write result to ofile in qdp bench

qdp_project/src/Benchmark.cpp

@@ -150,7 +150,7 @@ int main() {
     const std::string ofname = "results/qdp-xeonmax-simpleq-" + std::string(MODE_STRING) + "-tca" + std::to_string(TC_SCANA) + "-tcb" + std::to_string(TC_SCANB) + "-tcj" + std::to_string(TC_AGGRJ) + "-tmul" + std::to_string(GROUP_COUNT) + "-wl" + std::to_string(WL_SIZE_B) + "-cs" + std::to_string(CHUNK_SIZE_B) + ".csv";
     std::ofstream fout(ofname);
 
-    fout << "run;time;" << std::endl;
+    fout << "run;time;result[0];" << std::endl;
 
     if constexpr (DATA_IN_HBM) {
         DATA_A_ = (uint64_t*) numa_alloc_onnode(WL_SIZE_B, cache_node);
@@ -209,7 +209,7 @@ int main() {
         const auto time_end = std::chrono::steady_clock::now();
 
         if (i >= WARMUP_ITERATION_COUNT) {
-            fout << i << ";" << std::chrono::duration_cast<std::chrono::nanoseconds>(time_end - time_start).count() << std::endl;
+            fout << i << ";" << std::chrono::duration_cast<std::chrono::nanoseconds>(time_end - time_start).count() << std::endl << ";" << DATA_DST_[0] << ";" << std::endl;
         }
 
         for (std::barrier<NopStruct>* b : BARRIERS_) {