[RISCV] Fix incorrect slide offset when using vnsrl to de-interleave (#132123)

Given this shuffle:
```
shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 undef, i32 undef, i32 undef, i32 undef>
```
#127272 lowers it with a bunch of vnsrl. If we describe the result in
terms of the shuffle mask, we expect:
```
<0, 4, 8, 12, u, u, u, u>
```
but we actually got:
```
<0, 4, u, u, 8, 12, u, u>
```
for factor larger than 2. This is caused by `CONCAT_VECTORS` on
incorrect (sub) vector types. This patch fixes the said issue by
building an aggregate vector with the correct sub vector types.

Fix #132071

Author: mshockwave

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -5545,12 +5545,25 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
             })) {
           // Narrow each source and concatenate them.
           // FIXME: For small LMUL it is better to concatenate first.
-          MVT HalfVT = VT.getHalfNumVectorElementsVT();
+          MVT EltVT = VT.getVectorElementType();
+          auto EltCnt = VT.getVectorElementCount();
+          MVT SubVT =
+              MVT::getVectorVT(EltVT, EltCnt.divideCoefficientBy(Factor));
+
           SDValue Lo =
-              getDeinterleaveShiftAndTrunc(DL, HalfVT, V1, Factor, Index, DAG);
+              getDeinterleaveShiftAndTrunc(DL, SubVT, V1, Factor, Index, DAG);
           SDValue Hi =
-              getDeinterleaveShiftAndTrunc(DL, HalfVT, V2, Factor, Index, DAG);
-          return DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, Lo, Hi);
+              getDeinterleaveShiftAndTrunc(DL, SubVT, V2, Factor, Index, DAG);
+
+          SDValue Concat =
+              DAG.getNode(ISD::CONCAT_VECTORS, DL,
+                          SubVT.getDoubleNumVectorElementsVT(), Lo, Hi);
+          if (Factor == 2)
+            return Concat;
+
+          SDValue Vec = DAG.getUNDEF(VT);
+          return DAG.getNode(ISD::INSERT_SUBVECTOR, DL, VT, Vec, Concat,
+                             DAG.getVectorIdxConstant(0, DL));
         }
       }
     }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-deinterleave.ll

@@ -378,8 +378,9 @@ define void @deinterleave4_0_i8_two_source(ptr %in0, ptr %in1, ptr %out) {
 ; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vnsrl.wi v8, v8, 0
 ; CHECK-NEXT:    vnsrl.wi v9, v9, 0
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
+; CHECK-NEXT:    vslideup.vi v9, v8, 2
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
-; CHECK-NEXT:    vslideup.vi v9, v8, 4
 ; CHECK-NEXT:    vse8.v v9, (a2)
 ; CHECK-NEXT:    ret
 entry:
@@ -402,8 +403,9 @@ define void @deinterleave4_8_i8_two_source(ptr %in0, ptr %in1, ptr %out) {
 ; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, ma
 ; CHECK-NEXT:    vnsrl.wi v8, v8, 0
 ; CHECK-NEXT:    vnsrl.wi v9, v9, 0
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
+; CHECK-NEXT:    vslideup.vi v9, v8, 2
 ; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
-; CHECK-NEXT:    vslideup.vi v9, v8, 4
 ; CHECK-NEXT:    vse8.v v9, (a2)
 ; CHECK-NEXT:    ret
 entry: