resolve conflicts

.github/workflows/deploy.yml

@@ -23,7 +23,6 @@ jobs:
       - name: Build wheels
         env:
           AER_CMAKE_OPENMP_BUILD: 1
-          CIBW_SKIP: "pp* cp38-macosx_arm64 cp39-macosx_arm64"
         run: python -m cibuildwheel --output-dir wheelhouse
       - uses: actions/upload-artifact@v4
         with:
@@ -133,30 +132,31 @@ jobs:
       - name: Maximize build space
         uses: easimon/maximize-build-space@master
         with:
-          root-reserve-mb: 30000
+          root-reserve-mb: 32000
           swap-size-mb: 1024
           remove-dotnet: 'true'
           remove-android: 'true'
           remove-haskell: 'true'
           remove-codeql: 'true'
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
           python-version: '3.10'
       - name: Install cibuildwheel
         run: |
-          python -m pip install cibuildwheel==2.17.0
+          python -m pip install cibuildwheel==2.16.2
       - name: Build wheels
         env:
-          CIBW_BEFORE_ALL: "yum install -y yum-utils wget && wget -q https://developer.download.nvidia.com/compute/cuda/11.8.0/local_installers/cuda-repo-rhel7-11-8-local-11.8.0_520.61.05-1.x86_64.rpm && rpm -i cuda-repo-rhel7-11-8-local-11.8.0_520.61.05-1.x86_64.rpm && yum clean all && yum -y install cuda && yum -y install openblas-devel && yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel7/x86_64/cuda-rhel7.repo && yum clean all"
-          CIBW_BEFORE_BUILD : "pip cache purge && pip install nvidia-cuda-runtime-cu11 nvidia-cublas-cu11 nvidia-cusolver-cu11 nvidia-cusparse-cu11 cuquantum-cu11"
+          CIBW_BEFORE_ALL: "pip cache purge && yum install -y yum-utils wget && wget -q https://developer.download.nvidia.com/compute/cuda/11.8.0/local_installers/cuda-repo-rhel7-11-8-local-11.8.0_520.61.05-1.x86_64.rpm && rpm -i cuda-repo-rhel7-11-8-local-11.8.0_520.61.05-1.x86_64.rpm && yum clean all && yum -y install cuda && yum -y install openblas-devel && yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel7/x86_64/cuda-rhel7.repo && yum clean all"
+          CIBW_BEFORE_BUILD : "pip install nvidia-cuda-runtime-cu11 nvidia-cublas-cu11 nvidia-cusolver-cu11 nvidia-cusparse-cu11 cuquantum-cu11"
           CIBW_SKIP: "*-manylinux_i686 pp* cp36* cp37* *musllinux*"
+          CIBW_TEST_SKIP: "*"
           CIBW_ENVIRONMENT: QISKIT_AER_PACKAGE_NAME=qiskit-aer-gpu-cu11 QISKIT_AER_CUDA_MAJOR=11 CMAKE_VERBOSE_MAKEFILE=true AER_THRUST_BACKEND=CUDA CUDACXX=/usr/local/cuda/bin/nvcc AER_CUDA_ARCH="7.0 7.2 7.5 8.0 8.6 8.7" AER_PYTHON_CUDA_ROOT=/opt/_internal AER_CIBUILD=true
           CIBW_REPAIR_WHEEL_COMMAND: 'auditwheel repair --exclude libcudart.so.11.0 --exclude libcustatevec.so.1 --exclude libcutensornet.so.2 --exclude libcutensor.so.1 --exclude libcutensorMg.so.1 --exclude libcusolver.so.11 --exclude libcusolverMg.so.11 --exclude libcusparse.so.11 --exclude libcublas.so.11 --exclude libcublasLt.so.11 -w {dest_dir} {wheel}'
         run: |
           python -m cibuildwheel --output-dir wheelhouse
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v3
         with:
           path: ./wheelhouse/*.whl
       - name: Publish package distributions to PyPI
