[DAG] Restrict insert_subvector undef, splat_veector, dontcare transform

[reames]

Summary

On the extract_subvector side, we already have the restriction. With D158201, we'd start getting unprofitable splat combines unless we add the same one on the extract_subvector side.

[RKSimon]

LGTM

[craig.topper]

LGTM

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

if (isNullConstant(N2) &&
         return DAG.getNode(ISD::EXTRACT_SUBVECTOR, SDLoc(N),
                            VT, N1.getOperand(0), N2);
     }
   }
 
   // Simplify scalar inserts into an undef vector:
   // insert_subvector undef, (splat X), N2 -> splat X
   if (N0.isUndef() && N1.getOpcode() == ISD::SPLAT_VECTOR)
+    if (DAG.isConstantValueOfAnyType(N1.getOperand(0)) || N1.hasOneUse())
       return DAG.getNode(ISD::SPLAT_VECTOR, SDLoc(N), VT, N1.getOperand(0));
 
   // If we are inserting a bitcast value into an undef, with the same
   // number of elements, just use the bitcast input of the extract.
   // i.e. INSERT_SUBVECTOR UNDEF (BITCAST N1) N2 ->
   //        BITCAST (INSERT_SUBVECTOR UNDEF N1 N2)
   if (N0.isUndef() && N1.getOpcode() == ISD::BITCAST &&
       N1.getOperand(0).getOpcode() == ISD::EXTRACT_SUBVECTOR &&
       N1.getOperand(0).getOperand(1) == N2 &&

llvm/test/CodeGen/RISCV/rvv/splats-with-mixed-vl.ll

; CHECK-NEXT:    ret
   ret void
 }
 
 define <vscale x 1 x i32> @extract_vector_multiuse2(ptr %p, ptr %p2, i32 %v) {
 ; CHECK-LABEL: extract_vector_multiuse2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a1, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a2
-; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v9, a2
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT:    vse32.v v9, (a0)
+; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    ret
   %elt.head = insertelement <vscale x 1 x i32> poison, i32 %v, i32 0
   %splat = shufflevector <vscale x 1 x i32> %elt.head, <vscale x 1 x i32> poison, <vscale x 1 x i32> zeroinitializer
 
   %fv = call <4 x i32> @llvm.vector.extract.v4i32.nxv1132(<vscale x 1 x i32> %splat, i64 0)
   store <4 x i32> %fv, ptr %p
   ret <vscale x 1 x i32> %splat
 }
 
 define void @extract_vector_mixed1(ptr %p, ptr %p2, i32 %v) {
 ; CHECK-LABEL: extract_vector_mixed1:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a3, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a2
-; CHECK-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v9, a2
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT:    vse32.v v9, (a0)
+; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vse32.v v8, (a1)
 ; CHECK-NEXT:    ret
   %elt.head = insertelement <vscale x 1 x i32> poison, i32 %v, i32 0
   %splat = shufflevector <vscale x 1 x i32> %elt.head, <vscale x 1 x i32> poison, <vscale x 1 x i32> zeroinitializer
 
   %fv = call <4 x i32> @llvm.vector.extract.v4i32.nxv1132(<vscale x 1 x i32> %splat, i64 0)
 
   store <4 x i32> %fv, ptr %p
   store <vscale x 1 x i32> %splat, ptr %p2
   ret void
 }
 
 define void @extract_vector_mixed2(ptr %p, ptr %p2, i32 %v) {
 ; CHECK-LABEL: extract_vector_mixed2:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a3, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a2
 ; CHECK-NEXT:    vse32.v v8, (a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v8, a2
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
 ; CHECK-NEXT:    vse32.v v8, (a1)
 ; CHECK-NEXT:    ret
   %elt.head = insertelement <vscale x 1 x i32> poison, i32 %v, i32 0
   %splat = shufflevector <vscale x 1 x i32> %elt.head, <vscale x 1 x i32> poison, <vscale x 1 x i32> zeroinitializer
   store <vscale x 1 x i32> %splat, ptr %p
 
   %fv = call <4 x i32> @llvm.vector.extract.v4i32.nxv1132(<vscale x 1 x i32> %splat, i64 0)
   store <4 x i32> %fv, ptr %p2
   ret void
 }
 
 define void @extract_vector_mixed3(ptr %p, ptr %p2, i32 %v) {
 ; CHECK-LABEL: extract_vector_mixed3:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a3, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a2
-; CHECK-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v9, a2
-; CHECK-NEXT:    vsetvli a2, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT:    vse32.v v9, (a1)
+; CHECK-NEXT:    vse32.v v8, (a1)
 ; CHECK-NEXT:    ret
   %elt.head = insertelement <vscale x 1 x i32> poison, i32 %v, i32 0
   %splat = shufflevector <vscale x 1 x i32> %elt.head, <vscale x 1 x i32> poison, <vscale x 1 x i32> zeroinitializer
   %fv = call <4 x i32> @llvm.vector.extract.v4i32.nxv1132(<vscale x 1 x i32> %splat, i64 0)
 
   store <vscale x 1 x i32> %splat, ptr %p
   store <4 x i32> %fv, ptr %p2
   ret void
 }
 
 
 declare <4 x i32> @llvm.vector.extract.v4i32.nxv1132(<vscale x 1 x i32> %vec, i64 %idx)