[RISCV] Model select and insertsubvector shuffle kinds

Selects get lowered to a vmerge with a mask, and insertsubvectors get
lowered to a vslideup.

Differential Revision: https://reviews.llvm.org/D146747

Author: lukel97

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -292,6 +292,19 @@ InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
     // TODO: Most of these cases will return getInvalid in generic code, and
     // must be implemented here.
     break;
+  case TTI::SK_InsertSubvector:
+    // Example sequence:
+    // vsetivli     zero, 4, e8, mf2, tu, ma (ignored)
+    // vslideup.vi  v8, v9, 2
+    return LT.first * getLMULCost(LT.second);
+  case TTI::SK_Select: {
+    // Example sequence:
+    // li           a0, 90
+    // vsetivli     zero, 8, e8, mf2, ta, ma (ignored)
+    // vmv.s.x      v0, a0
+    // vmerge.vvm   v8, v9, v8, v0
+    return LT.first * 3 * getLMULCost(LT.second);
+  }
   case TTI::SK_Broadcast: {
     bool HasScalar = (Args.size() > 0) && (Operator::getOpcode(Args[0]) ==
                                            Instruction::InsertElement);

llvm/test/Analysis/CostModel/RISCV/rvv-shuffle.ll

@@ -37,7 +37,7 @@ define void  @vector_broadcast() {
 define void @vector_insert_extract(<vscale x 4 x i32> %v0, <vscale x 16 x i32> %v1, <16 x i32> %v2) {
 ; CHECK-LABEL: 'vector_insert_extract'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %insert_scalable_into_scalable = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> %v1, <vscale x 4 x i32> %v0, i64 0)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void

llvm/test/Analysis/CostModel/RISCV/shuffle-insert.ll

@@ -4,7 +4,7 @@
 
 define <8 x i8> @insert_subvector_middle_v8i8(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: 'insert_subvector_middle_v8i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 10, i32 11, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 10, i32 11, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 10, i32 11, i32 6, i32 7>
@@ -13,7 +13,7 @@ define <8 x i8> @insert_subvector_middle_v8i8(<8 x i8> %v, <8 x i8> %w) {
 
 define <8 x i8> @insert_subvector_end_v8i8(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: 'insert_subvector_end_v8i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
@@ -22,7 +22,7 @@ define <8 x i8> @insert_subvector_end_v8i8(<8 x i8> %v, <8 x i8> %w) {
 
 define <8 x i8> @insert_subvector_end_swapped_v8i8(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: 'insert_subvector_end_swapped_v8i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 0, i32 1, i32 2, i32 3>
@@ -31,7 +31,7 @@ define <8 x i8> @insert_subvector_end_swapped_v8i8(<8 x i8> %v, <8 x i8> %w) {
 
 define <8 x i8> @insert_subvector_short_v8i8(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: 'insert_subvector_short_v8i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
@@ -40,23 +40,42 @@ define <8 x i8> @insert_subvector_short_v8i8(<8 x i8> %v, <8 x i8> %w) {
 
 define <8 x i8> @insert_subvector_offset_1_v8i8(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: 'insert_subvector_offset_1_v8i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
   ret <8 x i8> %res
 }
 
 define <8 x i64> @insert_subvector_offset_1_v8i64(<8 x i64> %v, <8 x i64> %w) {
-; RV32-LABEL: 'insert_subvector_offset_1_v8i64'
-; RV32-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
-;
-; RV64-LABEL: 'insert_subvector_offset_1_v8i64'
-; RV64-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
+; CHECK-LABEL: 'insert_subvector_offset_1_v8i64'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
 ;
   %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 0, i32 8, i32 9, i32 10, i32 11, i32 5, i32 6, i32 7>
   ret <8 x i64> %res
 }
 
+; FIXME: This is expensive and involves vrgathers and vslideups
+define <12 x i8> @insert_subvector_concat_v6i8(<6 x i8> %x, <6 x i8> %y) {
+; CHECK-LABEL: 'insert_subvector_concat_v6i8'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = shufflevector <6 x i8> %x, <6 x i8> %y, <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <12 x i8> %a
+;
+  %a = shufflevector <6 x i8> %x, <6 x i8> %y, <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+  ret <12 x i8> %a
+}
+
+; FIXME: This is a concat is emitted as one vslideup
+define <8 x i8> @insert_subvector_concat_v8i8(<4 x i8> %x, <4 x i8> %y) {
+; CHECK-LABEL: 'insert_subvector_concat_v8i8'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = shufflevector <4 x i8> %x, <4 x i8> %y, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %a
+;
+  %a = shufflevector <4 x i8> %x, <4 x i8> %y, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+  ret <8 x i8> %a
+}
+
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; RV32: {{.*}}
+; RV64: {{.*}}

