File: interleaved-accesses.ll

package info (click to toggle)
llvm-toolchain-20 1%3A20.1.6-1~exp1
links: PTS, VCS
area: main
in suites: experimental
size: 2,111,304 kB
sloc: cpp: 7,438,677; ansic: 1,393,822; asm: 1,012,926; python: 241,650; f90: 86,635; objc: 75,479; lisp: 42,144; pascal: 17,286; sh: 10,027; ml: 5,082; perl: 4,730; awk: 3,523; makefile: 3,349; javascript: 2,251; xml: 892; fortran: 672
file content (679 lines) | stat: -rw-r--r-- 67,959 bytes
parent folder | download | duplicates (2)
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -mtriple=riscv32 -mattr=+v -interleaved-access -S | FileCheck %s --check-prefix=RV32
; RUN: opt < %s -mtriple=riscv64 -mattr=+v -interleaved-access -S | FileCheck %s --check-prefix=RV64
; RUN: opt < %s -mtriple=riscv32 -mattr=+v -passes=interleaved-access -S | FileCheck %s --check-prefix=RV32
; RUN: opt < %s -mtriple=riscv64 -mattr=+v -passes=interleaved-access -S | FileCheck %s --check-prefix=RV64

define void @load_factor2(ptr %ptr) {
; RV32-LABEL: @load_factor2(
; RV32-NEXT:    [[TMP1:%.*]] = call { <8 x i32>, <8 x i32> } @llvm.riscv.seg2.load.v8i32.p0.i32(ptr [[PTR:%.*]], i32 8)
; RV32-NEXT:    [[TMP2:%.*]] = extractvalue { <8 x i32>, <8 x i32> } [[TMP1]], 1
; RV32-NEXT:    [[TMP3:%.*]] = extractvalue { <8 x i32>, <8 x i32> } [[TMP1]], 0
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor2(
; RV64-NEXT:    [[TMP1:%.*]] = call { <8 x i32>, <8 x i32> } @llvm.riscv.seg2.load.v8i32.p0.i64(ptr [[PTR:%.*]], i64 8)
; RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <8 x i32>, <8 x i32> } [[TMP1]], 1
; RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <8 x i32>, <8 x i32> } [[TMP1]], 0
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <16 x i32>, ptr %ptr
  %v0 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %v1 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  ret void
}

define void @load_factor2_as(ptr addrspace(1) %ptr) {
; RV32-LABEL: @load_factor2_as(
; RV32-NEXT:    [[TMP1:%.*]] = call { <8 x i32>, <8 x i32> } @llvm.riscv.seg2.load.v8i32.p1.i32(ptr addrspace(1) [[PTR:%.*]], i32 8)
; RV32-NEXT:    [[TMP2:%.*]] = extractvalue { <8 x i32>, <8 x i32> } [[TMP1]], 1
; RV32-NEXT:    [[TMP3:%.*]] = extractvalue { <8 x i32>, <8 x i32> } [[TMP1]], 0
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor2_as(
; RV64-NEXT:    [[TMP1:%.*]] = call { <8 x i32>, <8 x i32> } @llvm.riscv.seg2.load.v8i32.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 8)
; RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <8 x i32>, <8 x i32> } [[TMP1]], 1
; RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <8 x i32>, <8 x i32> } [[TMP1]], 0
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <16 x i32>, ptr addrspace(1) %ptr
  %v0 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
  %v1 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
  ret void
}

define void @load_factor2_vscale(ptr %ptr) {
; RV32-LABEL: @load_factor2_vscale(
; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @llvm.riscv.vlseg2.triscv.vector.tuple_nxv32i8_2t.i32(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 0)
; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } poison, <vscale x 8 x i32> [[TMP2]], 0
; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 1)
; RV32-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[TMP3]], <vscale x 8 x i32> [[TMP4]], 1
; RV32-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[TMP5]], 0
; RV32-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[TMP5]], 1
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor2_vscale(
; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @llvm.riscv.vlseg2.triscv.vector.tuple_nxv32i8_2t.i64(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 0)
; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } poison, <vscale x 8 x i32> [[TMP2]], 0
; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 1)
; RV64-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[TMP3]], <vscale x 8 x i32> [[TMP4]], 1
; RV64-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[TMP5]], 0
; RV64-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[TMP5]], 1
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <vscale x 16 x i32>, ptr %ptr
  %v = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> %interleaved.vec)
  %t0 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %v, 0
  %t1 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %v, 1
  ret void
}

