[RISCV] Handle scalable ops with EEW > 2 dests in combineBinOp_VLToVWBinOp_VL

We can remove the restriction that the narrow type needs to be exactly EEW
/ 2 for scalable ISD::{ADD,SUB,MUL} nodes. This allows us to perform the
combine even if we can't fully fold the extend into the widening op.

VP intrinsics already do this, since they are lowered to _VL nodes which
don't have this restriction.

The "exactly EEW / 2" narrow type restriction prevented us from emitting
V{S,Z}EXT_VL nodes with i1 element types which crash when we try to select
them, since no other legal type is double the size of i1.

So to preserve this, this also restricts the combine to only run after the
legalize vector ops phase, at which point all unselectable i1 vectors
should be custom lowered away.

Author: lukel97

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -13646,16 +13646,6 @@ struct NodeExtensionHelper {
       if (!VT.isVector())
         break;
 
-      SDValue NarrowElt = OrigOperand.getOperand(0);
-      MVT NarrowVT = NarrowElt.getSimpleValueType();
-
-      unsigned ScalarBits = VT.getScalarSizeInBits();
-      unsigned NarrowScalarBits = NarrowVT.getScalarSizeInBits();
-
-      // Ensure the extension's semantic is equivalent to rvv vzext or vsext.
-      if (ScalarBits != NarrowScalarBits * 2)
-        break;
-
       SupportsZExt = Opc == ISD::ZERO_EXTEND;
       SupportsSExt = Opc == ISD::SIGN_EXTEND;
 
@@ -14106,7 +14096,9 @@ static SDValue combineBinOp_VLToVWBinOp_VL(SDNode *N,
                                            TargetLowering::DAGCombinerInfo &DCI,
                                            const RISCVSubtarget &Subtarget) {
   SelectionDAG &DAG = DCI.DAG;
-  if (DCI.isBeforeLegalize())
+  // Don't perform this until types are legalized and any legal i1 types are
+  // custom lowered to avoid introducing unselectable V{S,Z}EXT_VLs.
+  if (DCI.isBeforeLegalizeOps())
     return SDValue();
 
   if (!NodeExtensionHelper::isSupportedRoot(N))

llvm/test/CodeGen/RISCV/rvv/vscale-vw-web-simplification.ll

@@ -283,18 +283,19 @@ define <vscale x 2 x i32> @vwop_vscale_sext_i8i32_multiple_users(ptr %x, ptr %y,
 ;
 ; FOLDING-LABEL: vwop_vscale_sext_i8i32_multiple_users:
 ; FOLDING:       # %bb.0:
-; FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
+; FOLDING-NEXT:    vsetvli a3, zero, e16, mf2, ta, ma
 ; FOLDING-NEXT:    vle8.v v8, (a0)
 ; FOLDING-NEXT:    vle8.v v9, (a1)
 ; FOLDING-NEXT:    vle8.v v10, (a2)
-; FOLDING-NEXT:    vsext.vf4 v11, v8
-; FOLDING-NEXT:    vsext.vf4 v8, v9
-; FOLDING-NEXT:    vsext.vf4 v9, v10
-; FOLDING-NEXT:    vmul.vv v8, v11, v8
-; FOLDING-NEXT:    vadd.vv v10, v11, v9
-; FOLDING-NEXT:    vsub.vv v9, v11, v9
-; FOLDING-NEXT:    vor.vv v8, v8, v10
-; FOLDING-NEXT:    vor.vv v8, v8, v9
+; FOLDING-NEXT:    vsext.vf2 v11, v8
+; FOLDING-NEXT:    vsext.vf2 v8, v9
+; FOLDING-NEXT:    vsext.vf2 v9, v10
+; FOLDING-NEXT:    vwmul.vv v10, v11, v8
+; FOLDING-NEXT:    vwadd.vv v8, v11, v9
+; FOLDING-NEXT:    vwsub.vv v12, v11, v9
+; FOLDING-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
+; FOLDING-NEXT:    vor.vv v8, v10, v8
+; FOLDING-NEXT:    vor.vv v8, v8, v12
 ; FOLDING-NEXT:    ret
   %a = load <vscale x 2 x i8>, ptr %x
   %b = load <vscale x 2 x i8>, ptr %y
@@ -563,18 +564,19 @@ define <vscale x 2 x i32> @vwop_vscale_zext_i8i32_multiple_users(ptr %x, ptr %y,
 ;
 ; FOLDING-LABEL: vwop_vscale_zext_i8i32_multiple_users:
 ; FOLDING:       # %bb.0:
-; FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
+; FOLDING-NEXT:    vsetvli a3, zero, e16, mf2, ta, ma
 ; FOLDING-NEXT:    vle8.v v8, (a0)
 ; FOLDING-NEXT:    vle8.v v9, (a1)
 ; FOLDING-NEXT:    vle8.v v10, (a2)
-; FOLDING-NEXT:    vzext.vf4 v11, v8
-; FOLDING-NEXT:    vzext.vf4 v8, v9
-; FOLDING-NEXT:    vzext.vf4 v9, v10
-; FOLDING-NEXT:    vmul.vv v8, v11, v8
-; FOLDING-NEXT:    vadd.vv v10, v11, v9
-; FOLDING-NEXT:    vsub.vv v9, v11, v9
-; FOLDING-NEXT:    vor.vv v8, v8, v10
-; FOLDING-NEXT:    vor.vv v8, v8, v9
+; FOLDING-NEXT:    vzext.vf2 v11, v8
+; FOLDING-NEXT:    vzext.vf2 v8, v9
+; FOLDING-NEXT:    vzext.vf2 v9, v10
+; FOLDING-NEXT:    vwmulu.vv v10, v11, v8
+; FOLDING-NEXT:    vwaddu.vv v8, v11, v9
+; FOLDING-NEXT:    vwsubu.vv v12, v11, v9
+; FOLDING-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
+; FOLDING-NEXT:    vor.vv v8, v10, v8
+; FOLDING-NEXT:    vor.vv v8, v8, v12
 ; FOLDING-NEXT:    ret
   %a = load <vscale x 2 x i8>, ptr %x
   %b = load <vscale x 2 x i8>, ptr %y