; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-amd-amdpal -mattr=-real-true16 -mcpu=gfx1100 -o - %s | FileCheck -check-prefixes=GCN,GFX11 %s
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-amd-amdpal -mattr=-real-true16 -mcpu=gfx1200 -o - %s | FileCheck -check-prefixes=GCN,GFX12 %s

define amdgpu_ps void @v_fabs_f16(half %in, ptr addrspace(1) %out) {
; GCN-LABEL: v_fabs_f16:
; GCN:       ; %bb.0:
; GCN-NEXT:    v_and_b32_e32 v0, 0x7fff, v0
; GCN-NEXT:    global_store_b16 v[1:2], v0, off
; GCN-NEXT:    s_endpgm
  %fabs = call half @llvm.fabs.f16(half %in)
  store half %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_f16(half inreg %in, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_f16:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_and_b32_e64 v2, 0x7fff, s0
; GFX11-NEXT:    global_store_b16 v[0:1], v2, off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_f16:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_and_b32 s0, s0, 0x7fff
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
; GFX12-NEXT:    v_mov_b32_e32 v2, s0
; GFX12-NEXT:    global_store_b16 v[0:1], v2, off
; GFX12-NEXT:    s_endpgm
  %fabs = call half @llvm.fabs.f16(half %in)
  store half %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_f16_salu_use(half inreg %in, i32 inreg %val, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_f16_salu_use:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_and_b32_e64 v2, 0x7fff, s0
; GFX11-NEXT:    s_cmp_eq_u32 s1, 0
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(SALU_CYCLE_1)
; GFX11-NEXT:    v_readfirstlane_b32 s0, v2
; GFX11-NEXT:    s_cselect_b32 s0, s0, 0
; GFX11-NEXT:    v_mov_b32_e32 v2, s0
; GFX11-NEXT:    global_store_b16 v[0:1], v2, off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_f16_salu_use:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_and_b32 s0, s0, 0x7fff
; GFX12-NEXT:    s_cmp_eq_u32 s1, 0
; GFX12-NEXT:    s_cselect_b32 s0, s0, 0
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
; GFX12-NEXT:    v_mov_b32_e32 v2, s0
; GFX12-NEXT:    global_store_b16 v[0:1], v2, off
; GFX12-NEXT:    s_endpgm
  %fabs = call half @llvm.fabs.f16(half %in)
  %cond = icmp eq i32 %val, 0
  %sel = select i1 %cond, half %fabs, half 0.0
  store half %sel, ptr addrspace(1) %out
  ret void
}

define amdgpu_ps void @v_fabs_f32(float %in, ptr addrspace(1) %out) {
; GCN-LABEL: v_fabs_f32:
; GCN:       ; %bb.0:
; GCN-NEXT:    v_and_b32_e32 v0, 0x7fffffff, v0
; GCN-NEXT:    global_store_b32 v[1:2], v0, off
; GCN-NEXT:    s_endpgm
  %fabs = call float @llvm.fabs.f32(float %in)
  store float %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_f32(float inreg %in, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_f32:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_and_b32_e64 v2, 0x7fffffff, s0
; GFX11-NEXT:    global_store_b32 v[0:1], v2, off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_f32:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_bitset0_b32 s0, 31
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
; GFX12-NEXT:    v_mov_b32_e32 v2, s0
; GFX12-NEXT:    global_store_b32 v[0:1], v2, off
; GFX12-NEXT:    s_endpgm
  %fabs = call float @llvm.fabs.f32(float %in)
  store float %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_f32_salu_use(float inreg %in, i32 inreg %val, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_f32_salu_use:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_and_b32_e64 v2, 0x7fffffff, s0
; GFX11-NEXT:    s_cmp_eq_u32 s1, 0
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(SALU_CYCLE_1)
; GFX11-NEXT:    v_readfirstlane_b32 s0, v2
; GFX11-NEXT:    s_cselect_b32 s0, s0, 0
; GFX11-NEXT:    v_mov_b32_e32 v2, s0
; GFX11-NEXT:    global_store_b32 v[0:1], v2, off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_f32_salu_use:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_bitset0_b32 s0, 31
; GFX12-NEXT:    s_cmp_eq_u32 s1, 0
; GFX12-NEXT:    s_cselect_b32 s0, s0, 0
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
; GFX12-NEXT:    v_mov_b32_e32 v2, s0
; GFX12-NEXT:    global_store_b32 v[0:1], v2, off
; GFX12-NEXT:    s_endpgm
  %fabs = call float @llvm.fabs.f32(float %in)
  %cond = icmp eq i32 %val, 0
  %sel = select i1 %cond, float %fabs, float 0.0
  store float %sel, ptr addrspace(1) %out
  ret void
}

