; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd- -O0 -mcpu=gfx600 < %s | FileCheck --check-prefixes=GFX6 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx700 < %s | FileCheck --check-prefixes=GFX7 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1010 < %s | FileCheck --check-prefixes=GFX10-WGP %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1010 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX10-CU %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -O0 -mcpu=gfx700 -amdgcn-skip-cache-invalidations < %s | FileCheck --check-prefixes=SKIP-CACHE-INV %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1100 < %s | FileCheck --check-prefixes=GFX11-WGP %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1100 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX11-CU %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX12-WGP %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX12-CU %s

define amdgpu_kernel void @private_volatile_load_0(
; GFX6-LABEL: private_volatile_load_0:
; GFX6:       ; %bb.0: ; %entry
; GFX6-NEXT:    s_mov_b32 s12, SCRATCH_RSRC_DWORD0
; GFX6-NEXT:    s_mov_b32 s13, SCRATCH_RSRC_DWORD1
; GFX6-NEXT:    s_mov_b32 s14, -1
; GFX6-NEXT:    s_mov_b32 s15, 0xe8f000
; GFX6-NEXT:    s_add_u32 s12, s12, s11
; GFX6-NEXT:    s_addc_u32 s13, s13, 0
; GFX6-NEXT:    s_mov_b64 s[0:1], s[4:5]
; GFX6-NEXT:    s_load_dword s4, s[0:1], 0x9
; GFX6-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0xb
; GFX6-NEXT:    s_waitcnt lgkmcnt(0)
; GFX6-NEXT:    s_mov_b32 s7, s1
; GFX6-NEXT:    ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
; GFX6-NEXT:    s_mov_b32 s5, 0xf000
; GFX6-NEXT:    s_mov_b32 s6, -1
; GFX6-NEXT:    ; kill: def $sgpr0 killed $sgpr0 def $sgpr0_sgpr1_sgpr2_sgpr3
; GFX6-NEXT:    s_mov_b32 s1, s7
; GFX6-NEXT:    s_mov_b32 s2, s6
; GFX6-NEXT:    s_mov_b32 s3, s5
; GFX6-NEXT:    v_mov_b32_e32 v0, s4
; GFX6-NEXT:    buffer_load_dword v0, v0, s[12:15], 0 offen glc
; GFX6-NEXT:    s_waitcnt vmcnt(0)
; GFX6-NEXT:    buffer_store_dword v0, off, s[0:3], 0
; GFX6-NEXT:    s_endpgm
;
; GFX7-LABEL: private_volatile_load_0:
; GFX7:       ; %bb.0: ; %entry
; GFX7-NEXT:    s_add_u32 s0, s0, s15
; GFX7-NEXT:    s_addc_u32 s1, s1, 0
; GFX7-NEXT:    s_load_dword s6, s[8:9], 0x0
; GFX7-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x2
; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
; GFX7-NEXT:    v_mov_b32_e32 v0, s6
; GFX7-NEXT:    buffer_load_dword v2, v0, s[0:3], 0 offen glc
; GFX7-NEXT:    s_waitcnt vmcnt(0)
; GFX7-NEXT:    v_mov_b32_e32 v0, s4
; GFX7-NEXT:    v_mov_b32_e32 v1, s5
; GFX7-NEXT:    flat_store_dword v[0:1], v2
; GFX7-NEXT:    s_endpgm
;
; GFX10-WGP-LABEL: private_volatile_load_0:
; GFX10-WGP:       ; %bb.0: ; %entry
; GFX10-WGP-NEXT:    s_add_u32 s0, s0, s15
; GFX10-WGP-NEXT:    s_addc_u32 s1, s1, 0
; GFX10-WGP-NEXT:    s_load_dword s6, s[8:9], 0x0
; GFX10-WGP-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x8
; GFX10-WGP-NEXT:    v_mov_b32_e32 v0, 0
; GFX10-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT:    v_mov_b32_e32 v1, s6
; GFX10-WGP-NEXT:    buffer_load_dword v1, v1, s[0:3], 0 offen glc dlc
; GFX10-WGP-NEXT:    s_waitcnt vmcnt(0)
; GFX10-WGP-NEXT:    global_store_dword v0, v1, s[4:5]
; GFX10-WGP-NEXT:    s_endpgm
;
; GFX10-CU-LABEL: private_volatile_load_0:
; GFX10-CU:       ; %bb.0: ; %entry
; GFX10-CU-NEXT:    s_add_u32 s0, s0, s15
; GFX10-CU-NEXT:    s_addc_u32 s1, s1, 0
; GFX10-CU-NEXT:    s_load_dword s6, s[8:9], 0x0
; GFX10-CU-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x8
; GFX10-CU-NEXT:    v_mov_b32_e32 v0, 0
; GFX10-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT:    v_mov_b32_e32 v1, s6
; GFX10-CU-NEXT:    buffer_load_dword v1, v1, s[0:3], 0 offen glc dlc
; GFX10-CU-NEXT:    s_waitcnt vmcnt(0)
; GFX10-CU-NEXT:    global_store_dword v0, v1, s[4:5]
; GFX10-CU-NEXT:    s_endpgm
;
; SKIP-CACHE-INV-LABEL: private_volatile_load_0:
; SKIP-CACHE-INV:       ; %bb.0: ; %entry
; SKIP-CACHE-INV-NEXT:    s_getpc_b64 s[12:13]
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s12, s0
; SKIP-CACHE-INV-NEXT:    s_load_dwordx4 s[12:15], s[12:13], 0x0
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_add_u32 s12, s12, s11
; SKIP-CACHE-INV-NEXT:    s_addc_u32 s13, s13, 0
; SKIP-CACHE-INV-NEXT:    s_mov_b64 s[0:1], s[4:5]
; SKIP-CACHE-INV-NEXT:    s_load_dword s4, s[0:1], 0x0
; SKIP-CACHE-INV-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x2
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s7, s1
; SKIP-CACHE-INV-NEXT:    ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s5, 0xf000
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s6, -1
; SKIP-CACHE-INV-NEXT:    ; kill: def $sgpr0 killed $sgpr0 def $sgpr0_sgpr1_sgpr2_sgpr3
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s1, s7
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s2, s6
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s3, s5
; SKIP-CACHE-INV-NEXT:    v_mov_b32_e32 v0, s4
; SKIP-CACHE-INV-NEXT:    buffer_load_dword v0, v0, s[12:15], 0 offen glc
; SKIP-CACHE-INV-NEXT:    s_waitcnt vmcnt(0)
; SKIP-CACHE-INV-NEXT:    buffer_store_dword v0, off, s[0:3], 0
; SKIP-CACHE-INV-NEXT:    s_endpgm
;
; GFX11-WGP-LABEL: private_volatile_load_0:
; GFX11-WGP:       ; %bb.0: ; %entry
; GFX11-WGP-NEXT:    s_load_b32 s2, s[4:5], 0x0
; GFX11-WGP-NEXT:    s_load_b64 s[0:1], s[4:5], 0x8
; GFX11-WGP-NEXT:    v_mov_b32_e32 v0, 0
; GFX11-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-WGP-NEXT:    scratch_load_b32 v1, off, s2 glc dlc
; GFX11-WGP-NEXT:    s_waitcnt vmcnt(0)
; GFX11-WGP-NEXT:    global_store_b32 v0, v1, s[0:1]
; GFX11-WGP-NEXT:    s_endpgm
;
; GFX11-CU-LABEL: private_volatile_load_0:
; GFX11-CU:       ; %bb.0: ; %entry
; GFX11-CU-NEXT:    s_load_b32 s2, s[4:5], 0x0
; GFX11-CU-NEXT:    s_load_b64 s[0:1], s[4:5], 0x8
; GFX11-CU-NEXT:    v_mov_b32_e32 v0, 0
; GFX11-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-CU-NEXT:    scratch_load_b32 v1, off, s2 glc dlc
; GFX11-CU-NEXT:    s_waitcnt vmcnt(0)
; GFX11-CU-NEXT:    global_store_b32 v0, v1, s[0:1]
; GFX11-CU-NEXT:    s_endpgm
;
; GFX12-WGP-LABEL: private_volatile_load_0:
; GFX12-WGP:       ; %bb.0: ; %entry
; GFX12-WGP-NEXT:    s_load_b32 s2, s[4:5], 0x0
; GFX12-WGP-NEXT:    s_load_b64 s[0:1], s[4:5], 0x8
; GFX12-WGP-NEXT:    v_mov_b32_e32 v0, 0
; GFX12-WGP-NEXT:    s_wait_kmcnt 0x0
; GFX12-WGP-NEXT:    scratch_load_b32 v1, off, s2 scope:SCOPE_SYS
; GFX12-WGP-NEXT:    s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT:    s_wait_samplecnt 0x0
; GFX12-WGP-NEXT:    s_wait_loadcnt 0x0
; GFX12-WGP-NEXT:    global_store_b32 v0, v1, s[0:1]
; GFX12-WGP-NEXT:    s_endpgm
;
; GFX12-CU-LABEL: private_volatile_load_0:
; GFX12-CU:       ; %bb.0: ; %entry
; GFX12-CU-NEXT:    s_load_b32 s2, s[4:5], 0x0
; GFX12-CU-NEXT:    s_load_b64 s[0:1], s[4:5], 0x8
; GFX12-CU-NEXT:    v_mov_b32_e32 v0, 0
; GFX12-CU-NEXT:    s_wait_kmcnt 0x0
; GFX12-CU-NEXT:    scratch_load_b32 v1, off, s2 scope:SCOPE_SYS
; GFX12-CU-NEXT:    s_wait_bvhcnt 0x0
; GFX12-CU-NEXT:    s_wait_samplecnt 0x0
; GFX12-CU-NEXT:    s_wait_loadcnt 0x0
; GFX12-CU-NEXT:    global_store_b32 v0, v1, s[0:1]
; GFX12-CU-NEXT:    s_endpgm
    ptr addrspace(5) %in, ptr addrspace(1) %out) {
entry:
