Add minnum / maxnum intrinsics

These are named following the IEEE-754 names for these
functions, rather than the libm fmin / fmax to avoid
possible ambiguities. Some languages may implement something
resembling fmin / fmax which return NaN if either operand is
to propagate errors. These implement the IEEE-754 semantics
of returning the other operand if either is a NaN representing
missing data.

llvm-svn: 220341

2 files changed, 86 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index c2fecde3929..2a14723a040 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -519,6 +519,90 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
       }
     }
     break;
+  case Intrinsic::minnum:
+  case Intrinsic::maxnum: {
+    Value *Arg0 = II->getArgOperand(0);
+    Value *Arg1 = II->getArgOperand(1);
+
+    // fmin(x, x) -> x
+    if (Arg0 == Arg1)
+      return ReplaceInstUsesWith(CI, Arg0);
+
+    const ConstantFP *C0 = dyn_cast<ConstantFP>(Arg0);
+    const ConstantFP *C1 = dyn_cast<ConstantFP>(Arg1);
+
+    // Canonicalize constants into the RHS.
+    if (C0 && !C1) {
+      II->setArgOperand(0, Arg1);
+      II->setArgOperand(1, Arg0);
+      return II;
+    }
+
+    // fmin(x, nan) -> x
+    if (C1 && C1->isNaN())
+      return ReplaceInstUsesWith(CI, Arg0);
+
+    // This is the value because if undef were NaN, we would return the other
+    // value and cannot return a NaN unless both operands are.
+    //
+    // fmin(undef, x) -> x
+    if (isa<UndefValue>(Arg0))
+      return ReplaceInstUsesWith(CI, Arg1);
+
+    // fmin(x, undef) -> x
+    if (isa<UndefValue>(Arg1))
+      return ReplaceInstUsesWith(CI, Arg0);
+
+    Value *X = nullptr;
+    Value *Y = nullptr;
+    if (II->getIntrinsicID() == Intrinsic::minnum) {
+      // fmin(x, fmin(x, y)) -> fmin(x, y)
+      // fmin(y, fmin(x, y)) -> fmin(x, y)
+      if (match(Arg1, m_FMin(m_Value(X), m_Value(Y)))) {
+        if (Arg0 == X || Arg0 == Y)
+          return ReplaceInstUsesWith(CI, Arg1);
+      }
+
+      // fmin(fmin(x, y), x) -> fmin(x, y)
+      // fmin(fmin(x, y), y) -> fmin(x, y)
+      if (match(Arg0, m_FMin(m_Value(X), m_Value(Y)))) {
+        if (Arg1 == X || Arg1 == Y)
+          return ReplaceInstUsesWith(CI, Arg0);
+      }
+
+      // TODO: fmin(nnan x, inf) -> x
+      // TODO: fmin(nnan ninf x, flt_max) -> x
+      if (C1 && C1->isInfinity()) {
+        // fmin(x, -inf) -> -inf
+        if (C1->isNegative())
+          return ReplaceInstUsesWith(CI, Arg1);
+      }
+    } else {
+      assert(II->getIntrinsicID() == Intrinsic::maxnum);
+      // fmax(x, fmax(x, y)) -> fmax(x, y)
+      // fmax(y, fmax(x, y)) -> fmax(x, y)
+      if (match(Arg1, m_FMax(m_Value(X), m_Value(Y)))) {
+        if (Arg0 == X || Arg0 == Y)
+          return ReplaceInstUsesWith(CI, Arg1);
+      }
+
+      // fmax(fmax(x, y), x) -> fmax(x, y)
+      // fmax(fmax(x, y), y) -> fmax(x, y)
+      if (match(Arg0, m_FMax(m_Value(X), m_Value(Y)))) {
+        if (Arg1 == X || Arg1 == Y)
+          return ReplaceInstUsesWith(CI, Arg0);
+      }
+
+      // TODO: fmax(nnan x, -inf) -> x
+      // TODO: fmax(nnan ninf x, -flt_max) -> x
+      if (C1 && C1->isInfinity()) {
+        // fmax(x, inf) -> inf
+        if (!C1->isNegative())
+          return ReplaceInstUsesWith(CI, Arg1);
+      }
+    }
+    break;
+  }
   case Intrinsic::ppc_altivec_lvx:
   case Intrinsic::ppc_altivec_lvxl:
     // Turn PPC lvx -> load if the pointer is known aligned.
diff --git a/llvm/lib/Transforms/Vectorize/BBVectorize.cpp b/llvm/lib/Transforms/Vectorize/BBVectorize.cpp
index 50c3fa41b1d..b4991bc497a 100644
--- a/llvm/lib/Transforms/Vectorize/BBVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/BBVectorize.cpp
@@ -685,6 +685,8 @@ namespace {
       case Intrinsic::trunc:
       case Intrinsic::floor:
       case Intrinsic::fabs:
+      case Intrinsic::minnum:
+      case Intrinsic::maxnum:
         return Config.VectorizeMath;
       case Intrinsic::bswap:
       case Intrinsic::ctpop: