[RISCV] Add tests for vector.deinterleave2s of loads

Reviewed By: reames

Differential Revision: https://reviews.llvm.org/D153875

diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vector-deinterleave-load.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vector-deinterleave-load.ll
new file mode 100644 (file)
index 0000000..654ef66
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vector-deinterleave-load.ll
@@ -0,0 +1,241 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=riscv32 -mattr=+v,+zfh,+experimental-zvfh | FileCheck %s -check-prefixes=CHECK,RV32
+; RUN: llc < %s -mtriple=riscv64 -mattr=+v,+zfh,+experimental-zvfh | FileCheck %s -check-prefixes=CHECK,RV64
+
+; Integers
+
+define {<16 x i1>, <16 x i1>} @vector_deinterleave_load_v16i1_v32i1(ptr %p) {
+; RV32-LABEL: vector_deinterleave_load_v16i1_v32i1:
+; RV32:       # %bb.0:
+; RV32-NEXT:    li a1, 32
+; RV32-NEXT:    vsetvli zero, a1, e8, m2, ta, ma
+; RV32-NEXT:    vlm.v v8, (a0)
+; RV32-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
+; RV32-NEXT:    vslidedown.vi v0, v8, 2
+; RV32-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
+; RV32-NEXT:    vmv.v.i v9, 0
+; RV32-NEXT:    vmerge.vim v10, v9, 1, v0
+; RV32-NEXT:    vmv1r.v v0, v8
+; RV32-NEXT:    vmerge.vim v8, v9, 1, v0
+; RV32-NEXT:    vid.v v9
+; RV32-NEXT:    vadd.vv v11, v9, v9
+; RV32-NEXT:    vrgather.vv v9, v8, v11
+; RV32-NEXT:    vadd.vi v12, v11, -16
+; RV32-NEXT:    lui a0, 16
+; RV32-NEXT:    addi a0, a0, -256
+; RV32-NEXT:    vsetivli zero, 1, e16, mf4, ta, ma
+; RV32-NEXT:    vmv.v.x v0, a0
+; RV32-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; RV32-NEXT:    vrgather.vv v9, v10, v12, v0.t
+; RV32-NEXT:    vmsne.vi v9, v9, 0
+; RV32-NEXT:    vadd.vi v12, v11, 1
+; RV32-NEXT:    vrgather.vv v13, v8, v12
+; RV32-NEXT:    vadd.vi v8, v11, -15
+; RV32-NEXT:    vrgather.vv v13, v10, v8, v0.t
+; RV32-NEXT:    vmsne.vi v8, v13, 0
+; RV32-NEXT:    vmv.v.v v0, v9
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: vector_deinterleave_load_v16i1_v32i1:
+; RV64:       # %bb.0:
+; RV64-NEXT:    li a1, 32
+; RV64-NEXT:    vsetvli zero, a1, e8, m2, ta, ma
+; RV64-NEXT:    vlm.v v8, (a0)
+; RV64-NEXT:    vsetivli zero, 2, e8, mf4, ta, ma
+; RV64-NEXT:    vslidedown.vi v0, v8, 2
+; RV64-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
+; RV64-NEXT:    vmv.v.i v9, 0
+; RV64-NEXT:    vmerge.vim v10, v9, 1, v0
+; RV64-NEXT:    vmv1r.v v0, v8
+; RV64-NEXT:    vmerge.vim v8, v9, 1, v0
+; RV64-NEXT:    vid.v v9
+; RV64-NEXT:    vadd.vv v11, v9, v9
+; RV64-NEXT:    vrgather.vv v9, v8, v11
+; RV64-NEXT:    vadd.vi v12, v11, -16
+; RV64-NEXT:    lui a0, 16
+; RV64-NEXT:    addiw a0, a0, -256
+; RV64-NEXT:    vsetivli zero, 1, e16, mf4, ta, ma
+; RV64-NEXT:    vmv.v.x v0, a0
+; RV64-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
+; RV64-NEXT:    vrgather.vv v9, v10, v12, v0.t
+; RV64-NEXT:    vmsne.vi v9, v9, 0
+; RV64-NEXT:    vadd.vi v12, v11, 1
+; RV64-NEXT:    vrgather.vv v13, v8, v12
+; RV64-NEXT:    vadd.vi v8, v11, -15
+; RV64-NEXT:    vrgather.vv v13, v10, v8, v0.t
+; RV64-NEXT:    vmsne.vi v8, v13, 0
+; RV64-NEXT:    vmv.v.v v0, v9
+; RV64-NEXT:    ret
+  %vec = load <32 x i1>, ptr %p
+  %retval = call {<16 x i1>, <16 x i1>} @llvm.experimental.vector.deinterleave2.v32i1(<32 x i1> %vec)
+  ret {<16 x i1>, <16 x i1>} %retval
+}
+
+define {<16 x i8>, <16 x i8>} @vector_deinterleave_load_v16i8_v32i8(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v16i8_v32i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a1, 32
+; CHECK-NEXT:    vsetvli zero, a1, e8, m2, ta, ma
+; CHECK-NEXT:    vle8.v v10, (a0)
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v10, 0
+; CHECK-NEXT:    vnsrl.wi v9, v10, 8
+; CHECK-NEXT:    ret
