; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1250 < %s | FileCheck -check-prefixes=GCN,SDAG %s
; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1250 < %s | FileCheck -check-prefixes=GCN,GISEL %s

define amdgpu_ps float @add_max_u32_vvv(i32 %a, i32 %b, i32 %c) {
; GCN-LABEL: add_max_u32_vvv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_max_u32 v0, v0, v1, v2
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_u32_svv(i32 inreg %a, i32 %b, i32 %c) {
; GCN-LABEL: add_max_u32_svv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_max_u32 v0, s0, v0, v1
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_u32_ssv(i32 inreg %a, i32 inreg %b, i32 %c) {
; GCN-LABEL: add_max_u32_ssv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_max_u32 v0, s0, s1, v0
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_u32_sss(i32 inreg %a, i32 inreg %b, i32 inreg %c) {
; SDAG-LABEL: add_max_u32_sss:
; SDAG:       ; %bb.0:
; SDAG-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; SDAG-NEXT:    v_add_nc_u32_e64 v0, s0, s1 clamp
; SDAG-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; SDAG-NEXT:    v_max_u32_e32 v0, s2, v0
; SDAG-NEXT:    ; return to shader part epilog
;
; GISEL-LABEL: add_max_u32_sss:
; GISEL:       ; %bb.0:
; GISEL-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GISEL-NEXT:    v_mov_b32_e32 v0, s2
; GISEL-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GISEL-NEXT:    v_add_max_u32 v0, s0, s1, v0
; GISEL-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_u32_vsi(i32 %a, i32 inreg %b) {
; GCN-LABEL: add_max_u32_vsi:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_max_u32 v0, v0, s0, 4
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.umax.i32(i32 %add, i32 4)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_u32_svl(i32 inreg %a, i32 %b) {
; GCN-LABEL: add_max_u32_svl:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_max_u32 v0, s0, v0, 0x64
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.umax.i32(i32 %add, i32 100)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_u32_slv(i32 inreg %a, i32 %b, i32 %c) {
; GCN-LABEL: add_max_u32_slv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_max_u32 v0, s0, v0, v1
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_i32_vvv(i32 %a, i32 %b, i32 %c) {
; GCN-LABEL: add_max_i32_vvv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_max_i32 v0, v0, v1, v2
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.sadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.smax.i32(i32 %add, i32 %c)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_min_u32_vvv(i32 %a, i32 %b, i32 %c) {
; GCN-LABEL: add_min_u32_vvv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_min_u32 v0, v0, v1, v2
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.umin.i32(i32 %add, i32 %c)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_min_i32_vvv(i32 %a, i32 %b, i32 %c) {
; GCN-LABEL: add_min_i32_vvv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_add_min_i32 v0, v0, v1, v2
; GCN-NEXT:    ; return to shader part epilog
  %add = call i32 @llvm.sadd.sat.i32(i32 %a, i32 %b)
  %max = call i32 @llvm.smin.i32(i32 %add, i32 %c)
  %ret = bitcast i32 %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_v2u16_vvv(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_max_v2u16_vvv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_max_u16 v0, v0, v1, v2
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.uadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %c)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_v2u16_svv(<2 x i16> inreg %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_max_v2u16_svv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_max_u16 v0, s0, v0, v1
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.uadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %c)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_v2u16_ssv(<2 x i16> inreg %a, <2 x i16> inreg %b, <2 x i16> %c) {
; GCN-LABEL: add_max_v2u16_ssv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_max_u16 v0, s0, s1, v0
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.uadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %c)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_v2u16_sss(<2 x i16> inreg %a, <2 x i16> inreg %b, <2 x i16> inreg %c) {
; SDAG-LABEL: add_max_v2u16_sss:
; SDAG:       ; %bb.0:
; SDAG-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; SDAG-NEXT:    v_pk_add_u16 v0, s0, s1 clamp
; SDAG-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; SDAG-NEXT:    v_pk_max_u16 v0, v0, s2
; SDAG-NEXT:    ; return to shader part epilog
;
; GISEL-LABEL: add_max_v2u16_sss:
; GISEL:       ; %bb.0:
; GISEL-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GISEL-NEXT:    v_mov_b32_e32 v0, s2
; GISEL-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GISEL-NEXT:    v_pk_add_max_u16 v0, s0, s1, v0
; GISEL-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.uadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %c)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_v2u16_vsi(<2 x i16> %a, <2 x i16> inreg %b) {
; GCN-LABEL: add_max_v2u16_vsi:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_max_u16 v0, v0, s0, 4
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.uadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> <i16 4, i16 0>)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_v2u16_svl(<2 x i16> inreg %a, <2 x i16> %b) {
; GCN-LABEL: add_max_v2u16_svl:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_max_u16 v0, s0, v0, 0x650064
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.uadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> <i16 100, i16 101>)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_v2u16_slv(<2 x i16> inreg %a, <2 x i16> %b) {
; GCN-LABEL: add_max_v2u16_slv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_max_u16 v0, 0x640064, s0, v0
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.uadd.sat.i32(<2 x i16> %a, <2 x i16> <i16 100, i16 100>)
  %max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %b)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_max_v2s16_vvv(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_max_v2s16_vvv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_max_i16 v0, v0, v1, v2
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.sadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.smax.v216(<2 x i16> %add, <2 x i16> %c)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_min_v2u16_vvv(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_min_v2u16_vvv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_min_u16 v0, v0, v1, v2
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.uadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.umin.v216(<2 x i16> %add, <2 x i16> %c)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

define amdgpu_ps float @add_min_v2s16_vvv(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_min_v2s16_vvv:
; GCN:       ; %bb.0:
; GCN-NEXT:    s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; GCN-NEXT:    v_pk_add_min_i16 v0, v0, v1, v2
; GCN-NEXT:    ; return to shader part epilog
  %add = call <2 x i16> @llvm.sadd.sat.i32(<2 x i16> %a, <2 x i16> %b)
  %max = call <2 x i16> @llvm.smin.v216(<2 x i16> %add, <2 x i16> %c)
  %ret = bitcast <2 x i16> %max to float
  ret float %ret
}

declare <2 x i16> @llvm.smin.v216(<2 x i16>, <2 x i16>)
declare <2 x i16> @llvm.smax.v216(<2 x i16>, <2 x i16>)
declare <2 x i16> @llvm.umin.v216(<2 x i16>, <2 x i16>)
declare <2 x i16> @llvm.umax.v216(<2 x i16>, <2 x i16>)
declare i32 @llvm.smin.i32(i32, i32)
declare i32 @llvm.smax.i32(i32, i32)
declare i32 @llvm.umin.i32(i32, i32)
declare i32 @llvm.umax.i32(i32, i32)