| commit | cc3573ab4451853774cd5c3497373d5fe8914774 | [log] [tgz] |
|---|---|---|
| author | Antonio Sanchez <cantonios@google.com> | Tue Aug 31 08:33:19 2021 -0700 |
| committer | Rasmus Munk Larsen <rmlarsen@google.com> | Tue Aug 31 19:13:12 2021 +0000 |
| tree | b2b07e694bbfab6548be8dc95da5f1cb2865d041 | |
| parent | 1415817d8daa7fa72ec9b26a6b9d166a1d54626a [diff] |
Disable cuda Eigen::half vectorization on host. All cuda `__half` functions are device-only in CUDA 9, including conversions. Host-side conversions were added in CUDA 10. The existing code doesn't build prior to 10.0. All arithmetic functions are always device-only, so there's therefore no reason to use vectorization on the host at all. Modified the code to disable vectorization for `__half` on host, which required also updating the `TensorReductionGpu` implementation which previously made assumptions about available packets.
Eigen is a C++ template library for linear algebra: matrices, vectors, numerical solvers, and related algorithms.
For more information go to http://eigen.tuxfamily.org/.
For pull request, bug reports, and feature requests, go to https://gitlab.com/libeigen/eigen.