning has been changed on Mac and Windows.
- Extracting the Linux installer via the -extract=<path> option currently requires root permissions.
- In certain hardware configurations, the CUDA 5.0 installer on Windows may fail to install the display driver.
- On Mac OS X, cuda-gdb is not required to be a member of the procmod group, and the task-gated process does not need to be reconfigured anymore.
- The NPP ColorTwist_32f_8u_P3R primitive does not work properly for line strides that are not 64-byte aligned.
- All user-loaded modules, as well as modules containing system calls, are exposed via the debug API to retain backwards compatibility with existing CUDA toolkits.
- The hardware counter (event) values may be incorrect in some cases on GPUs with compute capability (SM type) 3.5.
- Old-style cubin support in cuobjdump has been deprecated by removing the - cubin and -fname options, and removing support for fatbin versions less than 4.
- Conditional breakpoints can now be set before the device ELF image is loaded
- A new error, CUDBG_ERROR_NO_DEVICE_AVAILABLE, will be returned at initialization time if no CUDA-capable device can be found.

  It is highly recommended to always use the most recent driver version available.

Try to set a system restore point before installing a device driver. This will help if you installed an incorrect or mismatched driver. Problems can arise when your hardware device is too old or not supported any longer.

Related NVIDIA Drivers