I'd like to know if thereare tools (aside from papi) that can be used to obtain hardware counter information such as floating point operations, cache misses, cache access for and application on Nehalem processor.
I'd like to know if thereare tools (aside from papi) that can be used to obtain hardware counter information such as floating point operations, cache misses, cache access for and application on Nehalem processor.
Current released versions of VTune and PTU support Nehalem events. Both worked well for me on 64-bit linux; PTU worked well on both 64-bit Windows and linux.
