Build ARM CUDA

[johnnynunez]

Describe the bug
ARM CUDA build.

To Reproduce
uses clang natively because not exists url for aarch64

Log/Screenshots

[479/656] cd /opt/taichi/taichi/runtime/llvm/runtime_module && /usr/bin/clang -c runtime.cpp -o runtime_arm64.bc -fno-exceptions -emit-llvm -std=c++17 -D ARCH_arm64 -I /opt/taichi
[480/656] cd /opt/taichi/taichi/runtime/llvm/runtime_module && /usr/bin/clang -c runtime.cpp -o runtime_cuda.bc -fno-exceptions -emit-llvm -std=c++17 -D ARCH_cuda -I /opt/taichi
FAILED: taichi/runtime/llvm/runtime_module/CMakeFiles/generate_llvm_runtime_cuda /opt/taichi/_skbuild/linux-aarch64-3.10/cmake-build/taichi/runtime/llvm/runtime_module/CMakeFiles/generate_llvm_runtime_cuda 
cd /opt/taichi/taichi/runtime/llvm/runtime_module && /usr/bin/clang -c runtime.cpp -o runtime_cuda.bc -fno-exceptions -emit-llvm -std=c++17 -D ARCH_cuda -I /opt/taichi
runtime.cpp:1137:23: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
               : "=r"(ret)
                      ^
runtime.cpp:1136:37: note: use constraint modifier "w"
  asm volatile("match.all.sync.b32  %0, %1, %2;"
                                    ^~
                                    %w0
runtime.cpp:1138:22: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
               : "r"(value), "r"(mask));
                     ^
runtime.cpp:1136:41: note: use constraint modifier "w"
  asm volatile("match.all.sync.b32  %0, %1, %2;"
                                        ^~
                                        %w1
runtime.cpp:1138:34: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
               : "r"(value), "r"(mask));
                                 ^
runtime.cpp:1136:45: note: use constraint modifier "w"
  asm volatile("match.all.sync.b32  %0, %1, %2;"
                                            ^~
                                            %w2
runtime.cpp:1150:18: error: invalid input constraint 'l' in asm
               : "l"(value), "r"(mask));
                 ^
runtime.cpp:1160:44: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
  asm volatile("activemask.b32 %0;" : "=r"(mask));
                                           ^
runtime.cpp:1160:32: note: use constraint modifier "w"
  asm volatile("activemask.b32 %0;" : "=r"(mask));
                               ^~
                               %w0
4 warnings and 1 error generated.
[481/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderable.cpp.o
[482/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderer.cpp.o
[483/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderables/circles.cpp.o
[484/656] Building CXX object external/SPIRV-Cross/CMakeFiles/spirv-cross-msl.dir/spirv_msl.cpp.o
[485/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderables/lines.cpp.o
[486/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderables/mesh.cpp.o
[487/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderables/particles.cpp.o
[488/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderables/scene_lines.cpp.o
[489/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderables/set_image.cpp.o
[490/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/renderables/triangles.cpp.o
[491/656] Building CXX object taichi/ui/ggui/CMakeFiles/taichi_ui_ggui.dir/window.cpp.o
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
  File "/root/.cache/ti-build-cache/miniforge/envs/3.10/lib/python3.10/site-packages/skbuild/setuptools_wrap.py", line 668, in setup
    cmkr.make(make_args, install_target=cmake_install_target, env=env)
  File "/root/.cache/ti-build-cache/miniforge/envs/3.10/lib/python3.10/site-packages/skbuild/cmaker.py", line 696, in make
    self.make_impl(clargs=clargs, config=config, source_dir=source_dir, install_target=install_target, env=env)
  File "/root/.cache/ti-build-cache/miniforge/envs/3.10/lib/python3.10/site-packages/skbuild/cmaker.py", line 741, in make_impl
    raise SKBuildError(msg)

An error occurred while building with CMake.
  Command:
    /root/.cache/ti-build-cache/miniforge/envs/3.10/lib/python3.10/site-packages/cmake/data/bin/cmake --build . --target install --config Release -- -j12
  Install target:
    install
  Source directory:
    /opt/taichi
  Working directory:
    /opt/taichi/_skbuild/linux-aarch64-3.10/cmake-build
Please check the install target is valid and see CMake's output for more information.

!! -----EXCEPTION Build Taichi Wheel-----
Traceback (most recent call last):
  File "/opt/taichi/./build.py", line 11, in <module>
    sys.exit(ti_build.entry.main())
  File "/opt/taichi/.github/workflows/scripts/ti_build/entry.py", line 196, in main
    dispatch.get(options.action, action_notimpl)()
  File "/opt/taichi/.github/workflows/scripts/ti_build/entry.py", line 106, in action_wheel
    build_wheel(python, pip)
  File "/opt/taichi/.github/workflows/scripts/ti_build/misc.py", line 67, in wrapper
    ret = f(*args, **kwargs)
  File "/opt/taichi/.github/workflows/scripts/ti_build/entry.py", line 70, in build_wheel
    python("setup.py", *proj_tags, "bdist_wheel", *extra)
  File "/opt/taichi/.github/workflows/scripts/ti_build/tinysh.py", line 160, in __call__
    raise CommandFailed(cmd, code)
ti_build.tinysh.CommandFailed: Command nice /root/.cache/ti-build-cache/miniforge/envs/3.10/bin/python setup.py bdist_wheel -p manylinux_2_28_aarch64 failed with code 1
The command '/bin/sh -c /tmp/TAICHI/install.sh || /tmp/TAICHI/build.sh' returned a non-zero code: 1
Traceback (most recent call last):
  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "/home/johnny/Projects/jetson-containers/jetson_containers/build.py", line 112, in <module>
    build_container(args.name, args.packages, args.base, args.build_flags, args.build_args, args.simulate, args.skip_tests, args.test_only, args.push, args.no_github_api, args.skip_packages)
  File "/home/johnny/Projects/jetson-containers/jetson_containers/container.py", line 147, in build_container
    status = subprocess.run(cmd.replace(_NEWLINE_, ' '), executable='/bin/bash', shell=True, check=True)  
  File "/usr/lib/python3.10/subprocess.py", line 526, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command 'DOCKER_BUILDKIT=0 docker build --network=host --tag genesis:r36.4.3-cu126-cp310-taichi --file /home/johnny/Projects/jetson-containers/packages/robots/genesis/taichi/Dockerfile --build-arg BASE_IMAGE=genesis:r36.4.3-cu126-cp310-ninja --build-arg CUDAARCHS="87" --build-arg TAICHI_VERSION="1.7.4" /home/johnny/Projects/jetson-containers/packages/robots/genesis/taichi 2>&1 | tee /home/johnny/Projects/jetson-containers/logs/20250202_190455/build/genesis_r36.4.3-cu126-cp310-taichi.txt; exit ${PIPESTATUS[0]}' returned non-zero exit status 1.

Additional comments
#8629

vulkan sdk arm from my builds it is working...