Why does this loop produce "warning: iteration 3u invokes undefined behavior" and output more than 4 lines?
Signed integer overflow (as strictly speaking, there is no such thing as "unsigned integer overflow") means undefined behaviour. And this means anything can happen, and discussing why does it happen under the rules of C++ doesn't make sense.
C++11 draft N3337: §5.4:1
If during the evaluation of an expression, the result is not mathematically defined or not in the range of representable values for its type, the behavior is undefined. [ Note: most existing implementations of C++ ignore integer overflows. Treatment of division by zero, forming a remainder using a zero divisor, and all floating point exceptions vary among machines, and is usually adjustable by a library function. —end note ]
Your code compiled with g++ -O3 emits warning (even without -Wall)
a.cpp: In function 'int main()':
a.cpp:11:18: warning: iteration 3u invokes undefined behavior [-Waggressive-loop-optimizations]
std::cout << i*1000000000 << std::endl;
^
a.cpp:9:2: note: containing loop
for (int i = 0; i < 4; ++i)
^
The only way we can analyze what the program is doing, is by reading the generated assembly code.
Here is the full assembly listing:
.file "a.cpp"
.section .text$_ZNKSt5ctypeIcE8do_widenEc,"x"
.linkonce discard
.align 2
LCOLDB0:
LHOTB0:
.align 2
.p2align 4,,15
.globl __ZNKSt5ctypeIcE8do_widenEc
.def __ZNKSt5ctypeIcE8do_widenEc; .scl 2; .type 32; .endef
__ZNKSt5ctypeIcE8do_widenEc:
LFB860:
.cfi_startproc
movzbl 4(%esp), %eax
ret $4
.cfi_endproc
LFE860:
LCOLDE0:
LHOTE0:
.section .text.unlikely,"x"
LCOLDB1:
.text
LHOTB1:
.p2align 4,,15
.def ___tcf_0; .scl 3; .type 32; .endef
___tcf_0:
LFB1091:
.cfi_startproc
movl $__ZStL8__ioinit, %ecx
jmp __ZNSt8ios_base4InitD1Ev
.cfi_endproc
LFE1091:
.section .text.unlikely,"x"
LCOLDE1:
.text
LHOTE1:
.def ___main; .scl 2; .type 32; .endef
.section .text.unlikely,"x"
LCOLDB2:
.section .text.startup,"x"
LHOTB2:
.p2align 4,,15
.globl _main
.def _main; .scl 2; .type 32; .endef
_main:
LFB1084:
.cfi_startproc
leal 4(%esp), %ecx
.cfi_def_cfa 1, 0
andl $-16, %esp
pushl -4(%ecx)
pushl %ebp
.cfi_escape 0x10,0x5,0x2,0x75,0
movl %esp, %ebp
pushl %edi
pushl %esi
pushl %ebx
pushl %ecx
.cfi_escape 0xf,0x3,0x75,0x70,0x6
.cfi_escape 0x10,0x7,0x2,0x75,0x7c
.cfi_escape 0x10,0x6,0x2,0x75,0x78
.cfi_escape 0x10,0x3,0x2,0x75,0x74
xorl %edi, %edi
subl $24, %esp
call ___main
L4:
movl %edi, (%esp)
movl $__ZSt4cout, %ecx
call __ZNSolsEi
movl %eax, %esi
movl (%eax), %eax
subl $4, %esp
movl -12(%eax), %eax
movl 124(%esi,%eax), %ebx
testl %ebx, %ebx
je L15
cmpb $0, 28(%ebx)
je L5
movsbl 39(%ebx), %eax
L6:
movl %esi, %ecx
movl %eax, (%esp)
addl $1000000000, %edi
call __ZNSo3putEc
subl $4, %esp
movl %eax, %ecx
call __ZNSo5flushEv
jmp L4
.p2align 4,,10
L5:
movl %ebx, %ecx
call __ZNKSt5ctypeIcE13_M_widen_initEv
movl (%ebx), %eax
movl 24(%eax), %edx
movl $10, %eax
cmpl $__ZNKSt5ctypeIcE8do_widenEc, %edx
je L6
movl $10, (%esp)
movl %ebx, %ecx
call *%edx
movsbl %al, %eax
pushl %edx
jmp L6
L15:
call __ZSt16__throw_bad_castv
.cfi_endproc
LFE1084:
.section .text.unlikely,"x"
LCOLDE2:
.section .text.startup,"x"
LHOTE2:
.section .text.unlikely,"x"
LCOLDB3:
.section .text.startup,"x"
LHOTB3:
.p2align 4,,15
