TheRock/compiler/amd-llvm/llvm/test/CodeGen/Hexagon/swp-loop-carried-order-dep5.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 dependencies are correctly added when two
# arrays may point to the same memory location.
#
# ```
# void f(int *a, int *b, int n) {
#   for (int i = 0; i < n; i++) {
#     a[i] += b[i];
#     b[i] += a[i];
#   }
# }
# ```
#
# Here is what each instruction does.
# SU(2): Load b[i]
# SU(3): Load a[i]
# SU(5): Store a[i]
# SU(6): Load b[i]
# SU(8): Store b[i]
#
# Note that if there is already a dependency between two instructions, we don't
# add loop-carried on between them since non-loop-carried one imposes stronger
# constraint than loop-carried one.

# CHECK:      ===== Loop Carried Edges Begin =====
# CHECK-NEXT:   Loop carried edges from SU(5)
# CHECK-NEXT:     Order
# CHECK-NEXT:       SU(2)
# CHECK-NEXT:   Loop carried edges from SU(6)
# CHECK-NEXT:     Order
# CHECK-NEXT:       SU(5)
# CHECK-NEXT:   Loop carried edges from SU(8)
# CHECK-NEXT:     Order
# CHECK-NEXT:       SU(3)
# CHECK-NEXT:       SU(5)
# CHECK-NEXT: ===== Loop Carried Edges End =====

--- |
  define dso_local void @f(ptr nocapture noundef %a, ptr nocapture noundef %b, i32 noundef %n) local_unnamed_addr {
  entry:
    %cmp12 = icmp sgt i32 %n, 0
    br i1 %cmp12, label %for.body, label %for.cond.cleanup

  for.cond.cleanup:
    ret void

  for.body:
    %lsr.iv15 = phi ptr [ %cgep17, %for.body ], [ %b, %entry ]
    %lsr.iv14 = phi ptr [ %cgep, %for.body ], [ %a, %entry ]
    %lsr.iv = phi i32 [ %lsr.iv.next, %for.body ], [ %n, %entry ]
    %0 = load i32, ptr %lsr.iv15, align 4, !tbaa !5
    %1 = load i32, ptr %lsr.iv14, align 4, !tbaa !5
    %add = add nsw i32 %1, %0
    store i32 %add, ptr %lsr.iv14, align 4, !tbaa !5
    %2 = load i32, ptr %lsr.iv15, align 4, !tbaa !5
    %add4 = add nsw i32 %2, %add
    store i32 %add4, ptr %lsr.iv15, align 4, !tbaa !5
    %lsr.iv.next = add i32 %lsr.iv, -1
    %exitcond.not = icmp eq i32 %lsr.iv.next, 0
    %cgep = getelementptr i8, ptr %lsr.iv14, i32 4
    %cgep17 = 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.3, %bb.1
    liveins: $r0, $r1, $r2
  
    %8:intregs = COPY $r2
    %7:intregs = COPY $r1
    %6:intregs = COPY $r0
    %9:predregs = C2_cmpgti %8, 0
    J2_jumpf %9, %bb.1, implicit-def $pc
  
  bb.3:
    %16:intregs = COPY %8
    J2_loop0r %bb.2, %16, implicit-def $lc0, implicit-def $sa0, implicit-def $usr
    J2_jump %bb.2, implicit-def $pc
  
  bb.1.for.cond.cleanup:
    PS_jmpret $r31, implicit-def dead $pc
  
  bb.2.for.body:
    successors: %bb.1, %bb.2
  
    %0:intregs = PHI %7, %bb.3, %5, %bb.2
    %1:intregs = PHI %6, %bb.3, %4, %bb.2
    %10:intregs = L2_loadri_io %0, 0 :: (load (s32) from %ir.lsr.iv15, !tbaa !5)
    %11:intregs = L2_loadri_io %1, 0 :: (load (s32) from %ir.lsr.iv14, !tbaa !5)
    %12:intregs = nsw A2_add killed %11, killed %10
    %4:intregs = S2_storeri_pi %1, 4, %12 :: (store (s32) into %ir.lsr.iv14, !tbaa !5)
    %13:intregs = L2_loadri_io %0, 0 :: (load (s32) from %ir.lsr.iv15, !tbaa !5)
    %14:intregs = nsw A2_add killed %13, %12
    %5:intregs = S2_storeri_pi %0, 4, killed %14 :: (store (s32) into %ir.lsr.iv15, !tbaa !5)
    ENDLOOP0 %bb.2, implicit-def $pc, implicit-def $lc0, implicit $sa0, implicit $lc0
    J2_jump %bb.1, implicit-def $pc
...