[RISCV][TTI] Scale the cost of ArithmeticInstr with LMUL

Address comments
- Add tests for and,or,xor
- Separate FMUL from FADD group
- Rebase on commit that removes `-riscv-v-fixed-length-vector-lmul-max`

Author: arcbbb

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -1612,29 +1612,58 @@ InstructionCost RISCVTTIImpl::getArithmeticInstrCost(
   if (Op2Info.isConstant())
     ConstantMatCost += getConstantMatCost(1, Op2Info);
 
+  // Assuming instructions falling through the switch-cases have the same cost
+  // until a need arises to differentiate them.
+  unsigned Op;
   switch (TLI->InstructionOpcodeToISD(Opcode)) {
   case ISD::ADD:
   case ISD::SUB:
-  case ISD::AND:
-  case ISD::OR:
-  case ISD::XOR:
+    Op = RISCV::VADD_VV;
+    break;
   case ISD::SHL:
   case ISD::SRL:
   case ISD::SRA:
+    Op = RISCV::VSLL_VV;
+    break;
+  case ISD::AND:
+  case ISD::OR:
+  case ISD::XOR:
+    Op = (Ty->getScalarSizeInBits() == 1) ? RISCV::VMAND_MM : RISCV::VAND_VV;
+    break;
   case ISD::MUL:
   case ISD::MULHS:
   case ISD::MULHU:
+    Op = RISCV::VMUL_VV;
+    break;
+  case ISD::SDIV:
+  case ISD::UDIV:
+    Op = RISCV::VDIV_VV;
+    break;
+  case ISD::SREM:
+  case ISD::UREM:
+    Op = RISCV::VREM_VV;
+    break;
   case ISD::FADD:
   case ISD::FSUB:
+    // TODO: Address FP16 with VFHMIN
+    Op = RISCV::VFADD_VV;
   case ISD::FMUL:
-  case ISD::FNEG: {
-    return ConstantMatCost + TLI->getLMULCost(LT.second) * LT.first * 1;
-  }
+    // TODO: Address FP16 with VFHMIN
+    Op = RISCV::VFMUL_VV;
+    break;
+  case ISD::FDIV:
+    Op = RISCV::VFDIV_VV;
+    break;
+  case ISD::FNEG:
+    Op = RISCV::VFSGNJN_VV;
+    break;
   default:
-    return ConstantMatCost +
-           BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind, Op1Info, Op2Info,
-                                         Args, CxtI);
+    return ConstantMatCost + BaseT::getArithmeticInstrCost(Opcode, Ty, CostKind,
+                                                           Op1Info, Op2Info,
+                                                           Args, CxtI);
   }
+  return ConstantMatCost +
+         LT.first * getRISCVInstructionCost(Op, LT.second, CostKind);
 }
 
 // TODO: Deduplicate from TargetTransformInfoImplCRTPBase.

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

@@ -248,36 +248,36 @@ define i32 @fdiv() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F16 = fdiv half undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F32 = fdiv float undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %F64 = fdiv double undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V1F16 = fdiv <1 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F16 = fdiv <2 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F16 = fdiv <4 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F16 = fdiv <8 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F16 = fdiv <16 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F16 = fdiv <1 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F16 = fdiv <2 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F16 = fdiv <4 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8F16 = fdiv <8 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16F16 = fdiv <16 x half> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32F16 = fdiv <32 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV1F16 = fdiv <vscale x 1 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV2F16 = fdiv <vscale x 2 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV4F16 = fdiv <vscale x 4 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NXV1F16 = fdiv <vscale x 1 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NXV2F16 = fdiv <vscale x 2 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NXV4F16 = fdiv <vscale x 4 x half> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV8F16 = fdiv <vscale x 8 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV32F16 = fdiv <vscale x 32 x half> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V1F32 = fdiv <1 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F32 = fdiv <2 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = fdiv <4 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F32 = fdiv <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NXV16F16 = fdiv <vscale x 16 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NXV32F16 = fdiv <vscale x 32 x half> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F32 = fdiv <1 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F32 = fdiv <2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4F32 = fdiv <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8F32 = fdiv <8 x float> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16F32 = fdiv <16 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV1F32 = fdiv <vscale x 1 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV2F32 = fdiv <vscale x 2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NXV1F32 = fdiv <vscale x 1 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NXV2F32 = fdiv <vscale x 2 x float> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV4F32 = fdiv <vscale x 4 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV8F32 = fdiv <vscale x 8 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV16F32 = fdiv <vscale x 16 x float> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V1F64 = fdiv <1 x double> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = fdiv <2 x double> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = fdiv <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NXV8F32 = fdiv <vscale x 8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NXV16F32 = fdiv <vscale x 16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1F64 = fdiv <1 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2F64 = fdiv <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4F64 = fdiv <4 x double> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8F64 = fdiv <8 x double> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV1F64 = fdiv <vscale x 1 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %NXV1F64 = fdiv <vscale x 1 x double> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV2F64 = fdiv <vscale x 2 x double> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV4F64 = fdiv <vscale x 4 x double> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %NXV8F64 = fdiv <vscale x 8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %NXV4F64 = fdiv <vscale x 4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %NXV8F64 = fdiv <vscale x 8 x double> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %F16 = fdiv half undef, undef