[PATCH] D154790: [HIP] Use native math functions for `-fcuda-approx-transcendentals`

[Brian Sumner via Phabricator via cfe-commits]

b-sumner added inline comments.


================
Comment at: clang/lib/Headers/__clang_hip_math.h:304
+__DEVICE__
+float __tanf(float __x) { return __ocml_tan_f32(__x); }
+// END INTRINSICS
----------------
We could consider multiplying native_sin here with the native_recip of native_cos.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D154790/new/

https://reviews.llvm.org/D154790