Only return a cost estimate for scalable types in AArch64 TTI

Author: huntergr-arm

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -554,7 +554,17 @@ static bool isUnpackedVectorVT(EVT VecVT) {
          VecVT.getSizeInBits().getKnownMinValue() < AArch64::SVEBitsPerBlock;
 }
 
-static InstructionCost getHistogramCost(const IntrinsicCostAttributes &ICA) {
+static InstructionCost getHistogramCost(const AArch64Subtarget *ST,
+                                        const IntrinsicCostAttributes &ICA) {
+  // We need to know at least the number of elements in the vector of buckets
+  // and the size of each element to update.
+  if (ICA.getArgTypes().size() < 2)
+    return InstructionCost::getInvalid();
+
+  // Only interested in costing for the hardware instruction from SVE2.
+  if (!ST->hasSVE2())
+    return InstructionCost::getInvalid();
+
   Type *BucketPtrsTy = ICA.getArgTypes()[0]; // Type of vector of pointers
   Type *EltTy = ICA.getArgTypes()[1];        // Type of bucket elements
   unsigned TotalHistCnts = 1;
@@ -579,9 +589,11 @@ static InstructionCost getHistogramCost(const IntrinsicCostAttributes &ICA) {
 
     unsigned NaturalVectorWidth = AArch64::SVEBitsPerBlock / LegalEltSize;
     TotalHistCnts = EC / NaturalVectorWidth;
+
+    return InstructionCost(BaseHistCntCost * TotalHistCnts);
   }
 
-  return InstructionCost(BaseHistCntCost * TotalHistCnts);
+  return InstructionCost::getInvalid();
 }
 
 InstructionCost
@@ -597,10 +609,13 @@ AArch64TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
       return InstructionCost::getInvalid();
 
   switch (ICA.getID()) {
-  case Intrinsic::experimental_vector_histogram_add:
-    if (!ST->hasSVE2())
-      return InstructionCost::getInvalid();
-    return getHistogramCost(ICA);
+  case Intrinsic::experimental_vector_histogram_add: {
+    InstructionCost HistCost = getHistogramCost(ST, ICA);
+    // If the cost isn't valid, we may still be able to scalarize
+    if (HistCost.isValid())
+      return HistCost;
+    break;
+  }
   case Intrinsic::umin:
   case Intrinsic::umax:
   case Intrinsic::smin:

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

@@ -8,10 +8,10 @@ define void @histograms() {
 ; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> poison, i32 1, <vscale x 4 x i1> poison)
 ; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> poison, i16 1, <vscale x 8 x i1> poison)
 ; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> poison, i8 1, <vscale x 16 x i1> poison)
-; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> poison, i64 1, <2 x i1> poison)
-; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> poison, i32 1, <4 x i1> poison)
-; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> poison, i16 1, <8 x i1> poison)
-; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> poison, i8 1, <16 x i1> poison)
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> poison, i64 1, <2 x i1> poison)
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> poison, i32 1, <4 x i1> poison)
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> poison, i16 1, <8 x i1> poison)
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> poison, i8 1, <16 x i1> poison)
 ; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.uadd.sat.nxv2p0.i64(<vscale x 2 x ptr> poison, i64 1, <vscale x 2 x i1> poison)
 ; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.uadd.sat.nxv4p0.i32(<vscale x 4 x ptr> poison, i32 1, <vscale x 4 x i1> poison)
 ; CHECK-SVE-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.uadd.sat.nxv8p0.i16(<vscale x 8 x ptr> poison, i16 1, <vscale x 8 x i1> poison)
@@ -43,10 +43,10 @@ define void @histograms() {
 ; CHECK-SVE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> poison, i32 1, <vscale x 4 x i1> poison)
 ; CHECK-SVE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> poison, i16 1, <vscale x 8 x i1> poison)
 ; CHECK-SVE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> poison, i8 1, <vscale x 16 x i1> poison)
-; CHECK-SVE2-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> poison, i64 1, <2 x i1> poison)
-; CHECK-SVE2-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> poison, i32 1, <4 x i1> poison)
-; CHECK-SVE2-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> poison, i16 1, <8 x i1> poison)
-; CHECK-SVE2-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> poison, i8 1, <16 x i1> poison)
+; CHECK-SVE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> poison, i64 1, <2 x i1> poison)
+; CHECK-SVE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> poison, i32 1, <4 x i1> poison)
+; CHECK-SVE2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> poison, i16 1, <8 x i1> poison)
+; CHECK-SVE2-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> poison, i8 1, <16 x i1> poison)
 ; CHECK-SVE2-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.uadd.sat.nxv2p0.i64(<vscale x 2 x ptr> poison, i64 1, <vscale x 2 x i1> poison)
 ; CHECK-SVE2-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.uadd.sat.nxv4p0.i32(<vscale x 4 x ptr> poison, i32 1, <vscale x 4 x i1> poison)
 ; CHECK-SVE2-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.uadd.sat.nxv8p0.i16(<vscale x 8 x ptr> poison, i16 1, <vscale x 8 x i1> poison)