.def __GLOBAL__sub_I_main; .scl 3; .type 32; .endef
__GLOBAL__sub_I_main:
LFB1092:
.cfi_startproc
subl $28, %esp
.cfi_def_cfa_offset 32
movl $__ZStL8__ioinit, %ecx
call __ZNSt8ios_base4InitC1Ev
movl $___tcf_0, (%esp)
call _atexit
addl $28, %esp
.cfi_def_cfa_offset 4
ret
.cfi_endproc
LFE1092:
.section .text.unlikely,"x"
LCOLDE3:
.section .text.startup,"x"
LHOTE3:
.section .ctors,"w"
.align 4
.long __GLOBAL__sub_I_main
.lcomm __ZStL8__ioinit,1,1
.ident "GCC: (i686-posix-dwarf-rev1, Built by MinGW-W64 project) 4.9.0"
.def __ZNSt8ios_base4InitD1Ev; .scl 2; .type 32; .endef
.def __ZNSolsEi; .scl 2; .type 32; .endef
.def __ZNSo3putEc; .scl 2; .type 32; .endef
.def __ZNSo5flushEv; .scl 2; .type 32; .endef
.def __ZNKSt5ctypeIcE13_M_widen_initEv; .scl 2; .type 32; .endef
.def __ZSt16__throw_bad_castv; .scl 2; .type 32; .endef
.def __ZNSt8ios_base4InitC1Ev; .scl 2; .type 32; .endef
.def _atexit; .scl 2; .type 32; .endef
I can barely even read assembly, but even I can see the addl $1000000000, %edi line.
The resulting code looks more like
for(int i = 0; /* nothing, that is - infinite loop */; i += 1000000000)
std::cout << i << std::endl;
This comment of @T.C.:
I suspect that it's something like: (1) because every iteration with
iof any value larger than 2 has undefined behavior -> (2) we can assume thati <= 2for optimization purposes -> (3) the loop condition is always true -> (4) it's optimized away into an infinite loop.
gave me idea to compare the assembly code of the OP's code to the assembly code of the following code, with no undefined behaviour.
#include <iostream>
int main()
{
// changed the termination condition
for (int i = 0; i < 3; ++i)
std::cout << i*1000000000 << std::endl;
}
And, in fact, the correct code has termination condition.
; ...snip...
L6:
mov ecx, edi
mov DWORD PTR [esp], eax
add esi, 1000000000
call __ZNSo3putEc
sub esp, 4
mov ecx, eax
call __ZNSo5flushEv
cmp esi, -1294967296 // here it is
jne L7
lea esp, [ebp-16]
xor eax, eax
pop ecx
; ...snip...
OMG, that's completely not obvious! It's not fair! I demand trial by fire!
Deal with it, you wrote the buggy code and you should feel bad. Bear the consequences.
...or, alternatively, make proper use of better diagnostics and better debugging tools - that's what they are for:
enable all warnings
-Wallis the gcc option that enables all useful warnings with no false positives. This is a bare minimum that you should always use.- gcc has many other warning options, however, they are not enabled with
-Wallas they may warn on false positives - Visual C++ unfortunately is lagging behind with the ability to give useful warnings. At least the IDE enables some by default.
use debug flags for debugging
- for integer overflow
-ftrapvtraps the program on overflow, - Clang compiler is excellent for this:
-fcatch-undefined-behaviorcatches a lot of instances of undefined behaviour (note:"a lot of" != "all of them")
- for integer overflow
I have a spaghetti mess of a program not written by me that needs to be shipped tomorrow! HELP!!!!!!111oneone
Use gcc's -fwrapv
This option instructs the compiler to assume that signed arithmetic overflow of addition, subtraction and multiplication wraps around using twos-complement representation.
