Merge branch 'main' into edits-to-Deutsch

.github/workflows/docker_images.yml

@@ -694,7 +694,7 @@ jobs:
           fi
 
           image_tag=`docker inspect $cudaq_image --format='{{json .Config.Labels}}' | jq -r '."org.opencontainers.image.version"'`
-          docs_version="CUDA_QUANTUM_VERSION=${image_tag%-base}"
+          docs_version="CUDA_QUANTUM_VERSION=$(echo $image_tag | sed -re 's/^(cu[0-9]+-)?(.*)-base$/\2/')"
           docker image rm $cudaq_image
           docker image prune --force
 

.github/workflows/integration_tests.yml

@@ -17,6 +17,7 @@ on:
         options:
           - nightly
           - anyon
+          - infleqtion
           - ionq
           - iqm
           - oqc
@@ -650,6 +651,51 @@ jobs:
           fi
         shell: bash
 
+      - name: Submit to Infleqtion test server
+        if: (success() || failure()) && (inputs.target == 'infleqtion' || github.event_name == 'schedule' || inputs.target == 'nightly')
+        run: |
+          echo "### Submit to Infleqtion server" >> $GITHUB_STEP_SUMMARY
+          export SUPERSTAQ_API_KEY='${{ secrets.SUPERSTAQ_API_KEY }}'
+          set +e # Allow script to keep going through errors
+          test_err_sum=0
+          cpp_tests="docs/sphinx/targets/cpp/infleqtion.cpp"
+          for filename in $cpp_tests; do
+            [ -e "$filename" ] || echo "::error::Couldn't find file ($filename)"
+            nvq++ --target infleqtion $filename
+            test_status=$?
+            if [ $test_status -eq 0 ]; then
+              ./a.out
+              test_status=$?
+              if [ $test_status -eq 0 ]; then
+                echo ":white_check_mark: Successfully ran test: $filename" >> $GITHUB_STEP_SUMMARY
+              else
+                echo ":x: Test failed (failed to execute): $filename" >> $GITHUB_STEP_SUMMARY
+                test_err_sum=$((test_err_sum+1))
+              fi
+            else
+              echo ":x: Test failed (failed to compile): $filename" >> $GITHUB_STEP_SUMMARY
+              test_err_sum=$((test_err_sum+1))
+            fi
+          done
+          python_tests="docs/sphinx/targets/python/infleqtion.py"
+          for filename in $python_tests; do
+            [ -e "$filename" ] || echo "::error::Couldn't find file ($filename)"
+            python3 $filename 1> /dev/null
+            test_status=$?
+            if [ $test_status -eq 0 ]; then
+              echo ":white_check_mark: Successfully ran test: $filename" >> $GITHUB_STEP_SUMMARY
+            else
+              echo ":x: Test failed (failed to execute): $filename" >> $GITHUB_STEP_SUMMARY
+              test_err_sum=$((test_err_sum+1))
+            fi
+          done
+          set -e # Re-enable exit code error checking
+          if [ ! $test_err_sum -eq 0 ]; then
+            echo "::error::${test_err_sum} tests failed. See step summary for a list of failures"
+            exit 1
+          fi
+        shell: bash
+
       - name: Submit to ${{ inputs.target }}
         # The full set of tests used by this step is currently only supported on
         # Quantinuum.  The other supported tests are tested by the step above.

docs/sphinx/applications/python/digitized_counterdiabatic_qaoa.ipynb

@@ -44,16 +44,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
     "import cudaq\n",
     "from cudaq import spin\n",
-    "import numpy as np\n",
-    "\n",
-    "cudaq.set_target('nvidia')\n",
-    "# cudaq.set_target('qpp-cpu') # Uncomment this line if no GPUs are available"
+    "import numpy as np\n"
    ]
   },
   {
@@ -65,7 +62,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {

docs/sphinx/applications/python/divisive_clustering_src/main_divisive_clustering.py

