mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
91525f438c
This reverts r319889. Unfortunately, wrapping flags are not a part of SCEV's identity (they do not participate in computing a hash value or in equality comparisons) and in fact they could be assigned after the fact w/o rebuilding a SCEV. Grep for const_cast's to see quite a few of examples, apparently all for AddRec's at the moment. So, if 2 expressions get built in 2 slightly different ways: one with flags set in the beginning, the other with the flags attached later on, we may end up with 2 expressions which are exactly the same but have their operands swapped in one of the commutative N-ary expressions, and at least one of them will have "sorted by complexity" invariant broken. 2 identical SCEV's won't compare equal by pointer comparison as they are supposed to. A real-world reproducer is added as a regression test: the issue described causes 2 identical SCEV expressions to have different order of operands and therefore compare not equal, which in its turn prevents LoadStoreVectorizer from vectorizing a pair of consecutive loads. On a larger example (the source of the test attached, which is a bugpoint) I have seen even weirder behavior: adding a constant to an existing SCEV changes the order of the existing terms, for instance, getAddExpr(1, ((A * B) + (C * D))) returns (1 + (C * D) + (A * B)). Differential Revision: https://reviews.llvm.org/D40645 llvm-svn: 340777
111 lines
4.0 KiB
LLVM
111 lines
4.0 KiB
LLVM
; RUN: opt -S -verify-loop-info -irce < %s | FileCheck %s
|
|
; RUN: opt -S -verify-loop-info -passes='require<branch-prob>,loop(irce)' < %s | FileCheck %s
|
|
|
|
define void @f_0(i32 *%arr, i32 *%a_len_ptr, i32 %n, i1* %cond_buf) {
|
|
; CHECK-LABEL: @f_0(
|
|
|
|
; CHECK: loop.preheader:
|
|
; CHECK: [[not_n:[^ ]+]] = sub i32 -1, %n
|
|
; CHECK: [[not_safe_range_end:[^ ]+]] = sub i32 3, %len
|
|
; CHECK: [[not_exit_main_loop_at_hiclamp_cmp:[^ ]+]] = icmp sgt i32 [[not_n]], [[not_safe_range_end]]
|
|
; CHECK: [[not_exit_main_loop_at_hiclamp:[^ ]+]] = select i1 [[not_exit_main_loop_at_hiclamp_cmp]], i32 [[not_n]], i32 [[not_safe_range_end]]
|
|
; CHECK: [[exit_main_loop_at_hiclamp:[^ ]+]] = sub i32 -1, [[not_exit_main_loop_at_hiclamp]]
|
|
; CHECK: [[exit_main_loop_at_loclamp_cmp:[^ ]+]] = icmp sgt i32 [[exit_main_loop_at_hiclamp]], 0
|
|
; CHECK: [[exit_main_loop_at_loclamp:[^ ]+]] = select i1 [[exit_main_loop_at_loclamp_cmp]], i32 [[exit_main_loop_at_hiclamp]], i32 0
|
|
; CHECK: [[enter_main_loop:[^ ]+]] = icmp slt i32 0, [[exit_main_loop_at_loclamp]]
|
|
; CHECK: br i1 [[enter_main_loop]], label %loop.preheader2, label %main.pseudo.exit
|
|
|
|
; CHECK: loop.preheader2:
|
|
; CHECK: br label %loop
|
|
|
|
entry:
|
|
%len = load i32, i32* %a_len_ptr, !range !0
|
|
%first.itr.check = icmp sgt i32 %n, 0
|
|
br i1 %first.itr.check, label %loop, label %exit
|
|
|
|
loop:
|
|
%idx = phi i32 [ 0, %entry ] , [ %idx.next, %in.bounds ]
|
|
