Skip to content

[RISCV] Decompose single source shuffles (without exact VLEN) #126108

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Feb 11, 2025
Merged

[RISCV] Decompose single source shuffles (without exact VLEN) #126108

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cb44b0a
[RISCV] Decompose single source shuffles (without exact VLEN)
preames Feb 6, 2025
849eff1
Minor style and comment improvements
preames Feb 6, 2025
c359d56
Address review comment
preames Feb 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 39 additions & 0 deletions llvm/lib/Target/RISCV/RISCVISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5350,6 +5350,12 @@ static bool isLocalRepeatingShuffle(ArrayRef<int> Mask, int Span) {
return true;
}

/// Is this mask only using elements from the first span of the input?
static bool isLowSourceShuffle(ArrayRef<int> Mask, int Span) {
return !any_of(Mask,
[&](const auto &Idx) { return Idx != -1 && Idx >= Span; });
}

/// Try to widen element type to get a new mask value for a better permutation
/// sequence. This doesn't try to inspect the widened mask for profitability;
/// we speculate the widened form is equal or better. This has the effect of
Expand Down Expand Up @@ -5766,6 +5772,39 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
Gather = DAG.getNode(ISD::INSERT_SUBVECTOR, DL, ContainerVT, Gather,
SubVec, SubIdx);
}
} else if (ContainerVT.bitsGT(M1VT) && isLowSourceShuffle(Mask, VLMAX)) {
// If we have a shuffle which only uses the first register in our
// source register group, we can do a linear number of m1 vrgathers
// reusing the same source register (but with different indices)
// TODO: This can be generalized for m2 or m4, or for any shuffle
// for which we can do a vslidedown followed by this expansion.
EVT SubIndexVT = M1VT.changeVectorElementType(IndexVT.getScalarType());
auto [InnerTrueMask, InnerVL] =
getDefaultScalableVLOps(M1VT, DL, DAG, Subtarget);
int N = ContainerVT.getVectorMinNumElements() /
M1VT.getVectorMinNumElements();
assert(isPowerOf2_32(N) && N <= 8);
Gather = DAG.getUNDEF(ContainerVT);
SDValue SlideAmt =
DAG.getElementCount(DL, XLenVT, M1VT.getVectorElementCount());
for (int i = 0; i < N; i++) {
if (i != 0)
LHSIndices = getVSlidedown(DAG, Subtarget, DL, IndexContainerVT,
DAG.getUNDEF(IndexContainerVT), LHSIndices,
SlideAmt, TrueMask, VL);
SDValue SubIdx =
DAG.getVectorIdxConstant(M1VT.getVectorMinNumElements() * i, DL);
SDValue SubV1 =
DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, M1VT, V1, SubIdx);
SDValue SubIndex =
DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SubIndexVT, LHSIndices,
DAG.getVectorIdxConstant(0, DL));
SDValue SubVec =
DAG.getNode(GatherVVOpc, DL, M1VT, SubV1, SubIndex,
DAG.getUNDEF(M1VT), InnerTrueMask, InnerVL);
Gather = DAG.getNode(ISD::INSERT_SUBVECTOR, DL, ContainerVT, Gather,
SubVec, SubIdx);
}
} else {
Gather = DAG.getNode(GatherVVOpc, DL, ContainerVT, V1, LHSIndices,
DAG.getUNDEF(ContainerVT), TrueMask, VL);
Expand Down
19 changes: 12 additions & 7 deletions llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,15 +38,20 @@ define <4 x float> @interleave_v2f32(<2 x float> %x, <2 x float> %y) {
define <4 x double> @interleave_v2f64(<2 x double> %x, <2 x double> %y) {
; V128-LABEL: interleave_v2f64:
; V128: # %bb.0:
; V128-NEXT: csrr a0, vlenb
; V128-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; V128-NEXT: vmv1r.v v12, v9
