[LoopVectorize] Add the cost of VPInstruction::AnyOf to vplan (llvm#125058)

This patch adds an initial implementation of
VPInstruction::computeCost with support for only one
instruction so far - VPInstruction::AnyOf. This is only
used when vectorising loops with uncountable early exits.

Author: david-arm

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -7552,7 +7552,14 @@ VectorizationFactor LoopVectorizationPlanner::computeBestVF() {
   VPCostContext CostCtx(CM.TTI, *CM.TLI, Legal->getWidestInductionType(), CM,
                         CM.CostKind);
   precomputeCosts(BestPlan, BestFactor.Width, CostCtx);
-  assert((BestFactor.Width == LegacyVF.Width ||
+  // Set PlanForEarlyExitLoop to true if the BestPlan has been built from a
+  // loop with an uncountable early exit. The legacy cost model doesn't
+  // properly model costs for such loops.
+  bool PlanForEarlyExitLoop =
+      BestPlan.getVectorLoopRegion() &&
+      BestPlan.getVectorLoopRegion()->getSingleSuccessor() !=
+          BestPlan.getMiddleBlock();
+  assert((BestFactor.Width == LegacyVF.Width || PlanForEarlyExitLoop ||
           planContainsAdditionalSimplifications(getPlanFor(BestFactor.Width),
                                                 CostCtx, OrigLoop) ||
           planContainsAdditionalSimplifications(getPlanFor(LegacyVF.Width),

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -972,10 +972,7 @@ class VPInstruction : public VPRecipeWithIRFlags,
 
   /// Return the cost of this VPInstruction.
   InstructionCost computeCost(ElementCount VF,
-                              VPCostContext &Ctx) const override {
-    // TODO: Compute accurate cost after retiring the legacy cost model.
-    return 0;
-  }
+                              VPCostContext &Ctx) const override;
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
   /// Print the VPInstruction to \p O.

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -711,6 +711,20 @@ Value *VPInstruction::generate(VPTransformState &State) {
   }
 }
 
+InstructionCost VPInstruction::computeCost(ElementCount VF,
+                                           VPCostContext &Ctx) const {
+  switch (getOpcode()) {
+  case VPInstruction::AnyOf: {
+    auto *VecTy = toVectorTy(Ctx.Types.inferScalarType(this), VF);
+    return Ctx.TTI.getArithmeticReductionCost(
+        Instruction::Or, cast<VectorType>(VecTy), std::nullopt, Ctx.CostKind);
+  }
+  default:
+    // TODO: Fill out other opcodes!
+    return 0;
+  }
+}
+
 bool VPInstruction::isVectorToScalar() const {
   return getOpcode() == VPInstruction::ExtractFromEnd ||
          getOpcode() == VPInstruction::ExtractFirstActive ||

llvm/test/Transforms/LoopVectorize/AArch64/simple_early_exit.ll

@@ -272,36 +272,52 @@ define i64 @loop_contains_safe_div() #1 {
 ; CHECK-NEXT:    [[P2:%.*]] = alloca [1024 x i8], align 4
 ; CHECK-NEXT:    call void @init_mem(ptr [[P1]], i64 1024)
 ; CHECK-NEXT:    call void @init_mem(ptr [[P2]], i64 1024)
+; CHECK-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP12:%.*]] = mul i64 [[TMP11]], 4
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP10]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 64, [[TMP3]]
+; CHECK-NEXT:    [[INDEX1:%.*]] = sub i64 64, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 3, [[INDEX1]]
+; CHECK-NEXT:    [[TMP16:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
+; CHECK-NEXT:    [[TMP17:%.*]] = mul <vscale x 4 x i64> [[TMP16]], splat (i64 1)
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> splat (i64 3), [[TMP17]]
+; CHECK-NEXT:    [[TMP9:%.*]] = mul i64 1, [[TMP5]]
+; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP9]], i64 0
+; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <2 x i64> [ <i64 3, i64 4>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 3, [[INDEX1]]
-; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
+; CHECK-NEXT:    [[INDEX2:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[OFFSET_IDX1:%.*]] = add i64 3, [[INDEX2]]
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[OFFSET_IDX1]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[P1]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i32>, ptr [[TMP2]], align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = udiv <2 x i32> [[WIDE_LOAD]], splat (i32 20000)
-; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq <2 x i32> [[TMP3]], splat (i32 1)
-; CHECK-NEXT:    [[INDEX_NEXT2]] = add nuw i64 [[INDEX1]], 2
-; CHECK-NEXT:    [[TMP5:%.*]] = xor <2 x i1> [[TMP4]], splat (i1 true)
-; CHECK-NEXT:    [[TMP6:%.*]] = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> [[TMP5]])
-; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT2]], 64
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <2 x i64> [[VEC_IND]], splat (i64 2)
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP2]], align 1
+; CHECK-NEXT:    [[TMP13:%.*]] = udiv <vscale x 4 x i32> [[WIDE_LOAD]], splat (i32 20000)
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq <vscale x 4 x i32> [[TMP13]], splat (i32 1)
+; CHECK-NEXT:    [[INDEX_NEXT2]] = add nuw i64 [[INDEX2]], [[TMP5]]
+; CHECK-NEXT:    [[TMP15:%.*]] = xor <vscale x 4 x i1> [[TMP14]], splat (i1 true)
+; CHECK-NEXT:    [[TMP6:%.*]] = call i1 @llvm.vector.reduce.or.nxv4i1(<vscale x 4 x i1> [[TMP15]])
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT2]], [[INDEX1]]
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
 ; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_SPLIT:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; CHECK:       middle.split:
 ; CHECK-NEXT:    br i1 [[TMP6]], label [[VECTOR_EARLY_EXIT:%.*]], label [[MIDDLE_BLOCK:%.*]]
 ; CHECK:       vector.early.exit:
-; CHECK-NEXT:    [[FIRST_ACTIVE_LANE:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.v2i1(<2 x i1> [[TMP5]], i1 true)
-; CHECK-NEXT:    [[EARLY_EXIT_VALUE:%.*]] = extractelement <2 x i64> [[VEC_IND]], i64 [[FIRST_ACTIVE_LANE]]
+; CHECK-NEXT:    [[FIRST_ACTIVE_LANE:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.nxv4i1(<vscale x 4 x i1> [[TMP15]], i1 true)
+; CHECK-NEXT:    [[EARLY_EXIT_VALUE:%.*]] = extractelement <vscale x 4 x i64> [[VEC_IND]], i64 [[FIRST_ACTIVE_LANE]]
 ; CHECK-NEXT:    br label [[LOOP_END:%.*]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[LOOP_END]], label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 64, [[INDEX1]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[LOOP_END]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 67, [[MIDDLE_BLOCK]] ], [ 3, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[OFFSET_IDX]], [[MIDDLE_BLOCK]] ], [ 3, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[LOOP_INC:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]