  %val = load volatile i32, ptr addrspace(5) %in, align 4
  store i32 %val, ptr addrspace(1) %out
  ret void
}

define amdgpu_kernel void @private_volatile_load_1(
; GFX6-LABEL: private_volatile_load_1:
; GFX6:       ; %bb.0: ; %entry
; GFX6-NEXT:    s_mov_b32 s12, SCRATCH_RSRC_DWORD0
; GFX6-NEXT:    s_mov_b32 s13, SCRATCH_RSRC_DWORD1
; GFX6-NEXT:    s_mov_b32 s14, -1
; GFX6-NEXT:    s_mov_b32 s15, 0xe8f000
; GFX6-NEXT:    s_add_u32 s12, s12, s11
; GFX6-NEXT:    s_addc_u32 s13, s13, 0
; GFX6-NEXT:    s_mov_b64 s[0:1], s[4:5]
; GFX6-NEXT:    s_load_dword s4, s[0:1], 0x9
; GFX6-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0xb
; GFX6-NEXT:    s_waitcnt lgkmcnt(0)
; GFX6-NEXT:    s_mov_b32 s7, s1
; GFX6-NEXT:    ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
; GFX6-NEXT:    s_mov_b32 s5, 0xf000
; GFX6-NEXT:    s_mov_b32 s6, -1
; GFX6-NEXT:    ; kill: def $sgpr0 killed $sgpr0 def $sgpr0_sgpr1_sgpr2_sgpr3
; GFX6-NEXT:    s_mov_b32 s1, s7
; GFX6-NEXT:    s_mov_b32 s2, s6
; GFX6-NEXT:    s_mov_b32 s3, s5
; GFX6-NEXT:    s_mov_b32 s5, 2
; GFX6-NEXT:    v_lshlrev_b32_e64 v0, s5, v0
; GFX6-NEXT:    v_add_i32_e64 v0, s[4:5], s4, v0
; GFX6-NEXT:    buffer_load_dword v0, v0, s[12:15], 0 offen glc
; GFX6-NEXT:    s_waitcnt vmcnt(0)
; GFX6-NEXT:    buffer_store_dword v0, off, s[0:3], 0
; GFX6-NEXT:    s_endpgm
;
; GFX7-LABEL: private_volatile_load_1:
; GFX7:       ; %bb.0: ; %entry
; GFX7-NEXT:    s_add_u32 s0, s0, s15
; GFX7-NEXT:    s_addc_u32 s1, s1, 0
; GFX7-NEXT:    s_load_dword s6, s[8:9], 0x0
; GFX7-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x2
; GFX7-NEXT:    s_mov_b32 s7, 2
; GFX7-NEXT:    v_lshlrev_b32_e64 v0, s7, v0
; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
; GFX7-NEXT:    v_add_i32_e64 v0, s[6:7], s6, v0
; GFX7-NEXT:    buffer_load_dword v2, v0, s[0:3], 0 offen glc
; GFX7-NEXT:    s_waitcnt vmcnt(0)
; GFX7-NEXT:    v_mov_b32_e32 v0, s4
; GFX7-NEXT:    v_mov_b32_e32 v1, s5
; GFX7-NEXT:    flat_store_dword v[0:1], v2
; GFX7-NEXT:    s_endpgm
;
; GFX10-WGP-LABEL: private_volatile_load_1:
; GFX10-WGP:       ; %bb.0: ; %entry
; GFX10-WGP-NEXT:    s_add_u32 s0, s0, s15
; GFX10-WGP-NEXT:    s_addc_u32 s1, s1, 0
; GFX10-WGP-NEXT:    v_mov_b32_e32 v1, v0
; GFX10-WGP-NEXT:    s_load_dword s7, s[8:9], 0x0
; GFX10-WGP-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x8
; GFX10-WGP-NEXT:    v_mov_b32_e32 v0, 0
; GFX10-WGP-NEXT:    s_mov_b32 s6, 2
; GFX10-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT:    v_lshl_add_u32 v1, v1, s6, s7
; GFX10-WGP-NEXT:    buffer_load_dword v1, v1, s[0:3], 0 offen glc dlc
; GFX10-WGP-NEXT:    s_waitcnt vmcnt(0)
; GFX10-WGP-NEXT:    global_store_dword v0, v1, s[4:5]
; GFX10-WGP-NEXT:    s_endpgm
;
; GFX10-CU-LABEL: private_volatile_load_1:
; GFX10-CU:       ; %bb.0: ; %entry
; GFX10-CU-NEXT:    s_add_u32 s0, s0, s15
; GFX10-CU-NEXT:    s_addc_u32 s1, s1, 0
; GFX10-CU-NEXT:    v_mov_b32_e32 v1, v0
; GFX10-CU-NEXT:    s_load_dword s7, s[8:9], 0x0
; GFX10-CU-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x8
; GFX10-CU-NEXT:    v_mov_b32_e32 v0, 0
; GFX10-CU-NEXT:    s_mov_b32 s6, 2
; GFX10-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT:    v_lshl_add_u32 v1, v1, s6, s7
; GFX10-CU-NEXT:    buffer_load_dword v1, v1, s[0:3], 0 offen glc dlc
; GFX10-CU-NEXT:    s_waitcnt vmcnt(0)
; GFX10-CU-NEXT:    global_store_dword v0, v1, s[4:5]
; GFX10-CU-NEXT:    s_endpgm
;
; SKIP-CACHE-INV-LABEL: private_volatile_load_1:
; SKIP-CACHE-INV:       ; %bb.0: ; %entry
; SKIP-CACHE-INV-NEXT:    s_getpc_b64 s[12:13]
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s12, s0
; SKIP-CACHE-INV-NEXT:    s_load_dwordx4 s[12:15], s[12:13], 0x0
