diff --git a/tests/hellocuda/.gitignore b/tests/hellocuda/.gitignore
new file mode 100644
index 0000000..8559f47
--- /dev/null
+++ b/tests/hellocuda/.gitignore
@@ -0,0 +1,2 @@
+hellocuda
+*.seer
diff --git a/tests/hellocuda/Makefile b/tests/hellocuda/Makefile
new file mode 100644
index 0000000..3a15eed
--- /dev/null
+++ b/tests/hellocuda/Makefile
@@ -0,0 +1,10 @@
+.PHONY: all
+all: hellocuda
+
+hellocuda: hellocuda.cu
+	/usr/local/cuda-12.2/bin/nvcc -g -G hellocuda.cu -o hellocuda
+
+.PHONY: clean
+clean:
+	rm -f hellocuda hellocuda.o
+
diff --git a/tests/hellocuda/hellocuda.cu b/tests/hellocuda/hellocuda.cu
new file mode 100644
index 0000000..1d678f7
--- /dev/null
+++ b/tests/hellocuda/hellocuda.cu
@@ -0,0 +1,27 @@
+#include "stdio.h"
+
+__global__ void add(int a, int b, int *c) {
+    *c = a + b;
+}
+
+int main() {
+
+    int a,b,c;
+    int* dev_c;
+
+    a=3;
+    b=4;
+
+    cudaMalloc((void**)&dev_c, sizeof(int));
+
+    add<<<1,1>>>(a,b,dev_c);
+
+    cudaMemcpy(&c, dev_c, sizeof(int), cudaMemcpyDeviceToHost);
+
+    printf("%d + %d is %d\n", a, b, c);
+
+    cudaFree(dev_c);
+
+    return 0;
+}
+
diff --git a/tests/hellocuda/hellocuda.cu-orig b/tests/hellocuda/hellocuda.cu-orig
new file mode 100644
index 0000000..2d45bd9
--- /dev/null
+++ b/tests/hellocuda/hellocuda.cu-orig
@@ -0,0 +1,47 @@
+#include <stdio.h>
+#include <stdlib.h>
+
+// Simple 8-bit bit reversal Compute test
+
+#define N 256
+
+__global__ void bitreverse (void *data) {
+
+    unsigned int *idata = (unsigned int*)data;
+    extern __shared__ int array[];
+
+    array[threadIdx.x] = idata[threadIdx.x];
+
+    array[threadIdx.x] = ((0xf0f0f0f0 & array[threadIdx.x]) >> 4) | ((0x0f0f0f0f & array[threadIdx.x]) << 4);
+    array[threadIdx.x] = ((0xcccccccc & array[threadIdx.x]) >> 2) | ((0x33333333 & array[threadIdx.x]) << 2);
+    array[threadIdx.x] = ((0xaaaaaaaa & array[threadIdx.x]) >> 1) | ((0x55555555 & array[threadIdx.x]) << 1);
+
+    idata[threadIdx.x] = array[threadIdx.x];
+}
+
+int main(void) {
+
+    void* d = NULL; 
+    int i;
+    unsigned int idata[N], odata[N];
+
+    for (i = 0; i < N; i++) {
+        idata[i] = (unsigned int)i;
+    }
+
+    cudaMalloc((void**)&d, sizeof(int)*N);
+    cudaMemcpy(d, idata, sizeof(int)*N, cudaMemcpyHostToDevice);
+
+    bitreverse<<<1, N, N*sizeof(int)>>>(d);
+
+    cudaMemcpy(odata, d, sizeof(int)*N, cudaMemcpyDeviceToHost);
+
+    for (i = 0; i < N; i++) {
+        printf("%u -> %u\n", idata[i], odata[i]);
+    }
+
+    cudaFree((void*)d);
+
+    return 0;
+}
+