[RISCV][CostModel] Make VMV_S_X and VMV_X_S cost independent of LMUL (#78739)

Following #77963, instructions like VMV_S_X/VMV_X_S 
handle single element, so the cost don't scale with LMUL.

Author: arcbbb

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -84,6 +84,10 @@ RISCVTTIImpl::getRISCVInstructionCost(ArrayRef<unsigned> OpCodes, MVT VT,
       Cost += VL;
       break;
     }
+    case RISCV::VMV_X_S:
+    case RISCV::VMV_S_X:
+      Cost += 1;
+      break;
     default:
       Cost += LMULCost;
     }
@@ -446,7 +450,7 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
     // should be a very small constant for the constant pool load.  As such,
     // we may bias towards large selects slightly more than truely warranted.
     return LT.first *
-           (2 + getRISCVInstructionCost({RISCV::VMERGE_VVM},
+           (1 + getRISCVInstructionCost({RISCV::VMV_S_X, RISCV::VMERGE_VVM},
                                         LT.second, CostKind));
   }
   case TTI::SK_Broadcast: {
@@ -475,10 +479,9 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
 
       return LT.first *
              (TLI->getLMULCost(LT.second) + // FIXME: this should be 1 for andi
-              TLI->getLMULCost(
-                  LT.second) + // FIXME: vmv.x.s is the same as extractelement
               getRISCVInstructionCost({RISCV::VMV_V_I, RISCV::VMERGE_VIM,
-                                       RISCV::VMV_V_X, RISCV::VMSNE_VI},
+                                       RISCV::VMV_X_S, RISCV::VMV_V_X,
+                                       RISCV::VMSNE_VI},
                                       LT.second, CostKind));
     }
 

llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll

@@ -14,7 +14,7 @@ define void  @vector_broadcast() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = shufflevector <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = shufflevector <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %7 = shufflevector <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %8 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %8 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %9 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %10 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %11 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
@@ -29,7 +29,7 @@ define void  @vector_broadcast() {
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %5 = shufflevector <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = shufflevector <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i32> zeroinitializer
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = shufflevector <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %8 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %8 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %9 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %10 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %11 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer

llvm/test/Analysis/CostModel/RISCV/shuffle-broadcast.ll

@@ -45,9 +45,9 @@ define void  @broadcast_scalable() #0{
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %38 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %39 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %40 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %41 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %42 = shufflevector <vscale x 32 x i1> undef, <vscale x 32 x i1> undef, <vscale x 32 x i32> zeroinitializer
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %43 = shufflevector <vscale x 64 x i1> undef, <vscale x 64 x i1> undef, <vscale x 64 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %41 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %42 = shufflevector <vscale x 32 x i1> undef, <vscale x 32 x i1> undef, <vscale x 32 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 41 for instruction: %43 = shufflevector <vscale x 64 x i1> undef, <vscale x 64 x i1> undef, <vscale x 64 x i32> zeroinitializer
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; SIZE-LABEL: 'broadcast_scalable'
@@ -92,9 +92,9 @@ define void  @broadcast_scalable() #0{
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %38 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %39 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %40 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %41 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %42 = shufflevector <vscale x 32 x i1> undef, <vscale x 32 x i1> undef, <vscale x 32 x i32> zeroinitializer
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %43 = shufflevector <vscale x 64 x i1> undef, <vscale x 64 x i1> undef, <vscale x 64 x i32> zeroinitializer
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %41 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %42 = shufflevector <vscale x 32 x i1> undef, <vscale x 32 x i1> undef, <vscale x 32 x i32> zeroinitializer
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %43 = shufflevector <vscale x 64 x i1> undef, <vscale x 64 x i1> undef, <vscale x 64 x i32> zeroinitializer
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %zero = shufflevector <vscale x 1 x half> undef, <vscale x 1 x half> undef, <vscale x 1 x i32> zeroinitializer