@@ -27,7 +27,7 @@
     type=str,
     choices=["qpp-cpu", "nvidia", "nvidia-mgpu"],
     help=
-    "Quantum simulator backend. Default is qpp-cpu. See https://nvidia.github.io/cuda-quantum/0.6.0/using/simulators.html for more options.",
+    "Quantum simulator backend. Default is qpp-cpu. See https://nvidia.github.io/cuda-quantum for more options.",
 )
 argparser.add_argument(
     "-d",

docs/sphinx/applications/python/hadamard_test.ipynb

@@ -37,7 +37,7 @@
     "![Htest2](./images/htestfactored.png)\n",
     "\n",
     "By preparing this circuit, and repeatedly measuring the ancilla qubit, we estimate the expectation value as $$P(0)-P(1) = Re \\bra{\\psi} O \\ket{\\phi}.$$\n",
-    "\,
+    "\n",
     "\n",
     "The following sections demonstrate how this can be performed in CUDA-Q."
    ]

docs/sphinx/applications/python/vqe_advanced.ipynb

@@ -331,7 +331,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[\u001b[38;2;255;000;000mwarning\u001b[0m] Target \u001b[38;2;000;000;255mnvidia-mqpu\u001b[0m: \u001b[38;2;000;000;255mThis target is deprecating. Please use the 'nvidia' target with option 'mqpu,fp32' or 'mqpu' (fp32 is the default precision option) by adding the command line option '--target-option mqpu,fp32' or passing it as cudaq.set_target('nvidia', option='mqpu,fp32') in Python. Please refer to CUDA-Q \u001b]8;;https://nvidia.github.io/cuda-quantum/latest/using/backends/platform.html#nvidia-mqpu-platform\u001b\\documentation\u001b]8;;\u001b\\ for more information.\u001b[0m\n"
+      "[\u001b[38;2;255;000;000mwarning\u001b[0m] Target \u001b[38;2;000;000;255mnvidia-mqpu\u001b[0m: \u001b[38;2;000;000;255mThis target is deprecating. Please use the 'nvidia' target with option 'mqpu,fp32' or 'mqpu' (fp32 is the default precision option) by adding the command line option '--target-option mqpu,fp32' or passing it as cudaq.set_target('nvidia', option='mqpu,fp32') in Python. Please refer to CUDA-Q \u001b]8;;https://nvidia.github.io/cuda-quantum/latest/using/backends/platform\u001b\\documentation\u001b]8;;\u001b\\ for more information.\u001b[0m\n"
      ]
     }
    ],

docs/sphinx/examples/python/building_kernels.ipynb

@@ -145,7 +145,7 @@
     "### Applying Gates\n",
     "\n",
     "\n",
-    "After a kernel is constructed, gates can be applied to start building out a quantum circuit. All the predefined gates in CUDA-Q can be found [here](https://nvidia.github.io/cuda-quantum/latest/api/default_ops.html#unitary-operations-on-qubits).\n",
+    "After a kernel is constructed, gates can be applied to start building out a quantum circuit. All the predefined gates in CUDA-Q can be found [here](https://nvidia.github.io/cuda-quantum/latest/api/default_ops).\n",
     "\n",
     "\n",
     "Gates can be applied to all qubits in a register:"

docs/sphinx/examples/python/building_kernels.py

@@ -100,7 +100,9 @@ def kernel(state: cudaq.State):
 # ### Applying Gates
 #
 #
-# After a kernel is constructed, gates can be applied to start building out a quantum circuit. All the predefined gates in CUDA-Q can be found [here](https://nvidia.github.io/cuda-quantum/latest/api/default_ops.html#unitary-operations-on-qubits).
+# After a kernel is constructed, gates can be applied to start building out a quantum circuit.
+# All the predefined gates in CUDA-Q can be found here:
+# https://nvidia.github.io/cuda-quantum/api/default_ops.
 #
 #
 # Gates can be applied to all qubits in a register:

