llvm/test/CodeGen/AMDGPU/fold-gep-offset.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py

; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -mattr=-enable-flat-scratch < %s | FileCheck --check-prefixes=GFX90A,GFX90A-MUBUF %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -mattr=+enable-flat-scratch < %s | FileCheck --check-prefixes=GFX90A,GFX90A-FLATSCR %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1030 -mattr=-enable-flat-scratch < %s | FileCheck --check-prefixes=GFX10,GFX10-MUBUF %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1030 -mattr=+enable-flat-scratch < %s | FileCheck --check-prefixes=GFX10,GFX10-FLATSCR %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck --check-prefixes=GFX942 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck --check-prefixes=GFX11 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX12 %s

; This test checks memory addresses with constant offset components that should
; not be folded into memory accesses with immediate offsets.
; SeparateConstOffsetsFromGEP transforms the GEPs in a way that can lead to
; out-of-bounds or negative intermediate results in the address computation,
; which are problematic for flat and scratch instructions:
;     gep[inbounds](p, i + 3) -> gep(gep(p, i), 3)


; FIXME the offset here should not be folded: if %p points to the beginning of
; scratch or LDS and %i is -1, a folded offset crashes the program.
define i32 @flat_offset_maybe_oob(ptr %p, i32 %i) {
; GFX90A-LABEL: flat_offset_maybe_oob:
; GFX90A:       ; %bb.0:
; GFX90A-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX90A-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
; GFX90A-NEXT:    v_lshlrev_b64 v[2:3], 2, v[2:3]
; GFX90A-NEXT:    v_add_co_u32_e32 v0, vcc, v0, v2
; GFX90A-NEXT:    v_addc_co_u32_e32 v1, vcc, v1, v3, vcc
; GFX90A-NEXT:    flat_load_dword v0, v[0:1] offset:12
; GFX90A-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX90A-NEXT:    s_setpc_b64 s[30:31]
;
; GFX10-LABEL: flat_offset_maybe_oob:
; GFX10:       ; %bb.0:
; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
; GFX10-NEXT:    v_lshlrev_b64 v[2:3], 2, v[2:3]
; GFX10-NEXT:    v_add_co_u32 v0, vcc_lo, v0, v2
; GFX10-NEXT:    v_add_co_ci_u32_e32 v1, vcc_lo, v1, v3, vcc_lo
; GFX10-NEXT:    flat_load_dword v0, v[0:1] offset:12
; GFX10-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX10-NEXT:    s_setpc_b64 s[30:31]
;
; GFX942-LABEL: flat_offset_maybe_oob:
; GFX942:       ; %bb.0:
; GFX942-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX942-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
; GFX942-NEXT:    v_lshl_add_u64 v[0:1], v[2:3], 2, v[0:1]
; GFX942-NEXT:    flat_load_dword v0, v[0:1] offset:12
; GFX942-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX942-NEXT:    s_setpc_b64 s[30:31]
;
; GFX11-LABEL: flat_offset_maybe_oob:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX11-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
; GFX11-NEXT:    v_lshlrev_b64 v[2:3], 2, v[2:3]
; GFX11-NEXT:    v_add_co_u32 v0, vcc_lo, v0, v2
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2)
; GFX11-NEXT:    v_add_co_ci_u32_e32 v1, vcc_lo, v1, v3, vcc_lo
; GFX11-NEXT:    flat_load_b32 v0, v[0:1] offset:12
; GFX11-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX11-NEXT:    s_setpc_b64 s[30:31]
;
; GFX12-LABEL: flat_offset_maybe_oob:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT:    s_wait_expcnt 0x0
; GFX12-NEXT:    s_wait_samplecnt 0x0
; GFX12-NEXT:    s_wait_bvhcnt 0x0
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
; GFX12-NEXT:    v_lshlrev_b64_e32 v[2:3], 2, v[2:3]
; GFX12-NEXT:    v_add_co_u32 v0, vcc_lo, v0, v2
; GFX12-NEXT:    s_wait_alu 0xfffd
; GFX12-NEXT:    v_add_co_ci_u32_e32 v1, vcc_lo, v1, v3, vcc_lo
; GFX12-NEXT:    flat_load_b32 v0, v[0:1] offset:12
; GFX12-NEXT:    s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT:    s_wait_alu 0xfffd
; GFX12-NEXT:    s_setpc_b64 s[30:31]
  %idx = add nsw i32 %i, 3
  %arrayidx = getelementptr inbounds i32, ptr %p, i32 %idx
  %l = load i32, ptr %arrayidx
  ret i32 %l
}