define void @load_factor2_vscale_as(ptr addrspace(1) %ptr) {
; RV32-LABEL: @load_factor2_vscale_as(
; RV32-NEXT:    [[INTERLEAVED_VEC:%.*]] = load <vscale x 16 x i32>, ptr addrspace(1) [[PTR:%.*]], align 64
; RV32-NEXT:    [[V:%.*]] = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> [[INTERLEAVED_VEC]])
; RV32-NEXT:    [[T0:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[V]], 0
; RV32-NEXT:    [[T1:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[V]], 1
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor2_vscale_as(
; RV64-NEXT:    [[INTERLEAVED_VEC:%.*]] = load <vscale x 16 x i32>, ptr addrspace(1) [[PTR:%.*]], align 64
; RV64-NEXT:    [[V:%.*]] = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> [[INTERLEAVED_VEC]])
; RV64-NEXT:    [[T0:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[V]], 0
; RV64-NEXT:    [[T1:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[V]], 1
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <vscale x 16 x i32>, ptr addrspace(1) %ptr
  %v = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> %interleaved.vec)
  %t0 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %v, 0
  %t1 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %v, 1
  ret void
}

define void @load_factor3(ptr %ptr) {
; RV32-LABEL: @load_factor3(
; RV32-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg3.load.v4i32.p0.i32(ptr [[PTR:%.*]], i32 4)
; RV32-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV32-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV32-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor3(
; RV64-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg3.load.v4i32.p0.i64(ptr [[PTR:%.*]], i64 4)
; RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV64-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <12 x i32>, ptr %ptr
  %v0 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
  %v1 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
  %v2 = shufflevector <12 x i32> %interleaved.vec, <12 x i32> poison, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
  ret void
}

define void @load_factor4(ptr %ptr) {
; RV32-LABEL: @load_factor4(
; RV32-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg4.load.v4i32.p0.i32(ptr [[PTR:%.*]], i32 4)
; RV32-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV32-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV32-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV32-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor4(
; RV64-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg4.load.v4i32.p0.i64(ptr [[PTR:%.*]], i64 4)
; RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV64-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV64-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <16 x i32>, ptr %ptr
  %v0 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
  %v1 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
  %v2 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
  %v3 = shufflevector <16 x i32> %interleaved.vec, <16 x i32> poison, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
  ret void
}

define void @load_factor4_vscale(ptr %ptr) {
; RV32-LABEL: @load_factor4_vscale(
; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 16 x i8>, 4) @llvm.riscv.vlseg4.triscv.vector.tuple_nxv16i8_4t.i32(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 0)
; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } poison, <vscale x 4 x i32> [[TMP2]], 0
; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 1)
; RV32-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP3]], <vscale x 4 x i32> [[TMP4]], 1
; RV32-NEXT:    [[TMP6:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 2)
; RV32-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP5]], <vscale x 4 x i32> [[TMP6]], 2
; RV32-NEXT:    [[TMP8:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 3)
; RV32-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP7]], <vscale x 4 x i32> [[TMP8]], 3
; RV32-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 0
; RV32-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 1
; RV32-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 2
; RV32-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 3
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor4_vscale(
; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 16 x i8>, 4) @llvm.riscv.vlseg4.triscv.vector.tuple_nxv16i8_4t.i64(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 0)
; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } poison, <vscale x 4 x i32> [[TMP2]], 0
; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 1)
; RV64-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP3]], <vscale x 4 x i32> [[TMP4]], 1
; RV64-NEXT:    [[TMP6:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 2)
; RV64-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP5]], <vscale x 4 x i32> [[TMP6]], 2
; RV64-NEXT:    [[TMP8:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 3)
; RV64-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP7]], <vscale x 4 x i32> [[TMP8]], 3
; RV64-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 0
; RV64-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 1
; RV64-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 2
; RV64-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 3
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <vscale x 16 x i32>, ptr %ptr
  %d0 = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> %interleaved.vec)
  %d0.0 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %d0, 0
  %d0.1 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %d0, 1
  %d1 = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %d0.0)
  %t0 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %d1, 0
  %t1 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %d1, 1
  %d2 = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %d0.1)
  %t2 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %d2, 0
  %t3 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %d2, 1
  ret void
}

define void @load_factor5(ptr %ptr) {
; RV32-LABEL: @load_factor5(
; RV32-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg5.load.v4i32.p0.i32(ptr [[PTR:%.*]], i32 4)
; RV32-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 4
; RV32-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV32-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV32-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV32-NEXT:    [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor5(
; RV64-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg5.load.v4i32.p0.i64(ptr [[PTR:%.*]], i64 4)
; RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 4
; RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV64-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV64-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV64-NEXT:    [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <20 x i32>, ptr %ptr
  %v0 = shufflevector <20 x i32> %interleaved.vec, <20 x i32> poison, <4 x i32> <i32 0, i32 5, i32 10, i32 15>
  %v1 = shufflevector <20 x i32> %interleaved.vec, <20 x i32> poison, <4 x i32> <i32 1, i32 6, i32 11, i32 16>
  %v2 = shufflevector <20 x i32> %interleaved.vec, <20 x i32> poison, <4 x i32> <i32 2, i32 7, i32 12, i32 17>
  %v3 = shufflevector <20 x i32> %interleaved.vec, <20 x i32> poison, <4 x i32> <i32 3, i32 8, i32 13, i32 18>
  %v4 = shufflevector <20 x i32> %interleaved.vec, <20 x i32> poison, <4 x i32> <i32 4, i32 9, i32 14, i32 19>
  ret void
}

define void @load_factor6(ptr %ptr) {
; RV32-LABEL: @load_factor6(
; RV32-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg6.load.v4i32.p0.i32(ptr [[PTR:%.*]], i32 4)
; RV32-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 5
; RV32-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 4
; RV32-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV32-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV32-NEXT:    [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV32-NEXT:    [[TMP7:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor6(
; RV64-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg6.load.v4i32.p0.i64(ptr [[PTR:%.*]], i64 4)
; RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 5
; RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 4
; RV64-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV64-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV64-NEXT:    [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV64-NEXT:    [[TMP7:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <24 x i32>, ptr %ptr
  %v0 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <4 x i32> <i32 0, i32 6, i32 12, i32 18>
  %v1 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <4 x i32> <i32 1, i32 7, i32 13, i32 19>
  %v2 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <4 x i32> <i32 2, i32 8, i32 14, i32 20>
  %v3 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <4 x i32> <i32 3, i32 9, i32 15, i32 21>
  %v4 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <4 x i32> <i32 4, i32 10, i32 16, i32 22>
  %v5 = shufflevector <24 x i32> %interleaved.vec, <24 x i32> poison, <4 x i32> <i32 5, i32 11, i32 17, i32 23>
  ret void
}

define void @load_factor7(ptr %ptr) {
; RV32-LABEL: @load_factor7(
; RV32-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg7.load.v4i32.p0.i32(ptr [[PTR:%.*]], i32 4)
; RV32-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 6
; RV32-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 5
; RV32-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 4
; RV32-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV32-NEXT:    [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV32-NEXT:    [[TMP7:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV32-NEXT:    [[TMP8:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor7(
; RV64-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg7.load.v4i32.p0.i64(ptr [[PTR:%.*]], i64 4)
; RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 6
; RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 5
; RV64-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 4
; RV64-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV64-NEXT:    [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV64-NEXT:    [[TMP7:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV64-NEXT:    [[TMP8:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <28 x i32>, ptr %ptr
  %v0 = shufflevector <28 x i32> %interleaved.vec, <28 x i32> poison, <4 x i32> <i32 0, i32 7, i32 14, i32 21>
  %v1 = shufflevector <28 x i32> %interleaved.vec, <28 x i32> poison, <4 x i32> <i32 1, i32 8, i32 15, i32 22>
  %v2 = shufflevector <28 x i32> %interleaved.vec, <28 x i32> poison, <4 x i32> <i32 2, i32 9, i32 16, i32 23>
  %v3 = shufflevector <28 x i32> %interleaved.vec, <28 x i32> poison, <4 x i32> <i32 3, i32 10, i32 17, i32 24>
  %v4 = shufflevector <28 x i32> %interleaved.vec, <28 x i32> poison, <4 x i32> <i32 4, i32 11, i32 18, i32 25>
  %v5 = shufflevector <28 x i32> %interleaved.vec, <28 x i32> poison, <4 x i32> <i32 5, i32 12, i32 19, i32 26>
  %v6 = shufflevector <28 x i32> %interleaved.vec, <28 x i32> poison, <4 x i32> <i32 6, i32 13, i32 20, i32 27>
  ret void
}

define void @load_factor8(ptr %ptr) {
; RV32-LABEL: @load_factor8(
; RV32-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg8.load.v4i32.p0.i32(ptr [[PTR:%.*]], i32 4)
; RV32-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 7
; RV32-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 6
; RV32-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 5
; RV32-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 4
; RV32-NEXT:    [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV32-NEXT:    [[TMP7:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV32-NEXT:    [[TMP8:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV32-NEXT:    [[TMP9:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor8(
; RV64-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg8.load.v4i32.p0.i64(ptr [[PTR:%.*]], i64 4)
; RV64-NEXT:    [[TMP2:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 7
; RV64-NEXT:    [[TMP3:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 6
; RV64-NEXT:    [[TMP4:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 5
; RV64-NEXT:    [[TMP5:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 4
; RV64-NEXT:    [[TMP6:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 3
; RV64-NEXT:    [[TMP7:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 2
; RV64-NEXT:    [[TMP8:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 1
; RV64-NEXT:    [[TMP9:%.*]] = extractvalue { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } [[TMP1]], 0
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <32 x i32>, ptr %ptr
  %v0 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <4 x i32> <i32 0, i32 8, i32 16, i32 24>
  %v1 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <4 x i32> <i32 1, i32 9, i32 17, i32 25>
  %v2 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <4 x i32> <i32 2, i32 10, i32 18, i32 26>
  %v3 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <4 x i32> <i32 3, i32 11, i32 19, i32 27>
  %v4 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <4 x i32> <i32 4, i32 12, i32 20, i32 28>
  %v5 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <4 x i32> <i32 5, i32 13, i32 21, i32 29>
  %v6 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <4 x i32> <i32 6, i32 14, i32 22, i32 30>
  %v7 = shufflevector <32 x i32> %interleaved.vec, <32 x i32> poison, <4 x i32> <i32 7, i32 15, i32 23, i32 31>
  ret void
}

define void @load_factor8_vscale(ptr %ptr) {
; RV32-LABEL: @load_factor8_vscale(
; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.vlseg8.triscv.vector.tuple_nxv8i8_8t.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 0)
; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 1)
; RV32-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP3]], <vscale x 2 x i32> [[TMP4]], 1
; RV32-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 2)
; RV32-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP5]], <vscale x 2 x i32> [[TMP6]], 2
; RV32-NEXT:    [[TMP8:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 3)
; RV32-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP7]], <vscale x 2 x i32> [[TMP8]], 3
; RV32-NEXT:    [[TMP10:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 4)
; RV32-NEXT:    [[TMP11:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP9]], <vscale x 2 x i32> [[TMP10]], 4
; RV32-NEXT:    [[TMP12:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 5)
; RV32-NEXT:    [[TMP13:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP11]], <vscale x 2 x i32> [[TMP12]], 5
; RV32-NEXT:    [[TMP14:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 6)
; RV32-NEXT:    [[TMP15:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], <vscale x 2 x i32> [[TMP14]], 6
; RV32-NEXT:    [[TMP16:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 7)
; RV32-NEXT:    [[TMP17:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP15]], <vscale x 2 x i32> [[TMP16]], 7
; RV32-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 0
; RV32-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 1
; RV32-NEXT:    [[TMP20:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 2
; RV32-NEXT:    [[TMP21:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 3
; RV32-NEXT:    [[TMP22:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 4
; RV32-NEXT:    [[TMP23:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 5
; RV32-NEXT:    [[TMP24:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 6
; RV32-NEXT:    [[TMP25:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 7
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor8_vscale(
; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.vlseg8.triscv.vector.tuple_nxv8i8_8t.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 0)
; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 1)
; RV64-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP3]], <vscale x 2 x i32> [[TMP4]], 1
; RV64-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 2)
; RV64-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP5]], <vscale x 2 x i32> [[TMP6]], 2
; RV64-NEXT:    [[TMP8:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 3)
; RV64-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP7]], <vscale x 2 x i32> [[TMP8]], 3
; RV64-NEXT:    [[TMP10:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 4)
; RV64-NEXT:    [[TMP11:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP9]], <vscale x 2 x i32> [[TMP10]], 4
; RV64-NEXT:    [[TMP12:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 5)
; RV64-NEXT:    [[TMP13:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP11]], <vscale x 2 x i32> [[TMP12]], 5
; RV64-NEXT:    [[TMP14:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 6)
; RV64-NEXT:    [[TMP15:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], <vscale x 2 x i32> [[TMP14]], 6
; RV64-NEXT:    [[TMP16:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 7)
; RV64-NEXT:    [[TMP17:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP15]], <vscale x 2 x i32> [[TMP16]], 7
; RV64-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 0
; RV64-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 1
; RV64-NEXT:    [[TMP20:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 2
; RV64-NEXT:    [[TMP21:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 3
; RV64-NEXT:    [[TMP22:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 4
; RV64-NEXT:    [[TMP23:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 5
; RV64-NEXT:    [[TMP24:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 6
; RV64-NEXT:    [[TMP25:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 7
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <vscale x 16 x i32>, ptr %ptr
  %d0 = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> %interleaved.vec)
  %d0.0 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %d0, 0
  %d0.1 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %d0, 1