llvm/test/Analysis/CostModel/RISCV/shuffle-interleave.ll

@@ -5,7 +5,7 @@
 ; The mask here interleaves (%v1, %v0), not (%v0, %v1): it should still be cheap.
 define <4 x i8> @interleave2_v2i8(<2 x i8> %v0, <2 x i8> %v1) {
 ; CHECK-LABEL: 'interleave2_v2i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %concat = shufflevector <2 x i8> %v0, <2 x i8> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %concat = shufflevector <2 x i8> %v0, <2 x i8> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = shufflevector <4 x i8> %concat, <4 x i8> poison, <4 x i32> <i32 2, i32 0, i32 3, i32 1>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <4 x i8> %res
 ;
@@ -16,7 +16,7 @@ define <4 x i8> @interleave2_v2i8(<2 x i8> %v0, <2 x i8> %v1) {
 
 define <8 x i8> @interleave2_v8i8(<4 x i8> %v0, <4 x i8> %v1) {
 ; CHECK-LABEL: 'interleave2_v8i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %concat = shufflevector <4 x i8> %v0, <4 x i8> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %concat = shufflevector <4 x i8> %v0, <4 x i8> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = shufflevector <8 x i8> %concat, <8 x i8> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
@@ -27,7 +27,7 @@ define <8 x i8> @interleave2_v8i8(<4 x i8> %v0, <4 x i8> %v1) {
 
 define <8 x i32> @interleave2_v8i32(<4 x i32> %v0, <4 x i32> %v1) {
 ; CHECK-LABEL: 'interleave2_v8i32'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %concat = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %concat = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = shufflevector <8 x i32> %concat, <8 x i32> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i32> %res
 ;
@@ -39,12 +39,12 @@ define <8 x i32> @interleave2_v8i32(<4 x i32> %v0, <4 x i32> %v1) {
 ; Should be expensive on RV32 because it can't widen
 define <8 x i64> @interleave2_v8i64(<4 x i64> %v0, <4 x i64> %v1) {
 ; RV32-LABEL: 'interleave2_v8i64'
-; RV32-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %concat = shufflevector <4 x i64> %v0, <4 x i64> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; RV32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %concat = shufflevector <4 x i64> %v0, <4 x i64> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; RV32-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %res = shufflevector <8 x i64> %concat, <8 x i64> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
 ; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
 ;
 ; RV64-LABEL: 'interleave2_v8i64'
-; RV64-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %concat = shufflevector <4 x i64> %v0, <4 x i64> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; RV64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %concat = shufflevector <4 x i64> %v0, <4 x i64> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
 ; RV64-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = shufflevector <8 x i64> %concat, <8 x i64> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
 ; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
 ;

llvm/test/Analysis/CostModel/RISCV/shuffle-select.ll

@@ -4,7 +4,7 @@
 
 define <8 x i8> @select_start_v8i8(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: 'select_start_v8i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
@@ -13,35 +13,30 @@ define <8 x i8> @select_start_v8i8(<8 x i8> %v, <8 x i8> %w) {
 
 define <8 x i8> @select_non_contiguous_v8i8(<8 x i8> %v, <8 x i8> %w) {
 ; CHECK-LABEL: 'select_non_contiguous_v8i8'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 4, i32 13, i32 6, i32 15>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 4, i32 13, i32 6, i32 15>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i8> %res
 ;
   %res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 4, i32 13, i32 6, i32 15>
   ret <8 x i8> %res
 }
 
 define <8 x i64> @select_start_v8i64(<8 x i64> %v, <8 x i64> %w) {
-; RV32-LABEL: 'select_start_v8i64'
-; RV32-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
-;
-; RV64-LABEL: 'select_start_v8i64'
-; RV64-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
+; CHECK-LABEL: 'select_start_v8i64'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
 ;
   %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 4, i32 5, i32 6, i32 7>
   ret <8 x i64> %res
 }
 
 define <8 x i64> @select_non_contiguous_v8i64(<8 x i64> %v, <8 x i64> %w) {
-; RV32-LABEL: 'select_non_contiguous_v8i64'
-; RV32-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 4, i32 13, i32 6, i32 15>
-; RV32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
-;
-; RV64-LABEL: 'select_non_contiguous_v8i64'
-; RV64-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 4, i32 13, i32 6, i32 15>
-; RV64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
+; CHECK-LABEL: 'select_non_contiguous_v8i64'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 4, i32 13, i32 6, i32 15>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret <8 x i64> %res
 ;
   %res = shufflevector <8 x i64> %v, <8 x i64> %w, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 4, i32 13, i32 6, i32 15>
   ret <8 x i64> %res
 }
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; RV32: {{.*}}
+; RV64: {{.*}}