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_add_u32 s12, s12, s11
; SKIP-CACHE-INV-NEXT:    s_addc_u32 s13, s13, 0
; SKIP-CACHE-INV-NEXT:    s_mov_b64 s[0:1], s[4:5]
; SKIP-CACHE-INV-NEXT:    s_load_dword s4, s[0:1], 0x0
; SKIP-CACHE-INV-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x2
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s7, s1
; SKIP-CACHE-INV-NEXT:    ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s5, 0xf000
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s6, -1
; SKIP-CACHE-INV-NEXT:    ; kill: def $sgpr0 killed $sgpr0 def $sgpr0_sgpr1_sgpr2_sgpr3
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s1, s7
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s2, s6
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s3, s5
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s5, 2
; SKIP-CACHE-INV-NEXT:    v_lshlrev_b32_e64 v0, s5, v0
; SKIP-CACHE-INV-NEXT:    v_add_i32_e64 v0, s[4:5], s4, v0
; SKIP-CACHE-INV-NEXT:    buffer_load_dword v0, v0, s[12:15], 0 offen glc
; SKIP-CACHE-INV-NEXT:    s_waitcnt vmcnt(0)
; SKIP-CACHE-INV-NEXT:    buffer_store_dword v0, off, s[0:3], 0
; SKIP-CACHE-INV-NEXT:    s_endpgm
;
; GFX11-WGP-LABEL: private_volatile_load_1:
; GFX11-WGP:       ; %bb.0: ; %entry
; GFX11-WGP-NEXT:    v_mov_b32_e32 v1, v0
; GFX11-WGP-NEXT:    s_load_b32 s3, s[4:5], 0x0
; GFX11-WGP-NEXT:    s_load_b64 s[0:1], s[4:5], 0x8
; GFX11-WGP-NEXT:    v_mov_b32_e32 v0, 0
; GFX11-WGP-NEXT:    s_mov_b32 s2, 0x3ff
; GFX11-WGP-NEXT:    v_and_b32_e64 v1, v1, s2
; GFX11-WGP-NEXT:    s_mov_b32 s2, 2
; GFX11-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-WGP-NEXT:    v_lshl_add_u32 v1, v1, s2, s3
; GFX11-WGP-NEXT:    scratch_load_b32 v1, v1, off glc dlc
; GFX11-WGP-NEXT:    s_waitcnt vmcnt(0)
; GFX11-WGP-NEXT:    global_store_b32 v0, v1, s[0:1]
; GFX11-WGP-NEXT:    s_endpgm
;
; GFX11-CU-LABEL: private_volatile_load_1:
; GFX11-CU:       ; %bb.0: ; %entry
; GFX11-CU-NEXT:    v_mov_b32_e32 v1, v0
; GFX11-CU-NEXT:    s_load_b32 s3, s[4:5], 0x0
; GFX11-CU-NEXT:    s_load_b64 s[0:1], s[4:5], 0x8
; GFX11-CU-NEXT:    v_mov_b32_e32 v0, 0
; GFX11-CU-NEXT:    s_mov_b32 s2, 0x3ff
; GFX11-CU-NEXT:    v_and_b32_e64 v1, v1, s2
; GFX11-CU-NEXT:    s_mov_b32 s2, 2
; GFX11-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-CU-NEXT:    v_lshl_add_u32 v1, v1, s2, s3
; GFX11-CU-NEXT:    scratch_load_b32 v1, v1, off glc dlc
; GFX11-CU-NEXT:    s_waitcnt vmcnt(0)
; GFX11-CU-NEXT:    global_store_b32 v0, v1, s[0:1]
; GFX11-CU-NEXT:    s_endpgm
;
; GFX12-WGP-LABEL: private_volatile_load_1:
; GFX12-WGP:       ; %bb.0: ; %entry
; GFX12-WGP-NEXT:    v_mov_b32_e32 v1, v0
; GFX12-WGP-NEXT:    s_load_b32 s2, s[4:5], 0x0
; GFX12-WGP-NEXT:    s_load_b64 s[0:1], s[4:5], 0x8
; GFX12-WGP-NEXT:    v_mov_b32_e32 v0, 0
; GFX12-WGP-NEXT:    s_mov_b32 s3, 0x3ff
; GFX12-WGP-NEXT:    s_wait_alu 0xfffe
; GFX12-WGP-NEXT:    v_and_b32_e64 v1, v1, s3
; GFX12-WGP-NEXT:    s_mov_b32 s3, 2
; GFX12-WGP-NEXT:    s_wait_alu 0xfffe
; GFX12-WGP-NEXT:    v_lshlrev_b32_e64 v1, s3, v1
; GFX12-WGP-NEXT:    s_wait_kmcnt 0x0
; GFX12-WGP-NEXT:    scratch_load_b32 v1, v1, s2 scope:SCOPE_SYS
; GFX12-WGP-NEXT:    s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT:    s_wait_samplecnt 0x0
; GFX12-WGP-NEXT:    s_wait_loadcnt 0x0
; GFX12-WGP-NEXT:    global_store_b32 v0, v1, s[0:1]
; GFX12-WGP-NEXT:    s_endpgm
;
; GFX12-CU-LABEL: private_volatile_load_1:
; GFX12-CU:       ; %bb.0: ; %entry
; GFX12-CU-NEXT:    v_mov_b32_e32 v1, v0
; GFX12-CU-NEXT:    s_load_b32 s2, s[4:5], 0x0
; GFX12-CU-NEXT:    s_load_b64 s[0:1], s[4:5], 0x8
; GFX12-CU-NEXT:    v_mov_b32_e32 v0, 0