+  %vec = load <32 x i8>, ptr %p
+  %retval = call {<16 x i8>, <16 x i8>} @llvm.experimental.vector.deinterleave2.v32i8(<32 x i8> %vec)
+  ret {<16 x i8>, <16 x i8>} %retval
+}
+
+define {<8 x i16>, <8 x i16>} @vector_deinterleave_load_v8i16_v16i16(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v8i16_v16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT:    vle16.v v10, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v10, 0
+; CHECK-NEXT:    vnsrl.wi v9, v10, 16
+; CHECK-NEXT:    ret
+  %vec = load <16 x i16>, ptr %p
+  %retval = call {<8 x i16>, <8 x i16>} @llvm.experimental.vector.deinterleave2.v16i16(<16 x i16> %vec)
+  ret {<8 x i16>, <8 x i16>} %retval
+}
+
+define {<4 x i32>, <4 x i32>} @vector_deinterleave_load_v4i32_vv8i32(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v4i32_vv8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; CHECK-NEXT:    vle32.v v10, (a0)
+; CHECK-NEXT:    li a0, 32
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vnsrl.wx v9, v10, a0
+; CHECK-NEXT:    vnsrl.wi v8, v10, 0
+; CHECK-NEXT:    ret
+  %vec = load <8 x i32>, ptr %p
+  %retval = call {<4 x i32>, <4 x i32>} @llvm.experimental.vector.deinterleave2.v8i32(<8 x i32> %vec)
+  ret {<4 x i32>, <4 x i32>} %retval
+}
+
+define {<2 x i64>, <2 x i64>} @vector_deinterleave_load_v2i64_v4i64(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v2i64_v4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e64, m2, ta, ma
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetivli zero, 2, e64, m2, ta, ma
+; CHECK-NEXT:    vslidedown.vi v10, v8, 2
+; CHECK-NEXT:    vsetivli zero, 1, e8, mf8, ta, ma
+; CHECK-NEXT:    vmv.v.i v0, 2
+; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
+; CHECK-NEXT:    vrgather.vi v9, v8, 1
+; CHECK-NEXT:    vrgather.vi v9, v10, 1, v0.t
+; CHECK-NEXT:    vslideup.vi v8, v10, 1
+; CHECK-NEXT:    ret
+  %vec = load <4 x i64>, ptr %p
+  %retval = call {<2 x i64>, <2 x i64>} @llvm.experimental.vector.deinterleave2.v4i64(<4 x i64> %vec)
+  ret {<2 x i64>, <2 x i64>} %retval
+}
+
+declare {<16 x i1>, <16 x i1>} @llvm.experimental.vector.deinterleave2.v32i1(<32 x i1>)
+declare {<16 x i8>, <16 x i8>} @llvm.experimental.vector.deinterleave2.v32i8(<32 x i8>)
+declare {<8 x i16>, <8 x i16>} @llvm.experimental.vector.deinterleave2.v16i16(<16 x i16>)
+declare {<4 x i32>, <4 x i32>} @llvm.experimental.vector.deinterleave2.v8i32(<8 x i32>)
+declare {<2 x i64>, <2 x i64>} @llvm.experimental.vector.deinterleave2.v4i64(<4 x i64>)
+
+; Floats
+
+define {<2 x half>, <2 x half>} @vector_deinterleave_load_v2f16_v4f16(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v2f16_v4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 2, e16, mf4, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v9, 0
+; CHECK-NEXT:    vnsrl.wi v9, v9, 16
+; CHECK-NEXT:    ret
+  %vec = load <4 x half>, ptr %p
+  %retval = call {<2 x half>, <2 x half>} @llvm.experimental.vector.deinterleave2.v4f16(<4 x half> %vec)
+  ret {<2 x half>, <2 x half>} %retval
+}
+
+define {<4 x half>, <4 x half>} @vector_deinterleave_load_v4f16_v8f16(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v4f16_v8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vle16.v v9, (a0)
+; CHECK-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v9, 0
+; CHECK-NEXT:    vnsrl.wi v9, v9, 16
+; CHECK-NEXT:    ret
+  %vec = load <8 x half>, ptr %p
+  %retval = call {<4 x half>, <4 x half>} @llvm.experimental.vector.deinterleave2.v8f16(<8 x half> %vec)
+  ret {<4 x half>, <4 x half>} %retval
+}
+
+define {<2 x float>, <2 x float>} @vector_deinterleave_load_v2f32_v4f32(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v2f32_v4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    li a0, 32
+; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT:    vnsrl.wx v9, v8, a0
+; CHECK-NEXT:    vnsrl.wi v8, v8, 0
+; CHECK-NEXT:    ret
+  %vec = load <4 x float>, ptr %p
+  %retval = call {<2 x float>, <2 x float>} @llvm.experimental.vector.deinterleave2.v4f32(<4 x float> %vec)
+  ret {<2 x float>, <2 x float>} %retval
+}
+
+define {<8 x half>, <8 x half>} @vector_deinterleave_load_v8f16_v16f16(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v8f16_v16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 16, e16, m2, ta, ma
+; CHECK-NEXT:    vle16.v v10, (a0)
+; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v10, 0
+; CHECK-NEXT:    vnsrl.wi v9, v10, 16
+; CHECK-NEXT:    ret
+  %vec = load <16 x half>, ptr %p
+  %retval = call {<8 x half>, <8 x half>} @llvm.experimental.vector.deinterleave2.v16f16(<16 x half> %vec)
+  ret {<8 x half>, <8 x half>} %retval
+}
+
+define {<4 x float>, <4 x float>} @vector_deinterleave_load_v4f32_v8f32(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v4f32_v8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
+; CHECK-NEXT:    vle32.v v10, (a0)
+; CHECK-NEXT:    li a0, 32
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vnsrl.wx v9, v10, a0
+; CHECK-NEXT:    vnsrl.wi v8, v10, 0
+; CHECK-NEXT:    ret
+  %vec = load <8 x float>, ptr %p
+  %retval = call {<4 x float>, <4 x float>} @llvm.experimental.vector.deinterleave2.v8f32(<8 x float> %vec)
+  ret  {<4 x float>, <4 x float>} %retval
+}
+
+define {<2 x double>, <2 x double>} @vector_deinterleave_load_v2f64_v4f64(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_v2f64_v4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e64, m2, ta, ma
+; CHECK-NEXT:    vle64.v v8, (a0)
+; CHECK-NEXT:    vsetivli zero, 2, e64, m2, ta, ma
+; CHECK-NEXT:    vslidedown.vi v10, v8, 2
+; CHECK-NEXT:    vsetivli zero, 1, e8, mf8, ta, ma
+; CHECK-NEXT:    vmv.v.i v0, 2
+; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
+; CHECK-NEXT:    vrgather.vi v9, v8, 1
+; CHECK-NEXT:    vrgather.vi v9, v10, 1, v0.t
+; CHECK-NEXT:    vslideup.vi v8, v10, 1
+; CHECK-NEXT:    ret
+  %vec = load <4 x double>, ptr %p
+  %retval = call {<2 x double>, <2 x double>} @llvm.experimental.vector.deinterleave2.v4f64(<4 x double> %vec)
+  ret {<2 x double>, <2 x double>} %retval
+}
+
+declare {<2 x half>,<2 x half>} @llvm.experimental.vector.deinterleave2.v4f16(<4 x half>)
+declare {<4 x half>, <4 x half>} @llvm.experimental.vector.deinterleave2.v8f16(<8 x half>)
+declare {<2 x float>, <2 x float>} @llvm.experimental.vector.deinterleave2.v4f32(<4 x float>)
+declare {<8 x half>, <8 x half>} @llvm.experimental.vector.deinterleave2.v16f16(<16 x half>)
+declare {<4 x float>, <4 x float>} @llvm.experimental.vector.deinterleave2.v8f32(<8 x float>)
+declare {<2 x double>, <2 x double>} @llvm.experimental.vector.deinterleave2.v4f64(<4 x double>)

diff --git a/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-load.ll b/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-load.ll
new file mode 100644 (file)
index 0000000..17bb68a
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-load.ll
@@ -0,0 +1,265 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=riscv32 -mattr=+v,+zfh,+experimental-zvfh,+m | FileCheck %s
+; RUN: llc < %s -mtriple=riscv64 -mattr=+v,+zfh,+experimental-zvfh,+m | FileCheck %s
+
+; Integers
+
+define {<vscale x 16 x i1>, <vscale x 16 x i1>} @vector_deinterleave_load_nxv16i1_nxv32i1(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv16i1_nxv32i1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e8, m4, ta, ma
+; CHECK-NEXT:    vlm.v v8, (a0)
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 2
+; CHECK-NEXT:    vsetvli a1, zero, e8, mf2, ta, ma
+; CHECK-NEXT:    vslidedown.vx v0, v8, a0
+; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, ma
