Jonathan R. Madsen
f17ff12a66
* omnitrace namespace
* Kokkos + Lulesh example/tests
* Sampling support + more
- OMNITRACE_BUILD_TESTING option
- sampling support
- pthread_gotcha
- fixes to labels for mpi_gotcha, fork_gotcha, omnitrace_component
- tasking::block_signals, tasking::unblock_signals
- instrumentation mode option in omnitrace exe
- argument option groups in omnitrace exe
- categories in omnitrace settings
- remove TIMEMORY_ prefixed options
* Release workflow updates
* Updated settings printing
* Fixed defaults in README
* Tweak setting defaults in README
* CMake fixes
* cmake-format
* clang-format
* LULESH_USE_MPI OFF
* LULESH_USE_MPI fix
* timemory add_secondary fix
* timemory ambiguous internal namespace fix
* Update timemory submodule
* Handle output path/prefix in omnitrace
- updated timemory
- updated test environment
* sampling + papi fix
* Fix to sampling without PAPI
* Fix for using too many processors in CI
* formatting
* Updated CI
- minor cmake tweaks
- updated timemory submodule
* Updated CI
* Updated CI
* CI + timemory updates
- data race fixes
* CI updates + debug for sampling
* Sampling updates
- moved tasking::{block,unblock}_signals to sampling namespace
- improvements to sampling w.r.t. thread-locality
* Minimum OMNITRACE_THREAD_COUNT of 128
* Handle multiple dims in sampler data
* Configure libunwind support for timemory
* Improved safeguards for sampling
- updated CI
- lulesh runtime-instrument test tweak
* formatting
* CI updates + sampler updates + misc
- fixed stack-buffer-overflow in omnitrace (get_*file_line_info)
- test labels
- steady_clock instead of system_clock in sampler
- update dyninst submodule with upgradePlaceholder fix
- disable OMNITRACE_BUILD_TESTING by default
* Updated timemory submodule
- hidden visibility for timemory
- storage finalizers do not capture this
* Update timemory submodule
- component visibility updates
* Reworked header includes
- use <...> for timemory headers
- always include <library/defines.hpp>
* Rename some config options
* Update PTL submodule
* Update kokkos submodule
* Updated sampling
* Updated CI
* Reworked instrumentation exe
- lowered min-address-range threshold to 256
- extended whole function exclude
* CI fix + timemory submodule update
- TIMEMORY_VISIBLE on component base
- RelWithDebugInfo -> RelWithDebInfo
- Info output for parallel-overhead
* Sampling flags + transpose update + CI update
- disable critical trace for parallel-overhead in CI
- SA_RESTART only in sampler
- reworked transpose example to use fewer threads
* CI update
- removed ubuntu-focal-external-debug
- reduced data artifacts upload
* CI timeouts
- updated timemory submodule
- minor tweaks to omnitrace exe logging
* LICENSE updates (partial)
* CI Test stage timeout extension
* Docker and Packaging updates
* Miscellaneous fixes/tweaks
- gpu.hpp / gpu.cpp
- disable roctracer component if no devices
- re-enable InstrStackFrames by default
- disable sampling by default
- pthread_gotcha::m_enable_sampling is false by default
- timemory submodule update w/ sampler and pop(tid) updates
- fix minor bug in sampler logic
- CMake: OMNITRACE_USE_HIP option
- roctracer + timemory fix
* Replaced OMNITRACE_USE_ROCTRACER with OMNITRACE_USE_HIP where appropriate
* cmake format
* Sampler deadlock fixes
* Removed debug messages from sampler
* Fix for MPI detection + test tweaks + misc
* Sampler deadlock fixes + misc
- removed papi_tot_ins
- pthread_gotcha blocks signals globally until sampler is setup
- metadata specialization for sampling components
- OMNITRACE_INSTRUMENTATION_MODE -> OMNITRACE_MODE
- default sampling delay increased to 0.05 from 1.0e-6
- removed {block,unblock}_signals from critical_trace and ptl
- no longer necessary to use
- sampling delay minimum is 1.0e-3
- OMNITRACE_BUILD_HIDDEN_VISIBILITY
* omnitrace-avail + libunwind update + restructure
- restructured omnitrace components
- build custom omnitrace-avail executable
- updated libunwind to avoid malloc in get_unw_backtrace
* Fix remaining reorganization issues
- removed some duplicate code
- fixed some trait specializations after implicit instatiation
- formatting
* ensure_storage fix + avail improvements
- fix ensure_storage when component not avail
- suppress irrelevant info in omnitrace-avail
* Delay settings initialization
- slight tweak to tests w/ MPI
* Disable OpenMPI testing w/ ubuntu-bionic
- MPI testing is hanging bc of network interface issue on system:
> [[20462,1],0]: A high-performance Open MPI point-to-point messaging module
> was unable to find any relevant network interfaces:
> Module: OpenFabrics (openib)
> Host: fv-az19-371
> Another transport will be used instead, although this may result in
> lower performance.
