test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.f32.bf16.ll

; 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 float @llvm.amdgcn.fdot2.f32.bf16(<2 x i16> %a, <2 x i16> %b, float %c, i1 %clamp)

define amdgpu_kernel void @test_llvm_amdgcn_fdot2_f32_bf16_clamp(
; GFX11-LABEL: test_llvm_amdgcn_fdot2_f32_bf16_clamp:
; GFX11:       ; %bb.0: ; %entry
; GFX11-NEXT:    s_load_b256 s[0:7], s[0:1], 0x24
; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-NEXT:    s_load_b32 s6, s[6:7], 0x0
; GFX11-NEXT:    s_load_b32 s2, s[2:3], 0x0
; GFX11-NEXT:    s_load_b32 s3, s[4:5], 0x0
; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v0, s6
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GFX11-NEXT:    v_dot2_f32_bf16 v0, s2, s3, v0 clamp
; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; GFX11-NEXT:    s_endpgm
    float addrspace(1)* %r,
    <2 x i16> addrspace(1)* %a,
    <2 x i16> addrspace(1)* %b,
    float 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 float, float addrspace(1)* %c
  %r.val = call float @llvm.amdgcn.fdot2.f32.bf16(<2 x i16> %a.val, <2 x i16> %b.val, float %c.val, i1 1)
  store float %r.val, float addrspace(1)* %r
  ret void
}


define amdgpu_kernel void @test_llvm_amdgcn_fdot2_f32_bf16_no_clamp(
; GFX11-LABEL: test_llvm_amdgcn_fdot2_f32_bf16_no_clamp:
; GFX11:       ; %bb.0: ; %entry
; GFX11-NEXT:    s_load_b256 s[0:7], s[0:1], 0x24
; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-NEXT:    s_load_b32 s6, s[6:7], 0x0
; GFX11-NEXT:    s_load_b32 s2, s[2:3], 0x0
; GFX11-NEXT:    s_load_b32 s3, s[4:5], 0x0
; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v0, s6
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GFX11-NEXT:    v_dot2_f32_bf16 v0, s2, s3, v0
; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
; GFX11-NEXT:    s_endpgm
    float addrspace(1)* %r,
    <2 x i16> addrspace(1)* %a,
    <2 x i16> addrspace(1)* %b,
    float 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 float, float addrspace(1)* %c
  %r.val = call float @llvm.amdgcn.fdot2.f32.bf16(<2 x i16> %a.val, <2 x i16> %b.val, float %c.val, i1 0)
  store float %r.val, float addrspace(1)* %r
  ret void
}