+; CHECK-NEXT:    vmv.v.i v10, 0
+; CHECK-NEXT:    vmerge.vim v14, v10, 1, v0
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v12, v10, 1, v0
+; CHECK-NEXT:    vnsrl.wi v8, v12, 0
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
+; CHECK-NEXT:    vnsrl.wi v10, v12, 8
+; CHECK-NEXT:    vmsne.vi v8, v10, 0
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 32 x i1>, ptr %p
+  %retval = call {<vscale x 16 x i1>, <vscale x 16 x i1>} @llvm.experimental.vector.deinterleave2.nxv32i1(<vscale x 32 x i1> %vec)
+  ret {<vscale x 16 x i1>, <vscale x 16 x i1>} %retval
+}
+
+define {<vscale x 16 x i8>, <vscale x 16 x i8>} @vector_deinterleave_load_nxv16i8_nxv32i8(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv16i8_nxv32i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl4r.v v12, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v12, 0
+; CHECK-NEXT:    vnsrl.wi v10, v12, 8
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 32 x i8>, ptr %p
+  %retval = call {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.experimental.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> %vec)
+  ret {<vscale x 16 x i8>, <vscale x 16 x i8>} %retval
+}
+
+define {<vscale x 8 x i16>, <vscale x 8 x i16>} @vector_deinterleave_load_nxv8i16_nxv16i16(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv8i16_nxv16i16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl4re16.v v12, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v12, 0
+; CHECK-NEXT:    vnsrl.wi v10, v12, 16
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 16 x i16>, ptr %p
+  %retval = call {<vscale x 8 x i16>, <vscale x 8 x i16>} @llvm.experimental.vector.deinterleave2.nxv16i16(<vscale x 16 x i16> %vec)
+  ret {<vscale x 8 x i16>, <vscale x 8 x i16>} %retval
+}
+
+define {<vscale x 4 x i32>, <vscale x 4 x i32>} @vector_deinterleave_load_nxv4i32_nxvv8i32(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv4i32_nxvv8i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl4re32.v v12, (a0)
+; CHECK-NEXT:    li a0, 32
+; CHECK-NEXT:    vsetvli a1, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vnsrl.wx v10, v12, a0
+; CHECK-NEXT:    vnsrl.wi v8, v12, 0
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 8 x i32>, ptr %p
+  %retval = call {<vscale x 4 x i32>, <vscale x 4 x i32>} @llvm.experimental.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %vec)
+  ret {<vscale x 4 x i32>, <vscale x 4 x i32>} %retval
+}
+
+define {<vscale x 2 x i64>, <vscale x 2 x i64>} @vector_deinterleave_load_nxv2i64_nxv4i64(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv2i64_nxv4i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl4re64.v v12, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vid.v v8
+; CHECK-NEXT:    vadd.vv v16, v8, v8
+; CHECK-NEXT:    vrgather.vv v8, v12, v16
+; CHECK-NEXT:    vadd.vi v16, v16, 1
+; CHECK-NEXT:    vrgather.vv v20, v12, v16
+; CHECK-NEXT:    vmv2r.v v10, v20
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 4 x i64>, ptr %p
+  %retval = call {<vscale x 2 x i64>, <vscale x 2 x i64>} @llvm.experimental.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> %vec)
+  ret {<vscale x 2 x i64>, <vscale x 2 x i64>} %retval
+}
+
+define {<vscale x 4 x i64>, <vscale x 4 x i64>} @vector_deinterleave_load_nxv4i64_nxv8i64(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv4i64_nxv8i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl8re64.v v16, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vid.v v8
+; CHECK-NEXT:    vadd.vv v24, v8, v8
+; CHECK-NEXT:    vrgather.vv v8, v16, v24
+; CHECK-NEXT:    vadd.vi v24, v24, 1
+; CHECK-NEXT:    vrgather.vv v0, v16, v24
+; CHECK-NEXT:    vmv4r.v v12, v0
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 8 x i64>, ptr %p
+  %retval = call {<vscale x 4 x i64>, <vscale x 4 x i64>} @llvm.experimental.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> %vec)
+  ret {<vscale x 4 x i64>, <vscale x 4 x i64>} %retval
+}
+
+; This shouldn't be lowered to a vlseg because EMUL * NFIELDS >= 8
+define {<vscale x 8 x i64>, <vscale x 8 x i64>} @vector_deinterleave_load_nxv8i64_nxv16i64(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv8i64_nxv16i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    li a2, 24
+; CHECK-NEXT:    mul a1, a1, a2
+; CHECK-NEXT:    sub sp, sp, a1
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 24 * vlenb
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 3
+; CHECK-NEXT:    add a1, a0, a1
+; CHECK-NEXT:    vl8re64.v v16, (a1)
+; CHECK-NEXT:    vl8re64.v v24, (a0)
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, ma
+; CHECK-NEXT:    vid.v v8
+; CHECK-NEXT:    vadd.vv v0, v8, v8
+; CHECK-NEXT:    vrgather.vv v8, v24, v0
+; CHECK-NEXT:    vrgather.vv v24, v16, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    vadd.vi v0, v0, 1
+; CHECK-NEXT:    vrgather.vv v24, v16, v0
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vs8r.v v24, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vl8r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vrgather.vv v16, v24, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vl8r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmv4r.v v12, v24
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmv4r.v v20, v24
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    li a1, 24
+; CHECK-NEXT:    mul a0, a0, a1
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 16 x i64>, ptr %p
+  %retval = call {<vscale x 8 x i64>, <vscale x 8 x i64>} @llvm.experimental.vector.deinterleave2.nxv16i64(<vscale x 16 x i64> %vec)
+  ret {<vscale x 8 x i64>, <vscale x 8 x i64>} %retval
+}
+
+declare {<vscale x 16 x i1>, <vscale x 16 x i1>} @llvm.experimental.vector.deinterleave2.nxv32i1(<vscale x 32 x i1>)
+declare {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.experimental.vector.deinterleave2.nxv32i8(<vscale x 32 x i8>)
+declare {<vscale x 8 x i16>, <vscale x 8 x i16>} @llvm.experimental.vector.deinterleave2.nxv16i16(<vscale x 16 x i16>)
+declare {<vscale x 4 x i32>, <vscale x 4 x i32>} @llvm.experimental.vector.deinterleave2.nxv8i32(<vscale x 8 x i32>)
+declare {<vscale x 2 x i64>, <vscale x 2 x i64>} @llvm.experimental.vector.deinterleave2.nxv4i64(<vscale x 4 x i64>)
+declare {<vscale x 4 x i64>, <vscale x 4 x i64>} @llvm.experimental.vector.deinterleave2.nxv8i64(<vscale x 8 x i64>)
+declare {<vscale x 8 x i64>, <vscale x 8 x i64>} @llvm.experimental.vector.deinterleave2.nxv16i64(<vscale x 16 x i64>)
+
+; Floats
+
+define {<vscale x 2 x half>, <vscale x 2 x half>} @vector_deinterleave_load_nxv2f16_nxv4f16(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv2f16_nxv4f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl1re16.v v9, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, mf2, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v9, 0
+; CHECK-NEXT:    vnsrl.wi v9, v9, 16
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 4 x half>, ptr %p
+  %retval = call {<vscale x 2 x half>, <vscale x 2 x half>} @llvm.experimental.vector.deinterleave2.nxv4f16(<vscale x 4 x half> %vec)
+  ret {<vscale x 2 x half>, <vscale x 2 x half>} %retval
+}
+
+define {<vscale x 4 x half>, <vscale x 4 x half>} @vector_deinterleave_load_nxv4f16_nxv8f16(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv4f16_nxv8f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl2re16.v v10, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, m1, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v10, 0
+; CHECK-NEXT:    vnsrl.wi v9, v10, 16
