tree e8a3ba297c9b09e678386ca1692baf0a6cc35591
parent 55e3ae02ac1f13fbcc7a83f5e37a39fd2b142db1
author Ben Barsdell <bbarsdell@nvidia.com> 1634551094 +1100
committer Ben Barsdell <bbarsdell@nvidia.com> 1636090777 +1100

Avoid integer overflow in EigenMetaKernel indexing

- The current implementation computes `size + total_threads`, which can
  overflow and cause CUDA_ERROR_ILLEGAL_ADDRESS when size is close to
  the maximum representable value.
- The num_blocks calculation can also overflow due to the implementation
  of divup().
- This patch prevents these overflows and allows the kernel to work
  correctly for the full representable range of tensor sizes.
- Also adds relevant tests.