%idx.next = add i32 %idx, 1
|
|
%idx.for.abc = add i32 %idx, 4
|
|
%abc.actual = icmp slt i32 %idx.for.abc, %len
|
|
%cond = load volatile i1, i1* %cond_buf
|
|
%abc = and i1 %cond, %abc.actual
|
|
br i1 %abc, label %in.bounds, label %out.of.bounds, !prof !1
|
|
|
|
; CHECK: loop:
|
|
; CHECK: %cond = load volatile i1, i1* %cond_buf
|
|
; CHECK: %abc = and i1 %cond, true
|
|
; CHECK: br i1 %abc, label %in.bounds, label %out.of.bounds.loopexit3, !prof !1
|
|
|
|
; CHECK: out.of.bounds.loopexit:
|
|
; CHECK: br label %out.of.bounds
|
|
|
|
in.bounds:
|
|
%addr = getelementptr i32, i32* %arr, i32 %idx.for.abc
|
|
store i32 0, i32* %addr
|
|
%next = icmp slt i32 %idx.next, %n
|
|
br i1 %next, label %loop, label %exit
|
|
|
|
out.of.bounds:
|
|
ret void
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
define void @f_1(
|
|
i32* %arr_a, i32* %a_len_ptr, i32* %arr_b, i32* %b_len_ptr, i32 %n) {
|
|
; CHECK-LABEL: @f_1(
|
|
|
|
; CHECK: loop.preheader:
|
|
; CHECK: [[not_len_b:[^ ]+]] = sub i32 -1, %len.b
|
|
; CHECK: [[not_len_a:[^ ]+]] = sub i32 -1, %len.a
|
|
; CHECK: [[smax_not_len_cond:[^ ]+]] = icmp sgt i32 [[not_len_b]], [[not_len_a]]
|
|
; CHECK: [[smax_not_len:[^ ]+]] = select i1 [[smax_not_len_cond]], i32 [[not_len_b]], i32 [[not_len_a]]
|
|
; CHECK: [[not_n:[^ ]+]] = sub i32 -1, %n
|
|
; CHECK: [[not_upper_limit_cond_loclamp:[^ ]+]] = icmp sgt i32 [[smax_not_len]], [[not_n]]
|
|
; CHECK: [[not_upper_limit_loclamp:[^ ]+]] = select i1 [[not_upper_limit_cond_loclamp]], i32 [[smax_not_len]], i32 [[not_n]]
|
|
; CHECK: [[upper_limit_loclamp:[^ ]+]] = sub i32 -1, [[not_upper_limit_loclamp]]
|
|
; CHECK: [[upper_limit_cmp:[^ ]+]] = icmp sgt i32 [[upper_limit_loclamp]], 0
|
|
; CHECK: [[upper_limit:[^ ]+]] = select i1 [[upper_limit_cmp]], i32 [[upper_limit_loclamp]], i32 0
|
|
|
|
entry:
|
|
%len.a = load i32, i32* %a_len_ptr, !range !0
|
|
%len.b = load i32, i32* %b_len_ptr, !range !0
|
|
%first.itr.check = icmp sgt i32 %n, 0
|
|
br i1 %first.itr.check, label %loop, label %exit
|
|
|
|
loop:
|
|
%idx = phi i32 [ 0, %entry ] , [ %idx.next, %in.bounds ]
|
|
%idx.next = add i32 %idx, 1
|
|
%abc.a = icmp slt i32 %idx, %len.a
|
|
%abc.b = icmp slt i32 %idx, %len.b
|
|
%abc = and i1 %abc.a, %abc.b
|
|
br i1 %abc, label %in.bounds, label %out.of.bounds, !prof !1
|
|
|
|
; CHECK: loop:
|
|
; CHECK: %abc = and i1 true, true
|
|
; CHECK: br i1 %abc, label %in.bounds, label %out.of.bounds.loopexit4, !prof !1
|
|
|
|
; CHECK: out.of.bounds.loopexit:
|
|
; CHECK-NEXT: br label %out.of.bounds
|
|
|
|
|
|
in.bounds:
|
|
%addr.a = getelementptr i32, i32* %arr_a, i32 %idx
|
|
store i32 0, i32* %addr.a
|
|
%addr.b = getelementptr i32, i32* %arr_b, i32 %idx
|
|
store i32 -1, i32* %addr.b
|
|
%next = icmp slt i32 %idx.next, %n
|
|
br i1 %next, label %loop, label %exit
|
|
|
|
out.of.bounds:
|
|
ret void
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
!0 = !{i32 0, i32 2147483647}
|
|
!1 = !{!"branch_weights", i32 64, i32 4}
|