Qiskit · hhorii · Jul 12, 2023 · Jul 7, 2023 · Jun 13, 2023 · Jul 5, 2023
diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
@@ -15,7 +15,7 @@ jobs:
       - uses: actions/setup-python@v2
         name: Install Python
         with:
-          python-version: '3.7'
+          python-version: '3.8'
       - name: Install cibuildwheel
         run: |
           python -m pip install cibuildwheel==2.11.2
@@ -45,7 +45,7 @@ jobs:
       - uses: actions/setup-python@v2
         name: Install Python
         with:
-          python-version: '3.7'
+          python-version: '3.8'
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: stable
@@ -119,28 +119,35 @@ jobs:
           TWINE_PASSWORD: ${{ secrets.TWINE_PASSWORD }}
           TWINE_USERNAME: qiskit
         run: twine upload dist/qiskit*
-  gpu-build:
-    name: Build qiskit-aer-gpu wheels
+  gpu-build-cuda11:
+    name: Build qiskit-aer-gpu-cu11 wheels
     runs-on: ubuntu-latest
     steps:
+      - name: Maximize build space
+        uses: easimon/maximize-build-space@master
+        with:
+          root-reserve-mb: 40000
+          swap-size-mb: 1024
+          remove-dotnet: 'true'
+          remove-android: 'true'
+          remove-haskell: 'true'
+          remove-codeql: 'true'
+          remove-docker-images: 'true'
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v2
         name: Install Python
         with:
-          python-version: '3.7'
-      - name: Add msbuild to PATH
-        uses: microsoft/[email protected]
-        if: runner.os == 'Windows'
+          python-version: '3.8'
       - name: Install cibuildwheel
         run: |
           python -m pip install cibuildwheel==2.11.2
       - name: Build wheels
         env:
-          CIBW_BEFORE_ALL: "yum install -y yum-utils wget && wget -q https://developer.download.nvidia.com/compute/cuda/10.1/Prod/local_installers/cuda-repo-rhel6-10-1-local-10.1.243-418.87.00-1.0-1.x86_64.rpm && rpm -i cuda-repo-rhel6-10-1-local-10.1.243-418.87.00-1.0-1.x86_64.rpm && yum clean all && yum -y install cuda-10-1 openblas-devel"
-          CIBW_MANYLINUX_X86_64_IMAGE: quay.io/pypa/manylinux2010_x86_64:latest
-          CIBW_SKIP: "*-manylinux_i686 cp310* pp* cp36* *musllinux*"
-          CIBW_TEST_SKIP: "cp*"
-          CIBW_ENVIRONMENT: QISKIT_AER_PACKAGE_NAME=qiskit-aer-gpu AER_THRUST_BACKEND=CUDA CUDACXX=/usr/local/cuda/bin/nvcc
+          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 install --user nvidia-cuda-runtime-cu11 nvidia-cublas-cu11 nvidia-cusolver-cu11 nvidia-cusparse-cu11 cuquantum-cu11 && pip show nvidia-cuda-runtime-cu11 nvidia-cublas-cu11 nvidia-cusolver-cu11 nvidia-cusparse-cu11 cuquantum-cu11"
+          CIBW_SKIP: "*-manylinux_i686 pp* cp36* *musllinux*"
+          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=/root/.local LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/root/.local/lib/python3.7/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.7/site-packages/cuquantum/lib:/root/.local/lib/python3.8/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.8/site-packages/cuquantum/lib:/root/.local/lib/python3.9/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.9/site-packages/cuquantum/lib:/root/.local/lib/python3.10/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.10/site-packages/cuquantum/lib:/root/.local/lib/python3.11/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.11/site-packages/cuquantum/lib
+          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@v2
@@ -153,26 +160,35 @@ jobs:
         run : |
           pip install -U twine
           twine upload wheelhouse/*
-  gpu-build-310:
-    name: Build qiskit-aer-gpu wheels