> NOTE: You can disable this warning by setting the MCA parameter
> btl_base_warn_component_unused to 0.
[ROCm/rocprofiler-systems commit: 778af2a760]
128 خطوط
2.7 KiB
C++
128 خطوط
2.7 KiB
C++
/*!
|
|
******************************************************************************
|
|
*
|
|
* \file
|
|
*
|
|
* \brief RAJA header file for simple class that can be used to
|
|
* time code sections.
|
|
*
|
|
* \author Rich Hornung, Center for Applied Scientific Computing, LLNL
|
|
* \author Jeff Keasler, Applications, Simulations And Quality, LLNL
|
|
*
|
|
******************************************************************************
|
|
*/
|
|
|
|
#ifndef RAJA_Timer_HXX
|
|
#define RAJA_Timer_HXX
|
|
|
|
#if defined(RAJA_USE_CYCLE)
|
|
# include "./cycle.h"
|
|
typedef ticks TimeType;
|
|
|
|
#elif defined(RAJA_USE_CLOCK)
|
|
# include <time.h>
|
|
typedef clock_t TimeType;
|
|
|
|
#elif defined(RAJA_USE_GETTIME)
|
|
# include <time.h>
|
|
typedef timespec TimeType;
|
|
|
|
#else
|
|
# error RAJA_TIMER_TYPE is undefined!
|
|
|
|
#endif
|
|
|
|
namespace RAJA
|
|
{
|
|
/*!
|
|
******************************************************************************
|
|
*
|
|
* \brief Simple timer class to time code sections.
|
|
*
|
|
******************************************************************************
|
|
*/
|
|
class Timer
|
|
{
|
|
public:
|
|
#if defined(RAJA_USE_CYCLE) || defined(RAJA_USE_CLOCK)
|
|
Timer()
|
|
: telapsed(0)
|
|
{
|
|
;
|
|
}
|
|
#endif
|
|
#if defined(RAJA_USE_GETTIME)
|
|
Timer()
|
|
: telapsed(0)
|
|
, stime_elapsed(0)
|
|
, nstime_elapsed(0)
|
|
{
|
|
;
|
|
}
|
|
#endif
|
|
|
|
#if defined(RAJA_USE_CYCLE)
|
|
void start() { tstart = getticks(); }
|
|
void stop()
|
|
{
|
|
tstop = getticks();
|
|
set_elapsed();
|
|
}
|
|
|
|
long double elapsed() { return static_cast<long double>(telapsed); }
|
|
#endif
|
|
|
|
#if defined(RAJA_USE_CLOCK)
|
|
void start() { tstart = clock(); }
|
|
void stop()
|
|
{
|
|
tstop = clock();
|
|
set_elapsed();
|
|
}
|
|
|
|
long double elapsed() { return static_cast<long double>(telapsed) / CLOCKS_PER_SEC; }
|
|
#endif
|
|
|
|
#if defined(RAJA_USE_GETTIME)
|
|
|
|
# if 0
|
|
void start() { clock_gettime(CLOCK_REALTIME, &tstart); }
|
|
void stop() { clock_gettime(CLOCK_REALTIME, &tstop); set_elapsed(); }
|
|
# else
|
|
void start() { clock_gettime(CLOCK_MONOTONIC, &tstart); }
|
|
void stop()
|
|
{
|
|
clock_gettime(CLOCK_MONOTONIC, &tstop);
|
|
set_elapsed();
|
|
}
|
|
# endif
|
|
|
|
long double elapsed() { return (stime_elapsed + nstime_elapsed); }
|
|
|
|
#endif
|
|
|
|
private:
|
|
TimeType tstart;
|
|
TimeType tstop;
|
|
long double telapsed;
|
|
|
|
#if defined(RAJA_USE_CYCLE) || defined(RAJA_USE_CLOCK)
|
|
void set_elapsed() { telapsed += (tstop - tstart); }
|
|
|
|
#elif defined(RAJA_USE_GETTIME)
|
|
long double stime_elapsed;
|
|
long double nstime_elapsed;
|
|
|
|
void set_elapsed()
|
|
{
|
|
stime_elapsed += static_cast<long double>(tstop.tv_sec - tstart.tv_sec);
|
|
nstime_elapsed +=
|
|
static_cast<long double>(tstop.tv_nsec - tstart.tv_nsec) / 1000000000.0;
|
|
}
|
|
#endif
|
|
};
|
|
|
|
} // namespace RAJA
|
|
|
|
#endif // closing endif for header file include guard
|