; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+zve64x,+experimental-zvqdotq \
; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+zve64x,+experimental-zvqdotq \
; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK

declare <vscale x 1 x i32> @llvm.riscv.vqdot.nxv1i32.nxv1i32(
  <vscale x 1 x i32>,
  <vscale x 4 x i8>,
  <vscale x 4 x i8>,
  iXLen,
  iXLen);

define <vscale x 1 x i32>  @intrinsic_vqdot_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vv_nxv1i32_nxv1i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, ma
; CHECK-NEXT:    vqdot.vv v8, v9, v10
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 1 x i32> @llvm.riscv.vqdot.nxv1i32.nxv1i32(
    <vscale x 1 x i32> %0,
    <vscale x 4 x i8> %1,
    <vscale x 4 x i8> %2,
    iXLen %3, iXLen 0)

  ret <vscale x 1 x i32> %a
}
declare <vscale x 2 x i32> @llvm.riscv.vqdot.nxv2i32.nxv2i32(
  <vscale x 2 x i32>,
  <vscale x 8 x i8>,
  <vscale x 8 x i8>,
  iXLen,
  iXLen);

define <vscale x 2 x i32>  @intrinsic_vqdot_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vv_nxv2i32_nxv2i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, ma
; CHECK-NEXT:    vqdot.vv v8, v9, v10
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 2 x i32> @llvm.riscv.vqdot.nxv2i32.nxv2i32(
    <vscale x 2 x i32> %0,
    <vscale x 8 x i8> %1,
    <vscale x 8 x i8> %2,
    iXLen %3, iXLen 0)

  ret <vscale x 2 x i32> %a
}
declare <vscale x 4 x i32> @llvm.riscv.vqdot.nxv4i32.nxv4i32(
  <vscale x 4 x i32>,
  <vscale x 16 x i8>,
  <vscale x 16 x i8>,
  iXLen,
  iXLen);

define <vscale x 4 x i32>  @intrinsic_vqdot_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vv_nxv4i32_nxv4i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
; CHECK-NEXT:    vqdot.vv v8, v10, v12
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 4 x i32> @llvm.riscv.vqdot.nxv4i32.nxv4i32(
    <vscale x 4 x i32> %0,
    <vscale x 16 x i8> %1,
    <vscale x 16 x i8> %2,
    iXLen %3, iXLen 0)

  ret <vscale x 4 x i32> %a
}
declare <vscale x 8 x i32> @llvm.riscv.vqdot.nxv8i32.nxv8i32(
  <vscale x 8 x i32>,
  <vscale x 32 x i8>,
  <vscale x 32 x i8>,
  iXLen,
  iXLen);

define <vscale x 8 x i32>  @intrinsic_vqdot_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vv_nxv8i32_nxv8i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
; CHECK-NEXT:    vqdot.vv v8, v12, v16
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 8 x i32> @llvm.riscv.vqdot.nxv8i32.nxv8i32(
    <vscale x 8 x i32> %0,
    <vscale x 32 x i8> %1,
    <vscale x 32 x i8> %2,
    iXLen %3, iXLen 0)

  ret <vscale x 8 x i32> %a
}
declare <vscale x 16 x i32> @llvm.riscv.vqdot.nxv16i32.nxv16i32(
  <vscale x 16 x i32>,
  <vscale x 64 x i8>,
  <vscale x 64 x i8>,
  iXLen,
  iXLen);

define <vscale x 16 x i32>  @intrinsic_vqdot_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vv_nxv16i32_nxv16i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vl8r.v v24, (a0)
; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, ma
; CHECK-NEXT:    vqdot.vv v8, v16, v24
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 16 x i32> @llvm.riscv.vqdot.nxv16i32.nxv16i32(
    <vscale x 16 x i32> %0,
    <vscale x 64 x i8> %1,
    <vscale x 64 x i8> %2,
    iXLen %3, iXLen 0)

  ret <vscale x 16 x i32> %a
}
declare <vscale x 1 x i32> @llvm.riscv.vqdot.mask.nxv1i32.nxv1i32(
  <vscale x 1 x i32>,
  <vscale x 4 x i8>,
  <vscale x 4 x i8>,
  <vscale x 1 x i1>,
  iXLen,
  iXLen);

