Publishing fixes for single-GPU runner (#1672)

Co-authored-by: Bettina Heim <[email protected]>
NVIDIA · May 14, 2024 · 1f8dd79 · 1f8dd79
1 parent 1926eea
commit 1f8dd79
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 6 deletions.
diff --git a/docs/sphinx/examples/python/tutorials/executing_circuits.ipynb b/docs/sphinx/examples/python/tutorials/executing_circuits.ipynb
@@ -150,9 +150,14 @@
     "    mz(qvector)\n",
     "\n",
     "\n",
-    "# Asynchronous execution on multiple qpus via nvidia gpus.\n",
-    "result_1 = cudaq.sample_async(kernel_1, qubit_count, shots_count=1000, qpu_id=0)\n",
-    "result_2 = cudaq.sample_async(kernel_2, qubit_count, shots_count=1000, qpu_id=1)\n",
+    "if cudaq.num_available_gpus() > 1:\n",
+    "    # Asynchronous execution on multiple virtual QPUs, each simulated by an NVIDIA GPU.\n",
+    "    result_1 = cudaq.sample_async(kernel_1, qubit_count, shots_count=1000, qpu_id=0)\n",
+    "    result_2 = cudaq.sample_async(kernel_2, qubit_count, shots_count=1000, qpu_id=1)\n",
+    "else:\n",
+    "    # Schedule for execution on the same virtual QPU.\n",
+    "    result_1 = cudaq.sample_async(kernel_1, qubit_count, shots_count=1000, qpu_id=0)\n",
+    "    result_2 = cudaq.sample_async(kernel_2, qubit_count, shots_count=1000, qpu_id=0)\n",
     "\n",
     "print(result_1.get())\n",
     "print(result_2.get())"

diff --git a/docs/sphinx/examples/python/tutorials/multi_gpu_workflows.ipynb b/docs/sphinx/examples/python/tutorials/multi_gpu_workflows.ipynb
@@ -339,15 +339,20 @@
    ],
    "source": [
     "%%timeit\n",
-    "\n",
-    "# Timing the execution on a single GPU vs 4 GPUs, users will see a 4x performance improvement\n",
+    "\n",    
+    "# Timing the execution on a single GPU vs 4 GPUs,\n",
+    "# one will see a 4x performance improvement if 4 GPUs are available.\n",
     "\n",
     "asyncresults = []\n",
+    "num_gpus = cudaq.num_available_gpus()\n",
     "\n",
     "for i in range(len(xi)):\n",
     "    for j in range(xi[i].shape[0]):\n",
+    "        qpu_id = i * num_gpus // len(xi)\n",
     "        asyncresults.append(\n",
-    "            cudaq.observe_async(kernel, h, xi[i][j, :], qpu_id=i))"
+    "            cudaq.observe_async(kernel, h, xi[i][j, :], qpu_id=qpu_id))\n",
+    "\n",
+    "result = [res.get() for res in asyncresults]"
    ]
   }
  ],