+  gpu-build-cuda12:
+    name: Build qiskit-aer-gpu-cu12 wheels
     runs-on: ubuntu-latest
     steps:
+      - name: Maximize build space
+        uses: easimon/maximize-build-space@master
+        with:
+          root-reserve-mb: 40000
+          swap-size-mb: 1024
+          remove-dotnet: 'true'
+          remove-android: 'true'
+          remove-haskell: 'true'
+          remove-codeql: 'true'
+          remove-docker-images: 'true'
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v2
         name: Install Python
         with:
-          python-version: '3.7'
-      - name: Add msbuild to PATH
-        uses: microsoft/[email protected]
-        if: runner.os == 'Windows'
+          python-version: '3.8'
       - name: Install cibuildwheel
         run: |
           python -m pip install cibuildwheel==2.11.2
       - name: Build wheels
         env:
-          CIBW_BEFORE_ALL: "yum install -y yum-utils wget && wget -q https://developer.nvidia.com/compute/cuda/10.1/Prod/local_installers/cuda-repo-rhel7-10-1-local-10.1.105-418.39-1.0-1.x86_64.rpm && rpm -i cuda-repo-rhel7-10-1-local-10.1.105-418.39-1.0-1.x86_64.rpm && yum clean all && yum -y install cuda-10-1 openblas-devel"
-          CIBW_BUILD: "cp310-manylinux_x86_64"
-          CIBW_ENVIRONMENT: QISKIT_AER_PACKAGE_NAME=qiskit-aer-gpu AER_THRUST_BACKEND=CUDA CUDACXX=/usr/local/cuda/bin/nvcc
+          CIBW_BEFORE_ALL: "yum install -y yum-utils wget && wget -q https://developer.download.nvidia.com/compute/cuda/12.1.1/local_installers/cuda-repo-rhel7-12-1-local-12.1.1_530.30.02-1.x86_64.rpm && rpm -i cuda-repo-rhel7-12-1-local-12.1.1_530.30.02-1.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 --user nvidia-cuda-runtime-cu12 nvidia-cublas-cu12 nvidia-cusolver-cu12 nvidia-cusparse-cu12 cuquantum-cu12"
+          CIBW_SKIP: "*-manylinux_i686 pp* cp36* *musllinux*"
+          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=/root/.local LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/root/.local/lib/python3.7/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.7/site-packages/cuquantum/lib:/root/.local/lib/python3.8/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.8/site-packages/cuquantum/lib:/root/.local/lib/python3.9/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.9/site-packages/cuquantum/lib:/root/.local/lib/python3.10/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.10/site-packages/cuquantum/lib:/root/.local/lib/python3.11/site-packages/nvidia/cuda_runtime/lib:/root/.local/lib/python3.11/site-packages/cuquantum/lib
+          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@v2
@@ -197,7 +213,7 @@ jobs:
       - uses: actions/setup-python@v2
         name: Install Python
         with:
-          python-version: '3.7'
+          python-version: '3.8'
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: stable
@@ -233,7 +249,7 @@ jobs:
       - uses: actions/setup-python@v2
         name: Install Python
         with:
-          python-version: '3.7'
+          python-version: '3.8'
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: stable

diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -259,49 +259,80 @@ if(AER_THRUST_SUPPORTED)
 		set(CMAKE_CUDA_ARCHITECTURES "${AER_CUDA_ARCHITECTURES}")
 		message(STATUS "CMAKE_CUDA_ARCHITECTURES = ${CMAKE_CUDA_ARCHITECTURES}")
 
-		set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} ${AER_CUDA_ARCH_FLAGS_EXPAND} -DAER_THRUST_CUDA -I${AER_SIMULATOR_CPP_SRC_DIR} -isystem ${AER_SIMULATOR_CPP_SRC_DIR}/third-party/headers -use_fast_math --expt-extended-lambda")
-
-		set(AER_COMPILER_DEFINITIONS ${AER_COMPILER_DEFINITIONS} THRUST_DEVICE_SYSTEM=THRUST_DEVICE_SYSTEM_CUDA)
