[DAG] Fold insert_subvector(N0, extract_subvector(N0, N2), N2) --> N0 (…

…llvm#86487)

Handle the case where we've ended up inserting back into the source vector we extracted the subvector from.

Change-Id: If875da06e87381972df34a4cc43dd456917f8d87

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -26135,6 +26135,13 @@ SDValue DAGCombiner::visitINSERT_SUBVECTOR(SDNode *N) {
     }
   }
 
+  // Handle case where we've ended up inserting back into the source vector
+  // we extracted the subvector from.
+  // insert_subvector(N0, extract_subvector(N0, N2), N2) --> N0
+  if (N1.getOpcode() == ISD::EXTRACT_SUBVECTOR && N1.getOperand(0) == N0 &&
+      N1.getOperand(1) == N2)
+    return N0;
+
   // Simplify scalar inserts into an undef vector:
   // insert_subvector undef, (splat X), N2 -> splat X
   if (N0.isUndef() && N1.getOpcode() == ISD::SPLAT_VECTOR)

llvm/test/CodeGen/RISCV/rvv/vector-interleave-store.ll

@@ -101,40 +101,36 @@ define void @vector_interleave_store_nxv16i64_nxv8i64(<vscale x 8 x i64> %a, <vs
 ; CHECK-NEXT:    slli a1, a1, 4
 ; CHECK-NEXT:    sub sp, sp, a1
 ; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    slli a1, a1, 3
-; CHECK-NEXT:    add a1, sp, a1
-; CHECK-NEXT:    addi a1, a1, 16
+; CHECK-NEXT:    addi a1, sp, 16
 ; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    srli a2, a1, 1
 ; CHECK-NEXT:    vsetvli a3, zero, e16, m2, ta, mu
 ; CHECK-NEXT:    vid.v v24
 ; CHECK-NEXT:    vand.vi v26, v24, 1
-; CHECK-NEXT:    vmsne.vi v0, v26, 0
-; CHECK-NEXT:    vsrl.vi v2, v24, 1
-; CHECK-NEXT:    csrr a3, vlenb
-; CHECK-NEXT:    slli a3, a3, 3
-; CHECK-NEXT:    add a3, sp, a3
-; CHECK-NEXT:    addi a3, a3, 16
-; CHECK-NEXT:    vl8r.v v8, (a3) # Unknown-size Folded Reload
-; CHECK-NEXT:    vadd.vx v2, v2, a2, v0.t
+; CHECK-NEXT:    vmsne.vi v28, v26, 0
+; CHECK-NEXT:    vsrl.vi v24, v24, 1
+; CHECK-NEXT:    vmv1r.v v0, v28
+; CHECK-NEXT:    vadd.vx v24, v24, a2, v0.t
 ; CHECK-NEXT:    vmv4r.v v12, v16
 ; CHECK-NEXT:    vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT:    vrgatherei16.vv v24, v8, v2
-; CHECK-NEXT:    addi a2, sp, 16
-; CHECK-NEXT:    vs8r.v v24, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    vrgatherei16.vv v0, v8, v24
 ; CHECK-NEXT:    csrr a2, vlenb
 ; CHECK-NEXT:    slli a2, a2, 3
 ; CHECK-NEXT:    add a2, sp, a2
 ; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    vs8r.v v0, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    addi a2, sp, 16
 ; CHECK-NEXT:    vl8r.v v8, (a2) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vmv4r.v v16, v12
-; CHECK-NEXT:    vrgatherei16.vv v8, v16, v2
+; CHECK-NEXT:    vrgatherei16.vv v8, v16, v24
 ; CHECK-NEXT:    slli a1, a1, 3
 ; CHECK-NEXT:    add a1, a0, a1
 ; CHECK-NEXT:    vs8r.v v8, (a1)
-; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 3
+; CHECK-NEXT:    add a1, sp, a1
+; CHECK-NEXT:    addi a1, a1, 16
 ; CHECK-NEXT:    vl8r.v v8, (a1) # Unknown-size Folded Reload
 ; CHECK-NEXT:    vs8r.v v8, (a0)
 ; CHECK-NEXT:    csrr a0, vlenb