TotalView 8.13 Parallel Debugger Beta Release
[[{“fid”:”96662″,”view_mode”:”default”,”fields”:{“field_file_image_alt_text[und][0][value]”:””,”field_file_image_title_text[und][0][value]”:””},”type”:”media”,”attributes”:{“height”:232,”width”:320,”style”:”float: left; margin: 5px;”,”class”:”media-element file-default”}}]]The beta release of the TotalView 8.13 parallel debugger for parallel applications written in C, C++ and Fortran features a combination of capabilities for pinpointing and fixing hard-to-find bugs, such as race conditions, memory leaks and memory overruns. Providing developers the ability to step freely, both forward and backwards, through program execution, its unique reverse debugging capabilities drastically reduce the amount of time invested in troubleshooting code. It allows users to work with an early-access version of the scalable architecture used to complete a successful 786,432 core debugging test. The software adds support for CUDA 5.0 and 5.5, including dynamic parallelism capabilities. This expanded support allows it to work seamlessly with NVIDIA’s latest hardware offering, the Kepler K40. In addition, it expands support for debugging on Intel Xeon Phi coprocessors. For the first time, users can debug applications running in Xeon Phi symmetric mode with seamless transitions when the code shifts between processor and coprocessor. TotalView MemoryScape has become the first memory debugging solution available for Xeon Phi applications. Functionality includes also Apple Macintosh OS X Mavericks support.