test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.interp.inreg.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s

define amdgpu_ps void @v_interp_f32(float inreg %i, float inreg %j, i32 inreg %m0) #0 {
; GCN-LABEL: v_interp_f32:
; GCN:       ; %bb.0: ; %main_body
; GCN-NEXT:    s_mov_b32 s3, exec_lo
; GCN-NEXT:    s_wqm_b32 exec_lo, exec_lo
; GCN-NEXT:    s_mov_b32 m0, s2
; GCN-NEXT:    lds_param_load v0, attr0.y wait_vdst:15
; GCN-NEXT:    lds_param_load v1, attr1.x wait_vdst:15
; GCN-NEXT:    s_mov_b32 exec_lo, s3
; GCN-NEXT:    v_mov_b32_e32 v2, s0
; GCN-NEXT:    v_mov_b32_e32 v4, s1
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_2)
; GCN-NEXT:    v_interp_p10_f32 v3, v0, v2, v0 wait_exp:1
; GCN-NEXT:    v_interp_p10_f32 v2, v1, v2, v1
; GCN-NEXT:    v_interp_p2_f32 v5, v0, v4, v3 wait_exp:7
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT:    v_interp_p2_f32 v4, v1, v4, v5 wait_exp:7
; GCN-NEXT:    exp mrt0 v3, v2, v5, v4 done
; GCN-NEXT:    s_endpgm
main_body:
  %p0 = call float @llvm.amdgcn.lds.param.load(i32 1, i32 0, i32 %m0)
  %p1 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 1, i32 %m0)
  %p0_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p0, float %i, float %p0)
  %p1_0 = call float @llvm.amdgcn.interp.inreg.p2(float %p0, float %j, float %p0_0)
  %p0_1 = call float @llvm.amdgcn.interp.inreg.p10(float %p1, float %i, float %p1)
  %p1_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p1, float %j, float %p1_0)
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %p0_0, float %p0_1, float %p1_0, float %p1_1, i1 true, i1 true) #0
  ret void
}

define amdgpu_ps void @v_interp_f32_many(float inreg %i, float inreg %j, i32 inreg %m0) #0 {
; GCN-LABEL: v_interp_f32_many:
; GCN:       ; %bb.0: ; %main_body
; GCN-NEXT:    s_mov_b32 s3, exec_lo
; GCN-NEXT:    s_wqm_b32 exec_lo, exec_lo
; GCN-NEXT:    s_mov_b32 m0, s2
; GCN-NEXT:    lds_param_load v0, attr0.x wait_vdst:15
; GCN-NEXT:    lds_param_load v1, attr1.x wait_vdst:15
; GCN-NEXT:    lds_param_load v2, attr2.x wait_vdst:15
; GCN-NEXT:    lds_param_load v3, attr3.x wait_vdst:15
; GCN-NEXT:    s_mov_b32 exec_lo, s3
; GCN-NEXT:    v_dual_mov_b32 v4, s0 :: v_dual_mov_b32 v5, s1
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_3) | instid1(VALU_DEP_4)
; GCN-NEXT:    v_interp_p10_f32 v6, v0, v4, v0 wait_exp:3
; GCN-NEXT:    v_interp_p10_f32 v7, v1, v4, v1 wait_exp:2
; GCN-NEXT:    v_interp_p10_f32 v8, v2, v4, v2 wait_exp:1
; GCN-NEXT:    v_interp_p10_f32 v4, v3, v4, v3
; GCN-NEXT:    v_interp_p2_f32 v6, v0, v5, v6 wait_exp:7
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_4)
; GCN-NEXT:    v_interp_p2_f32 v7, v1, v5, v7 wait_exp:7
; GCN-NEXT:    v_interp_p2_f32 v8, v2, v5, v8 wait_exp:7
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_4)
; GCN-NEXT:    v_interp_p2_f32 v4, v3, v5, v4 wait_exp:7
; GCN-NEXT:    exp mrt0 v6, v7, v8, v4 done
; GCN-NEXT:    s_endpgm
main_body:
  %p0 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 0, i32 %m0)
  %p1 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 1, i32 %m0)
  %p2 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 2, i32 %m0)
  %p3 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 3, i32 %m0)
  %p0_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p0, float %i, float %p0)
  %p0_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p0, float %j, float %p0_0)
  %p1_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p1, float %i, float %p1)
  %p1_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p1, float %j, float %p1_0)
  %p2_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p2, float %i, float %p2)
  %p2_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p2, float %j, float %p2_0)
  %p3_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p3, float %i, float %p3)
  %p3_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p3, float %j, float %p3_0)
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %p0_1, float %p1_1, float %p2_1, float %p3_1, i1 true, i1 true) #0
  ret void
}

