[PATCH] D153472: AMDGPU: Correctly expand f64 sqrt intrinsic

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp:4844
+  // For double type, the SQRT and RSQ instructions don't have required
+  // precision, we apply Goldschmidt's algorithm to improve the result:
+  //
----------------
Pierre-vh wrote:
> Add that they fail OCL conformance + many users avoid using it because of that, just for some context.
Seems like historical noise that doesn't explain what's going on


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153472/new/

https://reviews.llvm.org/D153472