address comments

Author: Chen Zheng

llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp

@@ -700,15 +700,17 @@ InstructionCost PPCTTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
   } else if (Val->getScalarType()->isIntegerTy()) {
     unsigned EltSize = Val->getScalarSizeInBits();
     // Computing on 1 bit values requires extra mask or compare operations.
-    unsigned MaskCost = VecMaskCost && EltSize == 1 ? 1 : 0;
+    unsigned MaskCostForOneBitSize = (VecMaskCost && EltSize == 1) ? 1 : 0;
+    // Computing on non const index requires extra mask or compare operations.
+    unsigned MaskCostForIdx = (Index != -1U) ? 0 : 1;
     if (ST->hasP9Altivec()) {
       // P10 has vxform insert which can handle non const index. The MaskCost is
       // for masking the index.
       // P9 has insert for const index. A move-to VSR and a permute/insert.
       // Assume vector operation cost for both (cost will be 2x on P9).
       if (ISD == ISD::INSERT_VECTOR_ELT) {
-        if (ST->isISA3_1())
-          return CostFactor + MaskCost;
+        if (ST->hasP10Vector())
+          return CostFactor + MaskCostForIdx;
         else if (Index != -1U)
           return 2 * CostFactor;
       } else if (ISD == ISD::EXTRACT_VECTOR_ELT) {
@@ -725,21 +727,21 @@ InstructionCost PPCTTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
             return 1;
 
           // For other indexs like non const, P9 has vxform extract. The
-          // MaskCost is for masking the index.
-          return CostFactor + MaskCost;
+          // MaskCostForIdx is for masking the index.
+          return CostFactor + MaskCostForIdx;
         }
 
         // We need a vector extract (or mfvsrld).  Assume vector operation cost.
         // The cost of the load constant for a vector extract is disregarded
         // (invariant, easily schedulable).
-        return CostFactor + MaskCost;
+        return CostFactor + MaskCostForOneBitSize + MaskCostForIdx;
       }
     } else if (ST->hasDirectMove() && Index != -1U) {
       // Assume permute has standard cost.
       // Assume move-to/move-from VSR have 2x standard cost.
       if (ISD == ISD::INSERT_VECTOR_ELT)
         return 3;
-      return 3 + MaskCost;
+      return 3 + MaskCostForOneBitSize;
     }
   }
 

llvm/test/Analysis/CostModel/PowerPC/insert_extract.ll

@@ -239,7 +239,7 @@ define <2 x i64> @insert_i64_x(<2 x i64> %dest, i64 %arg, i32 %idx) {
 ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %x
 ;
 ; CHECK-P10-LABEL: 'insert_i64_x'
-; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <2 x i64> %dest, i64 %arg, i32 %idx
+; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = insertelement <2 x i64> %dest, i64 %arg, i32 %idx
 ; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %x
 ;
   %x = insertelement <2 x i64> %dest, i64 %arg, i32 %idx
@@ -264,7 +264,7 @@ define <4 x i32> @insert_i32_x(<4 x i32> %dest, i32 %arg, i32 %idx) {
 ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %x
 ;
 ; CHECK-P10-LABEL: 'insert_i32_x'
-; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <4 x i32> %dest, i32 %arg, i32 %idx
+; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = insertelement <4 x i32> %dest, i32 %arg, i32 %idx
 ; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %x
 ;
   %x = insertelement <4 x i32> %dest, i32 %arg, i32 %idx
@@ -289,7 +289,7 @@ define  <8 x i16> @insert_i16_x(<8 x i16> %dest, i16 %arg, i32 %idx) {
 ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %x
 ;
 ; CHECK-P10-LABEL: 'insert_i16_x'
-; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <8 x i16> %dest, i16 %arg, i32 %idx
+; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = insertelement <8 x i16> %dest, i16 %arg, i32 %idx
 ; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i16> %x
 ;
   %x = insertelement <8 x i16> %dest, i16 %arg, i32 %idx
@@ -314,7 +314,7 @@ define  <16 x i8> @insert_i8_x(<16 x i8> %dest, i8 %arg, i32 %idx) {
 ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %x
 ;
 ; CHECK-P10-LABEL: 'insert_i8_x'
-; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x = insertelement <16 x i8> %dest, i8 %arg, i32 %idx
+; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = insertelement <16 x i8> %dest, i8 %arg, i32 %idx
 ; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x i8> %x
 ;
   %x = insertelement <16 x i8> %dest, i8 %arg, i32 %idx
@@ -331,15 +331,15 @@ define i64 @extract_i64_x(<2 x i64> %arg, i32 %idx) {
 ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %x
 ;
 ; CHECK-P9BE-LABEL: 'extract_i64_x'
-; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
+; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
 ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %x
 ;
 ; CHECK-P9LE-LABEL: 'extract_i64_x'
-; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
+; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
 ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %x
 ;
 ; CHECK-P10-LABEL: 'extract_i64_x'
-; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
+; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <2 x i64> %arg, i32 %idx
 ; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %x
 ;
   %x = extractelement <2 x i64> %arg, i32 %idx
@@ -356,15 +356,15 @@ define i32 @extract_i32_x(<4 x i32> %arg, i32 %idx) {
 ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
 ;
 ; CHECK-P9BE-LABEL: 'extract_i32_x'
-; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
+; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
 ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
 ;
 ; CHECK-P9LE-LABEL: 'extract_i32_x'
-; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
+; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
 ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
 ;
 ; CHECK-P10-LABEL: 'extract_i32_x'
-; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
+; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 %idx
 ; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
 ;
   %x = extractelement <4 x i32> %arg, i32 %idx
@@ -381,15 +381,15 @@ define i16 @extract_i16_x(<8 x i16> %arg, i32 %idx) {
 ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %x
 ;
 ; CHECK-P9BE-LABEL: 'extract_i16_x'
-; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
+; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
 ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %x
 ;
 ; CHECK-P9LE-LABEL: 'extract_i16_x'
-; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
+; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
 ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %x
 ;
 ; CHECK-P10-LABEL: 'extract_i16_x'
-; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
+; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <8 x i16> %arg, i32 %idx
 ; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %x
 ;
   %x = extractelement <8 x i16> %arg, i32 %idx
@@ -406,15 +406,15 @@ define i8 @extract_i8_x(<16 x i8> %arg, i32 %idx) {
 ; CHECK-P8LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i8 %x
 ;
 ; CHECK-P9BE-LABEL: 'extract_i8_x'
-; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
+; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
 ; CHECK-P9BE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i8 %x
 ;
 ; CHECK-P9LE-LABEL: 'extract_i8_x'
-; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
+; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
 ; CHECK-P9LE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i8 %x
 ;
 ; CHECK-P10-LABEL: 'extract_i8_x'
-; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
+; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <16 x i8> %arg, i32 %idx
 ; CHECK-P10-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i8 %x
 ;
   %x = extractelement <16 x i8> %arg, i32 %idx