; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GFX11,SDAG-GFX11
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GFX11,GISEL-GFX11

declare half @llvm.amdgcn.fdot2.f16.f16(<2 x half> %a, <2 x half> %b, half %c)

define amdgpu_kernel void @test_llvm_amdgcn_fdot2_f16_f16(
; GFX11-LABEL: test_llvm_amdgcn_fdot2_f16_f16:
; GFX11:       ; %bb.0: ; %entry
; GFX11-NEXT:    s_load_b256 s[0:7], s[0:1], 0x24
; GFX11-NEXT:    v_mov_b32_e32 v0, 0
; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-NEXT:    global_load_u16 v1, v0, s[6:7]
; GFX11-NEXT:    s_load_b32 s2, s[2:3], 0x0
; GFX11-NEXT:    s_load_b32 s3, s[4:5], 0x0
; GFX11-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX11-NEXT:    v_dot2_f16_f16 v1, s2, s3, v1
; GFX11-NEXT:    global_store_b16 v0, v1, s[0:1]
; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; GFX11-NEXT:    s_endpgm
    half addrspace(1)* %r,
    <2 x half> addrspace(1)* %a,
    <2 x half> addrspace(1)* %b,
    half addrspace(1)* %c) {
entry:
  %a.val = load <2 x half>, <2 x half> addrspace(1)* %a
  %b.val = load <2 x half>, <2 x half> addrspace(1)* %b
  %c.val = load half, half addrspace(1)* %c
  %r.val = call half @llvm.amdgcn.fdot2.f16.f16(<2 x half> %a.val, <2 x half> %b.val, half %c.val)
  store half %r.val, half addrspace(1)* %r
  ret void
}

define amdgpu_kernel void @test_llvm_amdgcn_fdot2_f16_f16_dpp(
; SDAG-GFX11-LABEL: test_llvm_amdgcn_fdot2_f16_f16_dpp:
; SDAG-GFX11:       ; %bb.0: ; %entry
; SDAG-GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
; SDAG-GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; SDAG-GFX11-NEXT:    scratch_load_b32 v0, off, s2
; SDAG-GFX11-NEXT:    scratch_load_u16 v1, off, s3
; SDAG-GFX11-NEXT:    scratch_load_b32 v2, off, s1
; SDAG-GFX11-NEXT:    s_waitcnt vmcnt(0)
; SDAG-GFX11-NEXT:    v_dot2_f16_f16_e64_dpp v0, v2, v0, v1 quad_perm:[1,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1
; SDAG-GFX11-NEXT:    scratch_store_b16 off, v0, s0
; SDAG-GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; SDAG-GFX11-NEXT:    s_endpgm
;
; GISEL-GFX11-LABEL: test_llvm_amdgcn_fdot2_f16_f16_dpp:
; GISEL-GFX11:       ; %bb.0: ; %entry
; GISEL-GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
; GISEL-GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; GISEL-GFX11-NEXT:    scratch_load_b32 v0, off, s1
; GISEL-GFX11-NEXT:    scratch_load_b32 v1, off, s2
; GISEL-GFX11-NEXT:    scratch_load_u16 v2, off, s3
; GISEL-GFX11-NEXT:    s_waitcnt vmcnt(0)
; GISEL-GFX11-NEXT:    v_dot2_f16_f16_e64_dpp v0, v0, v1, v2 quad_perm:[1,0,0,0] row_mask:0xf bank_mask:0xf bound_ctrl:1
; GISEL-GFX11-NEXT:    scratch_store_b16 off, v0, s0
; GISEL-GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; GISEL-GFX11-NEXT:    s_endpgm
    half addrspace(5)* %r,
    <2 x half> addrspace(5)* %a,
    <2 x half> addrspace(5)* %b,
    half addrspace(5)* %c) {
entry:
  %a.val = load <2 x half>, <2 x half> addrspace(5)* %a
  %b.val = load <2 x half>, <2 x half> addrspace(5)* %b
  %c.val = load half, half addrspace(5)* %c
  %a.val.i32 = bitcast <2 x half> %a.val to i32
  %dpp = call i32 @llvm.amdgcn.update.dpp.i32(i32 %a.val.i32, i32 %a.val.i32, i32 1, i32 15, i32 15, i1 1)
  %a.val.dpp.v2half = bitcast i32 %dpp to <2 x half>
  %r.val = call half @llvm.amdgcn.fdot2.f16.f16(<2 x half> %a.val.dpp.v2half, <2 x half> %b.val, half %c.val)
  store half %r.val, half addrspace(5)* %r
  ret void
}

declare i32 @llvm.amdgcn.update.dpp.i32(i32, i32, i32, i32, i32, i1)