Added adder circuit example for dm-sim and random circuit for TNQVM

Signed-off-by: Thien Nguyen <nguyentm@ornl.gov>

examples/qcor_demos/ibm_qasm3_demo_092021/qasm3-gpu-sim/adder_dm_sim.qasm

+/*
+ * quantum ripple-carry adder
+ * Cuccaro et al, quant-ph/0410184
+ */
+// Install DM-SIM plugin: 
+// qcor -install-plugin https://github.com/ORNL-QCI/DM-Sim.git
+// Using DM-Sim:
+// qcor -linker g++ -qrt nisq adder.qasm -shots 1024 -qpu dm-sim[gpus:1]
+// Note: on a login node, GPU-GPU comm is disabled, hence can only run with 1 GPU.
+
+// Multi-GPU on compute node: e.g, see the bsub example:
+OPENQASM 3;
+
+gate ccx a,b,c
+{
+  h c;
+  cx b,c; tdg c;
+  cx a,c; t c;
+  cx b,c; tdg c;
+  cx a,c; t b; t c; h c;
+  cx a,b; t a; tdg b;
+  cx a,b;
+}
+
+gate majority a, b, c {
+  cx c, b;
+  cx c, a;
+  ccx a, b, c;
+}
+
+gate unmaj a, b, c {
+  ccx a, b, c;
+  cx c, a;
+  cx a, b;
+}
+
+qubit cin;
+qubit a[4];
+qubit b[4];
+qubit cout;
+bit ans[5];
+// Input values:
+uint[4] a_in = 1;  
+uint[4] b_in = 15; 
+
+for i in [0:4] {  
+  if (bool(a_in[i])) {
+    x a[i];
+  }
+  if (bool(b_in[i])) {
+    x b[i];
+  }
+}
+// add a to b, storing result in b
+majority cin, b[0], a[0];
+
+for i in [0: 3] { 
+  majority a[i], b[i + 1], a[i + 1]; 
+}
+
+cx a[3], cout;
+
+for i in [2: -1: -1] { 
+  unmaj a[i], b[i+1], a[i+1]; 
+}
+unmaj cin, b[0], a[0];
+
+measure b[0:3] -> ans[0:3];
+measure cout[0] -> ans[4];
\ No newline at end of file

examples/qcor_demos/ibm_qasm3_demo_092021/qasm3-gpu-sim/random_circuit.qasm

+OPENQASM 3;
+include "stdgates.inc";
+
+const n_qubits = 50;
+const n_layers = 12;
+qubit q[n_qubits];
+
+// Compile: qcor random_circuit.qasm
+// Run by: mpiexec -n <N> ./a.out -qrt nisq -qpu tnqvm -qpu-config tnqvm.ini 
+
+// Loop over layers
+float[64] theta = 1.234;
+for i in [0:n_layers] {
+    // Single qubit layers:
+    for j in [0:n_qubits] {
+        rx(theta) q[j];
+    }
+
+    // For demonstration purposes, just change the 
+    // angle in each layer by adding 1.0.
+    theta += 1.0;
+    // Entanglement layers:
+    for j in [0:n_qubits - 1] {
+        cx q[j], q[j+1];
+    }
+}

examples/qcor_demos/ibm_qasm3_demo_092021/qasm3-gpu-sim/summit_job.lsf

+#!/bin/bash
+#BSUB -P <PROJECT_ID>
+#BSUB -W 1
+#BSUB -nnodes 1
+#BSUB -o out_cc.txt -e err_cc.txt
+
+module load python/3.8.10 gcc/9.3.0 cuda/11.4.0 openblas/0.3.15-omp
+
+## "--smpiargs=-gpu" is for enabling GPU-Direct RDMA
+## 4 GPUs
+jsrun -n4 -a1 -g1 -c1 --smpiargs="-gpu" ./a.out
\ No newline at end of file

examples/qcor_demos/ibm_qasm3_demo_092021/qasm3-gpu-sim/tnqvm.ini

+tnqvm-visitor=exatn:float
+exatn-buffer-size-gb=2
+bitstring=[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
\ No newline at end of file