diff --git a/compile_failures/legate_issue_959_oct_29_2024_after_patch.txt b/compile_failures/legate_issue_959_oct_29_2024_after_patch.txt new file mode 100644 index 0000000..1fc94a2 --- /dev/null +++ b/compile_failures/legate_issue_959_oct_29_2024_after_patch.txt @@ -0,0 +1,165 @@ +[224/308] Building CXX object _deps/legion-build/runtime/CMakeFiles/LegionRuntime.dir/legion/legion_analysis.cc.o +In file included from /usr/include/c++/13/bits/specfun.h:43, + from /usr/include/c++/13/cmath:3699, + from /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-src/runtime/legion/legion_analysis.cc:16: +In static member function ‘static _Up* std::__copy_move<_IsMove, true, std::random_access_iterator_tag>::__copy_m(_Tp*, _Tp*, _Up*) [with _Tp = Legion::Internal::CopyFillAggregator::CopyUpdate*; _Up = Legion::Internal::CopyFillAggregator::CopyUpdate*; bool _IsMove = false]’, + inlined from ‘_OI std::__copy_move_a2(_II, _II, _OI) [with bool _IsMove = false; _II = Legion::Internal::CopyFillAggregator::CopyUpdate**; _OI = Legion::Internal::CopyFillAggregator::CopyUpdate**]’ at /usr/include/c++/13/bits/stl_algobase.h:506:30, + inlined from ‘_OI std::__copy_move_a1(_II, _II, _OI) [with bool _IsMove = false; _II = Legion::Internal::CopyFillAggregator::CopyUpdate**; _OI = Legion::Internal::CopyFillAggregator::CopyUpdate**]’ at /usr/include/c++/13/bits/stl_algobase.h:533:42, + inlined from ‘_OI std::__copy_move_a(_II, _II, _OI) [with bool _IsMove = false; _II = __gnu_cxx::__normal_iterator >; _OI = Legion::Internal::CopyFillAggregator::CopyUpdate**]’ at /usr/include/c++/13/bits/stl_algobase.h:540:31, + inlined from ‘_OI std::copy(_II, _II, _OI) [with _II = __gnu_cxx::__normal_iterator >; _OI = Legion::Internal::CopyFillAggregator::CopyUpdate**]’ at /usr/include/c++/13/bits/stl_algobase.h:633:7, + inlined from ‘static _ForwardIterator std::__uninitialized_copy::__uninit_copy(_InputIterator, _InputIterator, _ForwardIterator) [with _InputIterator = __gnu_cxx::__normal_iterator >; _ForwardIterator = Legion::Internal::CopyFillAggregator::CopyUpdate**]’ at /usr/include/c++/13/bits/stl_uninitialized.h:147:27, + inlined from ‘_ForwardIterator std::uninitialized_copy(_InputIterator, _InputIterator, _ForwardIterator) [with _InputIterator = __gnu_cxx::__normal_iterator >; _ForwardIterator = Legion::Internal::CopyFillAggregator::CopyUpdate**]’ at /usr/include/c++/13/bits/stl_uninitialized.h:185:15, + inlined from ‘_ForwardIterator std::__uninitialized_copy_a(_InputIterator, _InputIterator, _ForwardIterator, allocator<_Tp>&) [with _InputIterator = __gnu_cxx::__normal_iterator >; _ForwardIterator = Legion::Internal::CopyFillAggregator::CopyUpdate**; _Tp = Legion::Internal::CopyFillAggregator::CopyUpdate*]’ at /usr/include/c++/13/bits/stl_uninitialized.h:373:37, + inlined from ‘void std::vector<_Tp, _Alloc>::_M_range_insert(iterator, _ForwardIterator, _ForwardIterator, std::forward_iterator_tag) [with _ForwardIterator = __gnu_cxx::__normal_iterator >; _Tp = Legion::Internal::CopyFillAggregator::CopyUpdate*; _Alloc = std::allocator]’ at /usr/include/c++/13/bits/vector.tcc:814:38, + inlined from ‘std::vector<_Tp, _Alloc>::iterator std::vector<_Tp, _Alloc>::insert(const_iterator, _InputIterator, _InputIterator) [with _InputIterator = __gnu_cxx::__normal_iterator >; = void; _Tp = Legion::Internal::CopyFillAggregator::CopyUpdate*; _Alloc = std::allocator]’ at /usr/include/c++/13/bits/stl_vector.h:1483:19, + inlined from ‘void Legion::Internal::CopyFillAggregator::issue_copies(Legion::Internal::InstanceView*, std::map >&, std::set&, Legion::Internal::ApEvent, const Legion::Internal::FieldMask&, const Legion::Internal::PhysicalTraceInfo&, bool, bool, std::vector*)’ at /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-src/runtime/legion/legion_analysis.cc:7339:28: +/usr/include/c++/13/bits/stl_algobase.h:437:30: warning: ‘void* __builtin_memmove(void*, const void*, long unsigned int)’ writing between 9 and 9223372036854775800 bytes into a region of size 0 overflows the destination [-Wstringop-overflow=] + 437 | __builtin_memmove(__result, __first, sizeof(_Tp) * _Num); + | ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +In file included from /usr/include/c++/13/aarch64-suse-linux/bits/c++allocator.h:33, + from /usr/include/c++/13/bits/allocator.h:46, + from /usr/include/c++/13/bits/stl_tree.h:64, + from /usr/include/c++/13/map:62, + from /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-src/runtime/legion/legion_types.h:30, + from /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-src/runtime/legion.h:56, + from /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-src/runtime/legion/legion_analysis.cc:17: +In member function ‘_Tp* std::__new_allocator<_Tp>::allocate(size_type, const void*) [with _Tp = Legion::Internal::InstanceView*]’, + inlined from ‘static _Tp* std::allocator_traits >::allocate(allocator_type&, size_type) [with _Tp = Legion::Internal::InstanceView*]’ at /usr/include/c++/13/bits/alloc_traits.h:482:28, + inlined from ‘std::_Vector_base<_Tp, _Alloc>::pointer std::_Vector_base<_Tp, _Alloc>::_M_allocate(std::size_t) [with _Tp = Legion::Internal::InstanceView*; _Alloc = std::allocator]’ at /usr/include/c++/13/bits/stl_vector.h:378:33, + inlined from ‘std::_Vector_base<_Tp, _Alloc>::pointer std::_Vector_base<_Tp, _Alloc>::_M_allocate(std::size_t) [with _Tp = Legion::Internal::CopyFillAggregator::CopyUpdate*; _Alloc = std::allocator]’ at /usr/include/c++/13/bits/stl_vector.h:375:7, + inlined from ‘void std::vector<_Tp, _Alloc>::_M_range_insert(iterator, _ForwardIterator, _ForwardIterator, std::forward_iterator_tag) [with _ForwardIterator = __gnu_cxx::__normal_iterator >; _Tp = Legion::Internal::CopyFillAggregator::CopyUpdate*; _Alloc = std::allocator]’ at /usr/include/c++/13/bits/vector.tcc:805:40, + inlined from ‘std::vector<_Tp, _Alloc>::iterator std::vector<_Tp, _Alloc>::insert(const_iterator, _InputIterator, _InputIterator) [with _InputIterator = __gnu_cxx::__normal_iterator >; = void; _Tp = Legion::Internal::CopyFillAggregator::CopyUpdate*; _Alloc = std::allocator]’ at /usr/include/c++/13/bits/stl_vector.h:1483:19, + inlined from ‘void Legion::Internal::CopyFillAggregator::issue_copies(Legion::Internal::InstanceView*, std::map >&, std::set&, Legion::Internal::ApEvent, const Legion::Internal::FieldMask&, const Legion::Internal::PhysicalTraceInfo&, bool, bool, std::vector*)’ at /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-src/runtime/legion/legion_analysis.cc:7339:28: +/usr/include/c++/13/bits/new_allocator.h:151:55: note: at offset [-9223372036854775808, -1] into destination object of size [8, 9223372036854775800] allocated by ‘operator new’ + 151 | return static_cast<_Tp*>(_GLIBCXX_OPERATOR_NEW(__n * sizeof(_Tp))); + | ^ +[295/308] Building CUDA object src/cpp/CMakeFiles/legate.dir/legate/comm/detail/comm_nccl.cu.o +FAILED: src/cpp/CMakeFiles/legate.dir/legate/comm/detail/comm_nccl.cu.o +/opt/nvidia/hpc_sdk/Linux_aarch64/24.7/cuda/12.5/bin/nvcc -forward-unknown-to-host-compiler -DFMT_SHARED -DTHRUST_DEVICE_SYSTEM=THRUST_DEVICE_SYSTEM_CUDA -DTHRUST_HOST_SYSTEM=THRUST_HOST_SYSTEM_CPP -DUSE_CUDA -DUSE_HDF -Dlegate_EXPORTS -I/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp -I/lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/src/cpp/include/legate -I/lustre/vescratch1/treddy/custom_nvidia/legate/share/legate/mpi_wrapper/src -isystem /opt/cray/pe/mpich/8.1.30/ofi/gnu/12.3/include -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/cccl-src/thrust/thrust/cmake/../.. -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/cccl-src/libcudacxx/lib/cmake/libcudacxx/../../../include -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/cccl-src/cub/cub/cmake/../.. -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-src/runtime -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-src/runtime/mappers -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/legion-build/runtime -isystem /opt/nvidia/hpc_sdk/Linux_aarch64/24.7/cuda/12.5/targets/sbsa-linux/include -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/mdspan-src/include -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/span-src/include -isystem /lustre/vescratch1/treddy/tyler_conda/conda_scratch/envs/legate_custom/include -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/fmt-src/include -isystem /lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/cmake_build/_deps/argparse-src/include --compiler-options=-O3 -O2 -std=c++17 -arch=all-major -Xcompiler=-fPIC -Xfatbin=-compress-all --expt-extended-lambda --expt-relaxed-constexpr -Wno-deprecated-gpu-targets -MD -MT src/cpp/CMakeFiles/legate.dir/legate/comm/detail/comm_nccl.cu.o -MF src/cpp/CMakeFiles/legate.dir/legate/comm/detail/comm_nccl.cu.o.d -x cu -c /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/comm/detail/comm_nccl.cu -o src/cpp/CMakeFiles/legate.dir/legate/comm/detail/comm_nccl.cu.o +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/variant_helper.h: In instantiation of ‘static void legate::detail::VariantHelper::record(const legate::Library&, legate::TaskInfo*, const std::map&) [with T = legate::detail::comm::nccl::InitId; SELECTOR = legate::detail::GPUVariant]’: +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:55:64: required from ‘static std::unique_ptr legate::LegateTask::create_task_info_(const legate::Library&, const std::map&) [with T = legate::detail::comm::nccl::InitId]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:44:37: required from ‘static void legate::LegateTask::register_variants(legate::Library, legate::LocalTaskID, const std::map&) [with T = legate::detail::comm::nccl::InitId]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:37:18: required from ‘static void legate::LegateTask::register_variants(legate::Library, const std::map&) [with T = legate::detail::comm::nccl::InitId]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/comm/detail/comm_nccl.cu:277:56: required from here +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/variant_helper.h:135:18: error: no matches converting function ‘task_wrapper_’ to type ‘void (* const)(const void*, std::size_t, const void*, std::size_t, Legion::Processor) {aka void (* const)(const void*, long unsigned int, const void*, long unsigned int, class Realm::Processor)}’ + constexpr void (*entry)( + ^~~~~ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/detail/legion_task.h:37:109: note: candidate is: template&, Legion::Context, Legion::Runtime*), legate::VariantCode variant_kind> static void legate::detail::LegionTask::task_wrapper_(const void*, std::size_t, const void*, std::size_t, Legion::Processor) [with U = U; U (* variant_fn)(const Legion::Task*, const std::vector&, Legion::Context, Legion::Runtime*) = variant_fn; legate::VariantCode variant_kind = ; T = legate::detail::comm::nccl::InitId] + template variant_fn, VariantCode variant_kind> + ^ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/variant_helper.h: In instantiation of ‘static void legate::detail::VariantHelper::record(const legate::Library&, legate::TaskInfo*, const std::map&) [with T = legate::detail::comm::nccl::Init; SELECTOR = legate::detail::GPUVariant]’: +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:55:64: required from ‘static std::unique_ptr legate::LegateTask::create_task_info_(const legate::Library&, const std::map&) [with T = legate::detail::comm::nccl::Init]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:44:37: required from ‘static void legate::LegateTask::register_variants(legate::Library, legate::LocalTaskID, const std::map&) [with T = legate::detail::comm::nccl::Init]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:37:18: required from ‘static void legate::LegateTask::register_variants(legate::Library, const std::map&) [with T = legate::detail::comm::nccl::Init]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/comm/detail/comm_nccl.cu:278:54: required from here +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/variant_helper.h:135:18: error: no matches converting function ‘task_wrapper_’ to type ‘void (* const)(const void*, std::size_t, const void*, std::size_t, Legion::Processor) {aka void (* const)(const void*, long unsigned int, const void*, long unsigned int, class Realm::Processor)}’ + constexpr void (*entry)( + ^~~~~ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/detail/legion_task.h:37:109: note: candidate is: template&, Legion::Context, Legion::Runtime*), legate::VariantCode variant_kind> static void legate::detail::LegionTask::task_wrapper_(const void*, std::size_t, const void*, std::size_t, Legion::Processor) [with U = U; U (* variant_fn)(const Legion::Task*, const std::vector&, Legion::Context, Legion::Runtime*) = variant_fn; legate::VariantCode variant_kind = ; T = legate::detail::comm::nccl::Init] + template variant_fn, VariantCode variant_kind> + ^ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/variant_helper.h: In instantiation of ‘static void legate::detail::VariantHelper::record(const legate::Library&, legate::TaskInfo*, const std::map&) [with T = legate::detail::comm::nccl::Finalize; SELECTOR = legate::detail::GPUVariant]’: +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:55:64: required from ‘static std::unique_ptr legate::LegateTask::create_task_info_(const legate::Library&, const std::map&) [with T = legate::detail::comm::nccl::Finalize]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:44:37: required from ‘static void legate::LegateTask::register_variants(legate::Library, legate::LocalTaskID, const std::map&) [with T = legate::detail::comm::nccl::Finalize]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/task.inl:37:18: required from ‘static void legate::LegateTask::register_variants(legate::Library, const std::map&) [with T = legate::detail::comm::nccl::Finalize]’ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/comm/detail/comm_nccl.cu:279:58: required from here +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/variant_helper.h:135:18: error: no matches converting function ‘task_wrapper_’ to type ‘void (* const)(const void*, std::size_t, const void*, std::size_t, Legion::Processor) {aka void (* const)(const void*, long unsigned int, const void*, long unsigned int, class Realm::Processor)}’ + constexpr void (*entry)( + ^~~~~ +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/task/detail/legion_task.h:37:109: note: candidate is: template&, Legion::Context, Legion::Runtime*), legate::VariantCode variant_kind> static void legate::detail::LegionTask::task_wrapper_(const void*, std::size_t, const void*, std::size_t, Legion::Processor) [with U = U; U (* variant_fn)(const Legion::Task*, const std::vector&, Legion::Context, Legion::Runtime*) = variant_fn; legate::VariantCode variant_kind = ; T = legate::detail::comm::nccl::Finalize] + template variant_fn, VariantCode variant_kind> + ^ +[300/308] Building CUDA object src/cpp/CMakeFiles/legate.dir/legate/partitioning/detail/partitioning_tasks.cu.o +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(50): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_low[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +Remark: The warnings can be suppressed with "-diag-suppress " + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(51): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_high[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(50): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_low[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +Remark: The warnings can be suppressed with "-diag-suppress " + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(51): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_high[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(50): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_low[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +Remark: The warnings can be suppressed with "-diag-suppress " + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(51): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_high[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(50): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_low[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +Remark: The warnings can be suppressed with "-diag-suppress " + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(51): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_high[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(50): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_low[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +Remark: The warnings can be suppressed with "-diag-suppress " + +/lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/partitioning/detail/partitioning_tasks.cu(51): warning #20054-D: dynamic initialization is not supported for a function-scope static __shared__ variable within a __device__/__global__ function + Point block_high[128 / 32]; + ^ + detected during: + instantiation of "void legate::detail::::block_reduce(legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, legate::Point, legate::Point) [with RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, NDIM=1]" at line 117 + instantiation of "void legate::detail::::find_bounding_box_kernel(legate::detail::Unravel, std::size_t, legate::detail::CUDAReductionBuffer, legate::detail::CUDAReductionBuffer, In, legate::Point, legate::Point) [with RECT=true, STORE_NDIM=1, POINT_NDIM=1, RED_LOW=legate::detail::ElementWiseMin<1>, RED_HIGH=legate::detail::ElementWiseMax<1>, In=Legion::FieldAccessor<(Legion::PrivilegeMode)1U, Realm::Rect<1, Legion::coord_t>, 1, long long, Realm::AffineAccessor, 1, long long>, false>]" at line 185 + instantiation of "void legate::detail::::FindBoundingBoxFn::operator()(const legate::TaskContext &, const legate::PhysicalStore &, const legate::PhysicalStore &) [with RECT=true, POINT_NDIM=1, STORE_NDIM=1]" at line 96 of /lustre/vescratch1/treddy/custom_nvidia/legate/src/cpp/legate/utilities/dispatch.h + +[301/308] Building CXX object _deps/legion-build/runtime/CMakeFiles/LegionRuntime.dir/legion/region_tree_2.cc.o +ninja: build stopped: subcommand failed. +make: *** [/lustre/vescratch1/treddy/custom_nvidia/legate/arch-linux-cuda-release/gmakevariables:59: default_all] Error 1