@@ -176,30 +176,31 @@ jobs:
       - name: Maximize build space
         uses: easimon/maximize-build-space@master
         with:
-          root-reserve-mb: 30000
+          root-reserve-mb: 32000
           swap-size-mb: 1024
           remove-dotnet: 'true'
           remove-android: 'true'
           remove-haskell: 'true'
           remove-codeql: 'true'
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
           python-version: '3.10'
       - name: Install cibuildwheel
         run: |
-          python -m pip install cibuildwheel==2.17.0
+          python -m pip install cibuildwheel==2.16.2
       - name: Build wheels
         env:
-          CIBW_BEFORE_ALL: "yum install -y yum-utils wget && wget -q https://developer.download.nvidia.com/compute/cuda/12.4.0/local_installers/cuda-repo-rhel7-12-4-local-12.4.0_550.54.14-1.x86_64.rpm && rpm -i cuda-repo-rhel7-12-4-local-12.4.0_550.54.14-1.x86_64.rpm && yum clean all && yum -y install nvidia-driver-latest-dkms && yum -y install cuda-toolkit-12-4 && yum -y install openblas-devel && yum clean all"
-          CIBW_BEFORE_BUILD : "pip cache purge && pip install nvidia-cuda-runtime-cu12 nvidia-nvjitlink-cu12 nvidia-cublas-cu12 nvidia-cusolver-cu12 nvidia-cusparse-cu12 cuquantum-cu12"
+          CIBW_BEFORE_ALL: "pip cache purge && yum install -y yum-utils wget && wget -q https://developer.download.nvidia.com/compute/cuda/12.4.0/local_installers/cuda-repo-rhel7-12-4-local-12.4.0_550.54.14-1.x86_64.rpm && rpm -i cuda-repo-rhel7-12-4-local-12.4.0_550.54.14-1.x86_64.rpm && yum clean all && yum -y install nvidia-driver-latest-dkms && yum -y install cuda-toolkit-12-4 && yum -y install openblas-devel && yum clean all"
+          CIBW_BEFORE_BUILD : "pip install nvidia-cuda-runtime-cu12 nvidia-nvjitlink-cu12 nvidia-cublas-cu12 nvidia-cusolver-cu12 nvidia-cusparse-cu12 cuquantum-cu12"
           CIBW_SKIP: "*-manylinux_i686 pp* cp36* cp37* *musllinux*"
+          CIBW_TEST_SKIP: "*"
           CIBW_ENVIRONMENT: QISKIT_AER_PACKAGE_NAME=qiskit-aer-gpu QISKIT_AER_CUDA_MAJOR=12 CMAKE_VERBOSE_MAKEFILE=true AER_THRUST_BACKEND=CUDA CUDACXX=/usr/local/cuda/bin/nvcc AER_CUDA_ARCH="7.0 7.2 7.5 8.0 8.6 8.7 9.0" AER_PYTHON_CUDA_ROOT=/opt/_internal AER_CIBUILD=true
           CIBW_REPAIR_WHEEL_COMMAND: 'auditwheel repair --exclude libcudart.so.12 --exclude libcustatevec.so.1 --exclude libcutensornet.so.2 --exclude libcutensor.so.1 --exclude libcutensorMg.so.1 --exclude libcusolver.so.11 --exclude libcusolverMg.so.11 --exclude libcusolver.so.12 --exclude libcusolverMg.so.12 --exclude libcusparse.so.12 --exclude libcublas.so.12 --exclude libcublasLt.so.12 --exclude libnvJitLink.so.12 -w {dest_dir} {wheel}'
         run: |
           python -m cibuildwheel --output-dir wheelhouse
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v3
         with:
           path: ./wheelhouse/*.whl
       - name: Publish package distributions to PyPI

README.md

@@ -134,13 +134,13 @@ provider = QiskitRuntimeService(channel='ibm_quantum', token="set your own token
 backend = provider.get_backend("ibm_kyoto")
 
 # create sampler from the actual backend
-sampler.from_backend(backend)
+sampler = SamplerV2.from_backend(backend)
 
