Release Notes for AMD APP Profiler

What's New

• v2.2.635 (March 25th 2011)
  • Support for AMD APP SDK v2.4.
  • Support for OpenCL™ application summary.
  • Support for profiling with AMD Radeon™ HD6900 series GPUs (requires AMD APP SDK v2.4 and AMD Catalyst 11.2 and newer).
  • ATI Stream Profiler is now AMD APP Profiler.
  • Improved Session List Explorer.
  • Improved user documentation (now, it is accessible online from the product's site).
  • Improved searching in the API Trace, including support for case-sensitive searches and searches using regular expressions.
  • Support for passing user-defined environment variables to the application being profiled.
  
  v2.1.320 (December 15th 2010)
  • Support for AMD APP SDK v2.3.
  • Added support for Linux (command-line version).
  • Added support for OpenCL™ timeline visualization.
  • Added support for OpenCL™ application tracing.
  • Added support for loading a previously-generated profile or trace result into Visual Studio
  • LDSSize counter is now LocalMemSize.
  • Improved the execution speed and memory consumption for profiling.
  • On the APP Profiler Session List panel inside Microsoft® Visual Studio®, you should find six buttons: Collect GPU Performance Counters, Collect Application Trace, Import Profile Results, Clear Sessions, Open Profile Settings and Open Help Panel. If you can only find four buttons on the APP Profiler Session List panel, please run C:\Program Files (x86)\Microsoft Visual Studio 9.0\Common7\IDE\devenv.exe /setup on a 64-bit OS or C:\Program Files\Microsoft Visual Studio 9.0\Common7\IDE\devenv.exe /setup on a 32-bit OS from a command line prompt (with "Run as Administrator" option). Then, reboot your machine.
  
  v2.0.441 (October 9th 2010)
  • Support for profiling DirectCompute (DirectX 11) applications.
  • Support for profiling 64-bit OpenCL™ applications.
  • Reduced plugin's installation time.
  • Improved updater.
  • Fixed an installation problem on a machine with VBScript disabled.
  • Added additional parameters to the command line interface.
  • Updated the kernel naming scheme.
  • When profiling using Visual Studio, the output from each session is stored in a separate subdirectory.
  • When profiling using the command-line interface, the default output directory is now an "AMD APP Profiler" directory under the current user's "Documents" directory.
  
  v1.4.368 (August 12th 2010)
  • Support for AMD APP SDK v2.2.
  • Support OpenCL™ 1.1.
  • Support Microsoft® Visual Studio® 2010.
  • Support for command line interface.
  • Added support to check whether the current version is up-to-date.
  • Fixed data transfer size for image objects.
  • Updated counter names and descriptions.
  • Support OpenCL™ ELF binary format (SDK 2.2).
  
  
• v1.3.254 (May 20th 2010)
  • Support data transfer for image objects.
  • Added five new performance counters: FetchMem, L1CacheHit, LDSFetch, LDSWrite, and LDSBankConflictAccess.
  • Added three shader compiler statistics: GPR, scratch register, and flow control stack size used by the kernel.
  • Added support to view the CL kernel source in the CodeViewer panel.
  • Added support to view the x86 assembly for CPU device in the CodeViewer panel.
  • Temporary files are now stored in the ProfilerOutput directory.
  • Improved Counter Selection Window.
  • Improved results for ATI Radeon™ HD5770 and ATI Radeon™ HD5570 graphics cards.
  • Report the API name for the data transfer operations and updated the unit from bytes to kilobytes.
  • The kernel name is now appended with the kernel handle to differentiate kernel dispatches for kernel with the same name but different contents.
  
  
• v1.2.183 (May 3rd 2010)
  • Support for AMD APP SDK v2.1.
  • Support for timing data transfer operations.
  • Added three new performance counters related to the global and local memory.
  • Support for image object operations.
  • Support for profiling on non-English OS and Microsoft® Visual Studio®.
  • Support for launching a Session csv file directly with an external application (such as Microsoft® Excel®).
  • Support for filtering the Session view to show or hide the kernel dispatch and/or data transfer operations.
  • Fixed the response to a situation where dispatching kernels that read and write the same global memory buffer produces incorrect results (KB# 81).
  • Improved performance counter results for ATI Radeon™ HD 5870.
  • Fixed LDSBankConflict performance counter.
  • Improved WriteUnitStalled performance counter.
  • Improved Counter Selection Window.
  • Improved session loading.
  
  
• v1.1.111 (February 4th 2010)
  • Support for AMD APP SDK v2.01.
  • Fixed the response to a situation where an application that uses a lot of video memory failed to profile to completion.
  • Fixed the response to a situation where the profiler might fail to run with an app that contains multiple project settings.
  • Fixed the response to a situation where Microsoft® Visual Studio® might crash after sorting the first column (Method) in the OpenCL™ Session panel.
  • Fixed the response to a situation where Microsoft® Visual Studio® might present an obsolete profile data.
  • Fixed IL/ISA support when the Debugging\Working Directory property is not empty.
  • Fixed ALUBusy counter on ATI Radeon™ HD5870 graphics cards.
  • Fixed WriteUnitStalled counter.
  • Added context menu support to copy IL/ISA text in the Code Viewer Panel.
  
  
• v1.0.84 (December 21st 2009) - Initial Public Release
  • Measure the execution time of an OpenCL™ kernel.
  • Query the hardware performance counters on ATI Radeon™ graphics card.
  • Show the memory traffic from and to GPU.
  • Compare multiple runs (sessions) of the same or different programs.
  • Store the profile data for each run in a csv file.
  • Display the IL and ISA (hardware disassembly) code of the kernel.