maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopPredication/predicate-exits.ll

1094 lines
47 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -loop-predication -S | FileCheck %s
declare void @prevent_merging()
; Base case - with side effects in loop
define i32 @test1(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
; CHECK-LABEL: @test1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1)
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP3]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %n
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded ]
ret i32 %result
}
define i32 @test_non_canonical(i32* %array, i32 %length, i1 %cond_0) {
; CHECK-LABEL: @test_non_canonical(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[LENGTH:%.*]], i32 1)
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH]], i32 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP3]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[LENGTH]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %length
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded ]
ret i32 %result
}
define i32 @test_two_range_checks(i32* %array, i32 %length.1, i32 %length.2, i32 %n, i1 %cond_0) {
; CHECK-LABEL: @test_two_range_checks(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH_2:%.*]], i32 [[LENGTH_1:%.*]])
; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1)
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1
; CHECK-NEXT: [[UMIN1:%.*]] = call i32 @llvm.umin.i32(i32 [[UMIN]], i32 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH_1]], [[UMIN1]]
; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]]
; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt i32 [[LENGTH_2]], [[UMIN1]]
; CHECK-NEXT: [[TMP5:%.*]] = freeze i1 [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = and i1 [[TMP5]], [[TMP3]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP6]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH_1]]
; CHECK-NEXT: br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[WITHIN_BOUNDS2:%.*]] = icmp ult i32 [[I]], [[LENGTH_2]]
; CHECK-NEXT: br i1 true, label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0
; CHECK: deopt3:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET3]]
; CHECK: guarded2:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length.1
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%within.bounds2 = icmp ult i32 %i, %length.2
br i1 %within.bounds2, label %guarded2, label %deopt3, !prof !0
deopt3:
call void @unknown()
%deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret3
guarded2:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %n
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded2 ]
ret i32 %result
}
@G = external global i32
define i32 @test_unanalyzeable_exit(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
; CHECK-LABEL: @test_unanalyzeable_exit(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[VOL:%.*]] = load volatile i32, i32* @G, align 4
; CHECK-NEXT: [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0
; CHECK-NEXT: br i1 [[UNKNOWN]], label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0
; CHECK: deopt3:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET3]]
; CHECK: guarded2:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N:%.*]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ]
call void @unknown()
%vol = load volatile i32, i32* @G
%unknown = icmp eq i32 %vol, 0
br i1 %unknown, label %guarded2, label %deopt3, !prof !0
deopt3:
call void @unknown()
%deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret3
guarded2:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %n
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded2 ]
ret i32 %result
}
define i32 @test_unanalyzeable_exit2(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
; CHECK-LABEL: @test_unanalyzeable_exit2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1)
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP3]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
; CHECK-NEXT: br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[VOL:%.*]] = load volatile i32, i32* @G, align 4
; CHECK-NEXT: [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0
; CHECK-NEXT: br i1 [[UNKNOWN]], label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0
; CHECK: deopt3:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET3]]
; CHECK: guarded2:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%vol = load volatile i32, i32* @G
%unknown = icmp eq i32 %vol, 0
br i1 %unknown, label %guarded2, label %deopt3, !prof !0
deopt3:
call void @unknown()
%deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret3
guarded2:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %n
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded2 ]
ret i32 %result
}
define i32 @test_unanalyzeable_latch(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
; CHECK-LABEL: @test_unanalyzeable_latch(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH:%.*]]
; CHECK-NEXT: br i1 [[WITHIN_BOUNDS]], label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[VOL:%.*]] = load volatile i32, i32* @G, align 4
; CHECK-NEXT: [[UNKNOWN:%.*]] = icmp eq i32 [[VOL]], 0
; CHECK-NEXT: br i1 [[UNKNOWN]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%vol = load volatile i32, i32* @G
%unknown = icmp eq i32 %vol, 0
br i1 %unknown, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded ]
ret i32 %result
}
define i32 @provably_taken(i32* %array, i1 %cond_0) {
; CHECK-LABEL: @provably_taken(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[TMP0:%.*]] = freeze i1 false
; CHECK-NEXT: [[TMP1:%.*]] = and i1 [[TMP0]], [[COND_0:%.*]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP1]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], 198
; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], 200
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, 198
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, 200
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded ]
ret i32 %result
}
define i32 @provably_not_taken(i32* %array, i1 %cond_0) {
; CHECK-LABEL: @provably_not_taken(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[TMP0:%.*]] = freeze i1 true
; CHECK-NEXT: [[TMP1:%.*]] = and i1 [[TMP0]], [[COND_0:%.*]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP1]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], 205
; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], 200
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, 205
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, 200
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded ]
ret i32 %result
}
;; Unswitch likes to produce some ugly exit blocks without simplifications
;; being applied. Make sure we can handle that form.