 # run a sampler job on the parameterized circuits with noise model of the actual hardware
-job3 = sampler.run([(pqc, theta1), (pqc2, theta2)])
+bell_t = transpile(bell, AerSimulator(basis_gates=["ecr", "id", "rz", "sx"]), optimization_level=0)
+job3 = sampler.run([bell_t], shots=128)
 job_result = job3.result()
-print(f"Parameterized for Bell circuit w/noise: {job_result[0].data.meas.get_counts()}")
-
+print(f"counts for Bell circuit w/noise: {job_result[0].data.meas.get_counts()}")
 ```
 
 ## Contribution Guidelines

qiskit_aer/backends/aer_compiler.py

@@ -820,6 +820,7 @@ def _assemble_op(
         "mcu", "mcu1", "mcu2", "mcu3", "mcx", "mcx_gray", "mcy", "mcz", "p", "r",
         "rx", "rxx", "ry", "ryy", "rz", "rzx", "rzz", "s", "sdg", "swap", "sx", "sxdg",
         "t", "tdg", "u", "x", "y", "z", "u1", "u2", "u3", "cu", "cu1", "cu2", "cu3",
+        "crx", "cry", "crz",
     }:
         aer_circ.gate(name, qubits, params, [], conditional_reg, aer_cond_expr,
                       label if label else name)

qiskit_aer/backends/backend_utils.py

@@ -91,6 +91,9 @@
             "rzx",
             "ccx",
             "ccz",
+            "crx",
+            "cry",
+            "crz",
             "cswap",
             "mcx",
             "mcy",
@@ -218,8 +221,6 @@
             "delay",
             "pauli",
             "ecr",
-            "rx",
-            "ry",
             "rz",
         ]
     ),
@@ -247,6 +248,7 @@
             "delay",
             "pauli",
             "ecr",
+            "rz",
         ]
     ),
     "unitary": sorted(
@@ -288,6 +290,9 @@
             "ccx",
             "ccz",
             "cswap",
+            "crx",
+            "cry",
+            "crz",
             "mcx",
             "mcy",
             "mcz",
@@ -389,6 +394,9 @@
             "ccx",
             "ccz",
             "cswap",
+            "crx",
+            "cry",
+            "crz",
             "mcx",
             "mcy",
             "mcz",

qiskit_aer/primitives/estimator_v2.py

@@ -70,12 +70,14 @@ def __init__(
                 the runtime options (``run_options``).
         """
         self._options = Options(**options) if options else Options()
-        method = "density_matrix" if "noise_model" in self.options.backend_options else "automatic"
-        self._backend = AerSimulator(method=method, **self.options.backend_options)
-
-    def from_backend(self, backend, **options):
-        """use external backend"""
-        self._backend.from_backend(backend, **options)
+        self._backend = AerSimulator(**self.options.backend_options)
+
+    @classmethod
+    def from_backend(cls, backend, **options):
+        """make new sampler that uses external backend"""
+        estimator = cls(**options)
+        estimator._backend = AerSimulator.from_backend(backend)
+        return estimator
 
     @property
     def options(self) -> Options:

qiskit_aer/primitives/sampler_v2.py

@@ -100,9 +100,12 @@ def __init__(
         self._options = Options(**options) if options else Options()
         self._backend = AerSimulator(**self.options.backend_options)
 
-    def from_backend(self, backend, **options):
