If someone is looking for a good answer:
Some time ago, I found some great code in this answer (for finding CPU time / memory usage in OSX) and adapted it a bit. I used this to compare some NEON optimizations on ARM. You probably only need a section that gets time for the current thread.
#include <sys/types.h>
#include <sys/sysctl.h>
#include <mach/mach_init.h>
#include <mach/mach_host.h>
#include <mach/mach_port.h>
#include <mach/mach_traps.h>
#include <mach/task_info.h>
#include <mach/thread_info.h>
#include <mach/thread_act.h>
#include <mach/vm_region.h>
#include <mach/vm_map.h>
#include <mach/task.h>
typedef struct {
double utime, stime;
} CPUTime;
int get_cpu_time(CPUTime *rpd, bool_t thread_only)
{
task_t task;
kern_return_t error;
mach_msg_type_number_t count;
thread_array_t thread_table;
thread_basic_info_t thi;
thread_basic_info_data_t thi_data;
unsigned table_size;
struct task_basic_info ti;
if (thread_only) {
count = THREAD_BASIC_INFO_COUNT;
thi = &thi_data;
error = thread_info(mach_thread_self(), THREAD_BASIC_INFO, (thread_info_t)thi, &count);
rpd->utime = thi->user_time.seconds + thi->user_time.microseconds * 1e-6;
rpd->stime = thi->system_time.seconds + thi->system_time.microseconds * 1e-6;
return 0;
}
task = mach_task_self();
count = TASK_BASIC_INFO_COUNT;
error = task_info(task, TASK_BASIC_INFO, (task_info_t)&ti, &count);
assert(error == KERN_SUCCESS);
{
unsigned i;
rpd->utime = ti.user_time.seconds + ti.user_time.microseconds * 1e-6;
rpd->stime = ti.system_time.seconds + ti.system_time.microseconds * 1e-6;
error = task_threads(task, &thread_table, &table_size);
assert(error == KERN_SUCCESS);
thi = &thi_data;
for (i = 0; i != table_size; ++i) {
count = THREAD_BASIC_INFO_COUNT;
error = thread_info(thread_table[i], THREAD_BASIC_INFO, (thread_info_t)thi, &count);
assert(error == KERN_SUCCESS);
if ((thi->flags & TH_FLAGS_IDLE) == 0) {
rpd->utime += thi->user_time.seconds + thi->user_time.microseconds * 1e-6;
rpd->stime += thi->system_time.seconds + thi->system_time.microseconds * 1e-6;
}
error = mach_port_deallocate(mach_task_self(), thread_table[i]);
assert(error == KERN_SUCCESS);
}
error = vm_deallocate(mach_task_self(), (vm_offset_t)thread_table, table_size * sizeof(thread_array_t));
assert(error == KERN_SUCCESS);
}
if (task != mach_task_self()) {
mach_port_deallocate(mach_task_self(), task);
assert(error == KERN_SUCCESS);
}
return 0;
}
tcovo source
share