llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-lastuse-metadata.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgpu12.00-amd-amdhsa < %s | FileCheck --check-prefix=GFX12 %s
; RUN: llc -mtriple=amdgpu12.00-amd-amdhsa -mattr=+cumode < %s | FileCheck --check-prefix=GFX12 %s


define amdgpu_kernel void @buffer_last_use_load_0(ptr addrspace(7) %in, ptr addrspace(7) %out) {
; GFX12-LABEL: buffer_last_use_load_0:
; GFX12:       ; %bb.0: ; %entry
; GFX12-NEXT:    s_clause 0x1
; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x0
; GFX12-NEXT:    s_load_b32 s11, s[4:5], 0x10
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_mov_b32_e32 v0, s0
; GFX12-NEXT:    s_mov_b32 s8, s1
; GFX12-NEXT:    s_mov_b32 s9, s2
; GFX12-NEXT:    s_mov_b32 s10, s3
; GFX12-NEXT:    s_clause 0x1
; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x20
; GFX12-NEXT:    s_load_b32 s7, s[4:5], 0x30
; GFX12-NEXT:    buffer_load_b32 v0, v0, s[8:11], null offen th:TH_LOAD_LU
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_mov_b32_e32 v1, s0
; GFX12-NEXT:    s_mov_b32 s4, s1
; GFX12-NEXT:    s_mov_b32 s5, s2
; GFX12-NEXT:    s_mov_b32 s6, s3
; GFX12-NEXT:    s_wait_loadcnt 0x0
; GFX12-NEXT:    buffer_store_b32 v0, v1, s[4:7], null offen
; GFX12-NEXT:    s_endpgm
entry:
  %val = load i32, ptr addrspace(7) %in, !amdgpu.last.use !{}
  store i32 %val, ptr addrspace(7) %out
  ret void
}

define amdgpu_kernel void @buffer_last_use_load_1(ptr addrspace(7) %in, ptr addrspace(7) %out) {
; GFX12-LABEL: buffer_last_use_load_1:
; GFX12:       ; %bb.0: ; %entry
; GFX12-NEXT:    s_clause 0x1
; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x0
; GFX12-NEXT:    s_load_b32 s11, s[4:5], 0x10
; GFX12-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GFX12-NEXT:    v_lshl_add_u32 v0, v0, 2, s0
; GFX12-NEXT:    s_mov_b32 s8, s1
; GFX12-NEXT:    s_mov_b32 s9, s2
; GFX12-NEXT:    s_mov_b32 s10, s3
; GFX12-NEXT:    s_clause 0x1
; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x20
; GFX12-NEXT:    s_load_b32 s7, s[4:5], 0x30
; GFX12-NEXT:    buffer_load_b32 v0, v0, s[8:11], null offen th:TH_LOAD_LU
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_mov_b32_e32 v1, s0
; GFX12-NEXT:    s_mov_b32 s4, s1
; GFX12-NEXT:    s_mov_b32 s5, s2
; GFX12-NEXT:    s_mov_b32 s6, s3
; GFX12-NEXT:    s_wait_loadcnt 0x0
; GFX12-NEXT:    buffer_store_b32 v0, v1, s[4:7], null offen
; GFX12-NEXT:    s_endpgm
entry:
  %tid = call i32 @llvm.amdgcn.workitem.id.x()
  %val.gep = getelementptr inbounds i32, ptr addrspace(7) %in, i32 %tid
  %val = load i32, ptr addrspace(7) %val.gep, align 4, !amdgpu.last.use !{}
  store i32 %val, ptr addrspace(7) %out
  ret void
}

define amdgpu_kernel void @buffer_last_use_and_volatile_load(ptr addrspace(7) %in, ptr addrspace(7) %out) {
; GFX12-LABEL: buffer_last_use_and_volatile_load:
; GFX12:       ; %bb.0: ; %entry
; GFX12-NEXT:    s_clause 0x1
; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x0
; GFX12-NEXT:    s_load_b32 s11, s[4:5], 0x10
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_mov_b32_e32 v0, s0
; GFX12-NEXT:    s_mov_b32 s8, s1
; GFX12-NEXT:    s_mov_b32 s9, s2
; GFX12-NEXT:    s_mov_b32 s10, s3
; GFX12-NEXT:    s_clause 0x1
; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x20
; GFX12-NEXT:    s_load_b32 s7, s[4:5], 0x30
; GFX12-NEXT:    buffer_load_b32 v0, v0, s[8:11], null offen th:TH_LOAD_BYPASS scope:SCOPE_SYS
; GFX12-NEXT:    s_wait_loadcnt 0x0
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_mov_b32_e32 v1, s0
; GFX12-NEXT:    s_mov_b32 s4, s1
; GFX12-NEXT:    s_mov_b32 s5, s2
; GFX12-NEXT:    s_mov_b32 s6, s3
; GFX12-NEXT:    buffer_store_b32 v0, v1, s[4:7], null offen
; GFX12-NEXT:    s_endpgm
entry:
  %val = load volatile i32, ptr addrspace(7) %in, !amdgpu.last.use !{}
  store i32 %val, ptr addrspace(7) %out
  ret void
}

define amdgpu_kernel void @buffer_last_use_and_nontemporal_load(ptr addrspace(7) %in, ptr addrspace(7) %out) {
; GFX12-LABEL: buffer_last_use_and_nontemporal_load:
; GFX12:       ; %bb.0: ; %entry
; GFX12-NEXT:    s_clause 0x1
; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x0
; GFX12-NEXT:    s_load_b32 s11, s[4:5], 0x10
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_mov_b32_e32 v0, s0
; GFX12-NEXT:    s_mov_b32 s8, s1
; GFX12-NEXT:    s_mov_b32 s9, s2
; GFX12-NEXT:    s_mov_b32 s10, s3
; GFX12-NEXT:    s_clause 0x1
; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x20
; GFX12-NEXT:    s_load_b32 s7, s[4:5], 0x30
; GFX12-NEXT:    buffer_load_b32 v0, v0, s[8:11], null offen th:TH_LOAD_LU
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_mov_b32_e32 v1, s0
; GFX12-NEXT:    s_mov_b32 s4, s1
; GFX12-NEXT:    s_mov_b32 s5, s2
; GFX12-NEXT:    s_mov_b32 s6, s3
; GFX12-NEXT:    s_wait_loadcnt 0x0
; GFX12-NEXT:    buffer_store_b32 v0, v1, s[4:7], null offen
; GFX12-NEXT:    s_endpgm
entry:
  %val = load i32, ptr addrspace(7) %in, !amdgpu.last.use !{}, !nontemporal !0
  store i32 %val, ptr addrspace(7) %out
  ret void
}

!0 = !{i32 1}
declare i32 @llvm.amdgcn.workitem.id.x()