Rebase

Author: nikolaypanchenko

llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp

@@ -263,9 +263,9 @@ Type *VPTypeAnalysis::inferScalarType(const VPValue *V) {
                 VPWidenCanonicalIVRecipe>([this](const VPRecipeBase *R) {
             return inferScalarType(R->getOperand(0));
           })
-          .Case<VPBlendRecipe, VPInstruction, VPWidenRecipe, VPReplicateRecipe,
-                VPWidenCallRecipe, VPWidenMemoryRecipe, VPWidenSelectRecipe,
-                VPWidenEVLRecipe>(
+          .Case<VPBlendRecipe, VPInstruction, VPWidenRecipe, VPWidenEVLRecipe,
+                VPReplicateRecipe, VPWidenCallRecipe, VPWidenMemoryRecipe,
+                VPWidenSelectRecipe>(
               [this](const auto *R) { return inferScalarTypeForRecipe(R); })
           .Case<VPInterleaveRecipe>([V](const VPInterleaveRecipe *R) {
             // TODO: Use info from interleave group.

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -1295,6 +1295,8 @@ void VPWidenEVLRecipe::execute(VPTransformState &State) {
   Builder.setMask(Mask).setEVL(EVLArg);
   Value *VPInst =
       Builder.createVectorInstruction(Opcode, Ops[0]->getType(), Ops, "vp.op");
+  // Currently vp-intrinsics only accept FMF flags.
+  // TODO: Enable other flags when support is added.
   if (isa<FPMathOperator>(VPInst))
     setFlags(cast<Instruction>(VPInst));
 

llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-masked-loadstore.ll

@@ -38,7 +38,7 @@ define void @masked_loadstore(ptr noalias %a, ptr noalias %b, i64 %n) {
 ; IF-EVL-NEXT:    [[TMP11:%.*]] = add i64 [[EVL_BASED_IV]], 0
 ; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[EVL_BASED_IV]], i64 0
 ; IF-EVL-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; IF-EVL-NEXT:    [[TMP12:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
+; IF-EVL-NEXT:    [[TMP12:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
 ; IF-EVL-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP12]]
 ; IF-EVL-NEXT:    [[VEC_IV:%.*]] = add <vscale x 4 x i64> [[BROADCAST_SPLAT]], [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP14:%.*]] = icmp ule <vscale x 4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT2]]