  %d1 = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %d0.0)
  %d1.0 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %d1, 0
  %d1.1 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %d1, 1
  %d2 = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %d0.1)
  %d2.0 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %d2, 0
  %d2.1 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %d2, 1

  %d3 = call { <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave2.nxv4i32(<vscale x 4 x i32> %d1.0)
  %t0 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %d3, 0
  %t1 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %d3, 1
  %d4 = call { <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave2.nxv4i32(<vscale x 4 x i32> %d1.1)
  %t2 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %d4, 0
  %t3 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %d4, 1
  %d5 = call { <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave2.nxv4i32(<vscale x 4 x i32> %d2.0)
  %t4 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %d5, 0
  %t5 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %d5, 1
  %d6 = call { <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave2.nxv4i32(<vscale x 4 x i32> %d2.1)
  %t6 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %d6, 0
  %t7 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32> } %d6, 1
  ret void
}


define void @store_factor2(ptr %ptr, <8 x i8> %v0, <8 x i8> %v1) {
; RV32-LABEL: @store_factor2(
; RV32-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i8> [[V0:%.*]], <8 x i8> [[V1:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i8> [[V0]], <8 x i8> [[V1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    call void @llvm.riscv.seg2.store.v8i8.p0.i32(<8 x i8> [[TMP1]], <8 x i8> [[TMP2]], ptr [[PTR:%.*]], i32 8)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor2(
; RV64-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i8> [[V0:%.*]], <8 x i8> [[V1:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i8> [[V0]], <8 x i8> [[V1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    call void @llvm.riscv.seg2.store.v8i8.p0.i64(<8 x i8> [[TMP1]], <8 x i8> [[TMP2]], ptr [[PTR:%.*]], i64 8)
; RV64-NEXT:    ret void
;
  %interleaved.vec = shufflevector <8 x i8> %v0, <8 x i8> %v1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  store <16 x i8> %interleaved.vec, ptr %ptr, align 4
  ret void
}

define void @store_factor2_as(ptr addrspace(1) %ptr, <8 x i8> %v0, <8 x i8> %v1) {
; RV32-LABEL: @store_factor2_as(
; RV32-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i8> [[V0:%.*]], <8 x i8> [[V1:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i8> [[V0]], <8 x i8> [[V1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    call void @llvm.riscv.seg2.store.v8i8.p1.i32(<8 x i8> [[TMP1]], <8 x i8> [[TMP2]], ptr addrspace(1) [[PTR:%.*]], i32 8)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor2_as(
; RV64-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i8> [[V0:%.*]], <8 x i8> [[V1:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i8> [[V0]], <8 x i8> [[V1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    call void @llvm.riscv.seg2.store.v8i8.p1.i64(<8 x i8> [[TMP1]], <8 x i8> [[TMP2]], ptr addrspace(1) [[PTR:%.*]], i64 8)
; RV64-NEXT:    ret void
;
  %interleaved.vec = shufflevector <8 x i8> %v0, <8 x i8> %v1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  store <16 x i8> %interleaved.vec, ptr addrspace(1) %ptr, align 4
  ret void
}

define void @store_factor2_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1) {
; RV32-LABEL: @store_factor2_vscale(
; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_2t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_2t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
; RV32-NEXT:    call void @llvm.riscv.vsseg2.triscv.vector.tuple_nxv8i8_2t.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP2]], ptr [[PTR:%.*]], i32 -1, i32 3)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor2_vscale(
; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_2t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_2t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
; RV64-NEXT:    call void @llvm.riscv.vsseg2.triscv.vector.tuple_nxv8i8_2t.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP2]], ptr [[PTR:%.*]], i64 -1, i64 3)
; RV64-NEXT:    ret void
;
  %interleaved.vec = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1)
  store <vscale x 16 x i8> %interleaved.vec, ptr %ptr, align 4
  ret void
}

define void @store_factor2_vscale_as(ptr addrspace(1) %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1) {
; RV32-LABEL: @store_factor2_vscale_as(
; RV32-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv16i8(<vscale x 8 x i8> [[V0:%.*]], <vscale x 8 x i8> [[V1:%.*]])
; RV32-NEXT:    store <vscale x 16 x i8> [[INTERLEAVED_VEC]], ptr addrspace(1) [[PTR:%.*]], align 4
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor2_vscale_as(
; RV64-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv16i8(<vscale x 8 x i8> [[V0:%.*]], <vscale x 8 x i8> [[V1:%.*]])
; RV64-NEXT:    store <vscale x 16 x i8> [[INTERLEAVED_VEC]], ptr addrspace(1) [[PTR:%.*]], align 4
; RV64-NEXT:    ret void
;
  %interleaved.vec = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1)
  store <vscale x 16 x i8> %interleaved.vec, ptr addrspace(1) %ptr, align 4
  ret void
}