define amdgpu_ps void @v_fabs_f64(double %in, ptr addrspace(1) %out) {
; GCN-LABEL: v_fabs_f64:
; GCN:       ; %bb.0:
; GCN-NEXT:    v_and_b32_e32 v1, 0x7fffffff, v1
; GCN-NEXT:    global_store_b64 v[2:3], v[0:1], off
; GCN-NEXT:    s_endpgm
  %fabs = call double @llvm.fabs.f64(double %in)
  store double %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_f64(double inreg %in, ptr addrspace(1) %out) {
; GCN-LABEL: s_fabs_f64:
; GCN:       ; %bb.0:
; GCN-NEXT:    v_dual_mov_b32 v3, s1 :: v_dual_mov_b32 v2, s0
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT:    v_and_b32_e32 v3, 0x7fffffff, v3
; GCN-NEXT:    global_store_b64 v[0:1], v[2:3], off
; GCN-NEXT:    s_endpgm
  %fabs = call double @llvm.fabs.f64(double %in)
  store double %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_f64_salu_use(double inreg %in, i32 inreg %val, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_f64_salu_use:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_dual_mov_b32 v3, s1 :: v_dual_mov_b32 v2, s0
; GFX11-NEXT:    s_cmp_eq_u32 s2, 0
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_2)
; GFX11-NEXT:    v_and_b32_e32 v3, 0x7fffffff, v3
; GFX11-NEXT:    v_readfirstlane_b32 s0, v2
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(SALU_CYCLE_1)
; GFX11-NEXT:    v_readfirstlane_b32 s1, v3
; GFX11-NEXT:    s_cselect_b64 s[0:1], s[0:1], 0
; GFX11-NEXT:    v_dual_mov_b32 v3, s1 :: v_dual_mov_b32 v2, s0
; GFX11-NEXT:    global_store_b64 v[0:1], v[2:3], off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_f64_salu_use:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    v_dual_mov_b32 v3, s1 :: v_dual_mov_b32 v2, s0
; GFX12-NEXT:    s_cmp_eq_u32 s2, 0
; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_2)
; GFX12-NEXT:    v_and_b32_e32 v3, 0x7fffffff, v3
; GFX12-NEXT:    v_readfirstlane_b32 s0, v2
; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_2)
; GFX12-NEXT:    v_readfirstlane_b32 s1, v3
; GFX12-NEXT:    s_cselect_b64 s[0:1], s[0:1], 0
; GFX12-NEXT:    s_wait_alu depctr_sa_sdst(0)
; GFX12-NEXT:    v_dual_mov_b32 v3, s1 :: v_dual_mov_b32 v2, s0
; GFX12-NEXT:    global_store_b64 v[0:1], v[2:3], off
; GFX12-NEXT:    s_endpgm
  %fabs = call double @llvm.fabs.f64(double %in)
  %cond = icmp eq i32 %val, 0
  %sel = select i1 %cond, double %fabs, double 0.0
  store double %sel, ptr addrspace(1) %out
  ret void
}

define amdgpu_ps void @v_fabs_v2f16(<2 x half> %in, ptr addrspace(1) %out) {
; GCN-LABEL: v_fabs_v2f16:
; GCN:       ; %bb.0:
; GCN-NEXT:    v_and_b32_e32 v0, 0x7fff7fff, v0
; GCN-NEXT:    global_store_b32 v[1:2], v0, off
; GCN-NEXT:    s_endpgm
  %fabs = call <2 x half> @llvm.fabs.v2f16(<2 x half> %in)
  store <2 x half> %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_v2f16(<2 x half> inreg %in, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_v2f16:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_and_b32_e64 v2, 0x7fff7fff, s0
; GFX11-NEXT:    global_store_b32 v[0:1], v2, off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_v2f16:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_lshr_b32 s1, s0, 16
; GFX12-NEXT:    s_and_b32 s0, s0, 0x7fff
; GFX12-NEXT:    s_and_b32 s1, s1, 0x7fff
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; GFX12-NEXT:    s_pack_ll_b32_b16 s0, s0, s1
; GFX12-NEXT:    v_mov_b32_e32 v2, s0
; GFX12-NEXT:    global_store_b32 v[0:1], v2, off
; GFX12-NEXT:    s_endpgm
  %fabs = call <2 x half> @llvm.fabs.v2f16(<2 x half> %in)
  store <2 x half> %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_v2f16_salu_use(<2 x half> inreg %in, i32 inreg %val, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_v2f16_salu_use:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_and_b32_e64 v2, 0x7fff7fff, s0
; GFX11-NEXT:    s_cmp_eq_u32 s1, 0
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(SALU_CYCLE_1)
; GFX11-NEXT:    v_readfirstlane_b32 s0, v2
; GFX11-NEXT:    s_cselect_b32 s0, s0, 0
; GFX11-NEXT:    v_mov_b32_e32 v2, s0
; GFX11-NEXT:    global_store_b32 v[0:1], v2, off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_v2f16_salu_use:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_lshr_b32 s2, s0, 16
; GFX12-NEXT:    s_and_b32 s0, s0, 0x7fff
; GFX12-NEXT:    s_and_b32 s2, s2, 0x7fff
; GFX12-NEXT:    s_cmp_eq_u32 s1, 0
; GFX12-NEXT:    s_pack_ll_b32_b16 s0, s0, s2
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; GFX12-NEXT:    s_cselect_b32 s0, s0, 0
; GFX12-NEXT:    v_mov_b32_e32 v2, s0
; GFX12-NEXT:    global_store_b32 v[0:1], v2, off
; GFX12-NEXT:    s_endpgm
  %fabs = call <2 x half> @llvm.fabs.v2f16(<2 x half> %in)
  %cond = icmp eq i32 %val, 0
  %sel = select i1 %cond, <2 x half> %fabs, <2 x half> <half 0.0, half 0.0>
  store <2 x half> %sel, ptr addrspace(1) %out
  ret void
}

