[PATCH] D50633: [AMDGPU] Add new Mode Register pass

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added a comment.

In https://reviews.llvm.org/D50633#1284297, @timcorringham wrote:

> I'm afraid I don't know anything about OpenCL non-default rounding modes - are they set per arithmetic operation or per function?  When will these be needed?


These are set per operation. For example one could use a builtin like convert_int4_rte() or convert_float4_rtp() to perform a conversion with a non-default rounding mode.
And yes, we need them.


Repository:
  rL LLVM

https://reviews.llvm.org/D50633