; V128-NEXT: vid.v v9
; V128-NEXT: vid.v v10
; V128-NEXT: srli a0, a0, 3
; V128-NEXT: vsrl.vi v10, v10, 1
; V128-NEXT: vslidedown.vx v12, v10, a0
; V128-NEXT: vsetvli a0, zero, e64, m1, ta, ma
; V128-NEXT: vrgatherei16.vv v13, v11, v12
; V128-NEXT: vrgatherei16.vv v12, v9, v10
; V128-NEXT: vmv.v.i v0, 10
; V128-NEXT: vsrl.vi v14, v9, 1
; V128-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; V128-NEXT: vrgatherei16.vv v10, v8, v14
; V128-NEXT: vrgatherei16.vv v10, v12, v14, v0.t
; V128-NEXT: vmv.v.v v8, v10
; V128-NEXT: vrgatherei16.vv v14, v8, v10
; V128-NEXT: vmv.v.v v15, v13
; V128-NEXT: vsetivli zero, 4, e64, m2, ta, ma
; V128-NEXT: vmerge.vvm v8, v14, v12, v0
; V128-NEXT: ret
;
; RV32-V512-LABEL: interleave_v2f64:
Expand Down
19 changes: 12 additions & 7 deletions llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,15 +51,20 @@ define <4 x i32> @interleave_v2i32(<2 x i32> %x, <2 x i32> %y) {
define <4 x i64> @interleave_v2i64(<2 x i64> %x, <2 x i64> %y) {
; V128-LABEL: interleave_v2i64:
; V128: # %bb.0:
; V128-NEXT: csrr a0, vlenb
; V128-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; V128-NEXT: vmv1r.v v12, v9
; V128-NEXT: vid.v v9
; V128-NEXT: vid.v v10
; V128-NEXT: srli a0, a0, 3
; V128-NEXT: vsrl.vi v10, v10, 1
; V128-NEXT: vslidedown.vx v12, v10, a0
; V128-NEXT: vsetvli a0, zero, e64, m1, ta, ma
; V128-NEXT: vrgatherei16.vv v13, v11, v12
; V128-NEXT: vrgatherei16.vv v12, v9, v10
; V128-NEXT: vmv.v.i v0, 10
; V128-NEXT: vsrl.vi v14, v9, 1
; V128-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; V128-NEXT: vrgatherei16.vv v10, v8, v14
; V128-NEXT: vrgatherei16.vv v10, v12, v14, v0.t
; V128-NEXT: vmv.v.v v8, v10
; V128-NEXT: vrgatherei16.vv v14, v8, v10
; V128-NEXT: vmv.v.v v15, v13
; V128-NEXT: vsetivli zero, 4, e64, m2, ta, ma
; V128-NEXT: vmerge.vvm v8, v14, v12, v0
; V128-NEXT: ret
;
; RV32-V512-LABEL: interleave_v2i64:
Expand Down
58 changes: 45 additions & 13 deletions llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -817,13 +817,17 @@ define <8 x i32> @shuffle_spread2_singlesrc_e32_index1(<8 x i32> %v) {
define <8 x i32> @shuffle_spread2_singlesrc_e32_index2(<8 x i32> %v) {
; CHECK-LABEL: shuffle_spread2_singlesrc_e32_index2:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vid.v v10
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: vsrl.vi v10, v10, 1
; CHECK-NEXT: vadd.vi v12, v10, -1
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT: vslidedown.vx v10, v12, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v11, v9, v10
; CHECK-NEXT: vrgatherei16.vv v10, v8, v12
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: vmv2r.v v8, v10
; CHECK-NEXT: ret
%out = shufflevector <8 x i32> %v, <8 x i32> poison, <8 x i32> <i32 undef, i32 undef, i32 0, i32 undef, i32 1, i32 undef, i32 2, i32 undef>
ret <8 x i32> %out
Expand All @@ -836,9 +840,13 @@ define <8 x i32> @shuffle_spread3_singlesrc_e32(<8 x i32> %v) {
; CHECK-NEXT: vmv.v.i v10, 0
; CHECK-NEXT: li a0, 1
; CHECK-NEXT: vslide1down.vx v12, v10, a0
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, ma
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: vslidedown.vx v10, v12, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v11, v9, v10
; CHECK-NEXT: vrgatherei16.vv v10, v8, v12
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: vmv2r.v v8, v10
; CHECK-NEXT: ret
