Serguei Katkov 0b5bb6923f [GuardWidening] Freeze the introduced use. Re-land.
Non-determenism is fixed.

Guard widening optimization is able to move the condition from one
guard to the previous one. As a result if the condition is poison
and orginal second guard is never executed but the first one does,
we introduce undefined behavior which was not observed in original
program.

To resolve the issue we must freeze the condition we are moving.
However optimization itself does not know how to work with freeze.
Additionally optimization is written in incremental way.
For example we have three guards
G1(base + 8 < L)
G2(base + 16 < L)
G3(base + 24 < L)

On the first step GW will combine G1 and G2 as
G1(base + 8 < L && freeze(base + 16 < L))
G2(true)
G3(base + 24 < L)

while combining G1 and G3 base appears to be different.

To keep optimization enabled after freezing the moving condition, the
freeze instruction is pushed as much as possible and later all uses
of freezed values are replaced with frozen version.

This is similar what instruction combining does but more aggressevely.
2023-03-30 10:59:01 +07:00

85 lines
3.0 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -passes='licm,guard-widening,licm' -verify-memoryssa -debug-pass-manager < %s 2>&1 | FileCheck %s
; Main point of this test is to check the scheduling -- there should be
; no analysis passes needed between LICM and LoopGuardWidening
; CHECK: LICMPass
; CHECK-NEXT: GuardWideningPass
; CHECK-NEXT: LICMPass
declare void @llvm.experimental.guard(i1,...)
define void @iter(i32 %a, i32 %b, ptr %c_p) {
; CHECK-LABEL: @iter(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[B_GW_FR:%.*]] = freeze i32 [[B:%.*]]
; CHECK-NEXT: [[COND_0:%.*]] = icmp ult i32 [[A:%.*]], 10
; CHECK-NEXT: [[COND_1:%.*]] = icmp ult i32 [[B_GW_FR]], 10
; CHECK-NEXT: [[WIDE_CHK:%.*]] = and i1 [[COND_0]], [[COND_1]]
; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[WIDE_CHK]]) [ "deopt"() ]
; CHECK-NEXT: [[CND:%.*]] = load i1, ptr [[C_P:%.*]], align 1
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: br i1 [[CND]], label [[LOOP]], label [[LEAVE_LOOPEXIT:%.*]]
; CHECK: leave.loopexit:
; CHECK-NEXT: br label [[LEAVE:%.*]]
; CHECK: leave:
; CHECK-NEXT: ret void
;
entry:
%cond_0 = icmp ult i32 %a, 10
call void (i1, ...) @llvm.experimental.guard(i1 %cond_0) [ "deopt"() ]
br label %loop
loop: ; preds = %loop.preheader, %loop
%cond_1 = icmp ult i32 %b, 10
call void (i1, ...) @llvm.experimental.guard(i1 %cond_1) [ "deopt"() ]
%cnd = load i1, ptr %c_p
br i1 %cnd, label %loop, label %leave.loopexit
leave.loopexit: ; preds = %loop
br label %leave
leave: ; preds = %leave.loopexit, %entry
ret void
}
define void @within_loop(i32 %a, i32 %b, ptr %c_p) {
; CHECK-LABEL: @within_loop(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[B_GW_FR:%.*]] = freeze i32 [[B:%.*]]
; CHECK-NEXT: [[COND_0:%.*]] = icmp ult i32 [[A:%.*]], 10
; CHECK-NEXT: [[COND_1:%.*]] = icmp ult i32 [[B_GW_FR]], 10
; CHECK-NEXT: [[WIDE_CHK:%.*]] = and i1 [[COND_0]], [[COND_1]]
; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[WIDE_CHK]]) [ "deopt"() ]
; CHECK-NEXT: [[CND:%.*]] = load i1, ptr [[C_P:%.*]], align 1
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: br i1 [[CND]], label [[LOOP]], label [[LEAVE_LOOPEXIT:%.*]]
; CHECK: leave.loopexit:
; CHECK-NEXT: br label [[LEAVE:%.*]]
; CHECK: leave:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop: ; preds = %loop.preheader, %loop
%cond_0 = icmp ult i32 %a, 10
call void (i1, ...) @llvm.experimental.guard(i1 %cond_0) [ "deopt"() ]
%cond_1 = icmp ult i32 %b, 10
call void (i1, ...) @llvm.experimental.guard(i1 %cond_1) [ "deopt"() ]
%cnd = load i1, ptr %c_p
br i1 %cnd, label %loop, label %leave.loopexit
leave.loopexit: ; preds = %loop
br label %leave
leave: ; preds = %leave.loopexit, %entry
ret void
}