diff --git a/C++/threadpi.cpp b/C++/threadpi.cpp
new file mode 100755
index 0000000000000000000000000000000000000000..0b6e285787be77bcba1ae1d6932eacb7a891c4f9
--- /dev/null
+++ b/C++/threadpi.cpp
@@ -0,0 +1,38 @@
+//
+// threadpi.cpp
+// Neil Gershenfeld 3/1/20
+// calculation of pi by a C++ thread sum
+// pi = 3.14159265358979323846 
+//
+#include <iostream>
+#include <chrono>
+#include <thread>
+#include <vector>
+unsigned int npts = 2e7;
+unsigned int nthreads = std::thread::hardware_concurrency();
+std::vector<double> results(nthreads);
+void sum(int index) {
+   unsigned int start = npts*index+1;
+   unsigned int end = npts*(index+1)+1;
+   double result = 0;
+   for (unsigned int i = start; i < end; ++i)
+      result += 0.5/((i-0.75)*(i-0.25));
+   results[index] = result;
+   }
+int main(void) {
+   double pi = 0;
+   std::thread threads[nthreads];
+   auto tstart = std::chrono::high_resolution_clock::now();        
+   for (int i = 0; i < nthreads; ++i)
+      threads[i] = std::thread(sum,i);
+   for (int i = 0; i < nthreads; ++i) {
+      threads[i].join();
+      pi += results[i];
+      }
+   auto tend = std::chrono::high_resolution_clock::now();        
+	auto dt = std::chrono::duration_cast<std::chrono::microseconds>(tend-tstart).count();
+   auto mflops = npts*nthreads*5.0/dt;
+   std::cout << "npts: " << npts << " nthreads: " << nthreads << " pi: " << pi << '\n';
+   std::cout << "time: " << 1e-6*dt << " estimated MFlops: " << mflops << '\n';
+   return 0;
+   }
diff --git a/README.md b/README.md
index 9539bfdd7bc5f94c3a236ad0212e518ea5452a07..a4ce0b087d155aff1d262730057ab5eb8b73783a 100644
--- a/README.md
+++ b/README.md
@@ -10,6 +10,7 @@
 |1,090|[numbapig.py](Python/numbapig.py)|Python, Numba, CUDA, 5120 cores|NVIDIA V100|March 1, 2020|
 |315|[numbapip.py](Python/numbapip.py)|Python, Numba, parallel, fastmath<br>96 cores|Intel 2x Xeon Platinum 8175M|Feb 7, 2020|
 |272|[threadpi.c](C/threadpi.c)|C, 96 threads<br>gcc threadpi.c -o threadpi -O3 -ffast-math -pthread|Intel 2x Xeon Platinum 8175M|Jun 3, 2019|
+|267|[threadpi.cpp](C++/threadpi.cpp)|C++, 96 threads<br>g++ threadpi.cpp -o threadpi -O3 -ffast-math -pthread|Intel 2x Xeon Platinum 8175M|Mar 1, 2020|
 |211|[mpipi2.c](MPI/mpipi2.c)|C, MPI, 1 node, 96 cores<br>mpicc mpipi2.c -o mpipi2 -O3 -ffast-math|Intel 2x Xeon Platinum 8175M|Oct 24, 2019|
 |180|[mpipi2.py](Python/mpipi2.py)|Python, Numba, MPI<br>mpirun -np 96 python mpipi2.py|Intel 2x Xeon Platinum 8175M|Feb 6, 2020|
 |173|[mppi.c](OpenMP/mppi.c)|C, OpenMP, 96 threads<br>gcc mppi.c -o mppi -O3 -ffast-math -fopenmp|Intel 2x Xeon Platinum 8175M|Jul 1, 2019|