Changpeng Fang 8b46b98b91 AMDGPU: Fix the double rounding issue in v2f64 -> v2f16 conversion (#135659) ...

On targets that support v_cvt_pk_f16_f32 instruction, if we make v2f64
-> v2f16 Legal, we will generate the following sequence of instructions:
  v_cvt_f32_f64_e32 v1, s[6:7]
  v_cvt_f32_f64_e32 v2, s[4:5]
  v_cvt_pk_f16_f32 v1, v2, v1
It possibly returns imprecise results due to double rounding. This patch
fixes the issue by not setting the conversion Legal. While we may still
expect the above sequence of code when unsafe fpmath is set, I hope
https://github.com/llvm/llvm-project/pull/134738 can address that
performance concern.

Fixes: SWDEV-523856

2025-04-17 11:15:49 -07:00

274 KiB

Raw Blame History

View Raw