llvm/test/CodeGen/AMDGPU/rewrite-vgpr-mfma-to-agpr-copy-from.mir

# 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 -verify-machineinstrs -o - %s | FileCheck %s

---
name:  test_rewrite_mfma_copy_from_agpr_physreg
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $agpr0_agpr1

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_physreg
    ; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $agpr0_agpr1
    ; 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: [[COPY3:%[0-9]+]]:vreg_64_align2 = COPY $agpr0_agpr1
    ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_vgprcd_e64_:%[0-9]+]]:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], [[COPY3]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[V_MFMA_F64_4X4X4F64_vgprcd_e64_]], 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 = COPY $agpr0_agpr1
    %4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %3, 0, 0, 0, implicit $mode, implicit $exec
    GLOBAL_STORE_DWORDX2 %0, %4, 0, 0, implicit $exec :: (store (s64), addrspace 1)
    SI_RETURN
...

---
name:  test_rewrite_mfma_copy_from_agpr_unrewritable_use
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_unrewritable_use
    ; 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_DWORDX4_:%[0-9]+]]:areg_128_align2 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, implicit $exec :: (load (s128), addrspace 1)
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vreg_128_align2 = COPY [[GLOBAL_LOAD_DWORDX4_]]
    ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_vgprcd_e64_:%[0-9]+]]:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], [[COPY3]].sub0_sub1, 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 3866633 /* reguse:VReg_64_Align2 */, [[V_MFMA_F64_4X4X4F64_vgprcd_e64_]]
    ; 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:areg_128_align2 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec :: (load (s128), addrspace 1)
    %4:vreg_128_align2 = COPY %3
    %5:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %4.sub0_sub1, 0, 0, 0, implicit $mode, implicit $exec
    INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 3866633 /* reguse:VReg_64_Align2 */, %5
    SI_RETURN
...

---
name:  test_rewrite_mfma_copy_from_agpr_src2_subreg_use
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_src2_subreg_use
    ; 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_DWORDX4_:%[0-9]+]]:areg_128_align2 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, implicit $exec :: (load (s128), addrspace 1)
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vreg_128_align2 = COPY [[GLOBAL_LOAD_DWORDX4_]]
    ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_vgprcd_e64_:%[0-9]+]]:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], [[COPY3]].sub0_sub1, 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[V_MFMA_F64_4X4X4F64_vgprcd_e64_]], 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:areg_128_align2 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec :: (load (s128), addrspace 1)
    %4:vreg_128_align2 = COPY %3
    %5:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %4.sub0_sub1, 0, 0, 0, implicit $mode, implicit $exec
    GLOBAL_STORE_DWORDX2 %0, %5, 0, 0, implicit $exec :: (store (s64), addrspace 1)
    SI_RETURN
...

---
name:  test_rewrite_mfma_copy_from_agpr_vdst_subreg_use
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_vdst_subreg_use
    ; 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_DWORDX4_:%[0-9]+]]:areg_128_align2 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, implicit $exec :: (load (s128), addrspace 1)
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vreg_128_align2 = COPY [[GLOBAL_LOAD_DWORDX4_]]
    ; CHECK-NEXT: [[COPY3:%[0-9]+]].sub0_sub1:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], [[COPY3]].sub2_sub3, 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 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:areg_128_align2 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec :: (load (s128), addrspace 1)
    %4:vreg_128_align2 = COPY %3
    %4.sub0_sub1:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %4.sub2_sub3, 0, 0, 0, implicit $mode, implicit $exec
    GLOBAL_STORE_DWORDX4 %0, %4, 0, 0, implicit $exec :: (store (s128), addrspace 1)
    SI_RETURN
...

# A-to-V copy is performed subregister at a time instead.
---
name:  test_rewrite_mfma_copy_from_agpr_split_copy
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_split_copy
    ; 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 [[COPY3:%[0-9]+]].sub0:vreg_64_align2 = COPY [[GLOBAL_LOAD_DWORDX2_]].sub0
    ; CHECK-NEXT: [[COPY3:%[0-9]+]].sub1:vreg_64_align2 = COPY [[GLOBAL_LOAD_DWORDX2_]].sub1
    ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_vgprcd_e64_:%[0-9]+]]:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], [[COPY3]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[V_MFMA_F64_4X4X4F64_vgprcd_e64_]], 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:areg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1)
    undef %4.sub0:vreg_64_align2 = COPY %3.sub0
    %4.sub1:vreg_64_align2 = COPY %3.sub1
    %5:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %4, 0, 0, 0, implicit $mode, implicit $exec
    GLOBAL_STORE_DWORDX2 %0, %5, 0, 0, implicit $exec :: (store (s64), addrspace 1)
    SI_RETURN
...

