| # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py |
| # RUN: llc -march=amdgcn -mcpu=tahiti -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX6 %s |
| # RUN: llc -march=amdgcn -mcpu=hawaii -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX7 %s |
| # RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX7 %s |
| # RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX9 %s |
| # RUN: llc -march=amdgcn -mcpu=gfx1010 -run-pass=instruction-select -verify-machineinstrs -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX9 %s |
| |
| |
| --- |
| name: atomicrmw_fadd_s32_local |
| legalized: true |
| regBankSelected: true |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $vgpr0, $vgpr1 |
| |
| ; GFX6-LABEL: name: atomicrmw_fadd_s32_local |
| ; GFX6: liveins: $vgpr0, $vgpr1 |
| ; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX6: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX6: $m0 = S_MOV_B32 -1 |
| ; GFX6: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 [[COPY]], [[COPY1]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| ; GFX6: $vgpr0 = COPY [[DS_ADD_RTN_F32_]] |
| ; GFX7-LABEL: name: atomicrmw_fadd_s32_local |
| ; GFX7: liveins: $vgpr0, $vgpr1 |
| ; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX7: $m0 = S_MOV_B32 -1 |
| ; GFX7: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 [[COPY]], [[COPY1]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| ; GFX7: $vgpr0 = COPY [[DS_ADD_RTN_F32_]] |
| ; GFX9-LABEL: name: atomicrmw_fadd_s32_local |
| ; GFX9: liveins: $vgpr0, $vgpr1 |
| ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX9: [[DS_ADD_RTN_F32_gfx9_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32_gfx9 [[COPY]], [[COPY1]], 0, 0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| ; GFX9: $vgpr0 = COPY [[DS_ADD_RTN_F32_gfx9_]] |
| %0:vgpr(p3) = COPY $vgpr0 |
| %1:vgpr(s32) = COPY $vgpr1 |
| %2:vgpr(s32) = G_ATOMICRMW_FADD %0(p3), %1 :: (load store seq_cst 4, addrspace 3) |
| $vgpr0 = COPY %2 |
| |
| ... |
| |
| --- |
| name: atomicrmw_fadd_s32_local_noret |
| legalized: true |
| regBankSelected: true |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $vgpr0, $vgpr1 |
| |
| ; GFX6-LABEL: name: atomicrmw_fadd_s32_local_noret |
| ; GFX6: liveins: $vgpr0, $vgpr1 |
| ; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX6: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX6: $m0 = S_MOV_B32 -1 |
| ; GFX6: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 [[COPY]], [[COPY1]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| ; GFX7-LABEL: name: atomicrmw_fadd_s32_local_noret |
| ; GFX7: liveins: $vgpr0, $vgpr1 |
| ; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX7: $m0 = S_MOV_B32 -1 |
| ; GFX7: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 [[COPY]], [[COPY1]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| ; GFX9-LABEL: name: atomicrmw_fadd_s32_local_noret |
| ; GFX9: liveins: $vgpr0, $vgpr1 |
| ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX9: [[DS_ADD_RTN_F32_gfx9_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32_gfx9 [[COPY]], [[COPY1]], 0, 0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| %0:vgpr(p3) = COPY $vgpr0 |
| %1:vgpr(s32) = COPY $vgpr1 |
| %2:vgpr(s32) = G_ATOMICRMW_FADD %0(p3), %1 :: (load store seq_cst 4, addrspace 3) |
| |
| ... |
| |
| --- |
| name: atomicrmw_fadd_s32_local_gep4 |
| legalized: true |
| regBankSelected: true |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $vgpr0, $vgpr1 |
| |
| ; GFX6-LABEL: name: atomicrmw_fadd_s32_local_gep4 |
| ; GFX6: liveins: $vgpr0, $vgpr1 |
| ; GFX6: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX6: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX6: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 4, implicit $exec |
| ; GFX6: %3:vgpr_32, dead %5:sreg_64_xexec = V_ADD_I32_e64 [[COPY]], [[V_MOV_B32_e32_]], 0, implicit $exec |
| ; GFX6: $m0 = S_MOV_B32 -1 |
| ; GFX6: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 %3, [[COPY1]], 0, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| ; GFX6: $vgpr0 = COPY [[DS_ADD_RTN_F32_]] |
| ; GFX7-LABEL: name: atomicrmw_fadd_s32_local_gep4 |
| ; GFX7: liveins: $vgpr0, $vgpr1 |
| ; GFX7: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX7: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX7: $m0 = S_MOV_B32 -1 |
| ; GFX7: [[DS_ADD_RTN_F32_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32 [[COPY]], [[COPY1]], 4, 0, implicit $m0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| ; GFX7: $vgpr0 = COPY [[DS_ADD_RTN_F32_]] |
| ; GFX9-LABEL: name: atomicrmw_fadd_s32_local_gep4 |
| ; GFX9: liveins: $vgpr0, $vgpr1 |
| ; GFX9: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 |
| ; GFX9: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1 |
| ; GFX9: [[DS_ADD_RTN_F32_gfx9_:%[0-9]+]]:vgpr_32 = DS_ADD_RTN_F32_gfx9 [[COPY]], [[COPY1]], 4, 0, implicit $exec :: (load store seq_cst 4, addrspace 3) |
| ; GFX9: $vgpr0 = COPY [[DS_ADD_RTN_F32_gfx9_]] |
| %0:vgpr(p3) = COPY $vgpr0 |
| %1:vgpr(s32) = COPY $vgpr1 |
| %2:vgpr(s32) = G_CONSTANT i32 4 |
| %3:vgpr(p3) = G_GEP %0, %2 |
| %4:vgpr(s32) = G_ATOMICRMW_FADD %3(p3), %1 :: (load store seq_cst 4, addrspace 3) |
| $vgpr0 = COPY %4 |
| |
| ... |