%out = shufflevector <8 x i32> %v, <8 x i32> poison, <8 x i32> <i32 0, i32 undef, i32 undef, i32 1, i32 undef, i32 undef, i32 2, i32 undef>
ret <8 x i32> %out
Expand All @@ -848,12 +856,16 @@ define <8 x i32> @shuffle_spread3_singlesrc_e32(<8 x i32> %v) {
define <8 x i32> @shuffle_spread4_singlesrc_e32(<8 x i32> %v) {
; CHECK-LABEL: shuffle_spread4_singlesrc_e32:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vid.v v10
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: vsrl.vi v12, v10, 2
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT: vslidedown.vx v10, v12, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v11, v9, v10
; CHECK-NEXT: vrgatherei16.vv v10, v8, v12
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: vmv2r.v v8, v10
; CHECK-NEXT: ret
%out = shufflevector <8 x i32> %v, <8 x i32> poison, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 1, i32 undef, i32 undef, i32 undef>
ret <8 x i32> %out
Expand Down Expand Up @@ -980,12 +992,16 @@ define <8 x i32> @shuffle_repeat3_singlesrc_e32(<8 x i32> %v) {
; CHECK-NEXT: vmv.v.i v11, 1
; CHECK-NEXT: li a0, 192
; CHECK-NEXT: vmv.s.x v10, a0
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: vmerge.vim v11, v11, 0, v0
; CHECK-NEXT: vmv.v.v v0, v10
; CHECK-NEXT: vmerge.vim v12, v11, 2, v0
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: vslidedown.vx v10, v12, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v11, v9, v10
; CHECK-NEXT: vrgatherei16.vv v10, v8, v12
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: vmv2r.v v8, v10
; CHECK-NEXT: ret
%out = shufflevector <8 x i32> %v, <8 x i32> poison, <8 x i32> <i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 2, i32 2>
ret <8 x i32> %out
Expand All @@ -994,12 +1010,16 @@ define <8 x i32> @shuffle_repeat3_singlesrc_e32(<8 x i32> %v) {
define <8 x i32> @shuffle_repeat4_singlesrc_e32(<8 x i32> %v) {
; CHECK-LABEL: shuffle_repeat4_singlesrc_e32:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vid.v v10
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: vsrl.vi v12, v10, 2
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
; CHECK-NEXT: vslidedown.vx v10, v12, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v11, v9, v10
; CHECK-NEXT: vrgatherei16.vv v10, v8, v12
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: vmv2r.v v8, v10
; CHECK-NEXT: ret
%out = shufflevector <8 x i32> %v, <8 x i32> poison, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1>
ret <8 x i32> %out
Expand Down Expand Up @@ -1291,11 +1311,23 @@ define void @shuffle_i128_splat(ptr %p) nounwind {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; CHECK-NEXT: vle64.v v8, (a0)
; CHECK-NEXT: lui a1, 16
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: lui a2, 16
; CHECK-NEXT: srli a1, a1, 3
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vmv.v.x v12, a1
; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; CHECK-NEXT: vmv.v.x v12, a2
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v13, v12, a1
Copy link
Collaborator Author

@preames preames Feb 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just to note here, we can do better for the splat cases. Since these share the same indices for all dest components, we can reuse a single source. However, we can also go further and just do a single m1 shuffle followed by a series of whole register moves. I'm planning a change for this down the road.

