[BUG] Failing to build on MSVC due to call to _div128 #1571
Description
Summary
pytorch/pytorch#125204
Is failing on windows with:
2024-06-03T10:06:46.7711483Z C:/cb/pytorch_1000000000000/work/aten/src/ATen/../../../third_party/cutlass/include\cutlass/uint128.h(189): error: calling a __host__ function("_udiv128") from a __host__ __device__ function("cutlass::uint128_t::operator / const") is not allowed
2024-06-03T10:06:46.7712785Z
2024-06-03T10:06:46.7713366Z 1 error detected in the compilation of "C:/cb/pytorch_1000000000000/work/aten/src/ATen/native/cuda/RowwiseScaledMM.cu".
2024-06-03T10:06:46.7715339Z C:/cb/pytorch_1000000000000/work/aten/src/ATen/../../../third_party/cutlass/include\cutlass/uint128.h(189): error: calling a __host__ function("_udiv128") from a __host__ __device__ function("cutlass::uint128_t::operator / const") is not allowedI feel like there a few options here to fix but not sure what is best, perhaps just not calling the intrinsic on windows?