[llvm-branch-commits] [llvm] InstCombine: Handle rounding intrinsics in SimplifyDemandedFPClass (PR #174842)

[Yingwei Zheng via llvm-branch-commits]

================
@@ -2548,6 +2548,72 @@ Value *InstCombinerImpl::SimplifyDemandedUseFPClass(Value *V,
 
       return getFPClassConstant(VTy, ValidResults, /*IsCanonicalizing=*/true);
     }
+    case Intrinsic::trunc:
+    case Intrinsic::floor:
+    case Intrinsic::ceil:
+    case Intrinsic::rint:
+    case Intrinsic::nearbyint:
+    case Intrinsic::round:
+    case Intrinsic::roundeven: {
+      FPClassTest DemandedSrcMask = DemandedMask;
+
+      // Zero results imply valid subnormal sources.
+      if (DemandedMask & fcNegZero)
+        DemandedSrcMask |= fcNegSubnormal;
+
+      if (DemandedMask & fcPosZero)
+        DemandedSrcMask |= fcPosSubnormal;
+
+      KnownFPClass KnownSrc;
+      if (SimplifyDemandedFPClass(CI, 0, DemandedSrcMask, KnownSrc, Depth + 1))
+        return I;
+
+      // Note: Possibly dropping snan quiet.
+      if (KnownSrc.isKnownAlways(fcInf | fcNan))
----------------
dtcxzyw wrote:

It also holds for fcZero.

https://github.com/llvm/llvm-project/pull/174842