[PATCH] D114765: [X86][FP16] Only generate approximate rsqrt when Reciprocal is true for half type
Craig Topper via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 29 18:59:51 PST 2021
craig.topper added a comment.
In D114765#3160245 <https://reviews.llvm.org/D114765#3160245>, @pengfei wrote:
> In D114765#3160232 <https://reviews.llvm.org/D114765#3160232>, @craig.topper wrote:
>
>> What's the correctness issue? It's fast math so the answer isn't required to be exact.
>
> See https://godbolt.org/z/P4Y89hsj4
> I guess we need at least `RefinementSteps = 1` for correntness when `Reciprocal == 0`.
That seems like a more general bug. The same issue happens if you force the estimate steps for floating point https://godbolt.org/z/vK8eab8zP
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D114765/new/
https://reviews.llvm.org/D114765
More information about the llvm-commits
mailing list