Skip to content
Commit e6686adf authored by Jan Vesely's avatar Jan Vesely Committed by Jan Vesely
Browse files

AMDGPU/EG,CM: Implement fsqrt using recip(rsqrt(x)) instead of x * rsqrt(x)

The old version might be faster on EG (RECIP_IEEE is Trans only),
but it'd need extra corner case checks.
This gives correct corner case behaviour and saves a register.
Fixes OCL CTS sqrt test (1-thread, scalar) on Turks.

Reviewer: arsenm
Differential Revision: https://reviews.llvm.org/D74017
parent 8c3e6af7
Loading
Loading
Loading
Loading
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment