; 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
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GFX11

declare i16 @llvm.amdgcn.fdot2.bf16.bf16(<2 x i16> %a, <2 x i16> %b, i16 %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_bf16_bf16 v1, s2, s3, v1
; GFX11-NEXT:    global_store_b16 v0, v1, s[0:1]
; GFX11-NEXT:    s_endpgm
    i16 addrspace(1)* %r,
    <2 x i16> addrspace(1)* %a,
    <2 x i16> addrspace(1)* %b,
    i16 addrspace(1)* %c) {
entry:
  %a.val = load <2 x i16>, <2 x i16> addrspace(1)* %a
  %b.val = load <2 x i16>, <2 x i16> addrspace(1)* %b
  %c.val = load i16, i16 addrspace(1)* %c
  %r.val = call i16 @llvm.amdgcn.fdot2.bf16.bf16(<2 x i16> %a.val, <2 x i16> %b.val, i16 %c.val)
  store i16 %r.val, i16 addrspace(1)* %r
  ret void
}