-		set(THRUST_DEPENDANT_LIBS "-L${CUDA_TOOLKIT_ROOT_DIR}/lib64")
-		if(NOT DEFINED CUQUANTUM_ROOT)
-			if(DEFINED ENV{CUQUANTUM_ROOT})
-				set(CUQUANTUM_ROOT $ENV{CUQUANTUM_ROOT})
-			endif()
-		endif()
-		if(NOT DEFINED CUTENSOR_ROOT)
-			if(DEFINED ENV{CUTENSOR_ROOT})
-				set(CUTENSOR_ROOT $ENV{CUTENSOR_ROOT})
-			endif()
-		endif()
-		if(NOT DEFINED AER_ENABLE_CUQUANTUM)
-			if(DEFINED ENV{AER_ENABLE_CUQUANTUM})
-				set(AER_ENABLE_CUQUANTUM $ENV{AER_ENABLE_CUQUANTUM})
-			endif()
+		if(NOT DEFINED AER_PYTHON_CUDA_ROOT AND DEFINED ENV{AER_PYTHON_CUDA_ROOT})
+			set(AER_PYTHON_CUDA_ROOT $ENV{AER_PYTHON_CUDA_ROOT})
 		endif()
+		if(AER_PYTHON_CUDA_ROOT)
+			find_package(Python)
+			set(PYTHON_SITE_PATH ${AER_PYTHON_CUDA_ROOT}/lib/python${Python_VERSION_MAJOR}.${Python_VERSION_MINOR}/site-packages)
+#			execute_process(COMMAND "${Python_EXECUTABLE}" -c "from distutils.sysconfig import get_python_lib; print (get_python_lib())"  OUTPUT_VARIABLE PYTHON_SITE_PATH OUTPUT_STRIP_TRAILING_WHITESPACE)
+			message(STATUS "PYTHON_SITE_PATH = ${PYTHON_SITE_PATH}")
 
-		if(AER_ENABLE_CUQUANTUM)
+			set(AER_COMPILER_DEFINITIONS ${AER_COMPILER_DEFINITIONS} THRUST_DEVICE_SYSTEM=THRUST_DEVICE_SYSTEM_CUDA)
 			set(AER_COMPILER_DEFINITIONS ${AER_COMPILER_DEFINITIONS} AER_CUSTATEVEC AER_CUTENSORNET)
-			if(DEFINED CUQUANTUM_ROOT)
-				set(AER_COMPILER_FLAGS "${AER_COMPILER_FLAGS} -I${CUQUANTUM_ROOT}/include")
-				set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${CUQUANTUM_ROOT}/lib/${CUDA_VERSION_MAJOR}")
+
+			set(CUDA_NVCC_FLAGS "${AER_CUDA_ARCH_FLAGS_EXPAND} -DAER_THRUST_CUDA -I${AER_SIMULATOR_CPP_SRC_DIR} -isystem ${AER_SIMULATOR_CPP_SRC_DIR}/third-party/headers -use_fast_math --expt-extended-lambda")
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -I${PYTHON_SITE_PATH}/cuquantum/include")
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -I${PYTHON_SITE_PATH}/cutensor/include")
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -Xlinker \"--disable-new-dtags\" ")
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -Xlinker \"--rpath=${PYTHON_SITE_PATH}/nvidia/cusolver/lib\" ")
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -Xlinker \"--rpath=${PYTHON_SITE_PATH}/nvidia/cusparse/lib\" ")
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -Xlinker \"--rpath=${PYTHON_SITE_PATH}/cutensor/lib\" ")
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -Xlinker \"--rpath=${PYTHON_SITE_PATH}/nvidia/cuda_runtime/lib\" ")
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -Xlinker \"--no-as-needed,-l:libcusolver.so.${CUDA_VERSION_MAJOR},-l:libcusparse.so.${CUDA_VERSION_MAJOR},--as-needed\" ")
+			set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${PYTHON_SITE_PATH}/cuquantum/lib -l:libcustatevec.so.1 -l:libcutensornet.so.2")
+			if(CUDA_VERSION_MAJOR STREQUAL "11")
+				set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${PYTHON_SITE_PATH}/nvidia/cuda_runtime/lib -l:libcudart.so.${CUDA_VERSION_MAJOR}.0")
+			else()
+				set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${PYTHON_SITE_PATH}/nvidia/cuda_runtime/lib -l:libcudart.so.${CUDA_VERSION_MAJOR}")
 			endif()
-			if(DEFINED CUTENSOR_ROOT)
-				set(AER_COMPILER_FLAGS "${AER_COMPILER_FLAGS} -I${CUTENSOR_ROOT}/include")
-				set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${CUTENSOR_ROOT}/lib/${CUDA_VERSION_MAJOR}")
+			string(STRIP ${CUDA_NVCC_FLAGS} CUDA_NVCC_FLAGS)
+			string(STRIP ${THRUST_DEPENDANT_LIBS} THRUST_DEPENDANT_LIBS)
+		else()