1 - this rule does not apply to "unsigned integer overflow", as §3.9.1.4 says that
Unsigned integers, declared unsigned, shall obey the laws of arithmetic modulo 2n where n is the number of bits in the value representation of that particular size of integer.
and e.g. result of UINT_MAX + 1 is mathematically defined - by the rules of arithmetic modulo 2n
Short answer, gcc specifically has documented this problem, we can see that in the gcc 4.8 release notes which says (emphasis mine going forward):
GCC now uses a more aggressive analysis to derive an upper bound for the number of iterations of loops using constraints imposed by language standards. This may cause non-conforming programs to no longer work as expected, such as SPEC CPU 2006 464.h264ref and 416.gamess. A new option, -fno-aggressive-loop-optimizations, was added to disable this aggressive analysis. In some loops that have known constant number of iterations, but undefined behavior is known to occur in the loop before reaching or during the last iteration, GCC will warn about the undefined behavior in the loop instead of deriving lower upper bound of the number of iterations for the loop. The warning can be disabled with -Wno-aggressive-loop-optimizations.
and indeed if we use -fno-aggressive-loop-optimizations the infinite loop behavior should cease and it does in all the cases I have tested.
The long answer starts with knowing that signed integer overflow is undefined behavior by looking at the draft C++ standard section 5 Expressions paragraph 4 which says:
If during the evaluation of an expression, the result is not mathematically defined or not in the range of representable values for its type, the behavior is undefined. [ Note: most existing implementations of C++ ignore integer overflows. Treatment of division by zero, forming a remainder using a zero divisor, and all floating point exceptions vary among machines, and is usually adjustable by a library function. —end note
We know that the standard says undefined behavior is unpredictable from the note that come with the definition which says:
[ Note: Undefined behavior may be expected when this International Standard omits any explicit definition of behavior or when a program uses an erroneous construct or erroneous data. Permissible undefined behavior ranges from ignoring the situation completely with unpredictable results, to behaving during translation or program execution in a documented manner characteristic of the environment (with or without the issuance of a diagnostic message), to terminating a translation or execution (with the issuance of a diagnostic message). Many erroneous program constructs do not engender undefined behavior; they are required to be diagnosed. —end note ]
But what in the world can the gcc optimizer be doing to turn this into an infinite loop? It sounds completely wacky. But thankfully gcc gives us a clue to figuring it out in the warning:
warning: iteration 3u invokes undefined behavior [-Waggressive-loop-optimizations]
std::cout << i*1000000000 << std::endl;
^
The clue is the Waggressive-loop-optimizations, what does that mean? Fortunately for us this is not the first time this optimization has broken code in this way and we are lucky because John Regehr has documented a case in the article GCC pre-4.8 Breaks Broken SPEC 2006 Benchmarks which shows the following code:
int d[16];
int SATD (void)
{
int satd = 0, dd, k;
for (dd=d[k=0]; k<16; dd=d[++k]) {
satd += (dd < 0 ? -dd : dd);
}
return satd;
}
the article says:
The undefined behavior is accessing d[16] just before exiting the loop. In C99 it is legal to create a pointer to an element one position past the end of the array, but that pointer must not be dereferenced.
and later on says:
In detail, here is what’s going on. A C compiler, upon seeing d[++k], is permitted to assume that the incremented value of k is within the array bounds, since otherwise undefined behavior occurs. For the code here, GCC can infer that k is in the range 0..15. A bit later, when GCC sees k<16, it says to itself: “Aha– that expression is always true, so we have an infinite loop.” The situation here, where the compiler uses the assumption of well-definedness to infer a useful dataflow fact,
So what the compiler must be doing in some cases is assuming since signed integer overflow is undefined behavior then i must always be less than 4 and thus we have an infinite loop.