; For MUBUF and for GFX12, folding the offset is okay.
define i32 @private_offset_maybe_oob(ptr addrspace(5) %p, i32 %i) {
; GFX90A-MUBUF-LABEL: private_offset_maybe_oob:
; GFX90A-MUBUF:       ; %bb.0:
; GFX90A-MUBUF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX90A-MUBUF-NEXT:    v_lshl_add_u32 v0, v1, 2, v0
; GFX90A-MUBUF-NEXT:    buffer_load_dword v0, v0, s[0:3], 0 offen offset:12
; GFX90A-MUBUF-NEXT:    s_waitcnt vmcnt(0)
; GFX90A-MUBUF-NEXT:    s_setpc_b64 s[30:31]
;
; GFX90A-FLATSCR-LABEL: private_offset_maybe_oob:
; GFX90A-FLATSCR:       ; %bb.0:
; GFX90A-FLATSCR-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX90A-FLATSCR-NEXT:    v_lshlrev_b32_e32 v1, 2, v1
; GFX90A-FLATSCR-NEXT:    v_add3_u32 v0, v0, v1, 12
; GFX90A-FLATSCR-NEXT:    scratch_load_dword v0, v0, off
; GFX90A-FLATSCR-NEXT:    s_waitcnt vmcnt(0)
; GFX90A-FLATSCR-NEXT:    s_setpc_b64 s[30:31]
;
; GFX10-MUBUF-LABEL: private_offset_maybe_oob:
; GFX10-MUBUF:       ; %bb.0:
; GFX10-MUBUF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-MUBUF-NEXT:    v_lshl_add_u32 v0, v1, 2, v0
; GFX10-MUBUF-NEXT:    buffer_load_dword v0, v0, s[0:3], 0 offen offset:12
; GFX10-MUBUF-NEXT:    s_waitcnt vmcnt(0)
; GFX10-MUBUF-NEXT:    s_setpc_b64 s[30:31]
;
; GFX10-FLATSCR-LABEL: private_offset_maybe_oob:
; GFX10-FLATSCR:       ; %bb.0:
; GFX10-FLATSCR-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-FLATSCR-NEXT:    v_lshlrev_b32_e32 v1, 2, v1
; GFX10-FLATSCR-NEXT:    v_add3_u32 v0, v0, v1, 12
; GFX10-FLATSCR-NEXT:    scratch_load_dword v0, v0, off
; GFX10-FLATSCR-NEXT:    s_waitcnt vmcnt(0)
; GFX10-FLATSCR-NEXT:    s_setpc_b64 s[30:31]
;
; GFX942-LABEL: private_offset_maybe_oob:
; GFX942:       ; %bb.0:
; GFX942-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX942-NEXT:    v_lshlrev_b32_e32 v1, 2, v1
; GFX942-NEXT:    v_add3_u32 v0, v0, v1, 12
; GFX942-NEXT:    scratch_load_dword v0, v0, off
; GFX942-NEXT:    s_waitcnt vmcnt(0)
; GFX942-NEXT:    s_setpc_b64 s[30:31]
;
; GFX11-LABEL: private_offset_maybe_oob:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX11-NEXT:    v_lshlrev_b32_e32 v1, 2, v1
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GFX11-NEXT:    v_add3_u32 v0, v0, v1, 12
; GFX11-NEXT:    scratch_load_b32 v0, v0, off
; GFX11-NEXT:    s_waitcnt vmcnt(0)
; GFX11-NEXT:    s_setpc_b64 s[30:31]
;
; GFX12-LABEL: private_offset_maybe_oob:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_wait_loadcnt_dscnt 0x0
; GFX12-NEXT:    s_wait_expcnt 0x0
; GFX12-NEXT:    s_wait_samplecnt 0x0
; GFX12-NEXT:    s_wait_bvhcnt 0x0
; GFX12-NEXT:    s_wait_kmcnt 0x0
; GFX12-NEXT:    v_lshl_add_u32 v0, v1, 2, v0
; GFX12-NEXT:    scratch_load_b32 v0, v0, off offset:12
; GFX12-NEXT:    s_wait_loadcnt 0x0
; GFX12-NEXT:    s_setpc_b64 s[30:31]
  %idx = add nsw i32 %i, 3
  %arrayidx = getelementptr inbounds i32, ptr addrspace(5) %p, i32 %idx
  %l = load i32, ptr addrspace(5) %arrayidx
  ret i32 %l
}