Jonathan R. Madsen
752424efc2
* Roctracer wall clock integration (#16) * Integrates roctracer values into wall-clock * Fixed scoping + timemory roctracer * Fixed data race in roctracer * Synchronized HIP API on main thread - Cache hip activity callbacks and execute on main thread - Minor updates to transpose * Debugging + MPI + transpose updates * PTL + HSA and timemory + kernel timing - PTL usage fixed HSA + timemory issues bc we could control the thread destruction - Fixed laps counting in roctracer callbacks * Ignore select HIP API types - The ignored API types are ignored because there appears to be a bug which causes the "end" callback to be labeled as begin - hipDeviceEnablePeerAccess - hipImportExternalMemory - hipDestroyExternalMemory * Tweaks to PTL config * Timemory update + pid-prefix w/ mpi headers - %pid%- prefix with mpi headers - timemory submodule update * CMake + critical trace + reorganize library source - clang-tidy tweaks - cmake function updates to use hosttrace_ prefix - update gitignore - cmake HOSTTRACE_MAX_THREADS option - Formatting.cmake - cleaned up MacroUtilities.cmake - PTL submodule + usage - tweak to Findroctracer.cmake - MT transpose - Updated PTL submodule - Updated timemory submodule - fix to hosttrace return value type if type not found - reorganized library source code - support for critical trace * Remove bits/stdint-uintn.h headers * Rename + config + depth + critical path - rename hosttrace_timemory_data to instrumentation_bundles - rename hosttrace_bundle_t to main_bundle_t - rename bundle_t to instrumentation_bundle_t - rework of configuration setup - critical_trace write directly to file option - tweaked depth calculation - updated timemory submodule - improved parallel support in roctracer callbacks - working critical_trace - perfetto device-critical-trace and host-critical-trace categories - made transpose example parallel - made parallel-overhead example a bit uneven - relocated LTO activation * Fixed duplicates in perfetto critical-trace * reworked critical trace support - substantial perf improvement (30-45 min -> 30 sec) - changes to configuration (new and removed options) * Removed "%pid%-" output prefix in mpi_gotcha * Update timemory submodule
53 rivejä
1.1 KiB
C++
53 rivejä
1.1 KiB
C++
|
|
#include <atomic>
|
|
#include <cstdio>
|
|
#include <cstdlib>
|
|
#include <thread>
|
|
#include <vector>
|
|
|
|
std::atomic<long> total{ 0 };
|
|
long
|
|
fib(long n) __attribute__((noinline));
|
|
void
|
|
run(size_t nitr, long) __attribute__((noinline));
|
|
|
|
long
|
|
fib(long n)
|
|
{
|
|
return (n < 2) ? n : fib(n - 1) + fib(n - 2);
|
|
}
|
|
|
|
void
|
|
run(size_t nitr, long n)
|
|
{
|
|
long local = 0;
|
|
for(size_t i = 0; i < nitr; ++i)
|
|
local += fib(n);
|
|
total += local;
|
|
}
|
|
|
|
int
|
|
main(int argc, char** argv)
|
|
{
|
|
size_t nthread = std::min<size_t>(16, std::thread::hardware_concurrency());
|
|
size_t nitr = 50000;
|
|
long nfib = 10;
|
|
if(argc > 1) nfib = atol(argv[1]);
|
|
if(argc > 2) nthread = atol(argv[2]);
|
|
if(argc > 3) nitr = atol(argv[3]);
|
|
|
|
std::vector<std::thread> threads{};
|
|
for(size_t i = 0; i < nthread; ++i)
|
|
{
|
|
size_t _nitr = ((i % 2) == 1) ? (nitr - (0.1 * nitr)) : (nitr + (0.1 * nitr));
|
|
threads.emplace_back(&run, _nitr, nfib);
|
|
}
|
|
|
|
for(auto& itr : threads)
|
|
itr.join();
|
|
|
|
printf("fibonacci(%li) x %lu = %li\n", nfib, nthread, total.load());
|
|
|
|
return 0;
|
|
}
|