define <vscale x 1 x i32>  @intrinsic_vqdot_mask_vv_nxv1i32_nxv1i32(<vscale x 1 x i32> %0, <vscale x 4 x i8> %1, <vscale x 4 x i8> %2, <vscale x 1 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vv_nxv1i32_nxv1i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, tu, mu
; CHECK-NEXT:    vqdot.vv v8, v9, v10, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 1 x i32> @llvm.riscv.vqdot.mask.nxv1i32.nxv1i32(
    <vscale x 1 x i32> %0,
    <vscale x 4 x i8> %1,
    <vscale x 4 x i8> %2,
    <vscale x 1 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 1 x i32> %a
}
declare <vscale x 2 x i32> @llvm.riscv.vqdot.mask.nxv2i32.nxv2i32(
  <vscale x 2 x i32>,
  <vscale x 8 x i8>,
  <vscale x 8 x i8>,
  <vscale x 2 x i1>,
  iXLen,
  iXLen);

define <vscale x 2 x i32>  @intrinsic_vqdot_mask_vv_nxv2i32_nxv2i32(<vscale x 2 x i32> %0, <vscale x 8 x i8> %1, <vscale x 8 x i8> %2, <vscale x 2 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vv_nxv2i32_nxv2i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, tu, mu
; CHECK-NEXT:    vqdot.vv v8, v9, v10, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 2 x i32> @llvm.riscv.vqdot.mask.nxv2i32.nxv2i32(
    <vscale x 2 x i32> %0,
    <vscale x 8 x i8> %1,
    <vscale x 8 x i8> %2,
    <vscale x 2 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 2 x i32> %a
}
declare <vscale x 4 x i32> @llvm.riscv.vqdot.mask.nxv4i32.nxv4i32(
  <vscale x 4 x i32>,
  <vscale x 16 x i8>,
  <vscale x 16 x i8>,
  <vscale x 4 x i1>,
  iXLen,
  iXLen);

define <vscale x 4 x i32>  @intrinsic_vqdot_mask_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 16 x i8> %1, <vscale x 16 x i8> %2, <vscale x 4 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vv_nxv4i32_nxv4i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, mu
; CHECK-NEXT:    vqdot.vv v8, v10, v12, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 4 x i32> @llvm.riscv.vqdot.mask.nxv4i32.nxv4i32(
    <vscale x 4 x i32> %0,
    <vscale x 16 x i8> %1,
    <vscale x 16 x i8> %2,
    <vscale x 4 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 4 x i32> %a
}
declare <vscale x 8 x i32> @llvm.riscv.vqdot.mask.nxv8i32.nxv8i32(
  <vscale x 8 x i32>,
  <vscale x 32 x i8>,
  <vscale x 32 x i8>,
  <vscale x 8 x i1>,
  iXLen,
  iXLen);

define <vscale x 8 x i32>  @intrinsic_vqdot_mask_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 32 x i8> %1, <vscale x 32 x i8> %2, <vscale x 8 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vv_nxv8i32_nxv8i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, mu
; CHECK-NEXT:    vqdot.vv v8, v12, v16, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 8 x i32> @llvm.riscv.vqdot.mask.nxv8i32.nxv8i32(
    <vscale x 8 x i32> %0,
    <vscale x 32 x i8> %1,
    <vscale x 32 x i8> %2,
    <vscale x 8 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 8 x i32> %a
}
declare <vscale x 16 x i32> @llvm.riscv.vqdot.mask.nxv16i32.nxv16i32(
  <vscale x 16 x i32>,
  <vscale x 64 x i8>,
  <vscale x 64 x i8>,
  <vscale x 16 x i1>,
  iXLen,
  iXLen);

define <vscale x 16 x i32>  @intrinsic_vqdot_mask_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 64 x i8> %1, <vscale x 64 x i8> %2, <vscale x 16 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vv_nxv16i32_nxv16i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vl8r.v v24, (a0)
; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, mu
; CHECK-NEXT:    vqdot.vv v8, v16, v24, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 16 x i32> @llvm.riscv.vqdot.mask.nxv16i32.nxv16i32(
    <vscale x 16 x i32> %0,
    <vscale x 64 x i8> %1,
    <vscale x 64 x i8> %2,
    <vscale x 16 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 16 x i32> %a
}
declare <vscale x 1 x i32> @llvm.riscv.vqdot.nxv1i32.i32(
  <vscale x 1 x i32>,
  <vscale x 4 x i8>,
  i32,
  iXLen,
  iXLen);

define <vscale x 1 x i32>  @intrinsic_vqdot_vx_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 4 x i8> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vx_nxv1i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, tu, ma
; CHECK-NEXT:    vqdot.vx v8, v9, a0
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 1 x i32> @llvm.riscv.vqdot.nxv1i32.i32(
    <vscale x 1 x i32> %0,
    <vscale x 4 x i8> %1,
    i32 %2,
    iXLen %3, iXLen 0)

  ret <vscale x 1 x i32> %a
}
declare <vscale x 2 x i32> @llvm.riscv.vqdot.nxv2i32.i32(
  <vscale x 2 x i32>,
  <vscale x 8 x i8>,
  i32,
  iXLen,
  iXLen);

define <vscale x 2 x i32>  @intrinsic_vqdot_vx_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 8 x i8> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vx_nxv2i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, tu, ma
; CHECK-NEXT:    vqdot.vx v8, v9, a0
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 2 x i32> @llvm.riscv.vqdot.nxv2i32.i32(
    <vscale x 2 x i32> %0,
    <vscale x 8 x i8> %1,
    i32 %2,
    iXLen %3, iXLen 0)

  ret <vscale x 2 x i32> %a
}
declare <vscale x 4 x i32> @llvm.riscv.vqdot.nxv4i32.i32(
  <vscale x 4 x i32>,
  <vscale x 16 x i8>,
  i32,
  iXLen,
  iXLen);

define <vscale x 4 x i32>  @intrinsic_vqdot_vx_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 16 x i8> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vx_nxv4i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, tu, ma
; CHECK-NEXT:    vqdot.vx v8, v10, a0
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 4 x i32> @llvm.riscv.vqdot.nxv4i32.i32(
    <vscale x 4 x i32> %0,
    <vscale x 16 x i8> %1,
    i32 %2,
    iXLen %3, iXLen 0)

  ret <vscale x 4 x i32> %a
}
declare <vscale x 8 x i32> @llvm.riscv.vqdot.nxv8i32.i32(
  <vscale x 8 x i32>,
  <vscale x 32 x i8>,
  i32,
  iXLen,
  iXLen);

define <vscale x 8 x i32>  @intrinsic_vqdot_vx_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 32 x i8> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vx_nxv8i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, tu, ma
; CHECK-NEXT:    vqdot.vx v8, v12, a0
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 8 x i32> @llvm.riscv.vqdot.nxv8i32.i32(
    <vscale x 8 x i32> %0,
    <vscale x 32 x i8> %1,
    i32 %2,
    iXLen %3, iXLen 0)

  ret <vscale x 8 x i32> %a
}
declare <vscale x 16 x i32> @llvm.riscv.vqdot.nxv16i32.i32(
  <vscale x 16 x i32>,
  <vscale x 64 x i8>,
  i32,
  iXLen,
  iXLen);

define <vscale x 16 x i32>  @intrinsic_vqdot_vx_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 64 x i8> %1, i32 %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_vx_nxv16i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, ma
; CHECK-NEXT:    vqdot.vx v8, v16, a0
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 16 x i32> @llvm.riscv.vqdot.nxv16i32.i32(
    <vscale x 16 x i32> %0,
    <vscale x 64 x i8> %1,
    i32 %2,
    iXLen %3, iXLen 0)

  ret <vscale x 16 x i32> %a
}
declare <vscale x 1 x i32> @llvm.riscv.vqdot.mask.nxv1i32.i32(
  <vscale x 1 x i32>,
  <vscale x 4 x i8>,
  i32,
  <vscale x 1 x i1>,
  iXLen,
  iXLen);

