[RISCV] Remove what appears to be an unnecessary check for LMUL_8 in getSingleShuffleSrc. (#127250)

I think this dates to a time when we used to use a type twice as large
as necessary for the input to the vnsrl. This was changed in #118509
when factor 4 and 8 were added.

The existing test for this regresses because it uses a lot of undef
elements and we previously figured out we could reduce its size and then
try the vnsrl again. We now match it before we try to reduce the width
so we miss this opportunity.

I've added a second test that doesn't have any undef elements in the
first half. Prior to this patch we used a vcompress lowering instead of
vnsrl.

Author: topperc

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -4498,11 +4498,9 @@ static SDValue lowerScalarInsert(SDValue Scalar, SDValue VL, MVT VT,
 }
 
 // Can this shuffle be performed on exactly one (possibly larger) input?
-static SDValue getSingleShuffleSrc(MVT VT, MVT ContainerVT, SDValue V1,
-                                   SDValue V2) {
+static SDValue getSingleShuffleSrc(MVT VT, SDValue V1, SDValue V2) {
 
-  if (V2.isUndef() &&
-      RISCVTargetLowering::getLMUL(ContainerVT) != RISCVII::VLMUL::LMUL_8)
+  if (V2.isUndef())
     return V1;
 
   // Both input must be extracts.
@@ -5593,7 +5591,7 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
       unsigned Index = 0;
       if (ShuffleVectorInst::isDeInterleaveMaskOfFactor(Mask, Factor, Index) &&
           1 < count_if(Mask, [](int Idx) { return Idx != -1; })) {
-        if (SDValue Src = getSingleShuffleSrc(VT, ContainerVT, V1, V2))
+        if (SDValue Src = getSingleShuffleSrc(VT, V1, V2))
           return getDeinterleaveShiftAndTrunc(DL, VT, Src, Factor, Index, DAG);
       }
     }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll

@@ -517,15 +517,15 @@ entry:
   ret void
 }
 
-; Can't match the m8 result type as the source would have to be m16 which
-; isn't a legal type.
+; FIXME: We could use a smaller vl for the vnsrl since some elts are undefined.
 define void @vnsrl_0_i32_single_src_m8(ptr %in, ptr %out) {
 ; V-LABEL: vnsrl_0_i32_single_src_m8:
 ; V:       # %bb.0: # %entry
 ; V-NEXT:    li a2, 64
 ; V-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
 ; V-NEXT:    vle32.v v8, (a0)
-; V-NEXT:    vsetivli zero, 16, e32, m2, ta, ma
+; V-NEXT:    li a0, 32
+; V-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
 ; V-NEXT:    vnsrl.wi v16, v8, 0
 ; V-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
 ; V-NEXT:    vse32.v v16, (a1)
@@ -551,3 +551,36 @@ entry:
   store <64 x i32> %shuffle.i5, ptr %out, align 4
   ret void
 }
+
+define void @vnsrl_0_i32_single_src_m8_2(ptr %in, ptr %out) {
+; V-LABEL: vnsrl_0_i32_single_src_m8_2:
+; V:       # %bb.0: # %entry
+; V-NEXT:    li a2, 64
+; V-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; V-NEXT:    vle32.v v8, (a0)
+; V-NEXT:    li a0, 32
+; V-NEXT:    vsetvli zero, a0, e32, m4, ta, ma
+; V-NEXT:    vnsrl.wi v16, v8, 0
+; V-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; V-NEXT:    vse32.v v16, (a1)
+; V-NEXT:    ret
+;
+; ZVE32F-LABEL: vnsrl_0_i32_single_src_m8_2:
+; ZVE32F:       # %bb.0: # %entry
+; ZVE32F-NEXT:    li a2, 64
+; ZVE32F-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; ZVE32F-NEXT:    vle32.v v8, (a0)
+; ZVE32F-NEXT:    lui a0, 349525
+; ZVE32F-NEXT:    addi a0, a0, 1365
+; ZVE32F-NEXT:    vsetivli zero, 2, e32, m1, ta, ma
+; ZVE32F-NEXT:    vmv.v.x v16, a0
+; ZVE32F-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; ZVE32F-NEXT:    vcompress.vm v24, v8, v16
+; ZVE32F-NEXT:    vse32.v v24, (a1)
+; ZVE32F-NEXT:    ret
+entry:
+  %0 = load <64 x i32>, ptr %in, align 4
+  %shuffle.i5 = shufflevector <64 x i32> %0, <64 x i32> poison, <64 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30, i32 32, i32 34, i32 36, i32 38, i32 40, i32 42, i32 44, i32 46, i32 48, i32 50, i32 52, i32 54, i32 56, i32 58, i32 60, i32 62, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+  store <64 x i32> %shuffle.i5, ptr %out, align 4
+  ret void
+}