define i32 @unswitch_exit_form(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
; CHECK-LABEL: @unswitch_exit_form(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1)
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP3]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt.loopexit:
; CHECK-NEXT: br label [[DEOPT]]
; CHECK: deopt:
; CHECK-NEXT: [[PHI:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ 1, [[DEOPT_LOOPEXIT:%.*]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: br label [[ACTUAL_DEOPT:%.*]]
; CHECK: actual_deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"(i32 [[PHI]]) ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT_LOOPEXIT]], !prof !0
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
;; This is written to look like an unsimplified loop exit after unswitch
;; (i.e. phis, merge, and branch to actual block)
%phi = phi i32 [0, %entry], [1, %loop]
call void @unknown() ;; it's okay to skip possible throws
br label %actual_deopt
actual_deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"(i32 %phi) ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt, !prof !0
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %n
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded ]
ret i32 %result
}
define i32 @swapped_wb(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
; CHECK-LABEL: @swapped_wb(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1)
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[WIDENABLE_COND]], [[TMP3]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %widenable_cond, %cond_0
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %n
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded ]
ret i32 %result
}
define i32 @trivial_wb(i32* %array, i32 %length, i32 %n) {
; CHECK-LABEL: @trivial_wb(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1)
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]]
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[TMP3]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
; CHECK-NEXT: br i1 true, label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
br i1 %widenable_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %n
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded ]
ret i32 %result
}
; TODO: Non-latch exits can still be predicated
; This is currently prevented by an overly restrictive profitability check.
define i32 @todo_unconditional_latch(i32* %array, i32 %length, i1 %cond_0) {
; CHECK-LABEL: @todo_unconditional_latch(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[COND_0:%.*]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH:%.*]]
; CHECK-NEXT: br i1 [[WITHIN_BOUNDS]], label [[GUARDED]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: br label [[LOOP]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
br label %loop
}
; If we have a stray widenable branch in the loop, we should still be able to
; run. This can happen when unswitching's cost model avoids unswitching some
; branches.
define i32 @wb_in_loop(i32* %array, i32 %length, i32 %n, i1 %cond_0) {
; CHECK-LABEL: @wb_in_loop(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[WC2:%.*]] = call i1 @llvm.experimental.widenable.condition()
; CHECK-NEXT: [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[N:%.*]], i32 1)
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[UMAX]], -1
; CHECK-NEXT: [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[LENGTH:%.*]], i32 [[TMP0]])
; CHECK-NEXT: [[TMP1:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
; CHECK-NEXT: [[TMP2:%.*]] = freeze i1 [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = and i1 [[TMP2]], [[COND_0:%.*]]
; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt i32 [[LENGTH]], [[UMIN]]
; CHECK-NEXT: [[TMP5:%.*]] = freeze i1 [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = and i1 [[TMP5]], [[TMP3]]
; CHECK-NEXT: [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[TMP6]], [[WIDENABLE_COND]]
; CHECK-NEXT: br i1 [[EXIPLICIT_GUARD_COND]], label [[LOOP_PREHEADER:%.*]], label [[DEOPT:%.*]], !prof !0
; CHECK: deopt:
; CHECK-NEXT: [[DEOPTRET:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[LOOP_ACC:%.*]] = phi i32 [ [[LOOP_ACC_NEXT:%.*]], [[GUARDED2:%.*]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[I_NEXT:%.*]], [[GUARDED2]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
; CHECK-NEXT: br i1 true, label [[GUARDED:%.*]], label [[DEOPT2:%.*]], !prof !0
; CHECK: deopt2:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET2:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET2]]
; CHECK: guarded:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[WITHIN_BOUNDS2:%.*]] = icmp ult i32 [[I]], [[LENGTH]]
; CHECK-NEXT: [[WB_COND:%.*]] = and i1 [[WITHIN_BOUNDS2]], true
; CHECK-NEXT: br i1 true, label [[GUARDED2]], label [[DEOPT3:%.*]], !prof !0
; CHECK: deopt3:
; CHECK-NEXT: call void @unknown()
; CHECK-NEXT: [[DEOPTRET3:%.*]] = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
; CHECK-NEXT: ret i32 [[DEOPTRET3]]
; CHECK: guarded2:
; CHECK-NEXT: [[I_I64:%.*]] = zext i32 [[I]] to i64
; CHECK-NEXT: [[ARRAY_I_PTR:%.*]] = getelementptr inbounds i32, i32* [[ARRAY:%.*]], i64 [[I_I64]]
; CHECK-NEXT: [[ARRAY_I:%.*]] = load i32, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: store i32 0, i32* [[ARRAY_I_PTR]], align 4
; CHECK-NEXT: [[LOOP_ACC_NEXT]] = add i32 [[LOOP_ACC]], [[ARRAY_I]]
; CHECK-NEXT: [[I_NEXT]] = add nuw i32 [[I]], 1
; CHECK-NEXT: [[CONTINUE:%.*]] = icmp ult i32 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[CONTINUE]], label [[LOOP]], label [[EXIT:%.*]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ [[LOOP_ACC_NEXT]], [[GUARDED2]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%wc2 = call i1 @llvm.experimental.widenable.condition()
%exiplicit_guard_cond = and i1 %cond_0, %widenable_cond
br i1 %exiplicit_guard_cond, label %loop.preheader, label %deopt, !prof !0
deopt:
%deoptret = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret
loop.preheader:
br label %loop
loop:
%loop.acc = phi i32 [ %loop.acc.next, %guarded2 ], [ 0, %loop.preheader ]
%i = phi i32 [ %i.next, %guarded2 ], [ 0, %loop.preheader ]
call void @unknown()
%within.bounds = icmp ult i32 %i, %length
br i1 %within.bounds, label %guarded, label %deopt2, !prof !0
deopt2:
call void @unknown()
%deoptret2 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret2
guarded:
call void @unknown()
%within.bounds2 = icmp ult i32 %i, %length
%wb_cond = and i1 %within.bounds2, %wc2
br i1 %wb_cond, label %guarded2, label %deopt3, !prof !0
deopt3:
call void @unknown()
%deoptret3 = call i32 (...) @llvm.experimental.deoptimize.i32() [ "deopt"() ]
ret i32 %deoptret3
guarded2:
%i.i64 = zext i32 %i to i64
%array.i.ptr = getelementptr inbounds i32, i32* %array, i64 %i.i64
%array.i = load i32, i32* %array.i.ptr, align 4
store i32 0, i32* %array.i.ptr
%loop.acc.next = add i32 %loop.acc, %array.i
%i.next = add nuw i32 %i, 1
%continue = icmp ult i32 %i.next, %n
br i1 %continue, label %loop, label %exit
exit:
%result = phi i32 [ %loop.acc.next, %guarded2 ]
ret i32 %result
}
declare void @unknown()
declare i1 @llvm.experimental.widenable.condition()
declare i32 @llvm.experimental.deoptimize.i32(...)
!0 = !{!"branch_weights", i32 1048576, i32 1}
!1 = !{i32 1, i32 -2147483648}
!2 = !{i32 0, i32 50}
Reference in New Issue View Git Blame Copy Permalink