; CHECK-NEXT: vslidedown.vx v14, v13, a1
; CHECK-NEXT: vsetvli a2, zero, e64, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v17, v9, v13
; CHECK-NEXT: vrgatherei16.vv v16, v8, v12
; CHECK-NEXT: vrgatherei16.vv v18, v10, v14
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v14, a1
; CHECK-NEXT: vsetvli a1, zero, e64, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v19, v11, v8
; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, ma
; CHECK-NEXT: vse64.v v16, (a0)
; CHECK-NEXT: ret
%a = load <4 x i128>, ptr %p
Expand Down
105 changes: 71 additions & 34 deletions llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-changes-length.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,10 +237,15 @@ define <8 x i32> @v8i32_v4i32(<4 x i32>) {
; CHECK: # %bb.0:
; CHECK-NEXT: lui a0, %hi(.LCPI5_0)
; CHECK-NEXT: addi a0, a0, %lo(.LCPI5_0)
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; CHECK-NEXT: vle16.v v12, (a0)
; CHECK-NEXT: vrgatherei16.vv v10, v8, v12
; CHECK-NEXT: vmv.v.v v8, v10
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vle16.v v9, (a0)
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: vslidedown.vx v10, v9, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v11, v12, v10
; CHECK-NEXT: vrgatherei16.vv v10, v8, v9
; CHECK-NEXT: vmv2r.v v8, v10
; CHECK-NEXT: ret
%2 = shufflevector <4 x i32> %0, <4 x i32> poison, <8 x i32> <i32 2, i32 3, i32 0, i32 1, i32 1, i32 2, i32 0, i32 3>
ret <8 x i32> %2
Expand All @@ -249,30 +254,38 @@ define <8 x i32> @v8i32_v4i32(<4 x i32>) {
define <16 x i32> @v16i32_v4i32(<4 x i32>) {
; CHECK-LABEL: v16i32_v4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: lui a0, 2
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vmv.v.i v9, 3
; CHECK-NEXT: vmv1r.v v10, v8
; CHECK-NEXT: lui a0, 2
; CHECK-NEXT: vmv.v.i v11, 3
; CHECK-NEXT: addi a1, a0, 265
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.s.x v0, a1
; CHECK-NEXT: lui a1, 4
; CHECK-NEXT: addi a1, a1, 548
; CHECK-NEXT: vsetvli zero, zero, e8, m1, ta, ma
; CHECK-NEXT: vmerge.vim v9, v9, 2, v0
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.s.x v0, a1
; CHECK-NEXT: vmv.s.x v8, a1
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: addi a0, a0, -1856
; CHECK-NEXT: srli a1, a1, 2
; CHECK-NEXT: vmv.s.x v9, a0
; CHECK-NEXT: vsetvli zero, zero, e8, m1, ta, ma
; CHECK-NEXT: vmerge.vim v9, v9, 0, v0
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.s.x v0, a0
; CHECK-NEXT: vsetvli zero, zero, e8, m1, ta, ma
; CHECK-NEXT: vmerge.vim v9, v9, 1, v0
; CHECK-NEXT: vmerge.vim v11, v11, 2, v0
; CHECK-NEXT: vmv1r.v v0, v8
; CHECK-NEXT: vmerge.vim v8, v11, 0, v0
; CHECK-NEXT: vmv1r.v v0, v9
; CHECK-NEXT: vmerge.vim v8, v8, 1, v0
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vsext.vf2 v16, v9
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, ma
; CHECK-NEXT: vrgatherei16.vv v12, v8, v16
; CHECK-NEXT: vmv.v.v v8, v12
; CHECK-NEXT: vsext.vf2 v14, v8
; CHECK-NEXT: vslidedown.vx v16, v14, a1
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v9, v12, v16
; CHECK-NEXT: vrgatherei16.vv v8, v10, v14
; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, ma
; CHECK-NEXT: vslidedown.vx v12, v16, a1
; CHECK-NEXT: vslidedown.vx v14, v12, a1
