llvm/test/CodeGen/AMDGPU/smfmac_alloc_failure_no_agpr_O0.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
; RUN: llc -O0 -mtriple=amdgcn -mcpu=gfx950 -amdgpu-mfma-vgpr-form=0 < %s | FileCheck %s
; RUN: llc -O0 -mtriple=amdgcn -mcpu=gfx950 -amdgpu-mfma-vgpr-form=1 < %s | FileCheck %s

declare <16 x float> @llvm.amdgcn.smfmac.f32.32x32x32.f16(<8 x half>, <16 x half>, <16 x float>, i32, i32 immarg, i32 immarg)

define amdgpu_kernel void @test_smfmac_f32_32x32x32_f16__vgpr(ptr addrspace(1) %arg, <8 x half> %a, <16 x half> %b, i32 %idx) #0 {
; CHECK-LABEL: test_smfmac_f32_32x32x32_f16__vgpr:
; CHECK:       ; %bb.0: ; %bb
; CHECK-NEXT:    s_mov_b64 s[2:3], s[4:5]
; CHECK-NEXT:    v_mov_b32_e32 v1, v0
; CHECK-NEXT:    v_mov_b32_e32 v0, 0
; CHECK-NEXT:    s_load_dwordx2 s[0:1], s[2:3], 0x24
; CHECK-NEXT:    s_load_dwordx4 s[12:15], s[2:3], 0x34
; CHECK-NEXT:    s_load_dwordx8 s[4:11], s[2:3], 0x44
; CHECK-NEXT:    s_nop 0
; CHECK-NEXT:    s_load_dword s2, s[2:3], 0x64
; CHECK-NEXT:    s_mov_b32 s3, 0x3ff
; CHECK-NEXT:    v_and_b32_e64 v1, v1, s3
; CHECK-NEXT:    s_mov_b32 s3, 6
; CHECK-NEXT:    v_lshlrev_b32_e64 v8, s3, v1
; CHECK-NEXT:    s_waitcnt lgkmcnt(0)
; CHECK-NEXT:    global_load_dwordx4 v[4:7], v8, s[0:1] offset:48
; CHECK-NEXT:    s_waitcnt vmcnt(0)
; CHECK-NEXT:    v_mov_b32_e32 v1, v7
; CHECK-NEXT:    v_mov_b32_e32 v2, v6
; CHECK-NEXT:    v_mov_b32_e32 v3, v5
; CHECK-NEXT:    ; kill: def $vgpr4 killed $vgpr4 killed $vgpr4_vgpr5_vgpr6_vgpr7 killed $exec
; CHECK-NEXT:    global_load_dwordx4 v[10:13], v8, s[0:1] offset:32
; CHECK-NEXT:    s_waitcnt vmcnt(0)
; CHECK-NEXT:    v_mov_b32_e32 v5, v13
; CHECK-NEXT:    v_mov_b32_e32 v6, v12
; CHECK-NEXT:    v_mov_b32_e32 v7, v11
; CHECK-NEXT:    v_mov_b32_e32 v24, v10
; CHECK-NEXT:    global_load_dwordx4 v[10:13], v8, s[0:1] offset:16
; CHECK-NEXT:    s_waitcnt vmcnt(0)
; CHECK-NEXT:    v_mov_b32_e32 v25, v13
; CHECK-NEXT:    v_mov_b32_e32 v26, v12
; CHECK-NEXT:    v_mov_b32_e32 v27, v11
; CHECK-NEXT:    v_mov_b32_e32 v28, v10
; CHECK-NEXT:    global_load_dwordx4 v[8:11], v8, s[0:1]
; CHECK-NEXT:    s_waitcnt vmcnt(0)
; CHECK-NEXT:    v_mov_b32_e32 v29, v11
; CHECK-NEXT:    v_mov_b32_e32 v30, v10
; CHECK-NEXT:    v_mov_b32_e32 v31, v9
; CHECK-NEXT:    ; kill: def $vgpr8 killed $vgpr8 killed $vgpr8_vgpr9_vgpr10_vgpr11 killed $exec
; CHECK-NEXT:    ; kill: def $vgpr8 killed $vgpr8 def $vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23 killed $exec
; CHECK-NEXT:    v_mov_b32_e32 v9, v31
; CHECK-NEXT:    v_mov_b32_e32 v10, v30
; CHECK-NEXT:    v_mov_b32_e32 v11, v29
; CHECK-NEXT:    v_mov_b32_e32 v12, v28
; CHECK-NEXT:    v_mov_b32_e32 v13, v27
; CHECK-NEXT:    v_mov_b32_e32 v14, v26
; CHECK-NEXT:    v_mov_b32_e32 v15, v25
; CHECK-NEXT:    v_mov_b32_e32 v16, v24
; CHECK-NEXT:    v_mov_b32_e32 v17, v7
; CHECK-NEXT:    v_mov_b32_e32 v18, v6
