#include <omp.h>
#include <stdio.h>

int main(void) {
    const int n = 1000000;
    double sum = 0.0;

    #pragma omp parallel for reduction(+:sum)
    for (int i = 0; i < n; i++)
        sum += i * 0.001;

    printf("sum = %f, threads = %d\n", sum, omp_get_max_threads());
    return 0;
}

gcc -fopenmp -O3 -o omp_sum omp_sum.c
export OMP_NUM_THREADS=8
./omp_sum

#pragma omp parallel for schedule(static)          // equal chunks, low overhead
#pragma omp parallel for schedule(dynamic, 64)     // dynamic chunks of 64
#pragma omp parallel for schedule(guided)          // decreasing chunk size
#pragma omp parallel for schedule(auto)            // compiler/runtime decides

int shared_var = 0;
#pragma omp parallel private(i) shared(shared_var)
{
    int i = omp_get_thread_num();
    #pragma omp atomic
    shared_var += i;
}

// firstprivate — copy in; lastprivate — copy out after loop
#pragma omp parallel for firstprivate(offset) lastprivate(result)
for (int i = 0; i < n; i++) { ... }

#pragma omp simd
for (int i = 0; i < n; i++)
    c[i] = a[i] + b[i];

// SIMD + parallel
#pragma omp parallel for simd
for (int i = 0; i < n; i++)
    c[i] = a[i] * b[i];

#pragma omp parallel
{
    #pragma omp single
    {
        for (int i = 0; i < 10; i++) {
            #pragma omp task firstprivate(i)
            process_subtree(i);
        }
        #pragma omp taskwait
    }
}

double start = omp_get_wtime();
#pragma omp parallel for
for (int i = 0; i < n; i++) work(i);
double elapsed = omp_get_wtime() - start;
printf("elapsed: %f s\n", elapsed);

#pragma omp target teams distribute parallel for map(to:a[0:n]) map(from:c[0:n])
for (int i = 0; i < n; i++)
    c[i] = a[i] * 2.0f;

# NVIDIA offload
gcc -fopenmp -foffload=-march=sm_80 -o offload offload.c

# Check device
export OMP_DEFAULT_TARGET_DEVICE=1

export OMP_NUM_THREADS=16
export OMP_PROC_BIND=close        # bind threads to nearby cores
export OMP_PLACES=cores
export GOMP_SPINCOUNT=2000        # spin before sleep
export OMP_WAIT_POLICY=active     # active vs passive waiting
export OMP_DISPLAY_ENV=true       # print config at startup

# Score-P (compile with wrapper)
scorep gcc -fopenmp -o app app.c
export SCOREP_METRIC_MANAGER=1
scorep ./app
scorep-score -f scorep_*/profile.cubex

# TAU
tau_cc.sh -fopenmp -o app app.c
export TAU_TRACE=1
./app
pprof app profile.*

// Bad: sum_array[tid] on same cache line
#pragma omp parallel
{
    int tid = omp_get_thread_num();
    sum_array[tid] += local_sum;  // pad to 64 bytes between elements
}

// Fix: padding
double sum_padded[MAX_THREADS][8];  // 8 doubles = 64 bytes

export OMP_MAX_ACTIVE_LEVELS=2
export OMP_NESTED=true   # deprecated; use MAX_ACTIVE_LEVELS