define amdgpu_ps void @v_fabs_v2f32(<2 x float> %in, ptr addrspace(1) %out) {
; GCN-LABEL: v_fabs_v2f32:
; GCN:       ; %bb.0:
; GCN-NEXT:    v_and_b32_e32 v0, 0x7fffffff, v0
; GCN-NEXT:    v_and_b32_e32 v1, 0x7fffffff, v1
; GCN-NEXT:    global_store_b64 v[2:3], v[0:1], off
; GCN-NEXT:    s_endpgm
  %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in)
  store <2 x float> %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_v2f32(<2 x float> inreg %in, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_v2f32:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_and_b32_e64 v2, 0x7fffffff, s0
; GFX11-NEXT:    v_and_b32_e64 v3, 0x7fffffff, s1
; GFX11-NEXT:    global_store_b64 v[0:1], v[2:3], off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_v2f32:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_bitset0_b32 s0, 31
; GFX12-NEXT:    s_bitset0_b32 s1, 31
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
; GFX12-NEXT:    v_dual_mov_b32 v3, s1 :: v_dual_mov_b32 v2, s0
; GFX12-NEXT:    global_store_b64 v[0:1], v[2:3], off
; GFX12-NEXT:    s_endpgm
  %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in)
  store <2 x float> %fabs, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_v2f32_salu_use(<2 x float> inreg %in, i32 inreg %val, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_v2f32_salu_use:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_and_b32_e64 v2, 0x7fffffff, s0
; GFX11-NEXT:    v_and_b32_e64 v3, 0x7fffffff, s1
; GFX11-NEXT:    s_cmp_eq_u32 s2, 0
; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
; GFX11-NEXT:    v_readfirstlane_b32 s0, v2
; GFX11-NEXT:    v_readfirstlane_b32 s1, v3
; GFX11-NEXT:    s_cselect_b64 s[0:1], s[0:1], 0
; GFX11-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
; GFX11-NEXT:    v_dual_mov_b32 v3, s1 :: v_dual_mov_b32 v2, s0
; GFX11-NEXT:    global_store_b64 v[0:1], v[2:3], off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_v2f32_salu_use:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_bitset0_b32 s0, 31
; GFX12-NEXT:    s_bitset0_b32 s1, 31
; GFX12-NEXT:    s_cmp_eq_u32 s2, 0
; GFX12-NEXT:    s_cselect_b64 s[0:1], s[0:1], 0
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
; GFX12-NEXT:    v_dual_mov_b32 v3, s1 :: v_dual_mov_b32 v2, s0
; GFX12-NEXT:    global_store_b64 v[0:1], v[2:3], off
; GFX12-NEXT:    s_endpgm
  %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in)
  %cond = icmp eq i32 %val, 0
  %sel = select i1 %cond, <2 x float> %fabs, <2 x float> <float 0.0, float 0.0>
  store <2 x float> %sel, ptr addrspace(1) %out
  ret void
}

define amdgpu_ps void @v_fabs_fneg_f32(float %in, ptr addrspace(1) %out) {
; GCN-LABEL: v_fabs_fneg_f32:
; GCN:       ; %bb.0:
; GCN-NEXT:    v_or_b32_e32 v0, 0x80000000, v0
; GCN-NEXT:    global_store_b32 v[1:2], v0, off
; GCN-NEXT:    s_endpgm
  %fabs = call float @llvm.fabs.f32(float %in)
  %fneg = fneg float %fabs
  store float %fneg, ptr addrspace(1) %out
  ret void
}
define amdgpu_ps void @s_fabs_fneg_f32(float inreg %in, ptr addrspace(1) %out) {
; GFX11-LABEL: s_fabs_fneg_f32:
; GFX11:       ; %bb.0:
; GFX11-NEXT:    v_or_b32_e64 v2, 0x80000000, s0
; GFX11-NEXT:    global_store_b32 v[0:1], v2, off
; GFX11-NEXT:    s_endpgm
;
; GFX12-LABEL: s_fabs_fneg_f32:
; GFX12:       ; %bb.0:
; GFX12-NEXT:    s_bitset1_b32 s0, 31
; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
; GFX12-NEXT:    v_mov_b32_e32 v2, s0
; GFX12-NEXT:    global_store_b32 v[0:1], v2, off
; GFX12-NEXT:    s_endpgm
  %fabs = call float @llvm.fabs.f32(float %in)
  %fneg = fneg float %fabs
  store float %fneg, ptr addrspace(1) %out
  ret void
}

declare half @llvm.fabs.f16(half)
declare float @llvm.fabs.f32(float)
declare double @llvm.fabs.f64(double)
declare <2 x half> @llvm.fabs.v2f16(<2 x half>)
declare <2 x float> @llvm.fabs.v2f32(<2 x float>)