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 8 x half>, ptr %p
+  %retval = call {<vscale x 4 x half>, <vscale x 4 x half>} @llvm.experimental.vector.deinterleave2.nxv8f16(<vscale x 8 x half> %vec)
+  ret {<vscale x 4 x half>, <vscale x 4 x half>} %retval
+}
+
+define {<vscale x 2 x float>, <vscale x 2 x float>} @vector_deinterleave_load_nxv2f32_nxv4f32(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv2f32_nxv4f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl2re32.v v10, (a0)
+; CHECK-NEXT:    li a0, 32
+; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vnsrl.wx v9, v10, a0
+; CHECK-NEXT:    vnsrl.wi v8, v10, 0
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 4 x float>, ptr %p
+  %retval = call {<vscale x 2 x float>, <vscale x 2 x float>} @llvm.experimental.vector.deinterleave2.nxv4f32(<vscale x 4 x float> %vec)
+  ret {<vscale x 2 x float>, <vscale x 2 x float>} %retval
+}
+
+define {<vscale x 8 x half>, <vscale x 8 x half>} @vector_deinterleave_load_nxv8f16_nxv16f16(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv8f16_nxv16f16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl4re16.v v12, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, ma
+; CHECK-NEXT:    vnsrl.wi v8, v12, 0
+; CHECK-NEXT:    vnsrl.wi v10, v12, 16
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 16 x half>, ptr %p
+  %retval = call {<vscale x 8 x half>, <vscale x 8 x half>} @llvm.experimental.vector.deinterleave2.nxv16f16(<vscale x 16 x half> %vec)
+  ret {<vscale x 8 x half>, <vscale x 8 x half>} %retval
+}
+
+define {<vscale x 4 x float>, <vscale x 4 x float>} @vector_deinterleave_load_nxv4f32_nxv8f32(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv4f32_nxv8f32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl4re32.v v12, (a0)
+; CHECK-NEXT:    li a0, 32
+; CHECK-NEXT:    vsetvli a1, zero, e32, m2, ta, ma
+; CHECK-NEXT:    vnsrl.wx v10, v12, a0
+; CHECK-NEXT:    vnsrl.wi v8, v12, 0
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 8 x float>, ptr %p
+  %retval = call {<vscale x 4 x float>, <vscale x 4 x float>} @llvm.experimental.vector.deinterleave2.nxv8f32(<vscale x 8 x float> %vec)
+  ret  {<vscale x 4 x float>, <vscale x 4 x float>} %retval
+}
+
+define {<vscale x 2 x double>, <vscale x 2 x double>} @vector_deinterleave_load_nxv2f64_nxv4f64(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_nxv2f64_nxv4f64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vl4re64.v v12, (a0)
+; CHECK-NEXT:    vsetvli a0, zero, e64, m4, ta, ma
+; CHECK-NEXT:    vid.v v8
+; CHECK-NEXT:    vadd.vv v16, v8, v8
+; CHECK-NEXT:    vrgather.vv v8, v12, v16
+; CHECK-NEXT:    vadd.vi v16, v16, 1
+; CHECK-NEXT:    vrgather.vv v20, v12, v16
+; CHECK-NEXT:    vmv2r.v v10, v20
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 4 x double>, ptr %p
+  %retval = call {<vscale x 2 x double>, <vscale x 2 x double>} @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %vec)
+  ret {<vscale x 2 x double>, <vscale x 2 x double>} %retval
+}
+
+declare {<vscale x 2 x half>,<vscale x 2 x half>} @llvm.experimental.vector.deinterleave2.nxv4f16(<vscale x 4 x half>)
+declare {<vscale x 4 x half>, <vscale x 4 x half>} @llvm.experimental.vector.deinterleave2.nxv8f16(<vscale x 8 x half>)
+declare {<vscale x 2 x float>, <vscale x 2 x float>} @llvm.experimental.vector.deinterleave2.nxv4f32(<vscale x 4 x float>)
+declare {<vscale x 8 x half>, <vscale x 8 x half>} @llvm.experimental.vector.deinterleave2.nxv16f16(<vscale x 16 x half>)
+declare {<vscale x 4 x float>, <vscale x 4 x float>} @llvm.experimental.vector.deinterleave2.nxv8f32(<vscale x 8 x float>)
+declare {<vscale x 2 x double>, <vscale x 2 x double>} @llvm.experimental.vector.deinterleave2.nxv4f64(<vscale x 4 x double>)