[BUG]: Host API memory access error in CUB's device_reduce test.

[alliepiper]

Is this a duplicate?

• I confirmed there appear to be no duplicate issues for this bug and that I agree to the Code of Conduct

Type of Bug

Something else

Component

CUB

Describe the bug

https://github.com/NVIDIA/cccl/actions/runs/9606424817/job/26497170841?pr=1879

	compute-sanitizer --tool initcheck --check-device-heap yes --leak-check full --padding 512 --track-stream-ordered-races all --check-warpgroup-mma yes --require-cuda-init no --check-exit-code yes --error-exitcode 1 --nvtx true /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
========= COMPUTE-SANITIZER
========= Host API memory access error at host access to 0x7f7941430200 of size 16 bytes
=========     Uninitialized access at 0x7f7941430200 on access by cudaMemcpy source
=========     Saved host backtrace up to driver entry point at error
=========     Host Frame: [0x2e8fa0]
=========                in /usr/lib/x86_64-linux-gnu/libcuda.so.1
=========     Host Frame:libcudart_static_1310e5fb72b7ef3b631832b7a0c7e3ebdd0f4cc9 [0x144728]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:libcudart_static_58f95088c96b3eda011d739033c2a2afd4fe0cab [0x110931]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:cudaMemcpyAsync [0x16e284]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:void C_A_T_C_H_T_E_M_P_L_A_T_E_T_E_S_T_F_U_N_C_0<metal::list<type_pair<long, long> > >() [0xa4838]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:Catch::RunContext::invokeActiveTestCase() [0x37a12]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:Catch::RunContext::runCurrentTest(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&) [0x4fe77]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:Catch::RunContext::runTest(Catch::TestCase const&) [0x58b5a]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:Catch::Session::runInternal() [0x62fdf]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:Catch::Session::run() [0x635cd]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame:main [0x2b595]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1
=========     Host Frame: [0x23a8f]
=========                in /usr/lib/x86_64-linux-gnu/libc.so.6
=========     Host Frame:__libc_start_main [0x23b48]
=========                in /usr/lib/x86_64-linux-gnu/libc.so.6
=========     Host Frame:_start [0x2e764]
=========                in /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1

How to Reproduce

compute-sanitizer --tool initcheck --check-device-heap yes --leak-check full --padding 512 --track-stream-ordered-races all --check-warpgroup-mma yes --require-cuda-init no --check-exit-code yes --error-exitcode 1 --nvtx true /home/coder/cccl/build/cuda12.4-gcc13/cub-cpp17/bin/cub.cpp17.test.device_reduce.lid_2.types_1

Expected behavior

No diagnostics emitted.

Reproduction link

No response

Operating System

No response

nvidia-smi output

No response

NVCC version

No response