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v10, v11, v12
; CHECK-NEXT: vrgatherei16.vv v11, v12, v14
; CHECK-NEXT: ret
%2 = shufflevector <4 x i32> %0, <4 x i32> poison, <16 x i32> <i32 2, i32 3, i32 0, i32 2, i32 3, i32 0, i32 1, i32 1, i32 2, i32 0, i32 3, i32 1, i32 1, i32 2, i32 0, i32 3>
ret <16 x i32> %2
Expand All @@ -281,31 +294,55 @@ define <16 x i32> @v16i32_v4i32(<4 x i32>) {
define <32 x i32> @v32i32_v4i32(<4 x i32>) {
; CHECK-LABEL: v32i32_v4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 1, e32, m4, ta, ma
; CHECK-NEXT: vmv1r.v v10, v8
; CHECK-NEXT: li a0, 32
; CHECK-NEXT: lui a1, 135432
; CHECK-NEXT: addi a1, a1, 1161
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, ma
; CHECK-NEXT: vmv.s.x v0, a1
; CHECK-NEXT: lui a1, 270865
; CHECK-NEXT: addi a1, a1, 548
; CHECK-NEXT: vmv.s.x v9, a1
; CHECK-NEXT: vmv.s.x v8, a1
; CHECK-NEXT: lui a1, 100550
; CHECK-NEXT: addi a1, a1, 64
; CHECK-NEXT: vmv.s.x v9, a1
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: vsetvli zero, a0, e8, m2, ta, ma
; CHECK-NEXT: vmv.v.i v10, 3
; CHECK-NEXT: addi a0, a1, 64
; CHECK-NEXT: vmerge.vim v18, v10, 2, v0
; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; CHECK-NEXT: vmv.s.x v16, a0
; CHECK-NEXT: vmv.v.i v12, 3
; CHECK-NEXT: srli a1, a1, 2
; CHECK-NEXT: vmerge.vim v12, v12, 2, v0
; CHECK-NEXT: vmv1r.v v0, v8
; CHECK-NEXT: vmerge.vim v12, v12, 0, v0
; CHECK-NEXT: vmv1r.v v0, v9
; CHECK-NEXT: vsetvli zero, zero, e8, m2, ta, ma
; CHECK-NEXT: vmerge.vim v18, v18, 0, v0
; CHECK-NEXT: vmv1r.v v0, v16
; CHECK-NEXT: vmerge.vim v16, v18, 1, v0
; CHECK-NEXT: vmerge.vim v8, v12, 1, v0
; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; CHECK-NEXT: vsext.vf2 v24, v16
; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, ma
; CHECK-NEXT: vrgatherei16.vv v16, v8, v24
; CHECK-NEXT: vmv.v.v v8, v16
; CHECK-NEXT: vsext.vf2 v16, v8
; CHECK-NEXT: vslidedown.vx v12, v16, a1
; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v9, v11, v12
; CHECK-NEXT: vrgatherei16.vv v8, v10, v16
; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT: vslidedown.vx v12, v12, a1
; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v10, v11, v12
; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT: vslidedown.vx v12, v12, a1
; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v11, v16, v12
; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT: vslidedown.vx v20, v12, a1
; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v12, v17, v20
; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT: vslidedown.vx v20, v20, a1
; CHECK-NEXT: vsetvli a2, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v13, v18, v20
; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
; CHECK-NEXT: vslidedown.vx v20, v20, a1
; CHECK-NEXT: vslidedown.vx v24, v20, a1
; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
; CHECK-NEXT: vrgatherei16.vv v14, v19, v20
; CHECK-NEXT: vrgatherei16.vv v15, v16, v24
; CHECK-NEXT: ret
%2 = shufflevector <4 x i32> %0, <4 x i32> poison, <32 x i32> <i32 2, i32 3, i32 0, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 2, i32 3, i32 0, i32 1, i32 1, i32 2, i32 0, i32 3, i32 1, i32 1, i32 2, i32 0, i32 3, i32 1, i32 2, i32 0, i32 3, i32 1, i32 1, i32 2, i32 0, i32 3>
ret <32 x i32> %2
Expand Down