-        """use external backend"""
-        self._backend.from_backend(backend, **options)
+    @classmethod
+    def from_backend(cls, backend, **options):
+        """make new sampler that uses external backend"""
+        sampler = cls(**options)
+        sampler._backend = AerSimulator.from_backend(backend)
+        return sampler
 
     @property
     def default_shots(self) -> int:
@@ -156,6 +159,7 @@ def _run_pub(self, pub: SamplerPub) -> PubResult:
             for item in meas_info
         }
 
+        metadata = {"shots": pub.shots}
         if qargs:
             circuit.measure_all()
             result = self._backend.run(
@@ -181,6 +185,7 @@ def _run_pub(self, pub: SamplerPub) -> PubResult:
                 for item in meas_info:
                     ary = _samples_to_packed_array(samples_array, item.num_bits, item.qreg_indices)
                     arrays[item.creg_name][index] = ary
+            metadata["simulator_metadata"] = result.metadata
         else:
             for index in np.ndenumerate(parameter_values.shape):
                 samples = [""] * pub.shots
@@ -199,7 +204,7 @@ def _run_pub(self, pub: SamplerPub) -> PubResult:
             item.creg_name: BitArray(arrays[item.creg_name], item.num_bits) for item in meas_info
         }
         data_bin = data_bin_cls(**meas)
-        return PubResult(data_bin, metadata={"shots": pub.shots})
+        return PubResult(data_bin, metadata=metadata)
 
 
 def _preprocess_circuit(circuit: QuantumCircuit):

releasenotes/notes/add_rotation_support-c0ef8155a761e560.yaml

@@ -0,0 +1,8 @@
+---
+features:
+  - |
+    Add `rz` gate with n*pi/2 cases to `extended_stabilizer` method
+    as well as `stabilizer` method.
+
+    Add `crx`, `cry` and `crz` gates to `statevector` and `tensor_netowork`
+    methods.

releasenotes/notes/add_sampler_v2_simulator_metadata-e17850d483439f9a.yaml

@@ -0,0 +1,5 @@
+---
+fixes:
+  - |
+    This fix adds `simulator_metadata` in the `metadata` of `PubResults`
+    for SamplerV2 primitive as similar to EstimatorV2 primitive

releasenotes/notes/fix_enabling_cuStateVec-1a2f1d3e35f3129d.yaml

@@ -0,0 +1,6 @@
+---
+fixes:
+  - |
+    The option `cuStateVec_enable=True` was not set correctly.
+    This fix set this option to statevector, unitary and density_matrix
+    simulator states classes before allocating their memory

releasenotes/notes/fix_primitiveV2_init-afe7b331ddbef538.yaml

@@ -0,0 +1,5 @@
+---
+fixes:
+  - |
+    Fixed init function of EstimatorV2 and SamplerV2 to set `method` in
+    its option property if there is no `method` in input parameter

releasenotes/notes/fix_stabilizer_measure-a06d761eba2546d2.yaml

@@ -0,0 +1,5 @@
+---
+fixes:
+  - |
+    Fix of deterministic measure of stabilizer and change of OpenMP
+    parallelization of loop

src/framework/operations.hpp

@@ -724,27 +724,29 @@ inline void check_duplicate_qubits(const Op &op) {
 }
 
 inline void check_gate_params(const Op &op) {
-  const stringmap_t<std::tuple<int_t, int_t>> param_tables(
-      {{"u1", {1, 1}},      {"u2", {1, 2}},       {"u3", {1, 3}},
-       {"u", {1, 3}},       {"U", {1, 3}},        {"CX", {2, 0}},
-       {"cx", {2, 0}},      {"cz", {2, 0}},       {"cy", {2, 0}},
-       {"cp", {2, 1}},      {"cu1", {2, 1}},      {"cu2", {2, 2}},
-       {"cu3", {2, 3}},     {"swap", {2, 0}},     {"id", {0, 0}},
-       {"p", {1, 1}},       {"x", {1, 0}},        {"y", {1, 0}},
-       {"z", {1, 0}},       {"h", {1, 0}},        {"s", {1, 0}},
-       {"sdg", {1, 0}},     {"t", {1, 0}},        {"tdg", {1, 0}},
-       {"r", {1, 2}},       {"rx", {1, 1}},       {"ry", {1, 1}},
-       {"rz", {1, 1}},      {"rxx", {2, 1}},      {"ryy", {2, 1}},
-       {"rzz", {2, 1}},     {"rzx", {2, 1}},      {"ccx", {3, 0}},
-       {"ccz", {3, 0}},     {"cswap", {3, 0}},    {"mcx", {1, 0}},
-       {"mcy", {1, 0}},     {"mcz", {1, 0}},      {"mcu1", {1, 1}},
-       {"mcu2", {1, 2}},    {"mcu3", {1, 3}},     {"mcswap", {2, 0}},
-       {"mcphase", {1, 1}}, {"mcr", {1, 1}},      {"mcrx", {1, 1}},
-       {"mcry", {1, 1}},    {"mcrz", {1, 1}},     {"sx", {1, 0}},
-       {"sxdg", {1, 0}},    {"csx", {2, 0}},      {"mcsx", {1, 0}},
-       {"csxdg", {2, 0}},   {"mcsxdg", {1, 0}},   {"delay", {1, 0}},
-       {"pauli", {1, 0}},   {"mcx_gray", {1, 0}}, {"cu", {2, 4}},
-       {"mcu", {1, 4}},     {"mcp", {1, 1}},      {"ecr", {2, 0}}});
+  const stringmap_t<std::tuple<int_t, int_t>> param_tables({
+      {"u1", {1, 1}},      {"u2", {1, 2}},       {"u3", {1, 3}},
+      {"u", {1, 3}},       {"U", {1, 3}},        {"CX", {2, 0}},
+      {"cx", {2, 0}},      {"cz", {2, 0}},       {"cy", {2, 0}},
+      {"cp", {2, 1}},      {"cu1", {2, 1}},      {"cu2", {2, 2}},
+      {"cu3", {2, 3}},     {"swap", {2, 0}},     {"id", {0, 0}},
+      {"p", {1, 1}},       {"x", {1, 0}},        {"y", {1, 0}},
+      {"z", {1, 0}},       {"h", {1, 0}},        {"s", {1, 0}},
+      {"sdg", {1, 0}},     {"t", {1, 0}},        {"tdg", {1, 0}},
+      {"r", {1, 2}},       {"rx", {1, 1}},       {"ry", {1, 1}},
+      {"rz", {1, 1}},      {"rxx", {2, 1}},      {"ryy", {2, 1}},
+      {"rzz", {2, 1}},     {"rzx", {2, 1}},      {"ccx", {3, 0}},
+      {"ccz", {3, 0}},     {"cswap", {3, 0}},    {"mcx", {1, 0}},
+      {"mcy", {1, 0}},     {"mcz", {1, 0}},      {"mcu1", {1, 1}},
+      {"mcu2", {1, 2}},    {"mcu3", {1, 3}},     {"mcswap", {2, 0}},
+      {"mcphase", {1, 1}}, {"mcr", {1, 1}},      {"mcrx", {1, 1}},
+      {"mcry", {1, 1}},    {"mcrz", {1, 1}},     {"sx", {1, 0}},
+      {"sxdg", {1, 0}},    {"csx", {2, 0}},      {"mcsx", {1, 0}},
+      {"csxdg", {2, 0}},   {"mcsxdg", {1, 0}},   {"delay", {1, 0}},
+      {"pauli", {1, 0}},   {"mcx_gray", {1, 0}}, {"cu", {2, 4}},
+      {"mcu", {1, 4}},     {"mcp", {1, 1}},      {"ecr", {2, 0}},
+      {"crx", {1, 1}},     {"cry", {1, 1}},      {"crz", {1, 1}},
+  });
 
   auto it = param_tables.find(op.name);
   if (it == param_tables.end()) {

src/simulators/density_matrix/densitymatrix_state.hpp

@@ -344,6 +344,9 @@ bool State<densmat_t>::allocate(uint_t num_qubits, uint_t block_bits,
     BaseState::qreg_.set_max_sampling_shots(BaseState::max_sampling_shots_);
 
   BaseState::qreg_.set_target_gpus(BaseState::target_gpus_);
+#ifdef AER_CUSTATEVEC
+  BaseState::qreg_.cuStateVec_enable(BaseState::cuStateVec_enable_);
+#endif
   BaseState::qreg_.chunk_setup(block_bits * 2, block_bits * 2, 0, 1);
 