define amdgpu_ps void @v_interp_f32_many_vm(ptr addrspace(1) %ptr, i32 inreg %m0) #0 {
; GCN-LABEL: v_interp_f32_many_vm:
; GCN:       ; %bb.0: ; %main_body
; GCN-NEXT:    global_load_b64 v[0:1], v[0:1], off offset:4
; GCN-NEXT:    s_mov_b32 m0, s0
; GCN-NEXT:    s_mov_b32 s0, exec_lo
; GCN-NEXT:    s_wqm_b32 exec_lo, exec_lo
; GCN-NEXT:    lds_param_load v2, attr0.x wait_vdst:15
; GCN-NEXT:    lds_param_load v3, attr1.x wait_vdst:15
; GCN-NEXT:    lds_param_load v4, attr2.x wait_vdst:15
; GCN-NEXT:    lds_param_load v5, attr3.x wait_vdst:15
; GCN-NEXT:    s_mov_b32 exec_lo, s0
; GCN-NEXT:    s_waitcnt vmcnt(0)
; GCN-NEXT:    v_interp_p10_f32 v6, v2, v0, v2 wait_exp:3
; GCN-NEXT:    v_interp_p10_f32 v7, v3, v0, v3 wait_exp:2
; GCN-NEXT:    v_interp_p10_f32 v8, v4, v0, v4 wait_exp:1
; GCN-NEXT:    v_interp_p10_f32 v0, v5, v0, v5
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_4)
; GCN-NEXT:    v_interp_p2_f32 v6, v2, v1, v6 wait_exp:7
; GCN-NEXT:    v_interp_p2_f32 v7, v3, v1, v7 wait_exp:7
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_4)
; GCN-NEXT:    v_interp_p2_f32 v8, v4, v1, v8 wait_exp:7
; GCN-NEXT:    v_interp_p2_f32 v0, v5, v1, v0 wait_exp:7
; GCN-NEXT:    exp mrt0 v6, v7, v8, v0 done
; GCN-NEXT:    s_endpgm
main_body:
  %i.ptr = getelementptr float, ptr addrspace(1) %ptr, i32 1
  %i = load float, ptr addrspace(1) %i.ptr, align 4
  %j.ptr = getelementptr float, ptr addrspace(1) %ptr, i32 2
  %j = load float, ptr addrspace(1) %j.ptr, align 4
  %p0 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 0, i32 %m0)
  %p1 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 1, i32 %m0)
  %p2 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 2, i32 %m0)
  %p3 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 3, i32 %m0)
  %p0_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p0, float %i, float %p0)
  %p0_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p0, float %j, float %p0_0)
  %p1_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p1, float %i, float %p1)
  %p1_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p1, float %j, float %p1_0)
  %p2_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p2, float %i, float %p2)
  %p2_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p2, float %j, float %p2_0)
  %p3_0 = call float @llvm.amdgcn.interp.inreg.p10(float %p3, float %i, float %p3)
  %p3_1 = call float @llvm.amdgcn.interp.inreg.p2(float %p3, float %j, float %p3_0)
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %p0_1, float %p1_1, float %p2_1, float %p3_1, i1 true, i1 true) #0
  ret void
}