; GFX12-CU-NEXT:    s_mov_b32 s3, 0x3ff
; GFX12-CU-NEXT:    s_wait_alu 0xfffe
; GFX12-CU-NEXT:    v_and_b32_e64 v1, v1, s3
; GFX12-CU-NEXT:    s_mov_b32 s3, 2
; GFX12-CU-NEXT:    s_wait_alu 0xfffe
; GFX12-CU-NEXT:    v_lshlrev_b32_e64 v1, s3, v1
; GFX12-CU-NEXT:    s_wait_kmcnt 0x0
; GFX12-CU-NEXT:    scratch_load_b32 v1, v1, s2 scope:SCOPE_SYS
; GFX12-CU-NEXT:    s_wait_bvhcnt 0x0
; GFX12-CU-NEXT:    s_wait_samplecnt 0x0
; GFX12-CU-NEXT:    s_wait_loadcnt 0x0
; GFX12-CU-NEXT:    global_store_b32 v0, v1, s[0:1]
; GFX12-CU-NEXT:    s_endpgm
    ptr addrspace(5) %in, ptr addrspace(1) %out) {
entry:
  %tid = call i32 @llvm.amdgcn.workitem.id.x()
  %val.gep = getelementptr inbounds i32, ptr addrspace(5) %in, i32 %tid
  %val = load volatile i32, ptr addrspace(5) %val.gep, align 4
  store i32 %val, ptr addrspace(1) %out
  ret void
}

define amdgpu_kernel void @private_volatile_store_0(
; GFX6-LABEL: private_volatile_store_0:
; GFX6:       ; %bb.0: ; %entry
; GFX6-NEXT:    s_mov_b32 s12, SCRATCH_RSRC_DWORD0
; GFX6-NEXT:    s_mov_b32 s13, SCRATCH_RSRC_DWORD1
; GFX6-NEXT:    s_mov_b32 s14, -1
; GFX6-NEXT:    s_mov_b32 s15, 0xe8f000
; GFX6-NEXT:    s_add_u32 s12, s12, s11
; GFX6-NEXT:    s_addc_u32 s13, s13, 0
; GFX6-NEXT:    s_load_dwordx2 s[2:3], s[4:5], 0x9
; GFX6-NEXT:    s_load_dword s0, s[4:5], 0xb
; GFX6-NEXT:    s_waitcnt lgkmcnt(0)
; GFX6-NEXT:    s_load_dword s1, s[2:3], 0x0
; GFX6-NEXT:    s_waitcnt lgkmcnt(0)
; GFX6-NEXT:    v_mov_b32_e32 v0, s1
; GFX6-NEXT:    v_mov_b32_e32 v1, s0
; GFX6-NEXT:    buffer_store_dword v0, v1, s[12:15], 0 offen
; GFX6-NEXT:    s_waitcnt vmcnt(0)
; GFX6-NEXT:    s_endpgm
;
; GFX7-LABEL: private_volatile_store_0:
; GFX7:       ; %bb.0: ; %entry
; GFX7-NEXT:    s_add_u32 s0, s0, s15
; GFX7-NEXT:    s_addc_u32 s1, s1, 0
; GFX7-NEXT:    s_load_dwordx2 s[6:7], s[8:9], 0x0
; GFX7-NEXT:    s_load_dword s4, s[8:9], 0x2
; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
; GFX7-NEXT:    s_load_dword s5, s[6:7], 0x0
; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
; GFX7-NEXT:    v_mov_b32_e32 v0, s5
; GFX7-NEXT:    v_mov_b32_e32 v1, s4
; GFX7-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
; GFX7-NEXT:    s_waitcnt vmcnt(0)
; GFX7-NEXT:    s_endpgm
;
; GFX10-WGP-LABEL: private_volatile_store_0:
; GFX10-WGP:       ; %bb.0: ; %entry
; GFX10-WGP-NEXT:    s_add_u32 s0, s0, s15
; GFX10-WGP-NEXT:    s_addc_u32 s1, s1, 0
; GFX10-WGP-NEXT:    s_load_dwordx2 s[6:7], s[8:9], 0x0
; GFX10-WGP-NEXT:    s_load_dword s4, s[8:9], 0x8
; GFX10-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT:    s_load_dword s5, s[6:7], 0x0
; GFX10-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT:    v_mov_b32_e32 v0, s5
; GFX10-WGP-NEXT:    v_mov_b32_e32 v1, s4
; GFX10-WGP-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
; GFX10-WGP-NEXT:    s_waitcnt_vscnt null, 0x0
; GFX10-WGP-NEXT:    s_endpgm
;
; GFX10-CU-LABEL: private_volatile_store_0:
; GFX10-CU:       ; %bb.0: ; %entry
; GFX10-CU-NEXT:    s_add_u32 s0, s0, s15
; GFX10-CU-NEXT:    s_addc_u32 s1, s1, 0
; GFX10-CU-NEXT:    s_load_dwordx2 s[6:7], s[8:9], 0x0
; GFX10-CU-NEXT:    s_load_dword s4, s[8:9], 0x8
; GFX10-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT:    s_load_dword s5, s[6:7], 0x0
; GFX10-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT:    v_mov_b32_e32 v0, s5
; GFX10-CU-NEXT:    v_mov_b32_e32 v1, s4
; GFX10-CU-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
; GFX10-CU-NEXT:    s_waitcnt_vscnt null, 0x0
; GFX10-CU-NEXT:    s_endpgm
;
; SKIP-CACHE-INV-LABEL: private_volatile_store_0:
; SKIP-CACHE-INV:       ; %bb.0: ; %entry
