[AArch64] Consider histcnt smaller than i32 in the cost model

This PR updates the AArch64 cost model to consider the cheaper cost of
<i32 histograms to reflect the improvements from
llvm#101017 and llvm#103037

Work by Max Beck-Jones (@DevM-uk)

Author: DevM-uk

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -517,25 +517,31 @@ static bool isUnpackedVectorVT(EVT VecVT) {
 static InstructionCost getHistogramCost(const IntrinsicCostAttributes &ICA) {
   Type *BucketPtrsTy = ICA.getArgTypes()[0]; // Type of vector of pointers
   Type *EltTy = ICA.getArgTypes()[1];        // Type of bucket elements
+  unsigned TotalHistCnts = 1;
 
-  // Only allow (32b and 64b) integers or pointers for now...
+  // Only allow (up to 64b) integers or pointers
   if ((!EltTy->isIntegerTy() && !EltTy->isPointerTy()) ||
-      (EltTy->getScalarSizeInBits() != 32 &&
-       EltTy->getScalarSizeInBits() != 64))
+      EltTy->getScalarSizeInBits() > 64)
     return InstructionCost::getInvalid();
 
-  // FIXME: Hacky check for legal vector types. We can promote smaller types
-  //        but we cannot legalize vectors via splitting for histcnt.
   // FIXME: We should be able to generate histcnt for fixed-length vectors
   //        using ptrue with a specific VL.
-  if (VectorType *VTy = dyn_cast<VectorType>(BucketPtrsTy))
-    if ((VTy->getElementCount().getKnownMinValue() != 2 &&
-         VTy->getElementCount().getKnownMinValue() != 4) ||
-        VTy->getPrimitiveSizeInBits().getKnownMinValue() > 128 ||
-        !VTy->isScalableTy())
+  if (VectorType *VTy = dyn_cast<VectorType>(BucketPtrsTy)) {
+    unsigned EC = VTy->getElementCount().getKnownMinValue();
+    if (!isPowerOf2_64(EC) || !VTy->isScalableTy())
       return InstructionCost::getInvalid();
 
-  return InstructionCost(BaseHistCntCost);
+    bool Element64b = EltTy->isIntegerTy(64);
+
+    if (EC == 2 || (!Element64b && EC == 4))
+      return InstructionCost(BaseHistCntCost);
+
+    unsigned NaturalVectorWidth = Element64b ? AArch64::SVEBitsPerBlock / 64
+                                             : AArch64::SVEBitsPerBlock / 32;
+    TotalHistCnts = EC / NaturalVectorWidth;
+  }
+
+  return InstructionCost(BaseHistCntCost * TotalHistCnts);
 }
 
 InstructionCost

llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll

@@ -971,26 +971,26 @@ define void @histogram_nxv4i32(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %m
   ret void
 }
 
-define void @histogram_nxv8i16(<vscale x 8 x ptr> %buckets, <vscale x 8 x i1> %mask) {
+define void @histogram_nxv8i16(<vscale x 8 x ptr> %buckets, <vscale x 8 x i1> %mask) #3 {
 ; CHECK-LABEL: 'histogram_nxv8i16'
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
+; CHECK-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> %buckets, i16 1, <vscale x 8 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPE_BASED_ONLY-LABEL: 'histogram_nxv8i16'
-; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
+; TYPE_BASED_ONLY-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> %buckets, i16 1, <vscale x 8 x i1> %mask)
 ; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
   ret void
 }
 
-define void @histogram_nxv16i8(<vscale x 16 x ptr> %buckets, <vscale x 16 x i1> %mask) {
+define void @histogram_nxv16i8(<vscale x 16 x ptr> %buckets, <vscale x 16 x i1> %mask) #3 {
 ; CHECK-LABEL: 'histogram_nxv16i8'
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
+; CHECK-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> %buckets, i8 1, <vscale x 16 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPE_BASED_ONLY-LABEL: 'histogram_nxv16i8'
-; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
+; TYPE_BASED_ONLY-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> %buckets, i8 1, <vscale x 16 x i1> %mask)
 ; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.experimental.vector.histogram.add.nxv16p0.i64(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
@@ -1049,13 +1049,13 @@ define void @histogram_v16i8(<16 x ptr> %buckets, <16 x i1> %mask) {
   ret void
 }
 
-define void @histogram_nxv4i64(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %mask) {
+define void @histogram_nxv4i64(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %mask) #3 {
 ; CHECK-LABEL: 'histogram_nxv4i64'
-; CHECK-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; TYPE_BASED_ONLY-LABEL: 'histogram_nxv4i64'
-; TYPE_BASED_ONLY-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
+; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
 ; TYPE_BASED_ONLY-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)