define void @store_factor3(ptr %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2) {
; RV32-LABEL: @store_factor3(
; RV32-NEXT:    [[S0:%.*]] = 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>
; RV32-NEXT:    [[S1:%.*]] = shufflevector <4 x i32> [[V2:%.*]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
; RV32-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; RV32-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 8, i32 9, i32 10, i32 11>
; RV32-NEXT:    call void @llvm.riscv.seg3.store.v4i32.p0.i32(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], ptr [[PTR:%.*]], i32 4)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor3(
; RV64-NEXT:    [[S0:%.*]] = 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>
; RV64-NEXT:    [[S1:%.*]] = shufflevector <4 x i32> [[V2:%.*]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
; RV64-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; RV64-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 8, i32 9, i32 10, i32 11>
; RV64-NEXT:    call void @llvm.riscv.seg3.store.v4i32.p0.i64(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], ptr [[PTR:%.*]], i64 4)
; RV64-NEXT:    ret void
;
  %s0 = 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>
  %s1 = shufflevector <4 x i32> %v2, <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
  %interleaved.vec = shufflevector <8 x i32> %s0, <8 x i32> %s1, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
  store <12 x i32> %interleaved.vec, ptr %ptr, align 4
  ret void
}

define void @store_factor4(ptr %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2, <4 x i32> %v3) {
; RV32-LABEL: @store_factor4(
; RV32-NEXT:    [[S0:%.*]] = 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>
; RV32-NEXT:    [[S1:%.*]] = shufflevector <4 x i32> [[V2:%.*]], <4 x i32> [[V3:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; RV32-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 8, i32 9, i32 10, i32 11>
; RV32-NEXT:    [[TMP4:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    call void @llvm.riscv.seg4.store.v4i32.p0.i32(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], ptr [[PTR:%.*]], i32 4)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor4(
; RV64-NEXT:    [[S0:%.*]] = 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>
; RV64-NEXT:    [[S1:%.*]] = shufflevector <4 x i32> [[V2:%.*]], <4 x i32> [[V3:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; RV64-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:    [[TMP3:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 8, i32 9, i32 10, i32 11>
; RV64-NEXT:    [[TMP4:%.*]] = shufflevector <8 x i32> [[S0]], <8 x i32> [[S1]], <4 x i32> <i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    call void @llvm.riscv.seg4.store.v4i32.p0.i64(<4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], ptr [[PTR:%.*]], i64 4)
; RV64-NEXT:    ret void
;
  %s0 = 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>
  %s1 = shufflevector <4 x i32> %v2, <4 x i32> %v3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %interleaved.vec = shufflevector <8 x i32> %s0, <8 x i32> %s1, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>
  store <16 x i32> %interleaved.vec, ptr %ptr, align 4
  ret void
}

define void @store_factor4_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1) {
; RV32-LABEL: @store_factor4_vscale(
; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP1]], <vscale x 8 x i8> [[V0]], i32 1)
; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP2]], <vscale x 8 x i8> [[V1:%.*]], i32 2)
; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP3]], <vscale x 8 x i8> [[V1]], i32 3)
; RV32-NEXT:    call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv8i8_4t.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], i32 -1, i32 3)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor4_vscale(
; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP1]], <vscale x 8 x i8> [[V0]], i32 1)
; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP2]], <vscale x 8 x i8> [[V1:%.*]], i32 2)
; RV64-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP3]], <vscale x 8 x i8> [[V1]], i32 3)
; RV64-NEXT:    call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv8i8_4t.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], i64 -1, i64 3)
; RV64-NEXT:    ret void
;
  %i0 = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1)
  %i1 = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1)
  %i2 = call <vscale x 32 x i8> @llvm.vector.interleave2.nxv16i8(<vscale x 16 x i8> %i0, <vscale x 16 x i8> %i1)
  store <vscale x 32 x i8> %i2, ptr %ptr, align 4
  ret void
}


