TheRock/compiler/amd-llvm/llvm/test/CodeGen/Hexagon/swp-loop-carried-order-dep4.mir

# RUN: llc -mtriple=hexagon -run-pass pipeliner -debug-only=pipeliner %s -o /dev/null 2>&1 -pipeliner-experimental-cg=true | FileCheck %s
# REQUIRES: asserts

# Test that loop carried memory dependences are computed correctly.
# The original code is as follows.
#
# ```
# void f(int *a, int n) {
#   for (int i = 0; i < n-2; i++) {
#     a[i] += a[i+10];
#     a[i+2] += i;
#   }
# }
# ```
#
# Here is what each instruction does.
# SU(2): Load a[i+10]
# SU(3): Store it to a[i]
# SU(4): Load a[i+2], add i, then store it
#
# FIXME: Currently the following dependencies are missed.
#

# CHECK:      ===== Loop Carried Edges Begin =====
# CHECK-NEXT:   Loop carried edges from SU(2)
# CHECK-NEXT:     Order
# CHECK-NEXT:       SU(3)
# CHECK-NEXT:       SU(4)
# CHECK-NEXT:   Loop carried edges from SU(4)
# CHECK-NEXT:     Order
# CHECK-NEXT:       SU(3)
# CHECK-NEXT: ===== Loop Carried Edges End =====

--- |
  define dso_local void @f(ptr nocapture noundef %a, i32 noundef %n) {
  entry:
    %cmp13 = icmp sgt i32 %n, 2
    br i1 %cmp13, label %for.body.preheader, label %for.cond.cleanup

  for.body.preheader:
    %0 = add i32 %n, -2
    br label %for.body

  for.cond.cleanup:
    ret void

  for.body:
    %lsr.iv15 = phi ptr [ %a, %for.body.preheader ], [ %cgep19, %for.body ]
    %lsr.iv = phi i32 [ %0, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
    %i.014 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
    %cgep = getelementptr i8, ptr %lsr.iv15, i32 40
    %1 = load i32, ptr %cgep, align 4, !tbaa !5
    %2 = load i32, ptr %lsr.iv15, align 4, !tbaa !5
    %add2 = add nsw i32 %2, %1
    store i32 %add2, ptr %lsr.iv15, align 4, !tbaa !5
    %cgep18 = getelementptr i8, ptr %lsr.iv15, i32 8
    %3 = load i32, ptr %cgep18, align 4, !tbaa !5
    %4 = add i32 %i.014, %3
    store i32 %4, ptr %cgep18, align 4, !tbaa !5
    %inc = add nuw nsw i32 %i.014, 1
    %lsr.iv.next = add i32 %lsr.iv, -1
    %exitcond.not = icmp eq i32 %lsr.iv.next, 0
    %cgep19 = getelementptr i8, ptr %lsr.iv15, i32 4
    br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
  }

  !5 = !{!6, !6, i64 0}
  !6 = !{!"int", !7, i64 0}
  !7 = !{!"omnipotent char", !8, i64 0}
  !8 = !{!"Simple C/C++ TBAA"}

...
---
name:            f
tracksRegLiveness: true
body:             |
  bb.0.entry:
    successors: %bb.1, %bb.2
    liveins: $r0, $r1
  
    %8:intregs = COPY $r1
    %7:intregs = COPY $r0
    %9:predregs = C2_cmpgti %8, 2
    J2_jumpf %9, %bb.2, implicit-def dead $pc
    J2_jump %bb.1, implicit-def dead $pc
  
  bb.1.for.body.preheader:
    %0:intregs = A2_addi %8, -2
    %11:intregs = A2_tfrsi 0
    %14:intregs = COPY %0
    J2_loop0r %bb.3, %14, implicit-def $lc0, implicit-def $sa0, implicit-def $usr
    J2_jump %bb.3, implicit-def dead $pc
  
  bb.2.for.cond.cleanup:
    PS_jmpret $r31, implicit-def dead $pc
  
  bb.3.for.body:
    successors: %bb.2, %bb.3
  
    %1:intregs = PHI %7, %bb.1, %6, %bb.3
    %3:intregs = PHI %11, %bb.1, %4, %bb.3
    %12:intregs = L2_loadri_io %1, 40 :: (load (s32) from %ir.cgep, !tbaa !5)
    L4_add_memopw_io %1, 0, killed %12 :: (store (s32) into %ir.lsr.iv15, !tbaa !5), (load (s32) from %ir.lsr.iv15, !tbaa !5)
    L4_add_memopw_io %1, 8, %3 :: (store (s32) into %ir.cgep18, !tbaa !5), (load (s32) from %ir.cgep18, !tbaa !5)
    %4:intregs = nuw nsw A2_addi %3, 1
    %6:intregs = A2_addi %1, 4
    ENDLOOP0 %bb.3, implicit-def $pc, implicit-def $lc0, implicit $sa0, implicit $lc0
    J2_jump %bb.2, implicit-def $pc
...