[AArch64] Report icmp as free if it can be folded into ands (llvm#143286)

Since changing the backend to fold x >= 1 / x < 1 -> x > 0 / x <= 0 and
x <= -1 / x > -1 -> x > 0 / x <= 0, this should be reflected in the
cost.

Author: AZero13

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -4353,15 +4353,26 @@ InstructionCost AArch64TTIImpl::getCmpSelInstrCost(
     }
   }
 
-  // Treat the icmp in icmp(and, 0) as free, as we can make use of ands.
-  // FIXME: This can apply to more conditions and add/sub if it can be shown to
-  // be profitable.
+  // Treat the icmp in icmp(and, 0) or icmp(and, -1/1) when it can be folded to
+  // icmp(and, 0) as free, as we can make use of ands, but only if the
+  // comparison is not unsigned.
   if (ValTy->isIntegerTy() && ISD == ISD::SETCC && I &&
-      ICmpInst::isEquality(VecPred) &&
+      !CmpInst::isUnsigned(VecPred) &&
       TLI->isTypeLegal(TLI->getValueType(DL, ValTy)) &&
-      match(I->getOperand(1), m_Zero()) &&
-      match(I->getOperand(0), m_And(m_Value(), m_Value())))
-    return 0;
+      match(I->getOperand(0), m_And(m_Value(), m_Value()))) {
+    if (match(I->getOperand(1), m_Zero()))
+      return 0;
+
+    // x >= 1 / x < 1 -> x > 0 / x <= 0
+    if (match(I->getOperand(1), m_One()) &&
+        (VecPred == CmpInst::ICMP_SLT || VecPred == CmpInst::ICMP_SGE))
+      return 0;
+
+    // x <= -1 / x > -1 -> x > 0 / x <= 0
+    if (match(I->getOperand(1), m_AllOnes()) &&
+        (VecPred == CmpInst::ICMP_SLE || VecPred == CmpInst::ICMP_SGT))
+      return 0;
+  }
 
   // The base case handles scalable vectors fine for now, since it treats the
   // cost as 1 * legalization cost.

llvm/test/Analysis/CostModel/AArch64/cmp.ll

@@ -53,6 +53,14 @@ define void @andcmp() {
 ; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c32 = icmp eq i32 %a32, 0
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %a64 = and i64 undef, undef
 ; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c64 = icmp ne i64 %a64, 0
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c32ge = icmp sge i32 %a32, 1
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c32le = icmp slt i32 %a32, 1
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c32leneg = icmp sle i32 %a32, -1
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c32gtneg = icmp sgt i32 %a32, -1
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c64ge = icmp sge i64 %a64, 1
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c64le = icmp slt i64 %a64, 1
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c64leneg = icmp sle i64 %a64, -1
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c64gtneg = icmp sgt i64 %a64, -1
 ; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %a128 = and i128 undef, undef
 ; CHECK-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:1 Lat:1 SizeLat:1 for: %c128 = icmp eq i128 %a128, 0
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %av16i8 = and <16 x i8> undef, undef
@@ -62,7 +70,7 @@ define void @andcmp() {
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %av4i32 = and <4 x i32> undef, undef
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %cv4i32 = icmp ne <4 x i32> %av4i32, zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found costs of 1 for: %c32not0 = icmp eq i32 %a32, 1
-; CHECK-NEXT:  Cost Model: Found costs of 1 for: %c64sle = icmp sle i64 %a64, 0
+; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: %c64sle = icmp sle i64 %a64, 0
 ; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
 ;
   %a8 = and i8 undef, undef
@@ -73,6 +81,17 @@ define void @andcmp() {
   %c32 = icmp eq i32 %a32, 0
   %a64 = and i64 undef, undef
   %c64 = icmp ne i64 %a64, 0
+
+  %c32ge = icmp sge i32 %a32, 1
+  %c32le = icmp slt i32 %a32, 1
+  %c32leneg = icmp sle i32 %a32, -1
+  %c32gtneg  = icmp sgt i32 %a32, -1
+
+  %c64ge = icmp sge i64 %a64, 1
+  %c64le = icmp slt i64 %a64, 1
+  %c64leneg = icmp sle i64 %a64, -1
+  %c64gtneg  = icmp sgt i64 %a64, -1
+
   %a128 = and i128 undef, undef
   %c128 = icmp eq i128 %a128, zeroinitializer
   %av16i8 = and <16 x i8> undef, undef