llvm/test/Transforms/IndVarSimplify/lftr-multi-exit.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=indvars -S | FileCheck %s
; This is a collection of tests specifically for LFTR of multiple exit loops.
; The actual LFTR performed is trivial so as to focus on the loop structure
; aspects.

; Provide legal integer types.
target datalayout = "n8:16:32:64"

@A = external global i32

define void @analyzeable_early_exit(i32 %n) {
; CHECK-LABEL: @analyzeable_early_exit(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT:    store i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND1:%.*]] = icmp ne i32 [[IV_NEXT]], 1000
; CHECK-NEXT:    br i1 [[EXITCOND1]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  br i1 %earlycnd, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  store i32 %iv, ptr @A
  %c = icmp ult i32 %iv.next, 1000
  br i1 %c, label %loop, label %exit

exit:
  ret void
}

define void @unanalyzeable_early_exit() {
; CHECK-LABEL: @unanalyzeable_early_exit(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[VOL:%.*]] = load volatile i32, ptr @A, align 4
; CHECK-NEXT:    [[EARLYCND:%.*]] = icmp ne i32 [[VOL]], 0
; CHECK-NEXT:    br i1 [[EARLYCND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT:    store i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV_NEXT]], 1000
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %vol = load volatile i32, ptr @A
  %earlycnd = icmp ne i32 %vol, 0
  br i1 %earlycnd, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  store i32 %iv, ptr @A
  %c = icmp ult i32 %iv.next, 1000
  br i1 %c, label %loop, label %exit

exit:
  ret void
}


define void @multiple_early_exits(i32 %n, i32 %m) {
; CHECK-LABEL: @multiple_early_exits(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[CONTINUE:%.*]], label [[EXIT:%.*]]
; CHECK:       continue:
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND1:%.*]] = icmp ne i32 [[IV]], [[M:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND1]], label [[LATCH]], label [[EXIT]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND2:%.*]] = icmp ne i32 [[IV_NEXT]], 1000
; CHECK-NEXT:    br i1 [[EXITCOND2]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  br i1 %earlycnd, label %continue, label %exit

continue:
  store volatile i32 %iv, ptr @A
  %earlycnd2 = icmp ult i32 %iv, %m
  br i1 %earlycnd2, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  store volatile i32 %iv, ptr @A
  %c = icmp ult i32 %iv.next, 1000
  br i1 %c, label %loop, label %exit

exit:
  ret void
}

; Note: This slightly odd form is what indvars itself produces for multiple
; exits without a side effect between them.
define void @compound_early_exit(i32 %n, i32 %m) {
; CHECK-LABEL: @compound_early_exit(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[M:%.*]], i32 [[N:%.*]])
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[UMIN]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND1:%.*]] = icmp ne i32 [[IV_NEXT]], 1000
; CHECK-NEXT:    br i1 [[EXITCOND1]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  %earlycnd2 = icmp ult i32 %iv, %m
  %and = and i1 %earlycnd, %earlycnd2
  br i1 %and, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  store volatile i32 %iv, ptr @A
  %c = icmp ult i32 %iv.next, 1000
  br i1 %c, label %loop, label %exit

exit:
  ret void
}


define void @unanalyzeable_latch(i32 %n) {
; CHECK-LABEL: @unanalyzeable_latch(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
; CHECK-NEXT:    store i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[VOL:%.*]] = load volatile i32, ptr @A, align 4
; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[VOL]], 1000
; CHECK-NEXT:    br i1 [[C]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  br i1 %earlycnd, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  store i32 %iv, ptr @A
  %vol = load volatile i32, ptr @A
  %c = icmp ult i32 %vol, 1000
  br i1 %c, label %loop, label %exit

exit:
  ret void
}

define void @single_exit_no_latch(i32 %n) {
; CHECK-LABEL: @single_exit_no_latch(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
; CHECK-NEXT:    store i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    br label [[LOOP]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  br i1 %earlycnd, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  store i32 %iv, ptr @A
  br label %loop

exit:
  ret void
}

; Multiple exits which could be LFTRed, but the latch itself is not an
; exiting block.
define void @no_latch_exit(i32 %n, i32 %m) {
; CHECK-LABEL: @no_latch_exit(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[CONTINUE:%.*]], label [[EXIT:%.*]]
; CHECK:       continue:
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND1:%.*]] = icmp ne i32 [[IV]], [[M:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND1]], label [[LATCH]], label [[EXIT]]
; CHECK:       latch:
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
; CHECK-NEXT:    br label [[LOOP]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  br i1 %earlycnd, label %continue, label %exit

continue:
  store volatile i32 %iv, ptr @A
  %earlycnd2 = icmp ult i32 %iv, %m
  br i1 %earlycnd2, label %latch, label %exit

latch:
  store volatile i32 %iv, ptr @A
  %iv.next = add i32 %iv, 1
  br label %loop

exit:
  ret void
}

;; Show the value of multiple exit LFTR (being able to eliminate all but
;; one IV when exit tests involve multiple IVs).
define void @combine_ivs(i32 %n) {
; CHECK-LABEL: @combine_ivs(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND1:%.*]] = icmp ne i32 [[IV_NEXT]], 999
; CHECK-NEXT:    br i1 [[EXITCOND1]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %iv2 = phi i32 [ 1, %entry], [ %iv2.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  br i1 %earlycnd, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  %iv2.next = add i32 %iv2, 1
  store volatile i32 %iv, ptr @A
  %c = icmp ult i32 %iv2.next, 1000
  br i1 %c, label %loop, label %exit

exit:
  ret void
}

; We can remove the decrementing IV entirely
define void @combine_ivs2(i32 %n) {
; CHECK-LABEL: @combine_ivs2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND1:%.*]] = icmp ne i32 [[IV_NEXT]], 1000
; CHECK-NEXT:    br i1 [[EXITCOND1]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %iv2 = phi i32 [ 1000, %entry], [ %iv2.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  br i1 %earlycnd, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  %iv2.next = sub i32 %iv2, 1
  store volatile i32 %iv, ptr @A
  %c = icmp ugt i32 %iv2.next, 0
  br i1 %c, label %loop, label %exit

exit:
  ret void
}

; An example where we can eliminate an f(i) computation entirely
; from a multiple exit loop with LFTR.
define void @simplify_exit_test(i32 %n) {
; CHECK-LABEL: @simplify_exit_test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV]], [[N:%.*]]
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[EXITCOND1:%.*]] = icmp ne i32 [[IV_NEXT]], 65
; CHECK-NEXT:    br i1 [[EXITCOND1]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %earlycnd = icmp ult i32 %iv, %n
  br i1 %earlycnd, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  %fx = shl i32 %iv, 4
  store volatile i32 %iv, ptr @A
  %c = icmp ult i32 %fx, 1024
  br i1 %c, label %loop, label %exit

exit:
  ret void
}


; Another example where we can remove an f(i) type computation, but this
; time in a loop w/o a statically computable exit count.
define void @simplify_exit_test2(i32 %n) {
; CHECK-LABEL: @simplify_exit_test2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LATCH:%.*]] ]
; CHECK-NEXT:    [[VOL:%.*]] = load volatile i32, ptr @A, align 4
; CHECK-NEXT:    [[EARLYCND:%.*]] = icmp ne i32 [[VOL]], 0
; CHECK-NEXT:    br i1 [[EARLYCND]], label [[LATCH]], label [[EXIT:%.*]]
; CHECK:       latch:
; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
; CHECK-NEXT:    [[FX:%.*]] = udiv i32 [[IV]], 4
; CHECK-NEXT:    store volatile i32 [[IV]], ptr @A, align 4
; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[FX]], 1024
; CHECK-NEXT:    br i1 [[C]], label [[LOOP]], label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i32 [ 0, %entry], [ %iv.next, %latch]
  %vol = load volatile i32, ptr @A
  %earlycnd = icmp ne i32 %vol, 0
  br i1 %earlycnd, label %latch, label %exit

latch:
  %iv.next = add i32 %iv, 1
  %fx = udiv i32 %iv, 4
  store volatile i32 %iv, ptr @A
  %c = icmp ult i32 %fx, 1024
  br i1 %c, label %loop, label %exit

exit:
  ret void
}

; Demonstrate a case where two nested loops share a single exiting block.
; The key point is that the exit count is *different* for the two loops, and
; thus we can't rewrite the exit for the outer one.  There are three sub-cases
; which can happen here: a) the outer loop has a backedge taken count of zero
; (for the case where we know the inner exit is known taken), b) the exit is
; known never taken (but may have an exit count outside the range of the IV)
; or c) the outer loop has an unanalyzable exit count (where we can't tell).
define void @nested(i32 %n) {
; CHECK-LABEL: @nested(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[N:%.*]], 1
; CHECK-NEXT:    br label [[OUTER:%.*]]
; CHECK:       outer:
; CHECK-NEXT:    [[IV1:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV1_NEXT:%.*]], [[OUTER_LATCH:%.*]] ]
; CHECK-NEXT:    store volatile i32 [[IV1]], ptr @A, align 4
; CHECK-NEXT:    [[IV1_NEXT]] = add nuw nsw i32 [[IV1]], 1
; CHECK-NEXT:    br label [[INNER:%.*]]
; CHECK:       inner:
; CHECK-NEXT:    [[IV2:%.*]] = phi i32 [ 0, [[OUTER]] ], [ [[IV2_NEXT:%.*]], [[INNER_LATCH:%.*]] ]
; CHECK-NEXT:    store volatile i32 [[IV2]], ptr @A, align 4
; CHECK-NEXT:    [[IV2_NEXT]] = add nuw nsw i32 [[IV2]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i32 [[IV2]], 20
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[INNER_LATCH]], label [[EXIT_LOOPEXIT:%.*]]
; CHECK:       inner_latch:
; CHECK-NEXT:    [[EXITCOND2:%.*]] = icmp ne i32 [[IV2_NEXT]], [[TMP0]]
; CHECK-NEXT:    br i1 [[EXITCOND2]], label [[INNER]], label [[OUTER_LATCH]]
; CHECK:       outer_latch:
; CHECK-NEXT:    [[EXITCOND3:%.*]] = icmp ne i32 [[IV1_NEXT]], 21
; CHECK-NEXT:    br i1 [[EXITCOND3]], label [[OUTER]], label [[EXIT_LOOPEXIT1:%.*]]
; CHECK:       exit.loopexit:
; CHECK-NEXT:    br label [[EXIT:%.*]]
; CHECK:       exit.loopexit1:
; CHECK-NEXT:    br label [[EXIT]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %outer

outer:
  %iv1 = phi i32 [ 0, %entry ], [ %iv1.next, %outer_latch ]
  store volatile i32 %iv1, ptr @A
  %iv1.next = add i32 %iv1, 1
  br label %inner

inner:
  %iv2 = phi i32 [ 0, %outer ], [ %iv2.next, %inner_latch ]
  store volatile i32 %iv2, ptr @A
  %iv2.next = add i32 %iv2, 1
  %innertest = icmp ult i32 %iv2, 20
  br i1 %innertest, label %inner_latch, label %exit

inner_latch:
  %innertestb = icmp ult i32 %iv2, %n
  br i1 %innertestb, label %inner, label %outer_latch

outer_latch:
  %outertest = icmp ult i32 %iv1, 20
  br i1 %outertest, label %outer, label %exit

exit:
  ret void
}