define amdgpu_ps half @v_interp_f16(float inreg %i, float inreg %j, i32 inreg %m0) #0 {
; GCN-LABEL: v_interp_f16:
; GCN:       ; %bb.0: ; %main_body
; GCN-NEXT:    s_mov_b32 s3, exec_lo
; GCN-NEXT:    s_wqm_b32 exec_lo, exec_lo
; GCN-NEXT:    s_mov_b32 m0, s2
; GCN-NEXT:    lds_param_load v1, attr0.x wait_vdst:15
; GCN-NEXT:    s_mov_b32 exec_lo, s3
; GCN-NEXT:    v_mov_b32_e32 v0, s0
; GCN-NEXT:    v_mov_b32_e32 v2, s1
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_2)
; GCN-NEXT:    v_interp_p10_f16_f32 v3, v1, v0, v1
; GCN-NEXT:    v_interp_p10_f16_f32 v0, v1, v0, v1 op_sel:[1,0,1,0] wait_exp:7
; GCN-NEXT:    v_interp_p2_f16_f32 v3, v1, v2, v3 wait_exp:7
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
; GCN-NEXT:    v_interp_p2_f16_f32 v0, v1, v2, v0 op_sel:[1,0,0,0] wait_exp:7
; GCN-NEXT:    v_add_f16_e32 v0, v3, v0
; GCN-NEXT:    ; return to shader part epilog
main_body:
  %p0 = call float @llvm.amdgcn.lds.param.load(i32 0, i32 0, i32 %m0)
  %l_p0 = call float @llvm.amdgcn.interp.inreg.p10.f16(float %p0, float %i, float %p0, i1 0)
  %l_p1 = call half @llvm.amdgcn.interp.inreg.p2.f16(float %p0, float %j, float %l_p0, i1 0)
  %h_p0 = call float @llvm.amdgcn.interp.inreg.p10.f16(float %p0, float %i, float %p0, i1 1)
  %h_p1 = call half @llvm.amdgcn.interp.inreg.p2.f16(float %p0, float %j, float %h_p0, i1 1)
  %res = fadd half %l_p1, %h_p1
  ret half %res
}

define amdgpu_ps half @v_interp_f16_imm_params(float inreg %i, float inreg %j) #0 {
; GCN-LABEL: v_interp_f16_imm_params:
; GCN:       ; %bb.0: ; %main_body
; GCN-NEXT:    v_dual_mov_b32 v0, 0 :: v_dual_mov_b32 v1, s0
; GCN-NEXT:    v_mov_b32_e32 v2, s1
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
; GCN-NEXT:    v_interp_p10_f16_f32 v1, v0, v1, v0 wait_exp:7
; GCN-NEXT:    v_interp_p2_f16_f32 v0, v0, v2, v0 wait_exp:7
; GCN-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
; GCN-NEXT:    v_cvt_f16_f32_e32 v1, v1
; GCN-NEXT:    v_add_f16_e32 v0, v1, v0
; GCN-NEXT:    ; return to shader part epilog
main_body:
  %l_p0 = call float @llvm.amdgcn.interp.inreg.p10.f16(float 0.0, float %i, float 0.0, i1 0)
  %l_p1 = call half @llvm.amdgcn.interp.inreg.p2.f16(float 0.0, float %j, float 0.0, i1 0)
  %h = fptrunc float %l_p0 to half
  %res = fadd half %h, %l_p1
  ret half %res
}

declare float @llvm.amdgcn.lds.param.load(i32, i32, i32) #1
declare float @llvm.amdgcn.interp.inreg.p10(float, float, float) #0
declare float @llvm.amdgcn.interp.inreg.p2(float, float, float) #0
declare float @llvm.amdgcn.interp.inreg.p10.f16(float, float, float, i1) #0
declare half @llvm.amdgcn.interp.inreg.p2.f16(float, float, float, i1) #0
declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #0
declare void @llvm.amdgcn.exp.f16(i32, i32, float, float, float, float, i1, i1) #0

attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }