Merge commit '14f1200a228e' from apple/main into swift/next

Author: git apple-llvm automerger

llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp

@@ -1409,6 +1409,21 @@ unsigned ARMTTIImpl::getGatherScatterOpCost(unsigned Opcode, Type *DataTy,
   return ScalarCost;
 }
 
+int ARMTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
+                                      TTI::TargetCostKind CostKind) {
+  // Currently we make a somewhat optimistic assumption that active_lane_mask's
+  // are always free. In reality it may be freely folded into a tail predicated
+  // loop, expanded into a VCPT or expanded into a lot of add/icmp code. We
+  // may need to improve this in the future, but being able to detect if it
+  // is free or not involves looking at a lot of other code. We currently assume
+  // that the vectorizer inserted these, and knew what it was doing in adding
+  // one.
+  if (ST->hasMVEIntegerOps() && ICA.getID() == Intrinsic::get_active_lane_mask)
+    return 0;
+
+  return BaseT::getIntrinsicInstrCost(ICA, CostKind);
+}
+
 bool ARMTTIImpl::isLoweredToCall(const Function *F) {
   if (!F->isIntrinsic())
     BaseT::isLoweredToCall(F);

llvm/lib/Target/ARM/ARMTargetTransformInfo.h

@@ -247,6 +247,9 @@ class ARMTTIImpl : public BasicTTIImplBase<ARMTTIImpl> {
                                   Align Alignment, TTI::TargetCostKind CostKind,
                                   const Instruction *I = nullptr);
 
+  int getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
+                            TTI::TargetCostKind CostKind);
+
   bool maybeLoweredToCall(Instruction &I);
   bool isLoweredToCall(const Function *F);
   bool isHardwareLoopProfitable(Loop *L, ScalarEvolution &SE,

llvm/test/Analysis/CostModel/ARM/mve-active_lane_mask.ll

@@ -0,0 +1,37 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -S -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve.fp -cost-model -analyze | FileCheck %s
+
+; Note that these instructions like this (not in a look that could be tail
+; predicated) should not really be free. We currently assume that all active
+; lane masks are free.
+
+define void @v4i32(i32 %index, i32 %TC) {
+; CHECK-LABEL: 'v4i32'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %TC)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %TC)
+  ret void
+}
+
+define void @v8i16(i32 %index, i32 %TC) {
+; CHECK-LABEL: 'v8i16'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %TC)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %TC)
+  ret void
+}
+
+define void @v16i8(i32 %index, i32 %TC) {
+; CHECK-LABEL: 'v16i8'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %TC)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 %index, i32 %TC)
+  ret void
+}
+
+declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
+declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)
+declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32, i32)