[AArch64] Avoid materializing 0.0 when generating FP SELECT

Transform `a == 0.0 ? 0.0 : x` to `a == 0.0 ? a : x` and `a != 0.0 ? x : 0.0`
to `a != 0.0 ? x : a` to avoid materializing 0.0 for FCSEL, since it does not
have to be materialized beforehand for FCMP, as it has a form that has 0.0
as an implicit operand.

Differential Revision: https://reviews.llvm.org/D24808

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@284531 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp
index 17cf8e0641ed654738bc660dff1639230ba56d85..8ef6d555b74d411c7272180c94b728e0d14e9c81 100644 (file)
--- a/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -4083,6 +4083,25 @@ SDValue AArch64TargetLowering::LowerSELECT_CC(ISD::CondCode CC, SDValue LHS,
   // clean.  Some of them require two CSELs to implement.
   AArch64CC::CondCode CC1, CC2;
   changeFPCCToAArch64CC(CC, CC1, CC2);
+
+  if (DAG.getTarget().Options.UnsafeFPMath) {
+    // Transform "a == 0.0 ? 0.0 : x" to "a == 0.0 ? a : x" and
+    // "a != 0.0 ? x : 0.0" to "a != 0.0 ? x : a" to avoid materializing 0.0.
+    ConstantFPSDNode *RHSVal = dyn_cast<ConstantFPSDNode>(RHS);
+    if (RHSVal && RHSVal->isZero()) {
+      ConstantFPSDNode *CFVal = dyn_cast<ConstantFPSDNode>(FVal);
+      ConstantFPSDNode *CTVal = dyn_cast<ConstantFPSDNode>(TVal);
+
+      if ((CC == ISD::SETEQ || CC == ISD::SETOEQ || CC == ISD::SETUEQ) &&
+          CTVal && CTVal->isZero())
+        TVal = LHS;
+      else if ((CC == ISD::SETNE || CC == ISD::SETONE || CC == ISD::SETUNE) &&
+               CFVal && CFVal->isZero())
+        FVal = LHS;
+    }
+  }
+
+  // Emit first, and possibly only, CSEL.
   SDValue CC1Val = DAG.getConstant(CC1, dl, MVT::i32);
   SDValue CS1 = DAG.getNode(AArch64ISD::CSEL, dl, VT, TVal, FVal, CC1Val, Cmp);
 

diff --git a/test/CodeGen/AArch64/fcsel-zero.ll b/test/CodeGen/AArch64/fcsel-zero.ll
new file mode 100644 (file)
index 0000000..43e07bf
--- /dev/null
+++ b/test/CodeGen/AArch64/fcsel-zero.ll
@@ -0,0 +1,82 @@
+; Check that 0.0 is not materialized for CSEL when comparing against it.
+
+; RUN: llc -mtriple=aarch64 -o - < %s | FileCheck %s
+
+define float @foeq(float %a, float %b) #0 {
+  %t = fcmp oeq float %a, 0.0
+  %v = select i1 %t, float 0.0, float %b
+  ret float %v
+; CHECK-LABEL: foeq
+; CHECK: fcmp [[R:s[0-9]+]], #0.0
+; CHECK-NEXT: fcsel {{s[0-9]+}}, [[R]], {{s[0-9]+}}, eq
+}
+
+define float @fueq(float %a, float %b) #0 {
+  %t = fcmp ueq float %a, 0.0
+  %v = select i1 %t, float 0.0, float %b
+  ret float %v
+; CHECK-LABEL: fueq
+; CHECK: fcmp [[R:s[0-9]+]], #0.0
+; CHECK-NEXT: fcsel {{s[0-9]+}}, [[R]], {{s[0-9]+}}, eq
+; CHECK-NEXT: fcsel {{s[0-9]+}}, [[R]], {{s[0-9]+}}, vs
+}
+
+define float @fone(float %a, float %b) #0 {
+  %t = fcmp one float %a, 0.0
+  %v = select i1 %t, float %b, float 0.0
+  ret float %v
+; CHECK-LABEL: fone
+; CHECK: fcmp [[R:s[0-9]+]], #0.0
+; CHECK-NEXT: fcsel {{s[0-9]+}}, {{s[0-9]+}}, [[R]], mi
+; CHECK-NEXT: fcsel {{s[0-9]+}}, {{s[0-9]+}}, [[R]], gt
+}
+
+define float @fune(float %a, float %b) #0 {
+  %t = fcmp une float %a, 0.0
+  %v = select i1 %t, float %b, float 0.0
+  ret float %v
+; CHECK-LABEL: fune
+; CHECK: fcmp [[R:s[0-9]+]], #0.0
+; CHECK-NEXT: fcsel {{s[0-9]+}}, {{s[0-9]+}}, [[R]], ne
+}
+
+define double @doeq(double %a, double %b) #0 {
+  %t = fcmp oeq double %a, 0.0
+  %v = select i1 %t, double 0.0, double %b
+  ret double %v
+; CHECK-LABEL: doeq
+; CHECK: fcmp [[R:d[0-9]+]], #0.0
+; CHECK-NEXT: fcsel {{d[0-9]+}}, [[R]], {{d[0-9]+}}, eq
+}
+
+define double @dueq(double %a, double %b) #0 {
+  %t = fcmp ueq double %a, 0.0
+  %v = select i1 %t, double 0.0, double %b
+  ret double %v
+; CHECK-LABEL: dueq
+; CHECK: fcmp [[R:d[0-9]+]], #0.0
+; CHECK-NEXT: fcsel {{d[0-9]+}}, [[R]], {{d[0-9]+}}, eq
+; CHECK-NEXT: fcsel {{d[0-9]+}}, [[R]], {{d[0-9]+}}, vs
+}
+
+define double @done(double %a, double %b) #0 {
+  %t = fcmp one double %a, 0.0
+  %v = select i1 %t, double %b, double 0.0
+  ret double %v
+; CHECK-LABEL: done
+; CHECK: fcmp [[R:d[0-9]+]], #0.0
+; CHECK-NEXT: fcsel {{d[0-9]+}}, {{d[0-9]+}}, [[R]], mi
+; CHECK-NEXT: fcsel {{d[0-9]+}}, {{d[0-9]+}}, [[R]], gt
+}
+
+define double @dune(double %a, double %b) #0 {
+  %t = fcmp une double %a, 0.0
+  %v = select i1 %t, double %b, double 0.0
+  ret double %v
+; CHECK-LABEL: dune
+; CHECK: fcmp [[R:d[0-9]+]], #0.0
+; CHECK-NEXT: fcsel {{d[0-9]+}}, {{d[0-9]+}}, [[R]], ne
+}
+
+attributes #0 = { nounwind "unsafe-fp-math"="true" }
+