docs/sphinx/examples/python/executing_kernels.ipynb

@@ -78,7 +78,7 @@
    "source": [
     "Note that there is a subtle difference between how `sample` is executed with the target device set to a simulator or with the target device set to a QPU. In simulation mode, the quantum state is built once and then sampled $s$ times where $s$ equals the `shots_count`. In hardware execution mode, the quantum state collapses upon measurement and hence needs to be rebuilt over and over again.\n",
     "\n",
-    "There are a number of helpful tools that can be found in the API [here](https://nvidia.github.io/cuda-quantum/latest/api/languages/python_api.html#cudaq.SampleResult) to process the `Sample_Result` object produced by `sample`."
+    "There are a number of helpful tools that can be found in the [API docs](https://nvidia.github.io/cuda-quantum/latest/api/languages/python_api) to process the `Sample_Result` object produced by `sample`."
    ]
   },
   {

docs/sphinx/releases.rst

@@ -4,20 +4,43 @@ CUDA-Q Releases
 
 **latest**
 
-The latest version of CUDA-Q is on the main branch of our `GitHub repository <https://github.com/NVIDIA/cuda-quantum>`__ and is also available as a Docker image. More information about installing the nightly builds can be found :doc:`here <using/install/install>`
+The latest version of CUDA-Q is on the main branch of our `GitHub repository <https://github.com/NVIDIA/cuda-quantum>`__ 
+and is also available as a Docker image. More information about installing the nightly builds can be found 
+:doc:`here <using/install/install>`
 
 - `Docker image (nightly builds) <https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nightly/containers/cuda-quantum>`__
 - `Documentation <https://nvidia.github.io/cuda-quantum/latest>`__
 - `Examples <https://github.com/NVIDIA/cuda-quantum/tree/main/docs/sphinx/examples>`__
 
+**0.9.0**
+
+We are very excited to share a new toolset added for modeling and manipulating the dynamics of physical systems. 
+The new API allows to define and execute a time evolution under arbitrary operators. For more information, take 
+a look at the `docs <https://nvidia.github.io/cuda-quantum/0.9.0/using/backends/dynamics.html>`__.
+The 0.9.0 release furthermore includes a range of contribution to add new backends to CUDA-Q, including backends 
+from `Anyon Technologies <https://nvidia.github.io/cuda-quantum/0.9.0/using/backends/hardware.html#anyon-technologies-anyon-computing>`__, 
+`Ferimioniq <https://nvidia.github.io/cuda-quantum/0.9.0/using/backends/simulators.html#fermioniq>`__, and 
+`QuEra Computing <https://nvidia.github.io/cuda-quantum/0.9.0/using/backends/hardware.html#quera-computing>`__, 
+as well as updates to existing backends from `ORCA <https://nvidia.github.io/cuda-quantum/latest/using/backends/hardware.html#orca-computing>`__ 
+and `OQC <https://nvidia.github.io/cuda-quantum/0.9.0/using/backends/hardware.html#oqc>`__.
+We hope you enjoy the new features - also check out our new notebooks and examples to dive into CUDA-Q.
+
+- `Docker image <https://catalog.ngc.nvidia.com/orgs/nvidia/teams/quantum/containers/cuda-quantum>`__
+- `Python wheel <https://pypi.org/project/cuda-quantum/0.9.0>`__
+- `C++ installer <https://github.com/NVIDIA/cuda-quantum/releases/0.9.0>`__
+- `Documentation <https://nvidia.github.io/cuda-quantum/0.9.0>`__
+- `Examples <https://github.com/NVIDIA/cuda-quantum/tree/releases/v0.9.0/docs/sphinx/examples>`__
+
+The full change log can be found `here <https://github.com/NVIDIA/cuda-quantum/releases/0.9.0>`__.
+
 **0.8.0**
 
 The 0.8.0 release adds a range of changes to improve the ease of use and performance with CUDA-Q. 
 The changes listed below highlight some of what we think will be the most useful features and changes 
 to know about. While the listed changes do not capture all of the great contributions, we would like 
 to extend many thanks for every contribution, in particular those from external contributors.
 
-- `Docker image <https://catalog.ngc.nvidia.com/orgs/nvidia/teams/quantum/containers/cuda-quantum>`__
+- `Docker image <https://catalog.ngc.nvidia.com/orgs/nvidia/teams/quantum/containers/cuda-quantum/tags>`__
 - `Python wheel <https://pypi.org/project/cuda-quantum/0.8.0>`__
 - `C++ installer <https://github.com/NVIDIA/cuda-quantum/releases/0.8.0>`__
 - `Documentation <https://nvidia.github.io/cuda-quantum/0.8.0>`__
@@ -30,7 +53,7 @@ The full change log can be found `here <https://github.com/NVIDIA/cuda-quantum/r
 The 0.7.1 release adds simulator optimizations with significant performance improvements and 
 extends their functionalities. The `nvidia-mgpu` backend now supports user customization of the 
 gate fusion level as controlled by the `CUDAQ_MGPU_FUSE` environment variable documented 
-`here <https://nvidia.github.io/cuda-quantum/latest/using/backends/simulators.html>`__.
+`here <https://nvidia.github.io/cuda-quantum/0.7.1/using/backends/simulators.html>`__.
 It furthermore adds a range of bug fixes and changes the Python wheel installation instructions.
 
 - `Docker image <https://catalog.ngc.nvidia.com/orgs/nvidia/teams/quantum/containers/cuda-quantum/tags>`__
@@ -46,7 +69,7 @@ The full change log can be found `here <https://github.com/NVIDIA/cuda-quantum/r
 The 0.7.0 release adds support for using :doc:`NVIDIA Quantum Cloud <using/backends/nvqc>`,
 giving you access to our most powerful GPU-accelerated simulators even if you don't have an NVIDIA GPU.
 With 0.7.0, we have furthermore greatly increased expressiveness of the Python and C++ language frontends. 
-Check out our `documentation <https://nvidia.github.io/cuda-quantum/latest/using/quick_start.html>`__ 
+Check out our `documentation <https://nvidia.github.io/cuda-quantum/0.7.0/using/quick_start.html>`__ 
 to get started with the new Python syntax support we have added, and `follow our blog <https://developer.nvidia.com/cuda-q>`__
 to learn more about the new setup and its performance benefits.
 

lib/Optimizer/CodeGen/ConvertToQIRProfile.cpp

@@ -516,7 +516,7 @@ namespace {
 /// trivial pass only does this preparation work. It performs no analysis and
 /// does not rewrite function body's, etc.
 
-static const std::vector<std::string> measurementFunctionNames{
+static constexpr std::array<const char *, 3> measurementFunctionNames{
     cudaq::opt::QIRMeasureBody, cudaq::opt::QIRMeasure,
     cudaq::opt::QIRMeasureToRegister};
 
@@ -564,7 +564,7 @@ struct QIRProfilePreparationPass
               func.getFunctionType().getParams(), module);
 
     // Apply irreversible attribute to measurement functions
-    for (auto &funcName : measurementFunctionNames) {
+    for (auto *funcName : measurementFunctionNames) {
       Operation *op = SymbolTable::lookupSymbolIn(module, funcName);
       auto funcOp = llvm::dyn_cast_if_present<LLVM::LLVMFuncOp>(op);
       if (funcOp) {

runtime/nvqir/custatevec/CuStateVecCircuitSimulator.cpp

@@ -216,7 +216,8 @@ class CuStateVecCircuitSimulator
     void *newDeviceStateVector;
     HANDLE_CUDA_ERROR(cudaMalloc((void **)&newDeviceStateVector,
                                  stateDimension * sizeof(CudaDataType)));
-
+    HANDLE_CUDA_ERROR(cudaMemset(newDeviceStateVector, 0,
+                                 stateDimension * sizeof(CudaDataType)));
     // Place the state data on device. Could be that
     // we just need the zero state, or the user could have provided one
     void *otherState;
@@ -283,6 +284,8 @@ class CuStateVecCircuitSimulator
     void *newDeviceStateVector;
     HANDLE_CUDA_ERROR(cudaMalloc((void **)&newDeviceStateVector,
                                  stateDimension * sizeof(CudaDataType)));
+    HANDLE_CUDA_ERROR(cudaMemset(newDeviceStateVector, 0,
+                                 stateDimension * sizeof(CudaDataType)));
     constexpr int32_t threads_per_block = 256;
     uint32_t n_blocks =
         (stateDimension + threads_per_block - 1) / threads_per_block;