define void @store_factor2_wide(ptr %ptr, <8 x i32> %v0, <8 x i32> %v1) {
; RV32-LABEL: @store_factor2_wide(
; RV32-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[V0:%.*]], <8 x i32> [[V1:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i32> [[V0]], <8 x i32> [[V1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    call void @llvm.riscv.seg2.store.v8i32.p0.i32(<8 x i32> [[TMP1]], <8 x i32> [[TMP2]], ptr [[PTR:%.*]], i32 8)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor2_wide(
; RV64-NEXT:    [[TMP1:%.*]] = shufflevector <8 x i32> [[V0:%.*]], <8 x i32> [[V1:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:    [[TMP2:%.*]] = shufflevector <8 x i32> [[V0]], <8 x i32> [[V1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    call void @llvm.riscv.seg2.store.v8i32.p0.i64(<8 x i32> [[TMP1]], <8 x i32> [[TMP2]], ptr [[PTR:%.*]], i64 8)
; RV64-NEXT:    ret void
;
  %interleaved.vec = shufflevector <8 x i32> %v0, <8 x i32> %v1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
  store <16 x i32> %interleaved.vec, ptr %ptr, align 4
  ret void
}

define void @store_factor3_wide(ptr %ptr, <8 x i32> %v0, <8 x i32> %v1, <8 x i32> %v2) {
; RV32-LABEL: @store_factor3_wide(
; RV32-NEXT:    [[S0:%.*]] = shufflevector <8 x i32> [[V0:%.*]], <8 x i32> [[V1:%.*]], <16 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, i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    [[S1:%.*]] = shufflevector <8 x i32> [[V2:%.*]], <8 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; RV32-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:    [[TMP2:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    [[TMP3:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; RV32-NEXT:    call void @llvm.riscv.seg3.store.v8i32.p0.i32(<8 x i32> [[TMP1]], <8 x i32> [[TMP2]], <8 x i32> [[TMP3]], ptr [[PTR:%.*]], i32 8)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor3_wide(
; RV64-NEXT:    [[S0:%.*]] = shufflevector <8 x i32> [[V0:%.*]], <8 x i32> [[V1:%.*]], <16 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, i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    [[S1:%.*]] = shufflevector <8 x i32> [[V2:%.*]], <8 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; RV64-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:    [[TMP2:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    [[TMP3:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; RV64-NEXT:    call void @llvm.riscv.seg3.store.v8i32.p0.i64(<8 x i32> [[TMP1]], <8 x i32> [[TMP2]], <8 x i32> [[TMP3]], ptr [[PTR:%.*]], i64 8)
; RV64-NEXT:    ret void
;
  %s0 = shufflevector <8 x i32> %v0, <8 x i32> %v1, <16 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, i32 12, i32 13, i32 14, i32 15>
  %s1 = shufflevector <8 x i32> %v2, <8 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
  %interleaved.vec = shufflevector <16 x i32> %s0, <16 x i32> %s1, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>
  store <24 x i32> %interleaved.vec, ptr %ptr, align 4
  ret void
}

define void @store_factor4_wide(ptr %ptr, <8 x i32> %v0, <8 x i32> %v1, <8 x i32> %v2, <8 x i32> %v3) {
; RV32-LABEL: @store_factor4_wide(
; RV32-NEXT:    [[S0:%.*]] = shufflevector <8 x i32> [[V0:%.*]], <8 x i32> [[V1:%.*]], <16 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, i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    [[S1:%.*]] = shufflevector <8 x i32> [[V2:%.*]], <8 x i32> [[V3:%.*]], <16 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, i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:    [[TMP2:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV32-NEXT:    [[TMP3:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; RV32-NEXT:    [[TMP4:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
; RV32-NEXT:    call void @llvm.riscv.seg4.store.v8i32.p0.i32(<8 x i32> [[TMP1]], <8 x i32> [[TMP2]], <8 x i32> [[TMP3]], <8 x i32> [[TMP4]], ptr [[PTR:%.*]], i32 8)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor4_wide(
; RV64-NEXT:    [[S0:%.*]] = shufflevector <8 x i32> [[V0:%.*]], <8 x i32> [[V1:%.*]], <16 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, i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    [[S1:%.*]] = shufflevector <8 x i32> [[V2:%.*]], <8 x i32> [[V3:%.*]], <16 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, i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:    [[TMP2:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; RV64-NEXT:    [[TMP3:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
; RV64-NEXT:    [[TMP4:%.*]] = shufflevector <16 x i32> [[S0]], <16 x i32> [[S1]], <8 x i32> <i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
; RV64-NEXT:    call void @llvm.riscv.seg4.store.v8i32.p0.i64(<8 x i32> [[TMP1]], <8 x i32> [[TMP2]], <8 x i32> [[TMP3]], <8 x i32> [[TMP4]], ptr [[PTR:%.*]], i64 8)
; RV64-NEXT:    ret void
;
  %s0 = shufflevector <8 x i32> %v0, <8 x i32> %v1, <16 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, i32 12, i32 13, i32 14, i32 15>
  %s1 = shufflevector <8 x i32> %v2, <8 x i32> %v3, <16 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, i32 12, i32 13, i32 14, i32 15>
  %interleaved.vec = shufflevector <16 x i32> %s0, <16 x i32> %s1, <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>
  store <32 x i32> %interleaved.vec, ptr %ptr, align 4
  ret void
}

