llvm/llvm/test/CodeGen/AMDGPU/sched-group-barrier-pre-RA.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx908 -misched-cluster=false -run-pass=machine-scheduler -verify-misched -o - %s | FileCheck %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx908 -misched-cluster=false -run-pass=machine-scheduler -amdgpu-igrouplp-exact-solver -verify-misched -o - %s | FileCheck -check-prefix=EXACT %s

--- |
  define amdgpu_kernel void @no_sched_group_barrier(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) { ret void }
  define amdgpu_kernel void @sched_group_barrier_1_VMEM_READ_1_VALU_5_MFMA_1_VMEM_READ_3_VALU_2_VMEM_WRITE(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) { ret void }
  define amdgpu_kernel void @sched_group_barrier_2_VMEM_1000_ALU_5_MFMA_2_VMEM_WRITE(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) { ret void }
  define amdgpu_kernel void @sched_group_barrier_MFMA_VALU_and_SALU_alternating(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in) { ret void }

  !0 = distinct !{!0}
  !1 = !{!1, !0}
...

---
name: no_sched_group_barrier
tracksRegLiveness: true
body: |
  bb.0:
    ; CHECK-LABEL: name: no_sched_group_barrier
    ; CHECK: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
    ; CHECK-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
    ; CHECK-NEXT: [[DEF2:%[0-9]+]]:areg_128 = IMPLICIT_DEF
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF2]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; CHECK-NEXT: S_NOP 0
    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_1:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_2:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_2:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_3:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_3:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_4:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_3]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_3]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; CHECK-NEXT: S_ENDPGM 0, implicit [[V_MUL_LO_U32_e64_1]], implicit [[V_MUL_LO_U32_e64_2]], implicit [[V_MFMA_F32_4X4X1F32_e64_4]]
    ;
    ; EXACT-LABEL: name: no_sched_group_barrier
    ; EXACT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
    ; EXACT-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
    ; EXACT-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
    ; EXACT-NEXT: [[DEF2:%[0-9]+]]:areg_128 = IMPLICIT_DEF
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF2]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; EXACT-NEXT: S_NOP 0
    ; EXACT-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_1:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_2:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_2:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_3:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_3:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_4:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_3]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_3]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; EXACT-NEXT: S_ENDPGM 0, implicit [[V_MUL_LO_U32_e64_1]], implicit [[V_MUL_LO_U32_e64_2]], implicit [[V_MFMA_F32_4X4X1F32_e64_4]]
    %0:sreg_64 = IMPLICIT_DEF
    %1:vgpr_32 = IMPLICIT_DEF
    %2:areg_128 = IMPLICIT_DEF
    %3:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    %4:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %3, implicit $exec
    GLOBAL_STORE_DWORD_SADDR %1, %4, %0, 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    %5:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %1, implicit $exec
    %6:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %1, implicit $exec
    S_NOP 0
    %7:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %2, 0, 0, 0, implicit $mode, implicit $exec
    %8:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %7, 0, 0, 0, implicit $mode, implicit $exec
    %9:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %8, 0, 0, 0, implicit $mode, implicit $exec
    %10:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %9, 0, 0, 0, implicit $mode, implicit $exec
    %11:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %10, 0, 0, 0, implicit $mode, implicit $exec
    %12:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    %13:vgpr_32 = nsw V_MUL_LO_U32_e64 %12, %12, implicit $exec
    GLOBAL_STORE_DWORD_SADDR %1, %13, %0, 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    S_ENDPGM 0, implicit %5, implicit %6, implicit %11
...

