Addressing reviewers.

Comparing against the default cost, and no longer restricting to
scalable types.

Author: paschalis-mpeis

llvm/lib/Analysis/TargetTransformInfo.cpp

@@ -17,6 +17,7 @@
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Operator.h"
+#include "llvm/IR/PatternMatch.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Support/CommandLine.h"
 #include <optional>

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -6950,24 +6950,27 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
         Legal->isInvariant(Op2))
       Op2Info.Kind = TargetTransformInfo::OK_UniformValue;
 
+    SmallVector<const Value *, 4> Operands(I->operand_values());
+    auto InstrCost = TTI.getArithmeticInstrCost(
+        I->getOpcode(), VectorTy, CostKind,
+        {TargetTransformInfo::OK_AnyValue, TargetTransformInfo::OP_None},
+        Op2Info, Operands, I);
+
     // Some targets replace frem with vector library calls.
-    if (I->getOpcode() == Instruction::FRem && VectorTy->isScalableTy()) {
+    if (I->getOpcode() == Instruction::FRem) {
       LibFunc Func;
       if (TLI->getLibFunc(I->getOpcode(), I->getType(), Func)) {
         if (TLI->isFunctionVectorizable(TLI->getName(Func))) {
           SmallVector<Type *, 4> OpTypes;
           for (auto &Op : I->operands())
             OpTypes.push_back(Op->getType());
-          return TTI.getCallInstrCost(nullptr, VectorTy, OpTypes, CostKind);
+          auto CallCost =
+              TTI.getCallInstrCost(nullptr, VectorTy, OpTypes, CostKind);
+          return std::min(InstrCost, CallCost);
         }
       }
     }
-
-    SmallVector<const Value *, 4> Operands(I->operand_values());
-    return TTI.getArithmeticInstrCost(
-        I->getOpcode(), VectorTy, CostKind,
-        {TargetTransformInfo::OK_AnyValue, TargetTransformInfo::OP_None},
-        Op2Info, Operands, I);
+    return InstrCost;
   }
   case Instruction::FNeg: {
     return TTI.getArithmeticInstrCost(

llvm/test/Analysis/CostModel/AArch64/arith-fp-sve.ll

@@ -1,8 +1,7 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 4
-; RUN: opt -mattr=+sve -mattr=+fullfp16 -enable-no-nans-fp-math -disable-output -passes="print<cost-model>" %s 2>&1 | FileCheck %s
-
-target triple = "aarch64-unknown-linux-gnu"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -enable-no-nans-fp-math -passes="print<cost-model>" 2>&1 -disable-output -mtriple=aarch64 -mattr=+fullfp16 -mattr=+sve | FileCheck %s
 
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 
 define void @fadd() {
 ; CHECK-LABEL: 'fadd'

llvm/test/Analysis/CostModel/AArch64/arith-fp.ll

@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -enable-no-nans-fp-math  -passes="print<cost-model>" 2>&1 -disable-output -mtriple=aarch64 -mattr=+fullfp16 | FileCheck %s
 
-target triple = "aarch64-unknown-linux-gnu"
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 
 define i32 @fadd(i32 %arg) {
 ; CHECK-LABEL: 'fadd'