Files
rocm-systems/examples/lulesh/lulesh-util.cc
T
Jonathan R. Madsen 778af2a760 Sampling support + testing + omnitrace namespace (#19)
* 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.
2022-01-24 20:49:17 -06:00

274 lines
8.4 KiB
C++

#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#if USE_MPI
# include <mpi.h>
#endif
#include "lulesh.h"
/* Helper function for converting strings to ints, with error checking */
int
StrToInt(const char* token, int* retVal)
{
const char* c;
char* endptr;
const int decimal_base = 10;
if(token == NULL)
return 0;
c = token;
*retVal = (int) strtol(c, &endptr, decimal_base);
if((endptr != c) && ((*endptr == ' ') || (*endptr == '\0')))
return 1;
else
return 0;
}
static void
PrintCommandLineOptions(char* execname, int myRank)
{
if(myRank == 0)
{
printf("Usage: %s [opts]\n", execname);
printf(" where [opts] is one or more of:\n");
printf(" -q : quiet mode - suppress all stdout\n");
printf(" -i <iterations> : number of cycles to run\n");
printf(" -s <size> : length of cube mesh along side\n");
printf(" -r <numregions> : Number of distinct regions (def: 11)\n");
printf(" -b <balance> : Load balance between regions of a domain (def: 1)\n");
printf(" -c <cost> : Extra cost of more expensive regions (def: 1)\n");
printf(" -f <numfiles> : Number of files to split viz dump into (def: "
"(np+10)/9)\n");
printf(" -p : Print out progress\n");
printf(
" -v : Output viz file (requires compiling with -DVIZ_MESH\n");
printf(" -h : This message\n");
printf("\n\n");
}
}
static void
ParseError(const char* message, int myRank)
{
if(myRank == 0)
{
printf("%s\n", message);
#if USE_MPI
MPI_Abort(MPI_COMM_WORLD, -1);
#else
exit(-1);
#endif
}
}
void
ParseCommandLineOptions(int argc, char* argv[], int myRank, struct cmdLineOpts* opts)
{
if(argc > 1)
{
int i = 1;
while(i < argc)
{
int ok;
/* -i <iterations> */
if(strcmp(argv[i], "-i") == 0)
{
if(i + 1 >= argc)
{
ParseError("Missing integer argument to -i", myRank);
}
ok = StrToInt(argv[i + 1], &(opts->its));
if(!ok)
{
ParseError("Parse Error on option -i integer value required after "
"argument\n",
myRank);
}
i += 2;
}
/* -s <size, sidelength> */
else if(strcmp(argv[i], "-s") == 0)
{
if(i + 1 >= argc)
{
ParseError("Missing integer argument to -s\n", myRank);
}
ok = StrToInt(argv[i + 1], &(opts->nx));
if(!ok)
{
ParseError("Parse Error on option -s integer value required after "
"argument\n",
myRank);
}
i += 2;
}
/* -r <numregions> */
else if(strcmp(argv[i], "-r") == 0)
{
if(i + 1 >= argc)
{
ParseError("Missing integer argument to -r\n", myRank);
}
ok = StrToInt(argv[i + 1], &(opts->numReg));
if(!ok)
{
ParseError("Parse Error on option -r integer value required after "
"argument\n",
myRank);
}
i += 2;
}
/* -f <numfilepieces> */
else if(strcmp(argv[i], "-f") == 0)
{
if(i + 1 >= argc)
{
ParseError("Missing integer argument to -f\n", myRank);
}
ok = StrToInt(argv[i + 1], &(opts->numFiles));
if(!ok)
{
ParseError("Parse Error on option -f integer value required after "
"argument\n",
myRank);
}
i += 2;
}
/* -p */
else if(strcmp(argv[i], "-p") == 0)
{
opts->showProg = 1;
i++;
}
/* -q */
else if(strcmp(argv[i], "-q") == 0)
{
opts->quiet = 1;
i++;
}
/* -q */
else if(strcmp(argv[i], "-a") == 0)
{
opts->do_atomic = 1;
i++;
}
else if(strcmp(argv[i], "-b") == 0)
{
if(i + 1 >= argc)
{
ParseError("Missing integer argument to -b\n", myRank);
}
ok = StrToInt(argv[i + 1], &(opts->balance));
if(!ok)
{
ParseError("Parse Error on option -b integer value required after "
"argument\n",
myRank);
}
i += 2;
}
else if(strcmp(argv[i], "-c") == 0)
{
if(i + 1 >= argc)
{
ParseError("Missing integer argument to -c\n", myRank);
}
ok = StrToInt(argv[i + 1], &(opts->cost));
if(!ok)
{
ParseError("Parse Error on option -c integer value required after "
"argument\n",
myRank);
}
i += 2;
}
/* -v */
else if(strcmp(argv[i], "-v") == 0)
{
#if VIZ_MESH
opts->viz = 1;
#else
ParseError("Use of -v requires compiling with -DVIZ_MESH\n", myRank);
#endif
i++;
}
/* -h */
else if(strcmp(argv[i], "-h") == 0)
{
PrintCommandLineOptions(argv[0], myRank);
#if USE_MPI
MPI_Abort(MPI_COMM_WORLD, 0);
#else
exit(0);
#endif
}
else
{
char msg[80];
PrintCommandLineOptions(argv[0], myRank);
sprintf(msg, "ERROR: Unknown command line argument: %s\n", argv[i]);
ParseError(msg, myRank);
}
}
}
}
/////////////////////////////////////////////////////////////////////
void
VerifyAndWriteFinalOutput(Real_t elapsed_time, Domain& locDom, Int_t nx, Int_t numRanks)
{
// GrindTime1 only takes a single domain into account, and is thus a good way to
// measure processor speed indepdendent of MPI parallelism. GrindTime2 takes into
// account speedups from MPI parallelism
Real_t grindTime1 = ((elapsed_time * 1e6) / locDom.cycle()) / (nx * nx * nx);
Real_t grindTime2 =
((elapsed_time * 1e6) / locDom.cycle()) / (nx * nx * nx * numRanks);
Index_t ElemId = 0;
printf("Run completed: \n");
printf(" Problem size = %i \n", nx);
printf(" MPI tasks = %i \n", numRanks);
printf(" Iteration count = %i \n", locDom.cycle());
printf(" Final Origin Energy = %12.6e \n", locDom.e(ElemId));
Real_t MaxAbsDiff = Real_t(0.0);
Real_t TotalAbsDiff = Real_t(0.0);
Real_t MaxRelDiff = Real_t(0.0);
for(Index_t j = 0; j < nx; ++j)
{
for(Index_t k = j + 1; k < nx; ++k)
{
Real_t AbsDiff = FABS(locDom.e(j * nx + k) - locDom.e(k * nx + j));
TotalAbsDiff += AbsDiff;
if(MaxAbsDiff < AbsDiff)
MaxAbsDiff = AbsDiff;
Real_t RelDiff = AbsDiff / locDom.e(k * nx + j);
if(MaxRelDiff < RelDiff)
MaxRelDiff = RelDiff;
}
}
// Quick symmetry check
printf(" Testing Plane 0 of Energy Array on rank 0:\n");
printf(" MaxAbsDiff = %12.6e\n", MaxAbsDiff);
printf(" TotalAbsDiff = %12.6e\n", TotalAbsDiff);
printf(" MaxRelDiff = %12.6e\n\n", MaxRelDiff);
// Timing information
printf("\nElapsed time = %10.2f (s)\n", elapsed_time);
printf("Grind time (us/z/c) = %10.8g (per dom) (%10.8g overall)\n", grindTime1,
grindTime2);
printf("FOM = %10.8g (z/s)\n\n",
1000.0 / grindTime2); // zones per second
return;
}