---
name: sched_group_barrier_1_VMEM_READ_1_VALU_5_MFMA_1_VMEM_READ_3_VALU_2_VMEM_WRITE
tracksRegLiveness: true
body: |
  bb.0:
    ; CHECK-LABEL: name: sched_group_barrier_1_VMEM_READ_1_VALU_5_MFMA_1_VMEM_READ_3_VALU_2_VMEM_WRITE
    ; CHECK: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
    ; CHECK-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; CHECK-NEXT: [[DEF2:%[0-9]+]]:areg_128 = IMPLICIT_DEF
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF2]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_1:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_2:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_3:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_4:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_3]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; CHECK-NEXT: S_NOP 0
    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_2:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_3:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_3]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 32, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 2, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 8, 5, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 32, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 2, 3, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 64, 2, 0
    ; CHECK-NEXT: S_ENDPGM 0, implicit [[V_MUL_LO_U32_e64_1]], implicit [[V_MUL_LO_U32_e64_2]], implicit [[V_MFMA_F32_4X4X1F32_e64_4]]
    ;
    ; EXACT-LABEL: name: sched_group_barrier_1_VMEM_READ_1_VALU_5_MFMA_1_VMEM_READ_3_VALU_2_VMEM_WRITE
    ; EXACT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
    ; EXACT-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
    ; EXACT-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; EXACT-NEXT: [[DEF2:%[0-9]+]]:areg_128 = IMPLICIT_DEF
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF2]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_1:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_2:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_3:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_4:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_3]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; EXACT-NEXT: S_NOP 0
    ; EXACT-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_2:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_3:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
    ; EXACT-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_3]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 32, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 2, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 8, 5, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 32, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 2, 3, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 64, 2, 0
    ; EXACT-NEXT: S_ENDPGM 0, implicit [[V_MUL_LO_U32_e64_1]], implicit [[V_MUL_LO_U32_e64_2]], implicit [[V_MFMA_F32_4X4X1F32_e64_4]]
    %0:sreg_64 = IMPLICIT_DEF
    %1:vgpr_32 = IMPLICIT_DEF
    %2:areg_128 = IMPLICIT_DEF
    %3:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    %4:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %3, implicit $exec
    GLOBAL_STORE_DWORD_SADDR %1, %4, %0, 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    %5:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %1, implicit $exec
    %6:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %1, implicit $exec
    S_NOP 0
    %7:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %2, 0, 0, 0, implicit $mode, implicit $exec
    %8:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %7, 0, 0, 0, implicit $mode, implicit $exec
    %9:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %8, 0, 0, 0, implicit $mode, implicit $exec
    %10:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %9, 0, 0, 0, implicit $mode, implicit $exec
    %11:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %10, 0, 0, 0, implicit $mode, implicit $exec
    %12:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    %13:vgpr_32 = nsw V_MUL_LO_U32_e64 %12, %12, implicit $exec
    GLOBAL_STORE_DWORD_SADDR %1, %13, %0, 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; 1 VMEM_READ
    SCHED_GROUP_BARRIER 32, 1, 0
    ; 1 VALU
    SCHED_GROUP_BARRIER 2, 1, 0
    ; 5 MFMA
    SCHED_GROUP_BARRIER 8, 5, 0
    ; 1 VMEM_READ
    SCHED_GROUP_BARRIER 32, 1, 0
    ; 3 VALU
    SCHED_GROUP_BARRIER 2, 3, 0
    ; 2 VMEM_WRITE
    SCHED_GROUP_BARRIER 64, 2, 0
    S_ENDPGM 0, implicit %5, implicit %6, implicit %11
...

---
name: sched_group_barrier_2_VMEM_1000_ALU_5_MFMA_2_VMEM_WRITE
tracksRegLiveness: true
body: |
  bb.0:
    ; CHECK-LABEL: name: sched_group_barrier_2_VMEM_1000_ALU_5_MFMA_2_VMEM_WRITE
    ; CHECK: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
    ; CHECK-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; CHECK-NEXT: S_NOP 0
    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; CHECK-NEXT: [[DEF2:%[0-9]+]]:areg_128 = IMPLICIT_DEF
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF2]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_1:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_2:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_2:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_3:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_3:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_4:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_3]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_3]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 16, 2, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 1, 10, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 8, 5, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 64, 2, 0
    ; CHECK-NEXT: S_ENDPGM 0, implicit [[V_MUL_LO_U32_e64_1]], implicit [[V_MUL_LO_U32_e64_2]], implicit [[V_MFMA_F32_4X4X1F32_e64_4]]
    ;
    ; EXACT-LABEL: name: sched_group_barrier_2_VMEM_1000_ALU_5_MFMA_2_VMEM_WRITE
    ; EXACT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
    ; EXACT-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
    ; EXACT-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
    ; EXACT-NEXT: [[DEF2:%[0-9]+]]:areg_128 = IMPLICIT_DEF
    ; EXACT-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; EXACT-NEXT: S_NOP 0
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF2]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_1:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_2:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_2:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_3:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_3:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_4:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_3]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_3]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 16, 2, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 1, 10, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 8, 5, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 64, 2, 0
    ; EXACT-NEXT: S_ENDPGM 0, implicit [[V_MUL_LO_U32_e64_1]], implicit [[V_MUL_LO_U32_e64_2]], implicit [[V_MFMA_F32_4X4X1F32_e64_4]]
    %0:sreg_64 = IMPLICIT_DEF
    %1:vgpr_32 = IMPLICIT_DEF
    %2:areg_128 = IMPLICIT_DEF
    %3:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    %4:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %3, implicit $exec
    GLOBAL_STORE_DWORD_SADDR %1, %4, %0, 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    %5:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %1, implicit $exec
    %6:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %1, implicit $exec
    S_NOP 0
    %7:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %2, 0, 0, 0, implicit $mode, implicit $exec
    %8:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %7, 0, 0, 0, implicit $mode, implicit $exec
    %9:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %8, 0, 0, 0, implicit $mode, implicit $exec
    %10:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %9, 0, 0, 0, implicit $mode, implicit $exec
    %11:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %10, 0, 0, 0, implicit $mode, implicit $exec
    %12:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    %13:vgpr_32 = nsw V_MUL_LO_U32_e64 %12, %12, implicit $exec
    GLOBAL_STORE_DWORD_SADDR %1, %13, %0, 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; 2 VMEM
    SCHED_GROUP_BARRIER 16, 2, 0
    ; 10 ALU
    SCHED_GROUP_BARRIER 1, 10, 0
    ; 5 MFMA
    SCHED_GROUP_BARRIER 8, 5, 0
    ; 2 VMEM_WRITE
    SCHED_GROUP_BARRIER 64, 2, 0
    S_ENDPGM 0, implicit %5, implicit %6, implicit %11
...

---
name: sched_group_barrier_MFMA_VALU_and_SALU_alternating
tracksRegLiveness: true
body: |
  bb.0:
    ; CHECK-LABEL: name: sched_group_barrier_MFMA_VALU_and_SALU_alternating
    ; CHECK: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
    ; CHECK-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; CHECK-NEXT: S_NOP 0
    ; CHECK-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; CHECK-NEXT: [[DEF2:%[0-9]+]]:areg_128 = IMPLICIT_DEF
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF2]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_1:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_2:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_2:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_3:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MFMA_F32_4X4X1F32_e64_4:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_3]], 0, 0, 0, implicit $mode, implicit $exec
    ; CHECK-NEXT: [[V_MUL_LO_U32_e64_3:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
    ; CHECK-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_3]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 16, 2, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; CHECK-NEXT: SCHED_GROUP_BARRIER 64, 2, 0
    ; CHECK-NEXT: S_ENDPGM 0, implicit [[V_MUL_LO_U32_e64_1]], implicit [[V_MUL_LO_U32_e64_2]], implicit [[V_MFMA_F32_4X4X1F32_e64_4]]
    ;
    ; EXACT-LABEL: name: sched_group_barrier_MFMA_VALU_and_SALU_alternating
    ; EXACT: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
    ; EXACT-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
    ; EXACT-NEXT: [[GLOBAL_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[GLOBAL_LOAD_DWORD_SADDR]], implicit $exec
    ; EXACT-NEXT: [[DEF2:%[0-9]+]]:areg_128 = IMPLICIT_DEF
    ; EXACT-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_]], [[DEF]], 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF2]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_1:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_1:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_2:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_1]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_2:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR]], [[DEF1]], implicit $exec
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_3:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_2]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: S_NOP 0
    ; EXACT-NEXT: [[GLOBAL_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR [[DEF]], [[DEF1]], 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    ; EXACT-NEXT: [[V_MFMA_F32_4X4X1F32_e64_4:%[0-9]+]]:areg_128 = V_MFMA_F32_4X4X1F32_e64 [[DEF1]], [[GLOBAL_LOAD_DWORD_SADDR]], [[V_MFMA_F32_4X4X1F32_e64_3]], 0, 0, 0, implicit $mode, implicit $exec
    ; EXACT-NEXT: [[V_MUL_LO_U32_e64_3:%[0-9]+]]:vgpr_32 = nsw V_MUL_LO_U32_e64 [[GLOBAL_LOAD_DWORD_SADDR1]], [[GLOBAL_LOAD_DWORD_SADDR1]], implicit $exec
    ; EXACT-NEXT: GLOBAL_STORE_DWORD_SADDR [[DEF1]], [[V_MUL_LO_U32_e64_3]], [[DEF]], 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 16, 2, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 8, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 6, 1, 0
    ; EXACT-NEXT: SCHED_GROUP_BARRIER 64, 2, 0
    ; EXACT-NEXT: S_ENDPGM 0, implicit [[V_MUL_LO_U32_e64_1]], implicit [[V_MUL_LO_U32_e64_2]], implicit [[V_MFMA_F32_4X4X1F32_e64_4]]
    %0:sreg_64 = IMPLICIT_DEF
    %1:vgpr_32 = IMPLICIT_DEF
    %2:areg_128 = IMPLICIT_DEF
    %3:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 0, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    %4:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %3, implicit $exec
    GLOBAL_STORE_DWORD_SADDR %1, %4, %0, 0, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    %5:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %1, implicit $exec
    %6:vgpr_32 = nsw V_MUL_LO_U32_e64 %3, %1, implicit $exec
    S_NOP 0
    %7:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %2, 0, 0, 0, implicit $mode, implicit $exec
    %8:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %7, 0, 0, 0, implicit $mode, implicit $exec
    %9:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %8, 0, 0, 0, implicit $mode, implicit $exec
    %10:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %9, 0, 0, 0, implicit $mode, implicit $exec
    %11:areg_128 = V_MFMA_F32_4X4X1F32_e64 %1, %3, %10, 0, 0, 0, implicit $mode, implicit $exec
    %12:vgpr_32 = GLOBAL_LOAD_DWORD_SADDR %0, %1, 512, 0, implicit $exec :: (load (s32) from %ir.in, !alias.scope !0, addrspace 1)
    %13:vgpr_32 = nsw V_MUL_LO_U32_e64 %12, %12, implicit $exec
    GLOBAL_STORE_DWORD_SADDR %1, %13, %0, 512, 0, implicit $exec :: (store (s32) into %ir.out, !noalias !0, addrspace 1)
    ; 2 VMEM
    SCHED_GROUP_BARRIER 16, 2, 0
    ; 1 VALU+SALU
    SCHED_GROUP_BARRIER 8, 1, 0
    ; 1 MFMA
    SCHED_GROUP_BARRIER 6, 1, 0
    ; 1 VALU+SALU
    SCHED_GROUP_BARRIER 8, 1, 0
    ; 1 MFMA
    SCHED_GROUP_BARRIER 6, 1, 0
    ; 1 VALU+SALU
    SCHED_GROUP_BARRIER 8, 1, 0
    ; 1 MFMA
    SCHED_GROUP_BARRIER 6, 1, 0
    ; 1 VALU+SALU
    SCHED_GROUP_BARRIER 8, 1, 0
    ; 1 MFMA
    SCHED_GROUP_BARRIER 6, 1, 0
    ; 1 VALU+SALU
    SCHED_GROUP_BARRIER 8, 1, 0
    ; 1 MFMA
    SCHED_GROUP_BARRIER 6, 1, 0
    ; 2 VMEM_WRITE
    SCHED_GROUP_BARRIER 64, 2, 0
    S_ENDPGM 0, implicit %5, implicit %6, implicit %11
...