[PATCH] D29942: Add custom lowering for llvm.log{, 10}.{f16, f32} intrinsics

[Jan Vesely via Phabricator via llvm-commits]

jvesely added inline comments.


================
Comment at: lib/Target/AMDGPU/AMDGPUISelLowering.cpp:1895
 
+SDValue AMDGPUTargetLowering::LowerFLOG(SDValue Op, SelectionDAG &DAG) const {
+  EVT VT = Op.getValueType();
----------------
You can pass the log2base constant here to avoid second switch and simplify the code. Just a nitpick


================
Comment at: lib/Target/AMDGPU/AMDGPUISelLowering.cpp:1914
+
+  return DAG.getNode(ISD::FDIV, SL, VT, Log2Operand, Log2Base);
+}
----------------
Using FMUL and inverted Log2Base should be both faster and more precise.


https://reviews.llvm.org/D29942