---
name:  test_rewrite_mfma_copy_from_agpr_copyback
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_copyback
    ; 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: [[COPY3:%[0-9]+]]:areg_64_align2 = COPY [[GLOBAL_LOAD_DWORDX2_]]
    ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_e64_:%[0-9]+]]:areg_64_align2 = V_MFMA_F64_4X4X4F64_e64 [[COPY1]], [[COPY2]], [[COPY3]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[COPY4:%[0-9]+]]:areg_64_align2 = COPY [[V_MFMA_F64_4X4X4F64_e64_]]
    ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[COPY4]], 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:areg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1)
    %4:vreg_64_align2 = COPY %3
    %5:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, %4, 0, 0, 0, implicit $mode, implicit $exec
    %6:areg_64_align2 = COPY %5
    GLOBAL_STORE_DWORDX2 %0, %6, 0, 0, implicit $exec :: (store (s64), addrspace 1)
    SI_RETURN
...

# There is a read of the copy from AGPR to VGPR in the dst operand of the MFMA.
---
name:  test_rewrite_mfma_copy_from_agpr_vdst_subreg_use_imm_src2
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_vdst_subreg_use_imm_src2
    ; 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_DWORDX4_:%[0-9]+]]:areg_128_align2 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, implicit $exec :: (load (s128), addrspace 1)
    ; CHECK-NEXT: [[COPY3:%[0-9]+]]:vreg_128_align2 = COPY [[GLOBAL_LOAD_DWORDX4_]]
    ; CHECK-NEXT: [[COPY3:%[0-9]+]].sub0_sub1:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], 0, 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY3]], 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:areg_128_align2 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec :: (load (s128), addrspace 1)
    %4:vreg_128_align2 = COPY %3
    %4.sub0_sub1:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, 0, 0, 0, 0, implicit $mode, implicit $exec
    GLOBAL_STORE_DWORDX4 %0, %4, 0, 0, implicit $exec :: (store (s128), addrspace 1)
    SI_RETURN
...

# Degenerate case. Copy from AGPR to VGPR is dead undef subreg def
---
name:  test_rewrite_mfma_copy_from_agpr_undef_vdst_subreg_use_imm_src2
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_undef_vdst_subreg_use_imm_src2
    ; 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_DWORDX4_:%[0-9]+]]:areg_128_align2 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, implicit $exec :: (load (s128), addrspace 1)
    ; CHECK-NEXT: dead [[COPY3:%[0-9]+]]:vreg_128_align2 = COPY [[GLOBAL_LOAD_DWORDX4_]]
    ; CHECK-NEXT: undef [[V_MFMA_F64_4X4X4F64_vgprcd_e64_:%[0-9]+]].sub0_sub1:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], 0, 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORDX4 [[COPY]], [[V_MFMA_F64_4X4X4F64_vgprcd_e64_]], 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:areg_128_align2 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec :: (load (s128), addrspace 1)
    %4:vreg_128_align2 = COPY %3
    undef %4.sub0_sub1:vreg_128_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, 0, 0, 0, 0, implicit $mode, implicit $exec
    GLOBAL_STORE_DWORDX4 %0, %4, 0, 0, implicit $exec :: (store (s128), addrspace 1)
    SI_RETURN
...

# Degenerate case. Copy from AGPR to VGPR is dead, but same register
# is redefined as whole register.
---
name:  test_rewrite_mfma_copy_from_agpr_to_vdst_def_imm_src2
tracksRegLiveness: true
body:             |
  bb.0:
    liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5

    ; CHECK-LABEL: name: test_rewrite_mfma_copy_from_agpr_to_vdst_def_imm_src2
    ; 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: dead [[COPY3:%[0-9]+]]:vreg_64_align2 = COPY [[GLOBAL_LOAD_DWORDX2_]]
    ; CHECK-NEXT: [[V_MFMA_F64_4X4X4F64_vgprcd_e64_:%[0-9]+]]:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 [[COPY1]], [[COPY2]], 0, 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORDX2 [[COPY]], [[V_MFMA_F64_4X4X4F64_vgprcd_e64_]], 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:areg_64_align2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec :: (load (s64), addrspace 1)
    %4:vreg_64_align2 = COPY %3
    %4:vreg_64_align2 = V_MFMA_F64_4X4X4F64_vgprcd_e64 %1, %2, 0, 0, 0, 0, implicit $mode, implicit $exec
    GLOBAL_STORE_DWORDX2 %0, %4, 0, 0, implicit $exec :: (store (s64), addrspace 1)
    SI_RETURN
...