# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5 # RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -run-pass=greedy,amdgpu-rewrite-agpr-copy-mfma -o - %s | FileCheck %s # V-to-A copy is a subregister insert --- name: test_rewrite_mfma_copy_subreg_insert tracksRegLiveness: true body: | bb.0: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-LABEL: name: test_rewrite_mfma_copy_subreg_insert ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5 ; CHECK-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY $vgpr0_vgpr1 ; CHECK-NEXT: [[COPY2:%[0-9]+]]:av_64_align2 = COPY $vgpr2_vgpr3 ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:areg_64_align2 = GLOBAL_LOAD_DWORDX2 [[COPY]], 0, 0, implicit $exec :: (load (s64), addrspace 1) ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec ; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]] ; CHECK-NEXT: [[COPY3:%[0-9]+]].sub2_sub3:areg_128_align2 = IMPLICIT_DEF ; CHECK-NEXT: INLINEASM &"; use $0", sideeffect attdialect, reguse:AReg_128_Align2, [[COPY3]] ; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1) ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY3]].sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1) ; CHECK-NEXT: SI_RETURN %0:vreg_64_align2 = COPY $vgpr4_vgpr5 %1:av_64_align2 = COPY $vgpr0_vgpr1 %2:av_64_align2 = COPY $vgpr2_vgpr3 %3:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1) %4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec undef %5.sub0_sub1:areg_128_align2 = COPY %4 %5.sub2_sub3 = IMPLICIT_DEF INLINEASM &"; use $0", sideeffect attdialect, reguse:AReg_128_Align2, %5 GLOBAL_STORE_DWORDX4 %0, %5, 0, 0, implicit $exec :: (store (s128), addrspace 1) GLOBAL_STORE_DWORDX2 %0, %5.sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1) SI_RETURN ... # V-to-A copy is a subregister extract --- name: test_rewrite_mfma_copy_subreg_extract tracksRegLiveness: true body: | bb.0: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-LABEL: name: test_rewrite_mfma_copy_subreg_extract ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5 ; CHECK-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY $vgpr0_vgpr1 ; CHECK-NEXT: [[COPY2:%[0-9]+]]:av_64_align2 = COPY $vgpr2_vgpr3 ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:areg_64_align2 = GLOBAL_LOAD_DWORDX2 [[COPY]], 0, 0, implicit $exec :: (load (s64), addrspace 1) ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec ; CHECK-NEXT: [[COPY3:%[0-9]+]]:agpr_32 = COPY [[V_MFMA_F64_4X4X4F64_e64_]].sub0 ; CHECK-NEXT: GLOBAL_STORE_DWORD [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s32), addrspace 1) ; CHECK-NEXT: SI_RETURN %0:vreg_64_align2 = COPY $vgpr4_vgpr5 %1:av_64_align2 = COPY $vgpr0_vgpr1 %2:av_64_align2 = COPY $vgpr2_vgpr3 %3:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1) %4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec %5:agpr_32 = COPY %4.sub0 GLOBAL_STORE_DWORD %0, %5, 0, 0, implicit $exec :: (store (s32), addrspace 1) SI_RETURN ... # V-to-A copy is a subregister-to-subregister copy --- name: test_rewrite_mfma_copy_subreg_insert_extract_same_subreg tracksRegLiveness: true body: | bb.0: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-LABEL: name: test_rewrite_mfma_copy_subreg_insert_extract_same_subreg ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5 ; CHECK-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY $vgpr0_vgpr1 ; CHECK-NEXT: [[COPY2:%[0-9]+]]:av_64_align2 = COPY $vgpr2_vgpr3 ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:areg_64_align2 = GLOBAL_LOAD_DWORDX2 [[COPY]], 0, 0, implicit $exec :: (load (s64), addrspace 1) ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec ; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0:areg_64_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]].sub0 ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s64), addrspace 1) ; CHECK-NEXT: SI_RETURN %0:vreg_64_align2 = COPY $vgpr4_vgpr5 %1:av_64_align2 = COPY $vgpr0_vgpr1 %2:av_64_align2 = COPY $vgpr2_vgpr3 %3:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1) %4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec undef %5.sub0:areg_64_align2 = COPY %4.sub0 GLOBAL_STORE_DWORDX2 %0, %5, 0, 0, implicit $exec :: (store (s64), addrspace 1) SI_RETURN ... # V-to-A copy is a subregister-to-subregister copy --- name: test_rewrite_mfma_copy_subreg_insert_extract_different_subreg tracksRegLiveness: true body: | bb.0: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-LABEL: name: test_rewrite_mfma_copy_subreg_insert_extract_different_subreg ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5 ; CHECK-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY $vgpr0_vgpr1 ; CHECK-NEXT: [[COPY2:%[0-9]+]]:av_64_align2 = COPY $vgpr2_vgpr3 ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:areg_64_align2 = GLOBAL_LOAD_DWORDX2 [[COPY]], 0, 0, implicit $exec :: (load (s64), addrspace 1) ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec ; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0:areg_64_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]].sub1 ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s64), addrspace 1) ; CHECK-NEXT: SI_RETURN %0:vreg_64_align2 = COPY $vgpr4_vgpr5 %1:av_64_align2 = COPY $vgpr0_vgpr1 %2:av_64_align2 = COPY $vgpr2_vgpr3 %3:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1) %4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec undef %5.sub0:areg_64_align2 = COPY %4.sub1 GLOBAL_STORE_DWORDX2 %0, %5, 0, 0, implicit $exec :: (store (s64), addrspace 1) SI_RETURN ... # V-to-A copy is a subregister extract, from a subregister def --- name: test_rewrite_mfma_copy_subreg_extract_from_subreg_def tracksRegLiveness: true body: | bb.0: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-LABEL: name: test_rewrite_mfma_copy_subreg_extract_from_subreg_def ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5 ; CHECK-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY $vgpr0_vgpr1 ; CHECK-NEXT: [[COPY2:%[0-9]+]]:av_64_align2 = COPY $vgpr2_vgpr3 ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:areg_64_align2 = GLOBAL_LOAD_DWORDX2 [[COPY]], 0, 0, implicit $exec :: (load (s64), addrspace 1) ; CHECK-NEXT: undef [[DEF:%[0-9]+]].sub0:areg_128_align2 = IMPLICIT_DEF ; CHECK-NEXT: [[DEF:%[0-9]+]].sub2_sub3:areg_128_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec ; CHECK-NEXT: [[COPY3:%[0-9]+]]:agpr_32 = COPY [[DEF]].sub0 ; CHECK-NEXT: GLOBAL_STORE_DWORD [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s32), addrspace 1) ; CHECK-NEXT: SI_RETURN %0:vreg_64_align2 = COPY $vgpr4_vgpr5 %1:av_64_align2 = COPY $vgpr0_vgpr1 %2:av_64_align2 = COPY $vgpr2_vgpr3 %3:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1) undef %4.sub0 = IMPLICIT_DEF %4.sub2_sub3:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec %5:agpr_32 = COPY %4.sub0 GLOBAL_STORE_DWORD %0, %5, 0, 0, implicit $exec :: (store (s32), addrspace 1) SI_RETURN ... # V-to-A copy is a subregister insert from a subregister_def --- name: test_rewrite_mfma_copy_subreg_insert_from_subreg_def_tuple tracksRegLiveness: true body: | bb.0: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-LABEL: name: test_rewrite_mfma_copy_subreg_insert_from_subreg_def_tuple ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5 ; CHECK-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY $vgpr0_vgpr1 ; CHECK-NEXT: [[COPY2:%[0-9]+]]:av_64_align2 = COPY $vgpr2_vgpr3 ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:areg_64_align2 = GLOBAL_LOAD_DWORDX2 [[COPY]], 0, 0, implicit $exec :: (load (s64), addrspace 1) ; CHECK-NEXT: undef [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]].sub2_sub3:areg_128_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec ; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub0_sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]].sub2_sub3 ; CHECK-NEXT: [[COPY3:%[0-9]+]].sub2_sub3:areg_128_align2 = IMPLICIT_DEF ; CHECK-NEXT: INLINEASM &"; use $0", sideeffect attdialect, reguse:AReg_128_Align2, [[COPY3]] ; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1) ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY3]].sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1) ; CHECK-NEXT: SI_RETURN %0:vreg_64_align2 = COPY $vgpr4_vgpr5 %1:av_64_align2 = COPY $vgpr0_vgpr1 %2:av_64_align2 = COPY $vgpr2_vgpr3 %3:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1) undef %4.sub2_sub3:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec undef %5.sub0_sub1:areg_128_align2 = COPY %4.sub2_sub3 %5.sub2_sub3 = IMPLICIT_DEF INLINEASM &"; use $0", sideeffect attdialect, reguse:AReg_128_Align2, %5 GLOBAL_STORE_DWORDX4 %0, %5, 0, 0, implicit $exec :: (store (s128), addrspace 1) GLOBAL_STORE_DWORDX2 %0, %5.sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1) SI_RETURN ... # V-to-A copy is a subregister insert of a subregister from a # subregister_def --- name: test_rewrite_mfma_copy_subreg_insert_from_subreg_def_subreg tracksRegLiveness: true body: | bb.0: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-LABEL: name: test_rewrite_mfma_copy_subreg_insert_from_subreg_def_subreg ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5 ; CHECK-NEXT: {{ $}} ; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY $vgpr4_vgpr5 ; CHECK-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY $vgpr0_vgpr1 ; CHECK-NEXT: [[COPY2:%[0-9]+]]:av_64_align2 = COPY $vgpr2_vgpr3 ; CHECK-NEXT: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 [[COPY]], 0, 0, implicit $exec :: (load (s64), addrspace 1) ; CHECK-NEXT: undef [[V_MFMA_F64_4X4X4F64_vgprcd_e64_:%[0-9]+]].sub2_sub3:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], [[GLOBAL_LOAD_DWORDX2_]], 0, 0, 0, implicit $mode, implicit $exec ; CHECK-NEXT: undef [[COPY3:%[0-9]+]].sub1:areg_128_align2 = COPY [[V_MFMA_F64_4X4X4F64_vgprcd_e64_]].sub2 ; CHECK-NEXT: [[COPY3:%[0-9]+]].sub2_sub3:areg_128_align2 = IMPLICIT_DEF ; CHECK-NEXT: INLINEASM &"; use $0", sideeffect attdialect, reguse:AReg_128_Align2, [[COPY3]] ; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 0, 0, implicit $exec :: (store (s128), addrspace 1) ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY3]].sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1) ; CHECK-NEXT: SI_RETURN %0:vreg_64_align2 = COPY $vgpr4_vgpr5 %1:av_64_align2 = COPY $vgpr0_vgpr1 %2:av_64_align2 = COPY $vgpr2_vgpr3 %3:vreg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1) undef %4.sub2_sub3:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec undef %5.sub1:areg_128_align2 = COPY %4.sub2 %5.sub2_sub3 = IMPLICIT_DEF INLINEASM &"; use $0", sideeffect attdialect, reguse:AReg_128_Align2, %5 GLOBAL_STORE_DWORDX4 %0, %5, 0, 0, implicit $exec :: (store (s128), addrspace 1) GLOBAL_STORE_DWORDX2 %0, %5.sub2_sub3, 0, 0, implicit $exec :: (store (s128), addrspace 1) SI_RETURN ...