Refactored code and removed flag propagation as they're not yet

supported by vp intrinsics

Author: nikolaypanchenko

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -1213,6 +1213,11 @@ InstructionCost VPWidenRecipe::computeCost(ElementCount VF,
 }
 
 void VPWidenEVLRecipe::execute(VPTransformState &State) {
+  unsigned Opcode = getOpcode();
+  // TODO: Support other opcodes
+  if (!Instruction::isBinaryOp(Opcode) && !Instruction::isUnaryOp(Opcode))
+    llvm_unreachable("Unsupported opcode in VPWidenEVLRecipe::execute");
+
   State.setDebugLocFrom(getDebugLoc());
   assert(State.UF == 1 && "Expected only UF == 1 when vectorizing with "
                           "explicit vector length.");
@@ -1223,34 +1228,23 @@ void VPWidenEVLRecipe::execute(VPTransformState &State) {
 
   VPValue *EVL = getEVL();
   Value *EVLArg = State.get(EVL, 0, /*NeedsScalar=*/true);
-  unsigned Opcode = getOpcode();
-  Instruction *I = getUnderlyingInstr();
   IRBuilderBase &BuilderIR = State.Builder;
   VectorBuilder Builder(BuilderIR);
   Value *Mask = BuilderIR.CreateVectorSplat(State.VF, BuilderIR.getTrue());
-  Value *VPInst = nullptr;
-
-  //===------------------- Binary and Unary Ops ---------------------===//
-  if (Instruction::isBinaryOp(Opcode) || Instruction::isUnaryOp(Opcode)) {
-    // Just widen unops and binops.
 
-    SmallVector<Value *, 4> Ops;
-    for (unsigned I = 0, E = getNumOperands() - 1; I < E; ++I) {
-      VPValue *VPOp = getOperand(I);
-      Ops.push_back(State.get(VPOp, 0));
-    }
+  SmallVector<Value *, 4> Ops;
+  for (unsigned I = 0, E = getNumOperands() - 1; I < E; ++I) {
+    VPValue *VPOp = getOperand(I);
+    Ops.push_back(State.get(VPOp, 0));
+  }
 
-    Builder.setMask(Mask).setEVL(EVLArg);
-    VPInst = Builder.createVectorInstruction(Opcode, Ops[0]->getType(), Ops,
-                                             "vp.op");
+  Builder.setMask(Mask).setEVL(EVLArg);
+  Value *VPInst =
+      Builder.createVectorInstruction(Opcode, Ops[0]->getType(), Ops, "vp.op");
 
-    if (auto *VecOp = dyn_cast_or_null<Instruction>(VPInst))
-      VecOp->copyIRFlags(I);
-  } else {
-    llvm_unreachable("Unsupported opcode in VPWidenEVLRecipe::execute");
-  }
   State.set(this, VPInst, 0);
-  State.addMetadata(VPInst, I);
+  State.addMetadata(VPInst,
+                    dyn_cast_or_null<Instruction>(getUnderlyingValue()));
 }
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)

llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-bin-unary-ops-args.ll

@@ -1267,7 +1267,7 @@ define void @test_fadd(ptr nocapture %a, ptr nocapture readonly %b) {
 ; IF-EVL-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
 ; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
-; IF-EVL-NEXT:    [[TMP16:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 3.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
+; IF-EVL-NEXT:    [[TMP16:%.*]] = call <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 3.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
 ; IF-EVL-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
 ; IF-EVL-NEXT:    call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[TMP16]], ptr align 4 [[TMP18]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
@@ -1362,7 +1362,7 @@ define void @test_fsub(ptr nocapture %a, ptr nocapture readonly %b) {
 ; IF-EVL-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
 ; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
-; IF-EVL-NEXT:    [[TMP16:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fsub.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 3.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
+; IF-EVL-NEXT:    [[TMP16:%.*]] = call <vscale x 4 x float> @llvm.vp.fsub.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 3.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
 ; IF-EVL-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
 ; IF-EVL-NEXT:    call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[TMP16]], ptr align 4 [[TMP18]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
@@ -1457,7 +1457,7 @@ define void @test_fmul(ptr nocapture %a, ptr nocapture readonly %b) {
 ; IF-EVL-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
 ; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
-; IF-EVL-NEXT:    [[TMP16:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fmul.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 3.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
+; IF-EVL-NEXT:    [[TMP16:%.*]] = call <vscale x 4 x float> @llvm.vp.fmul.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 3.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
 ; IF-EVL-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
 ; IF-EVL-NEXT:    call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[TMP16]], ptr align 4 [[TMP18]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
@@ -1552,7 +1552,7 @@ define void @test_fdiv(ptr nocapture %a, ptr nocapture readonly %b) {
 ; IF-EVL-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
 ; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
-; IF-EVL-NEXT:    [[TMP16:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fdiv.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 3.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
+; IF-EVL-NEXT:    [[TMP16:%.*]] = call <vscale x 4 x float> @llvm.vp.fdiv.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 3.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer), <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
 ; IF-EVL-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
 ; IF-EVL-NEXT:    call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[TMP16]], ptr align 4 [[TMP18]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
@@ -1700,7 +1700,7 @@ define void @test_fneg(ptr nocapture %a, ptr nocapture readonly %b) {
 ; IF-EVL-NEXT:    [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP15:%.*]] = getelementptr inbounds float, ptr [[TMP14]], i32 0
 ; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 4 x float> @llvm.vp.load.nxv4f32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
-; IF-EVL-NEXT:    [[TMP16:%.*]] = call fast <vscale x 4 x float> @llvm.vp.fneg.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
+; IF-EVL-NEXT:    [[TMP16:%.*]] = call <vscale x 4 x float> @llvm.vp.fneg.nxv4f32(<vscale x 4 x float> [[VP_OP_LOAD]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
 ; IF-EVL-NEXT:    [[TMP17:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP13]]
 ; IF-EVL-NEXT:    [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP17]], i32 0
 ; IF-EVL-NEXT:    call void @llvm.vp.store.nxv4f32.p0(<vscale x 4 x float> [[TMP16]], ptr align 4 [[TMP18]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])