; CHECK-NEXT:    v_mov_b32_e32 v19, v5
; CHECK-NEXT:    v_mov_b32_e32 v20, v4
; CHECK-NEXT:    v_mov_b32_e32 v21, v3
; CHECK-NEXT:    v_mov_b32_e32 v22, v2
; CHECK-NEXT:    v_mov_b32_e32 v23, v1
; CHECK-NEXT:    v_mov_b64_e32 v[2:3], s[12:13]
; CHECK-NEXT:    v_mov_b64_e32 v[4:5], s[14:15]
; CHECK-NEXT:    v_mov_b64_e32 v[30:31], s[10:11]
; CHECK-NEXT:    v_mov_b64_e32 v[28:29], s[8:9]
; CHECK-NEXT:    v_mov_b64_e32 v[26:27], s[6:7]
; CHECK-NEXT:    v_mov_b64_e32 v[24:25], s[4:5]
; CHECK-NEXT:    v_mov_b32_e32 v1, s2
; CHECK-NEXT:    s_nop 1
; CHECK-NEXT:    v_smfmac_f32_32x32x32_f16 v[8:23], v[2:5], v[24:31], v1 cbsz:1 abid:2
; CHECK-NEXT:    s_nop 11
; CHECK-NEXT:    v_mov_b32_e32 v1, v23
; CHECK-NEXT:    v_mov_b32_e32 v6, v22
; CHECK-NEXT:    v_mov_b32_e32 v7, v21
; CHECK-NEXT:    v_mov_b32_e32 v2, v20
; CHECK-NEXT:    ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3_vgpr4_vgpr5 killed $exec
; CHECK-NEXT:    v_mov_b32_e32 v3, v7
; CHECK-NEXT:    v_mov_b32_e32 v4, v6
; CHECK-NEXT:    v_mov_b32_e32 v5, v1
; CHECK-NEXT:    global_store_dwordx4 v0, v[2:5], s[0:1] offset:48
; CHECK-NEXT:    v_mov_b32_e32 v1, v19
; CHECK-NEXT:    v_mov_b32_e32 v6, v18
; CHECK-NEXT:    v_mov_b32_e32 v7, v17
; CHECK-NEXT:    v_mov_b32_e32 v2, v16
; CHECK-NEXT:    ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3_vgpr4_vgpr5 killed $exec
; CHECK-NEXT:    v_mov_b32_e32 v3, v7
; CHECK-NEXT:    v_mov_b32_e32 v4, v6
; CHECK-NEXT:    v_mov_b32_e32 v5, v1
; CHECK-NEXT:    global_store_dwordx4 v0, v[2:5], s[0:1] offset:32
; CHECK-NEXT:    v_mov_b32_e32 v1, v15
; CHECK-NEXT:    v_mov_b32_e32 v6, v14
; CHECK-NEXT:    v_mov_b32_e32 v7, v13
; CHECK-NEXT:    v_mov_b32_e32 v2, v12
; CHECK-NEXT:    ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3_vgpr4_vgpr5 killed $exec
; CHECK-NEXT:    v_mov_b32_e32 v3, v7
; CHECK-NEXT:    v_mov_b32_e32 v4, v6
; CHECK-NEXT:    v_mov_b32_e32 v5, v1
; CHECK-NEXT:    global_store_dwordx4 v0, v[2:5], s[0:1] offset:16
; CHECK-NEXT:    v_mov_b32_e32 v1, v11
; CHECK-NEXT:    v_mov_b32_e32 v6, v10
; CHECK-NEXT:    v_mov_b32_e32 v7, v9
; CHECK-NEXT:    v_mov_b32_e32 v2, v8
; CHECK-NEXT:    ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3_vgpr4_vgpr5 killed $exec
; CHECK-NEXT:    v_mov_b32_e32 v3, v7
; CHECK-NEXT:    v_mov_b32_e32 v4, v6
; CHECK-NEXT:    v_mov_b32_e32 v5, v1
; CHECK-NEXT:    global_store_dwordx4 v0, v[2:5], s[0:1]
; CHECK-NEXT:    s_endpgm
bb:
  %id = call i32 @llvm.amdgcn.workitem.id.x()
  %gep = getelementptr <16 x float>, ptr addrspace(1) %arg, i32 %id
  %in.1 = load <16 x float>, ptr addrspace(1) %gep
  %mai.1 = tail call <16 x float> @llvm.amdgcn.smfmac.f32.32x32x32.f16(<8 x half> %a, <16 x half> %b, <16 x float> %in.1, i32 %idx, i32 1, i32 2)
  store <16 x float> %mai.1, ptr addrspace(1) %arg
  ret void
}

attributes #0 = { "amdgpu-flat-work-group-size"="1,256" "amdgpu-agpr-alloc"="0,0" }