+			set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} ${AER_CUDA_ARCH_FLAGS_EXPAND} -DAER_THRUST_CUDA -I${AER_SIMULATOR_CPP_SRC_DIR} -isystem ${AER_SIMULATOR_CPP_SRC_DIR}/third-party/headers -use_fast_math --expt-extended-lambda")
+
+			set(AER_COMPILER_DEFINITIONS ${AER_COMPILER_DEFINITIONS} THRUST_DEVICE_SYSTEM=THRUST_DEVICE_SYSTEM_CUDA)
+			set(THRUST_DEPENDANT_LIBS "-L${CUDA_TOOLKIT_ROOT_DIR}/lib64")
+			if(NOT DEFINED CUQUANTUM_ROOT)
+				if(DEFINED ENV{CUQUANTUM_ROOT})
+					set(CUQUANTUM_ROOT $ENV{CUQUANTUM_ROOT})
+				endif()
 			endif()
-            if(CUQUANTUM_STATIC)
-				set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -lcustatevec_static -lcutensornet_static  -lcutensor_static -lmetis_static -lcusolver_static -lcusparse_static -lcusolver_lapack_static -lcublas_static -lcublasLt_static -lculibos")
-			else()
-				set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -lcustatevec -lcutensornet -lcutensor")
+			if(NOT DEFINED CUTENSOR_ROOT)
+				if(DEFINED ENV{CUTENSOR_ROOT})
+					set(CUTENSOR_ROOT $ENV{CUTENSOR_ROOT})
+				endif()
 			endif()
-		elseif(CUSTATEVEC_ROOT)
-			#TODO this is remained for backward compatibility, use CUQUANTUM_ROOT instead
-			set(AER_COMPILER_DEFINITIONS ${AER_COMPILER_DEFINITIONS} AER_CUSTATEVEC)
-			set(AER_COMPILER_FLAGS "${AER_COMPILER_FLAGS} -I${CUSTATEVEC_ROOT}/include")
-            if(CUSTATEVEC_STATIC)
-				set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${CUSTATEVEC_ROOT}/lib -L${CUSTATEVEC_ROOT}/lib/${CUDA_VERSION_MAJOR} -lcustatevec_static -lcusolver_static -lcusparse_static -lcusolver_lapack_static -lcublas_static -lcublasLt_static -lculibos")
-			else()
-				set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${CUSTATEVEC_ROOT}/lib -L${CUSTATEVEC_ROOT}/lib/${CUDA_VERSION_MAJOR} -lcustatevec")
+			if(NOT DEFINED AER_ENABLE_CUQUANTUM)
+				if(DEFINED ENV{AER_ENABLE_CUQUANTUM})
+					set(AER_ENABLE_CUQUANTUM $ENV{AER_ENABLE_CUQUANTUM})
+				endif()
+			endif()
+
+			if(AER_ENABLE_CUQUANTUM)
+				set(AER_COMPILER_DEFINITIONS ${AER_COMPILER_DEFINITIONS} AER_CUSTATEVEC AER_CUTENSORNET)
+				if(DEFINED CUQUANTUM_ROOT)
+					set(AER_COMPILER_FLAGS "${AER_COMPILER_FLAGS} -I${CUQUANTUM_ROOT}/include")
+					set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${CUQUANTUM_ROOT}/lib/${CUDA_VERSION_MAJOR}")
+				endif()
+				if(DEFINED CUTENSOR_ROOT)
+					set(AER_COMPILER_FLAGS "${AER_COMPILER_FLAGS} -I${CUTENSOR_ROOT}/include")
+					set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${CUTENSOR_ROOT}/lib/${CUDA_VERSION_MAJOR}")
+				endif()
+       	     if(CUQUANTUM_STATIC)
+					set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -lcustatevec_static -lcutensornet_static  -lcutensor_static -lmetis_static -lcusolver_static -lcusparse_static -lcusolver_lapack_static -lcublas_static -lcublasLt_static -lculibos")
+				else()
+					set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -lcustatevec -lcutensornet -lcutensor")
+				endif()
+			elseif(CUSTATEVEC_ROOT)
+				#TODO this is remained for backward compatibility, use CUQUANTUM_ROOT instead
+				set(AER_COMPILER_DEFINITIONS ${AER_COMPILER_DEFINITIONS} AER_CUSTATEVEC)
+				set(AER_COMPILER_FLAGS "${AER_COMPILER_FLAGS} -I${CUSTATEVEC_ROOT}/include")
+        	    if(CUSTATEVEC_STATIC)
+					set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${CUSTATEVEC_ROOT}/lib -L${CUSTATEVEC_ROOT}/lib/${CUDA_VERSION_MAJOR} -lcustatevec_static -lcusolver_static -lcusparse_static -lcusolver_lapack_static -lcublas_static -lcublasLt_static -lculibos")
+				else()
+					set(THRUST_DEPENDANT_LIBS "${THRUST_DEPENDANT_LIBS} -L${CUSTATEVEC_ROOT}/lib -L${CUSTATEVEC_ROOT}/lib/${CUDA_VERSION_MAJOR} -lcustatevec")
+				endif()
 			endif()
 		endif()
 	elseif(AER_THRUST_BACKEND STREQUAL "TBB")