; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5 ; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefix=OLD_RBS_GFX10 %s ; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 < %s | FileCheck -check-prefix=OLD_RBS_GFX12 %s ; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 -new-reg-bank-select < %s | FileCheck -check-prefix=NEW_RBS_GFX10 %s ; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -new-reg-bank-select < %s | FileCheck -check-prefix=NEW_RBS_GFX12 %s define amdgpu_ps void @salu_float(float inreg %a, float inreg %b, i32 inreg %c, ptr addrspace(1) %ptr) { ; OLD_RBS_GFX10-LABEL: salu_float: ; OLD_RBS_GFX10: ; %bb.0: ; OLD_RBS_GFX10-NEXT: v_add_f32_e64 v2, s0, s1 ; OLD_RBS_GFX10-NEXT: v_cvt_u32_f32_e32 v2, v2 ; OLD_RBS_GFX10-NEXT: v_add_nc_u32_e32 v2, s2, v2 ; OLD_RBS_GFX10-NEXT: global_store_dword v[0:1], v2, off ; OLD_RBS_GFX10-NEXT: s_endpgm ; ; OLD_RBS_GFX12-LABEL: salu_float: ; OLD_RBS_GFX12: ; %bb.0: ; OLD_RBS_GFX12-NEXT: s_add_f32 s0, s0, s1 ; OLD_RBS_GFX12-NEXT: s_delay_alu instid0(SALU_CYCLE_3) | instskip(NEXT) | instid1(SALU_CYCLE_3) ; OLD_RBS_GFX12-NEXT: s_cvt_u32_f32 s0, s0 ; OLD_RBS_GFX12-NEXT: s_add_co_i32 s0, s0, s2 ; OLD_RBS_GFX12-NEXT: s_delay_alu instid0(SALU_CYCLE_1) ; OLD_RBS_GFX12-NEXT: v_mov_b32_e32 v2, s0 ; OLD_RBS_GFX12-NEXT: global_store_b32 v[0:1], v2, off ; OLD_RBS_GFX12-NEXT: s_endpgm ; ; NEW_RBS_GFX10-LABEL: salu_float: ; NEW_RBS_GFX10: ; %bb.0: ; NEW_RBS_GFX10-NEXT: v_add_f32_e64 v2, s0, s1 ; NEW_RBS_GFX10-NEXT: v_cvt_u32_f32_e32 v2, v2 ; NEW_RBS_GFX10-NEXT: v_readfirstlane_b32 s0, v2 ; NEW_RBS_GFX10-NEXT: s_add_i32 s0, s0, s2 ; NEW_RBS_GFX10-NEXT: v_mov_b32_e32 v2, s0 ; NEW_RBS_GFX10-NEXT: global_store_dword v[0:1], v2, off ; NEW_RBS_GFX10-NEXT: s_endpgm ; ; NEW_RBS_GFX12-LABEL: salu_float: ; NEW_RBS_GFX12: ; %bb.0: ; NEW_RBS_GFX12-NEXT: s_add_f32 s0, s0, s1 ; NEW_RBS_GFX12-NEXT: s_delay_alu instid0(SALU_CYCLE_3) | instskip(NEXT) | instid1(SALU_CYCLE_3) ; NEW_RBS_GFX12-NEXT: s_cvt_u32_f32 s0, s0 ; NEW_RBS_GFX12-NEXT: s_add_co_i32 s0, s0, s2 ; NEW_RBS_GFX12-NEXT: s_delay_alu instid0(SALU_CYCLE_1) ; NEW_RBS_GFX12-NEXT: v_mov_b32_e32 v2, s0 ; NEW_RBS_GFX12-NEXT: global_store_b32 v[0:1], v2, off ; NEW_RBS_GFX12-NEXT: s_endpgm %add = fadd float %a, %b %add.i32 = fptoui float %add to i32 %res = add i32 %add.i32, %c store i32 %res, ptr addrspace(1) %ptr ret void }