; SKIP-CACHE-INV-NEXT:    s_getpc_b64 s[12:13]
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s12, s0
; SKIP-CACHE-INV-NEXT:    s_load_dwordx4 s[12:15], s[12:13], 0x0
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_add_u32 s12, s12, s11
; SKIP-CACHE-INV-NEXT:    s_addc_u32 s13, s13, 0
; SKIP-CACHE-INV-NEXT:    s_load_dwordx2 s[2:3], s[4:5], 0x0
; SKIP-CACHE-INV-NEXT:    s_load_dword s0, s[4:5], 0x2
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_load_dword s1, s[2:3], 0x0
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    v_mov_b32_e32 v0, s1
; SKIP-CACHE-INV-NEXT:    v_mov_b32_e32 v1, s0
; SKIP-CACHE-INV-NEXT:    buffer_store_dword v0, v1, s[12:15], 0 offen
; SKIP-CACHE-INV-NEXT:    s_waitcnt vmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_endpgm
;
; GFX11-WGP-LABEL: private_volatile_store_0:
; GFX11-WGP:       ; %bb.0: ; %entry
; GFX11-WGP-NEXT:    s_load_b64 s[2:3], s[4:5], 0x0
; GFX11-WGP-NEXT:    s_load_b32 s0, s[4:5], 0x8
; GFX11-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-WGP-NEXT:    s_load_b32 s1, s[2:3], 0x0
; GFX11-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-WGP-NEXT:    v_mov_b32_e32 v0, s1
; GFX11-WGP-NEXT:    scratch_store_b32 off, v0, s0 dlc
; GFX11-WGP-NEXT:    s_waitcnt_vscnt null, 0x0
; GFX11-WGP-NEXT:    s_endpgm
;
; GFX11-CU-LABEL: private_volatile_store_0:
; GFX11-CU:       ; %bb.0: ; %entry
; GFX11-CU-NEXT:    s_load_b64 s[2:3], s[4:5], 0x0
; GFX11-CU-NEXT:    s_load_b32 s0, s[4:5], 0x8
; GFX11-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-CU-NEXT:    s_load_b32 s1, s[2:3], 0x0
; GFX11-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-CU-NEXT:    v_mov_b32_e32 v0, s1
; GFX11-CU-NEXT:    scratch_store_b32 off, v0, s0 dlc
; GFX11-CU-NEXT:    s_waitcnt_vscnt null, 0x0
; GFX11-CU-NEXT:    s_endpgm
;
; GFX12-WGP-LABEL: private_volatile_store_0:
; GFX12-WGP:       ; %bb.0: ; %entry
; GFX12-WGP-NEXT:    s_load_b64 s[2:3], s[4:5], 0x0
; GFX12-WGP-NEXT:    s_load_b32 s0, s[4:5], 0x8
; GFX12-WGP-NEXT:    s_wait_kmcnt 0x0
; GFX12-WGP-NEXT:    s_load_b32 s1, s[2:3], 0x0
; GFX12-WGP-NEXT:    s_wait_kmcnt 0x0
; GFX12-WGP-NEXT:    v_mov_b32_e32 v0, s1
; GFX12-WGP-NEXT:    s_wait_loadcnt 0x0
; GFX12-WGP-NEXT:    s_wait_samplecnt 0x0
; GFX12-WGP-NEXT:    s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT:    s_wait_kmcnt 0x0
; GFX12-WGP-NEXT:    s_wait_storecnt 0x0
; GFX12-WGP-NEXT:    scratch_store_b32 off, v0, s0 scope:SCOPE_SYS
; GFX12-WGP-NEXT:    s_wait_storecnt 0x0
; GFX12-WGP-NEXT:    s_endpgm
;
; GFX12-CU-LABEL: private_volatile_store_0:
; GFX12-CU:       ; %bb.0: ; %entry
; GFX12-CU-NEXT:    s_load_b64 s[2:3], s[4:5], 0x0
; GFX12-CU-NEXT:    s_load_b32 s0, s[4:5], 0x8
; GFX12-CU-NEXT:    s_wait_kmcnt 0x0
; GFX12-CU-NEXT:    s_load_b32 s1, s[2:3], 0x0
; GFX12-CU-NEXT:    s_wait_kmcnt 0x0
; GFX12-CU-NEXT:    v_mov_b32_e32 v0, s1
; GFX12-CU-NEXT:    s_wait_loadcnt 0x0
; GFX12-CU-NEXT:    s_wait_samplecnt 0x0
; GFX12-CU-NEXT:    s_wait_bvhcnt 0x0
; GFX12-CU-NEXT:    s_wait_kmcnt 0x0
; GFX12-CU-NEXT:    s_wait_storecnt 0x0
; GFX12-CU-NEXT:    scratch_store_b32 off, v0, s0 scope:SCOPE_SYS
; GFX12-CU-NEXT:    s_wait_storecnt 0x0
; GFX12-CU-NEXT:    s_endpgm
    ptr addrspace(1) %in, ptr addrspace(5) %out) {
entry:
  %val = load i32, ptr addrspace(1) %in, align 4
  store volatile i32 %val, ptr addrspace(5) %out
  ret void
}

define amdgpu_kernel void @private_volatile_store_1(
; GFX6-LABEL: private_volatile_store_1:
; GFX6:       ; %bb.0: ; %entry
; GFX6-NEXT:    s_mov_b32 s12, SCRATCH_RSRC_DWORD0
; GFX6-NEXT:    s_mov_b32 s13, SCRATCH_RSRC_DWORD1
; GFX6-NEXT:    s_mov_b32 s14, -1
; GFX6-NEXT:    s_mov_b32 s15, 0xe8f000
; GFX6-NEXT:    s_add_u32 s12, s12, s11
; GFX6-NEXT:    s_addc_u32 s13, s13, 0
; GFX6-NEXT:    s_load_dwordx2 s[2:3], s[4:5], 0x9
; GFX6-NEXT:    s_load_dword s1, s[4:5], 0xb
; GFX6-NEXT:    s_waitcnt lgkmcnt(0)
; GFX6-NEXT:    s_load_dword s0, s[2:3], 0x0
; GFX6-NEXT:    s_mov_b32 s2, 2
; GFX6-NEXT:    v_lshlrev_b32_e64 v0, s2, v0
; GFX6-NEXT:    v_add_i32_e64 v1, s[2:3], s1, v0
; GFX6-NEXT:    s_waitcnt lgkmcnt(0)
; GFX6-NEXT:    v_mov_b32_e32 v0, s0
; GFX6-NEXT:    buffer_store_dword v0, v1, s[12:15], 0 offen
; GFX6-NEXT:    s_waitcnt vmcnt(0)
; GFX6-NEXT:    s_endpgm
;
; GFX7-LABEL: private_volatile_store_1:
; GFX7:       ; %bb.0: ; %entry
; GFX7-NEXT:    s_add_u32 s0, s0, s15
; GFX7-NEXT:    s_addc_u32 s1, s1, 0
; GFX7-NEXT:    s_load_dwordx2 s[6:7], s[8:9], 0x0
; GFX7-NEXT:    s_load_dword s5, s[8:9], 0x2
; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
; GFX7-NEXT:    s_load_dword s4, s[6:7], 0x0
; GFX7-NEXT:    s_mov_b32 s6, 2
; GFX7-NEXT:    v_lshlrev_b32_e64 v0, s6, v0
; GFX7-NEXT:    v_add_i32_e64 v1, s[6:7], s5, v0
; GFX7-NEXT:    s_waitcnt lgkmcnt(0)
; GFX7-NEXT:    v_mov_b32_e32 v0, s4
; GFX7-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
; GFX7-NEXT:    s_waitcnt vmcnt(0)
; GFX7-NEXT:    s_endpgm
;
; GFX10-WGP-LABEL: private_volatile_store_1:
; GFX10-WGP:       ; %bb.0: ; %entry
; GFX10-WGP-NEXT:    s_add_u32 s0, s0, s15
; GFX10-WGP-NEXT:    s_addc_u32 s1, s1, 0
; GFX10-WGP-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x0
; GFX10-WGP-NEXT:    s_load_dword s6, s[8:9], 0x8
; GFX10-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT:    s_load_dword s4, s[4:5], 0x0
; GFX10-WGP-NEXT:    s_mov_b32 s5, 2
; GFX10-WGP-NEXT:    v_lshl_add_u32 v1, v0, s5, s6
; GFX10-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT:    v_mov_b32_e32 v0, s4
; GFX10-WGP-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
; GFX10-WGP-NEXT:    s_waitcnt_vscnt null, 0x0
; GFX10-WGP-NEXT:    s_endpgm
;
; GFX10-CU-LABEL: private_volatile_store_1:
; GFX10-CU:       ; %bb.0: ; %entry
; GFX10-CU-NEXT:    s_add_u32 s0, s0, s15
; GFX10-CU-NEXT:    s_addc_u32 s1, s1, 0
; GFX10-CU-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x0
; GFX10-CU-NEXT:    s_load_dword s6, s[8:9], 0x8
; GFX10-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT:    s_load_dword s4, s[4:5], 0x0
; GFX10-CU-NEXT:    s_mov_b32 s5, 2
; GFX10-CU-NEXT:    v_lshl_add_u32 v1, v0, s5, s6
; GFX10-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT:    v_mov_b32_e32 v0, s4
; GFX10-CU-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
; GFX10-CU-NEXT:    s_waitcnt_vscnt null, 0x0
; GFX10-CU-NEXT:    s_endpgm
;
; SKIP-CACHE-INV-LABEL: private_volatile_store_1:
; SKIP-CACHE-INV:       ; %bb.0: ; %entry
; SKIP-CACHE-INV-NEXT:    s_getpc_b64 s[12:13]
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s12, s0
; SKIP-CACHE-INV-NEXT:    s_load_dwordx4 s[12:15], s[12:13], 0x0
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_add_u32 s12, s12, s11
; SKIP-CACHE-INV-NEXT:    s_addc_u32 s13, s13, 0
; SKIP-CACHE-INV-NEXT:    s_load_dwordx2 s[2:3], s[4:5], 0x0
; SKIP-CACHE-INV-NEXT:    s_load_dword s1, s[4:5], 0x2
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_load_dword s0, s[2:3], 0x0
; SKIP-CACHE-INV-NEXT:    s_mov_b32 s2, 2
; SKIP-CACHE-INV-NEXT:    v_lshlrev_b32_e64 v0, s2, v0
; SKIP-CACHE-INV-NEXT:    v_add_i32_e64 v1, s[2:3], s1, v0
; SKIP-CACHE-INV-NEXT:    s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT:    v_mov_b32_e32 v0, s0
; SKIP-CACHE-INV-NEXT:    buffer_store_dword v0, v1, s[12:15], 0 offen
; SKIP-CACHE-INV-NEXT:    s_waitcnt vmcnt(0)
; SKIP-CACHE-INV-NEXT:    s_endpgm
;
; GFX11-WGP-LABEL: private_volatile_store_1:
; GFX11-WGP:       ; %bb.0: ; %entry
; GFX11-WGP-NEXT:    s_load_b64 s[0:1], s[4:5], 0x0
; GFX11-WGP-NEXT:    s_load_b32 s2, s[4:5], 0x8
; GFX11-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-WGP-NEXT:    s_load_b32 s0, s[0:1], 0x0
; GFX11-WGP-NEXT:    s_mov_b32 s1, 0x3ff
; GFX11-WGP-NEXT:    v_and_b32_e64 v0, v0, s1
; GFX11-WGP-NEXT:    s_mov_b32 s1, 2
; GFX11-WGP-NEXT:    v_lshl_add_u32 v1, v0, s1, s2
; GFX11-WGP-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-WGP-NEXT:    v_mov_b32_e32 v0, s0
; GFX11-WGP-NEXT:    scratch_store_b32 v1, v0, off dlc
; GFX11-WGP-NEXT:    s_waitcnt_vscnt null, 0x0
; GFX11-WGP-NEXT:    s_endpgm
;
; GFX11-CU-LABEL: private_volatile_store_1:
; GFX11-CU:       ; %bb.0: ; %entry
; GFX11-CU-NEXT:    s_load_b64 s[0:1], s[4:5], 0x0
; GFX11-CU-NEXT:    s_load_b32 s2, s[4:5], 0x8
; GFX11-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-CU-NEXT:    s_load_b32 s0, s[0:1], 0x0
; GFX11-CU-NEXT:    s_mov_b32 s1, 0x3ff
; GFX11-CU-NEXT:    v_and_b32_e64 v0, v0, s1
; GFX11-CU-NEXT:    s_mov_b32 s1, 2
; GFX11-CU-NEXT:    v_lshl_add_u32 v1, v0, s1, s2
; GFX11-CU-NEXT:    s_waitcnt lgkmcnt(0)
; GFX11-CU-NEXT:    v_mov_b32_e32 v0, s0
; GFX11-CU-NEXT:    scratch_store_b32 v1, v0, off dlc
; GFX11-CU-NEXT:    s_waitcnt_vscnt null, 0x0
; GFX11-CU-NEXT:    s_endpgm
;
; GFX12-WGP-LABEL: private_volatile_store_1:
; GFX12-WGP:       ; %bb.0: ; %entry
; GFX12-WGP-NEXT:    s_load_b64 s[2:3], s[4:5], 0x0
; GFX12-WGP-NEXT:    s_load_b32 s0, s[4:5], 0x8
; GFX12-WGP-NEXT:    s_wait_kmcnt 0x0
; GFX12-WGP-NEXT:    s_load_b32 s1, s[2:3], 0x0
; GFX12-WGP-NEXT:    s_mov_b32 s2, 0x3ff
; GFX12-WGP-NEXT:    s_wait_alu 0xfffe
; GFX12-WGP-NEXT:    v_and_b32_e64 v0, v0, s2
; GFX12-WGP-NEXT:    s_mov_b32 s2, 2
; GFX12-WGP-NEXT:    s_wait_alu 0xfffe
; GFX12-WGP-NEXT:    v_lshlrev_b32_e64 v1, s2, v0
; GFX12-WGP-NEXT:    s_wait_kmcnt 0x0
; GFX12-WGP-NEXT:    v_mov_b32_e32 v0, s1
; GFX12-WGP-NEXT:    s_wait_loadcnt 0x0
; GFX12-WGP-NEXT:    s_wait_samplecnt 0x0
; GFX12-WGP-NEXT:    s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT:    s_wait_kmcnt 0x0
; GFX12-WGP-NEXT:    s_wait_storecnt 0x0
; GFX12-WGP-NEXT:    scratch_store_b32 v1, v0, s0 scope:SCOPE_SYS
; GFX12-WGP-NEXT:    s_wait_storecnt 0x0
; GFX12-WGP-NEXT:    s_endpgm
;
; GFX12-CU-LABEL: private_volatile_store_1:
; GFX12-CU:       ; %bb.0: ; %entry
; GFX12-CU-NEXT:    s_load_b64 s[2:3], s[4:5], 0x0
; GFX12-CU-NEXT:    s_load_b32 s0, s[4:5], 0x8
; GFX12-CU-NEXT:    s_wait_kmcnt 0x0
; GFX12-CU-NEXT:    s_load_b32 s1, s[2:3], 0x0
; GFX12-CU-NEXT:    s_mov_b32 s2, 0x3ff
; GFX12-CU-NEXT:    s_wait_alu 0xfffe
; GFX12-CU-NEXT:    v_and_b32_e64 v0, v0, s2
; GFX12-CU-NEXT:    s_mov_b32 s2, 2
; GFX12-CU-NEXT:    s_wait_alu 0xfffe
; GFX12-CU-NEXT:    v_lshlrev_b32_e64 v1, s2, v0
; GFX12-CU-NEXT:    s_wait_kmcnt 0x0
; GFX12-CU-NEXT:    v_mov_b32_e32 v0, s1
; GFX12-CU-NEXT:    s_wait_loadcnt 0x0
; GFX12-CU-NEXT:    s_wait_samplecnt 0x0
; GFX12-CU-NEXT:    s_wait_bvhcnt 0x0
; GFX12-CU-NEXT:    s_wait_kmcnt 0x0
; GFX12-CU-NEXT:    s_wait_storecnt 0x0
; GFX12-CU-NEXT:    scratch_store_b32 v1, v0, s0 scope:SCOPE_SYS
; GFX12-CU-NEXT:    s_wait_storecnt 0x0
; GFX12-CU-NEXT:    s_endpgm
    ptr addrspace(1) %in, ptr addrspace(5) %out) {
entry:
  %tid = call i32 @llvm.amdgcn.workitem.id.x()
  %val = load i32, ptr addrspace(1) %in, align 4
  %out.gep = getelementptr inbounds i32, ptr addrspace(5) %out, i32 %tid
  store volatile i32 %val, ptr addrspace(5) %out.gep
  ret void
}

declare i32 @llvm.amdgcn.workitem.id.x()