llvm/test/CodeGen/AMDGPU/nested-calls.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,FIJI %s
; RUN: llc -mtriple=amdgcn -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,HAWAII %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s

; Test calls when called by other callable functions rather than
; kernels.

declare void @external_void_func_i32(i32) #0

; Spill CSR VGPR used for SGPR spilling
define void @test_func_call_external_void_func_i32_imm() #0 {
; GCN-LABEL: test_func_call_external_void_func_i32_imm:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT:    s_mov_b32 s16, s33
; GCN-NEXT:    s_mov_b32 s33, s32
; GCN-NEXT:    s_or_saveexec_b64 s[18:19], -1
; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s33 ; 4-byte Folded Spill
; GCN-NEXT:    s_mov_b64 exec, s[18:19]
; GCN-NEXT:    s_addk_i32 s32, 0x400
; GCN-NEXT:    v_writelane_b32 v40, s16, 2
; GCN-NEXT:    s_getpc_b64 s[16:17]
; GCN-NEXT:    s_add_u32 s16, s16, external_void_func_i32@gotpcrel32@lo+4
; GCN-NEXT:    s_addc_u32 s17, s17, external_void_func_i32@gotpcrel32@hi+12
; GCN-NEXT:    s_load_dwordx2 s[16:17], s[16:17], 0x0
; GCN-NEXT:    v_writelane_b32 v40, s30, 0
; GCN-NEXT:    v_mov_b32_e32 v0, 42
; GCN-NEXT:    v_writelane_b32 v40, s31, 1
; GCN-NEXT:    s_waitcnt lgkmcnt(0)
; GCN-NEXT:    s_swappc_b64 s[30:31], s[16:17]
; GCN-NEXT:    v_readlane_b32 s31, v40, 1
; GCN-NEXT:    v_readlane_b32 s30, v40, 0
; GCN-NEXT:    s_mov_b32 s32, s33
; GCN-NEXT:    v_readlane_b32 s4, v40, 2
; GCN-NEXT:    s_or_saveexec_b64 s[6:7], -1
; GCN-NEXT:    buffer_load_dword v40, off, s[0:3], s33 ; 4-byte Folded Reload
; GCN-NEXT:    s_mov_b64 exec, s[6:7]
; GCN-NEXT:    s_mov_b32 s33, s4
; GCN-NEXT:    s_waitcnt vmcnt(0)
; GCN-NEXT:    s_setpc_b64 s[30:31]
  call void @external_void_func_i32(i32 42)
  ret void
}

define void @test_func_call_external_void_func_i32_imm_stack_use() #0 {
; GCN-LABEL: test_func_call_external_void_func_i32_imm_stack_use:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT:    s_mov_b32 s16, s33
; GCN-NEXT:    s_mov_b32 s33, s32
; GCN-NEXT:    s_or_saveexec_b64 s[18:19], -1
; GCN-NEXT:    buffer_store_dword v40, off, s[0:3], s33 offset:64 ; 4-byte Folded Spill
; GCN-NEXT:    s_mov_b64 exec, s[18:19]
; GCN-NEXT:    s_addk_i32 s32, 0x1400
; GCN-NEXT:    v_writelane_b32 v40, s16, 2
; GCN-NEXT:    s_getpc_b64 s[16:17]
; GCN-NEXT:    s_add_u32 s16, s16, external_void_func_i32@gotpcrel32@lo+4
; GCN-NEXT:    s_addc_u32 s17, s17, external_void_func_i32@gotpcrel32@hi+12
; GCN-NEXT:    s_load_dwordx2 s[16:17], s[16:17], 0x0
; GCN-NEXT:    v_mov_b32_e32 v0, 0
; GCN-NEXT:    v_writelane_b32 v40, s30, 0
; GCN-NEXT:    buffer_store_dword v0, off, s[0:3], s33
; GCN-NEXT:    s_waitcnt vmcnt(0)
; GCN-NEXT:    buffer_store_dword v0, off, s[0:3], s33 offset:64
; GCN-NEXT:    s_waitcnt vmcnt(0)
; GCN-NEXT:    v_mov_b32_e32 v0, 42
; GCN-NEXT:    v_writelane_b32 v40, s31, 1
; GCN-NEXT:    s_waitcnt lgkmcnt(0)
; GCN-NEXT:    s_swappc_b64 s[30:31], s[16:17]
; GCN-NEXT:    v_readlane_b32 s31, v40, 1
; GCN-NEXT:    v_readlane_b32 s30, v40, 0
; GCN-NEXT:    s_mov_b32 s32, s33
; GCN-NEXT:    v_readlane_b32 s4, v40, 2
; GCN-NEXT:    s_or_saveexec_b64 s[6:7], -1
; GCN-NEXT:    buffer_load_dword v40, off, s[0:3], s33 offset:64 ; 4-byte Folded Reload
; GCN-NEXT:    s_mov_b64 exec, s[6:7]
; GCN-NEXT:    s_mov_b32 s33, s4
; GCN-NEXT:    s_waitcnt vmcnt(0)
; GCN-NEXT:    s_setpc_b64 s[30:31]
  %alloca = alloca [16 x i32], align 4, addrspace(5)
  %gep15 = getelementptr inbounds [16 x i32], ptr addrspace(5) %alloca, i32 0, i32 16
  store volatile i32 0, ptr addrspace(5) %alloca
  store volatile i32 0, ptr addrspace(5) %gep15
  call void @external_void_func_i32(i32 42)
  ret void
}

attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
attributes #2 = { nounwind noinline }
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; FIJI: {{.*}}
; GFX9: {{.*}}
; HAWAII: {{.*}}