   return true;

src/simulators/extended_stabilizer/extended_stabilizer_state.hpp

@@ -46,7 +46,7 @@ const Operations::OpSet StateOpSet(
     // Gates
     {"CX", "u0",  "u1",  "p",   "cx",    "cz",    "swap", "id",
      "x",  "y",   "z",   "h",   "s",     "sdg",   "sx",   "sxdg",
-     "t",  "tdg", "ccx", "ccz", "delay", "pauli", "ecr"});
+     "t",  "tdg", "ccx", "ccz", "delay", "pauli", "ecr",  "rz"});
 
 using chpauli_t = CHSimulator::pauli_t;
 using chstate_t = CHSimulator::Runner;
@@ -89,6 +89,9 @@ class State : public QuantumState::State<chstate_t> {
   std::vector<SampleVector> sample_measure(const reg_t &qubits, uint_t shots,
                                            RngEngine &rng) override;
 
+  bool
+  validate_parameters(const std::vector<Operations::Op> &ops) const override;
+
 protected:
   // Alongside the sample measure optimisaiton, we can parallelise
   // circuit applicaiton over the states. This reduces the threading overhead
@@ -211,6 +214,7 @@ const stringmap_t<Gates> State::gateset_({
     {"sxdg", Gates::sxdg}, // Inverse sqrt(X) gate
     {"t", Gates::t},       // T-gate (sqrt(S))
     {"tdg", Gates::tdg},   // Conjguate-transpose of T gate
+    {"rz", Gates::rz},     // RZ gate (only support k * pi/2 cases)
     // Waltz Gates
     {"u0", Gates::u0}, // idle gate in multiples of X90
     {"u1", Gates::u1}, // zero-X90 pulse waltz gate
@@ -337,6 +341,23 @@ bool State::check_measurement_opt(InputIterator first,
   return true;
 }
 
+bool State::validate_parameters(const std::vector<Operations::Op> &ops) const {
+  for (uint_t i = 0; i < ops.size(); i++) {
+    if (ops[i].type == OpType::gate) {
+      // check parameter of RZ gates
+      if (ops[i].name == "rz") {
+        double pi2 = std::real(ops[i].params[0]) * 2.0 / M_PI;
+        double pi2_int = (double)std::round(pi2);
+
+        if (!AER::Linalg::almost_equal(pi2, pi2_int)) {
+          return false;
+        }
+      }
+    }
+  }
+  return true;
+}
+
 //-------------------------------------------------------------------------
 // Implementation: Operations
 //-------------------------------------------------------------------------
@@ -634,6 +655,7 @@ void State::apply_gate(const Operations::Op &op, RngEngine &rng) {
 }
 
 void State::apply_gate(const Operations::Op &op, RngEngine &rng, uint_t rank) {
+  int_t pi2;
   auto it = gateset_.find(op.name);
   if (it == gateset_.end()) {
     throw std::invalid_argument("CH::State: Invalid gate operation \'" +
@@ -703,6 +725,19 @@ void State::apply_gate(const Operations::Op &op, RngEngine &rng, uint_t rank) {
     BaseState::qreg_.apply_cx(op.qubits[0], op.qubits[1], rank);
     BaseState::qreg_.apply_x(op.qubits[0], rank);
     break;
+  case Gates::rz:
+    pi2 = (int_t)std::round(std::real(op.params[0]) * 2.0 / M_PI) & 3;
+    if (pi2 == 1) {
+      // S
+      BaseState::qreg_.apply_s(op.qubits[0], rank);
+    } else if (pi2 == 2) {
+      // Z
+      BaseState::qreg_.apply_z(op.qubits[0], rank);
+    } else if (pi2 == 3) {
+      // Sdg
+      BaseState::qreg_.apply_sdag(op.qubits[0], rank);
+    }
+    break;
   default: // u0 or Identity
     break;
   }