define <vscale x 1 x i32>  @intrinsic_vqdot_mask_vx_nxv1i32_i32(<vscale x 1 x i32> %0, <vscale x 4 x i8> %1, i32 %2, <vscale x 1 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vx_nxv1i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, tu, mu
; CHECK-NEXT:    vqdot.vx v8, v9, a0, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 1 x i32> @llvm.riscv.vqdot.mask.nxv1i32.i32(
    <vscale x 1 x i32> %0,
    <vscale x 4 x i8> %1,
    i32 %2,
    <vscale x 1 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 1 x i32> %a
}
declare <vscale x 2 x i32> @llvm.riscv.vqdot.mask.nxv2i32.i32(
  <vscale x 2 x i32>,
  <vscale x 8 x i8>,
  i32,
  <vscale x 2 x i1>,
  iXLen,
  iXLen);

define <vscale x 2 x i32>  @intrinsic_vqdot_mask_vx_nxv2i32_i32(<vscale x 2 x i32> %0, <vscale x 8 x i8> %1, i32 %2, <vscale x 2 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vx_nxv2i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, tu, mu
; CHECK-NEXT:    vqdot.vx v8, v9, a0, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 2 x i32> @llvm.riscv.vqdot.mask.nxv2i32.i32(
    <vscale x 2 x i32> %0,
    <vscale x 8 x i8> %1,
    i32 %2,
    <vscale x 2 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 2 x i32> %a
}
declare <vscale x 4 x i32> @llvm.riscv.vqdot.mask.nxv4i32.i32(
  <vscale x 4 x i32>,
  <vscale x 16 x i8>,
  i32,
  <vscale x 4 x i1>,
  iXLen,
  iXLen);

define <vscale x 4 x i32>  @intrinsic_vqdot_mask_vx_nxv4i32_i32(<vscale x 4 x i32> %0, <vscale x 16 x i8> %1, i32 %2, <vscale x 4 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vx_nxv4i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, tu, mu
; CHECK-NEXT:    vqdot.vx v8, v10, a0, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 4 x i32> @llvm.riscv.vqdot.mask.nxv4i32.i32(
    <vscale x 4 x i32> %0,
    <vscale x 16 x i8> %1,
    i32 %2,
    <vscale x 4 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 4 x i32> %a
}
declare <vscale x 8 x i32> @llvm.riscv.vqdot.mask.nxv8i32.i32(
  <vscale x 8 x i32>,
  <vscale x 32 x i8>,
  i32,
  <vscale x 8 x i1>,
  iXLen,
  iXLen);

define <vscale x 8 x i32>  @intrinsic_vqdot_mask_vx_nxv8i32_i32(<vscale x 8 x i32> %0, <vscale x 32 x i8> %1, i32 %2, <vscale x 8 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vx_nxv8i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, tu, mu
; CHECK-NEXT:    vqdot.vx v8, v12, a0, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 8 x i32> @llvm.riscv.vqdot.mask.nxv8i32.i32(
    <vscale x 8 x i32> %0,
    <vscale x 32 x i8> %1,
    i32 %2,
    <vscale x 8 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 8 x i32> %a
}
declare <vscale x 16 x i32> @llvm.riscv.vqdot.mask.nxv16i32.i32(
  <vscale x 16 x i32>,
  <vscale x 64 x i8>,
  i32,
  <vscale x 16 x i1>,
  iXLen,
  iXLen);

define <vscale x 16 x i32>  @intrinsic_vqdot_mask_vx_nxv16i32_i32(<vscale x 16 x i32> %0, <vscale x 64 x i8> %1, i32 %2, <vscale x 16 x i1> %m, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vqdot_mask_vx_nxv16i32_i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, mu
; CHECK-NEXT:    vqdot.vx v8, v16, a0, v0.t
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 16 x i32> @llvm.riscv.vqdot.mask.nxv16i32.i32(
    <vscale x 16 x i32> %0,
    <vscale x 64 x i8> %1,
    i32 %2,
    <vscale x 16 x i1> %m,
    iXLen %3, iXLen 0)

  ret <vscale x 16 x i32> %a
}