commit | f975b6103d381555a48e93bbeabe4b44f7f29aa3 | [log] [tgz] |
---|---|---|
author | Zahira Ammarguellat <zahira.ammarguellat@intel.com> | Wed Nov 17 11:53:36 2021 -0500 |
committer | Copybara-Service <copybara-worker@google.com> | Fri Nov 19 06:06:31 2021 -0800 |
tree | 71d62c8f66af78c116632132d36e2b22ecc8509b | |
parent | f49dbe585138f203bcc517aefc350d2a055162a6 [diff] |
The _Float16 type is supported on x86 systems with SSE2 enabled. Operations are emulated by software emulation and “float” instructions. This patch is allowing the support of _Float16 type without the use of -max512fp16 flag. The final goal being, perform _Float16 emulation for all arithmetic expressions. GitOrigin-RevId: 6623c02d70c3732dbea59c6d79c69501baf9627b