define void @store_factor8_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3) {
; RV32-LABEL: @store_factor8_vscale(
; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], <vscale x 8 x i8> [[V2:%.*]], i32 1)
; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP2]], <vscale x 8 x i8> [[V0]], i32 2)
; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP3]], <vscale x 8 x i8> [[V2]], i32 3)
; RV32-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP4]], <vscale x 8 x i8> [[V1:%.*]], i32 4)
; RV32-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP5]], <vscale x 8 x i8> [[V3:%.*]], i32 5)
; RV32-NEXT:    [[TMP7:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP6]], <vscale x 8 x i8> [[V1]], i32 6)
; RV32-NEXT:    [[TMP8:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP7]], <vscale x 8 x i8> [[V3]], i32 7)
; RV32-NEXT:    call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], i32 -1, i32 3)
; RV32-NEXT:    ret void
;
; RV64-LABEL: @store_factor8_vscale(
; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], <vscale x 8 x i8> [[V2:%.*]], i32 1)
; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP2]], <vscale x 8 x i8> [[V0]], i32 2)
; RV64-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP3]], <vscale x 8 x i8> [[V2]], i32 3)
; RV64-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP4]], <vscale x 8 x i8> [[V1:%.*]], i32 4)
; RV64-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP5]], <vscale x 8 x i8> [[V3:%.*]], i32 5)
; RV64-NEXT:    [[TMP7:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP6]], <vscale x 8 x i8> [[V1]], i32 6)
; RV64-NEXT:    [[TMP8:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP7]], <vscale x 8 x i8> [[V3]], i32 7)
; RV64-NEXT:    call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], i64 -1, i64 3)
; RV64-NEXT:    ret void
;
  %i0 = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1)
  %i1 = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1)
  %i2 = call <vscale x 32 x i8> @llvm.vector.interleave2.nxv16i8(<vscale x 16 x i8> %i0, <vscale x 16 x i8> %i1)

  %i3 = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3)
  %i4 = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3)
  %i5 = call <vscale x 32 x i8> @llvm.vector.interleave2.nxv16i8(<vscale x 16 x i8> %i3, <vscale x 16 x i8> %i4)

  %i6 = call <vscale x 64 x i8> @llvm.vector.interleave2.nxv32i8(<vscale x 32 x i8> %i2, <vscale x 32 x i8> %i5)
  store <vscale x 64 x i8> %i6, ptr %ptr, align 4
  ret void
}

define void @load_factor2_fp128(ptr %ptr) {
; RV32-LABEL: @load_factor2_fp128(
; RV32-NEXT:    [[INTERLEAVED_VEC:%.*]] = load <4 x fp128>, ptr [[PTR:%.*]], align 16
; RV32-NEXT:    [[V0:%.*]] = shufflevector <4 x fp128> [[INTERLEAVED_VEC]], <4 x fp128> poison, <2 x i32> <i32 0, i32 2>
; RV32-NEXT:    [[V1:%.*]] = shufflevector <4 x fp128> [[INTERLEAVED_VEC]], <4 x fp128> poison, <2 x i32> <i32 1, i32 3>
; RV32-NEXT:    ret void
;
; RV64-LABEL: @load_factor2_fp128(
; RV64-NEXT:    [[INTERLEAVED_VEC:%.*]] = load <4 x fp128>, ptr [[PTR:%.*]], align 16
; RV64-NEXT:    [[V0:%.*]] = shufflevector <4 x fp128> [[INTERLEAVED_VEC]], <4 x fp128> poison, <2 x i32> <i32 0, i32 2>
; RV64-NEXT:    [[V1:%.*]] = shufflevector <4 x fp128> [[INTERLEAVED_VEC]], <4 x fp128> poison, <2 x i32> <i32 1, i32 3>
; RV64-NEXT:    ret void
;
  %interleaved.vec = load <4 x fp128>, ptr %ptr, align 16
  %v0 = shufflevector <4 x fp128> %interleaved.vec, <4 x fp128> poison, <2 x i32> <i32 0, i32 2>
  %v1 = shufflevector <4 x fp128> %interleaved.vec, <4 x fp128> poison, <2 x i32> <i32 1, i32 3>
  ret void
}