diff --git a/hermit/usr/tests/Makefile b/hermit/usr/tests/Makefile
index 5dc839095..5aa452458 100644
--- a/hermit/usr/tests/Makefile
+++ b/hermit/usr/tests/Makefile
@@ -48,7 +48,7 @@ endif
 
 default: all
 
-all: hello.bin hello++.bin thr_hello.bin jacobi.bin hellof.bin #RCCE_minimum
+all: hello.bin hello++.bin thr_hello.bin jacobi.bin hellof.bin cpi.bin #RCCE_minimum
 
 hello++: hello++.o
 	@echo [LD] $@
@@ -79,7 +79,7 @@ jacobi: jacobi.o
 	$Qchmod a-x $@.sym
 
 thr_hello.o: thr_hello.c
-	 @echo [CC] $@
+	@echo [CC] $@
 	$Q$(CC_FOR_TARGET) -c $(CFLAGS_FOR_TARGET) -pthread -o $@ $<
 
 thr_hello: thr_hello.o
@@ -89,6 +89,17 @@ thr_hello: thr_hello.o
 	$Q$(OBJCOPY_FOR_TARGET) $(STRIP_DEBUG) $@
 	$Qchmod a-x $@.sym
 
+cpi.o: cpi.c
+	@echo [CC] $@
+	$Q$(CC_FOR_TARGET) -c $(CFLAGS_FOR_TARGET) -pthread -o $@ $<
+
+cpi: cpi.o
+	@echo [LD] $@
+	$Q$(CC_FOR_TARGET) $(LDFLAGS_FOR_TARGET) $(CFLAGS_FOR_TARGET) -o $@ $< -pthread -lmpi
+	$Q$(OBJCOPY_FOR_TARGET) $(KEEP_DEBUG) $@ $@.sym
+	$Q$(OBJCOPY_FOR_TARGET) $(STRIP_DEBUG) $@
+	$Qchmod a-x $@.sym
+
 RCCE_minimum: RCCE_minimum.o
 	@echo [LD] $@
 	$Q$(CC_FOR_TARGET) $(LDFLAGS_FOR_TARGET) $(CFLAGS_FOR_TARGET) -o $@ $< -lircce
diff --git a/hermit/usr/tests/cpi.c b/hermit/usr/tests/cpi.c
new file mode 100644
index 000000000..3c758067a
--- /dev/null
+++ b/hermit/usr/tests/cpi.c
@@ -0,0 +1,69 @@
+/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil ; -*- */
+/*
+ *  (C) 2001 by Argonne National Laboratory.
+ *      See COPYRIGHT in top-level directory.
+ */
+
+/*
+ * We take this example form the orginoal MPICH distributions
+ * => see COPYRIGHT statement in hermit/usr/mpich-3.2
+ */
+
+#include "mpi.h"
+#include <stdio.h>
+#include <math.h>
+
+double f(double);
+
+double f(double a)
+{
+    return (4.0 / (1.0 + a*a));
+}
+
+int main(int argc,char *argv[])
+{
+    int    n, myid, numprocs, i;
+    double PI25DT = 3.141592653589793238462643;
+    double mypi, pi, h, sum, x;
+    double startwtime = 0.0, endwtime;
+    int    namelen;
+    char   processor_name[MPI_MAX_PROCESSOR_NAME];
+
+    MPI_Init(&argc,&argv);
+    MPI_Comm_size(MPI_COMM_WORLD,&numprocs);
+    MPI_Comm_rank(MPI_COMM_WORLD,&myid);
+    MPI_Get_processor_name(processor_name,&namelen);
+
+    fprintf(stdout,"Process %d of %d is on %s\n",
+	    myid, numprocs, processor_name);
+    fflush(stdout);
+
+    n = 10000;			/* default # of rectangles */
+    if (myid == 0)
+	startwtime = MPI_Wtime();
+
+    MPI_Bcast(&n, 1, MPI_INT, 0, MPI_COMM_WORLD);
+
+    h   = 1.0 / (double) n;
+    sum = 0.0;
+    /* A slightly better approach starts from large i and works back */
+    for (i = myid + 1; i <= n; i += numprocs)
+    {
+	x = h * ((double)i - 0.5);
+	sum += f(x);
+    }
+    mypi = h * sum;
+
+    MPI_Reduce(&mypi, &pi, 1, MPI_DOUBLE, MPI_SUM, 0, MPI_COMM_WORLD);
+
+    if (myid == 0) {
+	endwtime = MPI_Wtime();
+	printf("pi is approximately %.16f, Error is %.16f\n",
+	       pi, fabs(pi - PI25DT));
+	printf("wall clock time = %f\n", endwtime-startwtime);	       
+	fflush(stdout);
+    }
+
+    MPI_Finalize();
+    return 0;
+}