He explains this is very similar to the infamous Linux kernel null pointer check removal where in seeing this code:
struct foo *s = ...;
int x = s->f;
if (!s) return ERROR;
gcc inferred that since s was deferenced in s->f; and since dereferencing a null pointer is undefined behavior then s must not be null and therefore optimizes away the if (!s) check on the next line.
The lesson here is that modern optimizers are very aggressive about exploiting undefined behavior and most likely will only get more aggressive. Clearly with just a few examples we can see the optimizer does things that seem completely unreasonable to a programmer but in retrospect from the optimizers perspective make sense.
tl;dr The code generates a test that integer + positive integer == negative integer. Usually the optimizer does not optimize this out, but in the specific case of std::endl being used next, the compiler does optimize this test out. I haven't figured out what's special about endl yet.
From the assembly code at -O1 and higher levels, it is clear that gcc refactors the loop to:
i = 0;
do {
cout << i << endl;
i += NUMBER;
}
while (i != NUMBER * 4)
The biggest value that works correctly is 715827882, i.e. floor(INT_MAX/3). The assembly snippet at -O1 is:
L4:
movsbl %al, %eax
movl %eax, 4(%esp)
movl $__ZSt4cout, (%esp)
call __ZNSo3putEc
movl %eax, (%esp)
call __ZNSo5flushEv
addl $715827882, %esi
cmpl $-1431655768, %esi
jne L6
// fallthrough to "return" code
Note, the -1431655768 is 4 * 715827882 in 2's complement.
Hitting -O2 optimizes that to the following:
L4:
movsbl %al, %eax
addl $715827882, %esi
movl %eax, 4(%esp)
movl $__ZSt4cout, (%esp)
call __ZNSo3putEc
movl %eax, (%esp)
call __ZNSo5flushEv
cmpl $-1431655768, %esi
jne L6
leal -8(%ebp), %esp
jne L6
// fallthrough to "return" code
So the optimization that has been made is merely that the addl was moved higher up.
If we recompile with 715827883 instead then the -O1 version is identical apart from the changed number and test value. However, -O2 then makes a change:
L4:
movsbl %al, %eax
addl $715827883, %esi
movl %eax, 4(%esp)
movl $__ZSt4cout, (%esp)
call __ZNSo3putEc
movl %eax, (%esp)
call __ZNSo5flushEv
jmp L2
Where there was cmpl $-1431655764, %esi at -O1, that line has been removed for -O2. The optimizer must have decided that adding 715827883 to %esi can never equal -1431655764.
This is pretty puzzling. Adding that to INT_MIN+1 does generate the expected result, so the optimizer must have decided that %esi can never be INT_MIN+1 and I'm not sure why it would decide that.
In the working example it seems it'd be equally valid to conclude that adding 715827882 to a number cannot equal INT_MIN + 715827882 - 2 ! (this is only possible if wraparound does actually occur), yet it does not optimize the line out in that example.
The code I was using is:
#include <iostream>
#include <cstdio>
int main()
{
for (int i = 0; i < 4; ++i)
{
//volatile int j = i*715827883;
volatile int j = i*715827882;
printf("%d\n", j);
std::endl(std::cout);
}
}
If the std::endl(std::cout) is removed then the optimization no longer occurs. In fact replacing it with std::cout.put('\n'); std::flush(std::cout); also causes the optimization to not happen, even though std::endl is inlined.
The inlining of std::endl seems to affect the earlier part of the loop structure (which I don't quite understand what it is doing but I'll post it here in case someone else does):
With original code and -O2:
L2:
movl %esi, 28(%esp)
movl 28(%esp), %eax
movl $LC0, (%esp)
movl %eax, 4(%esp)
call _printf
movl __ZSt4cout, %eax
movl -12(%eax), %eax
movl __ZSt4cout+124(%eax), %ebx
testl %ebx, %ebx
je L10
cmpb $0, 28(%ebx)
je L3
movzbl 39(%ebx), %eax
L4:
movsbl %al, %eax
addl $715827883, %esi
movl %eax, 4(%esp)
movl $__ZSt4cout, (%esp)
call __ZNSo3putEc
movl %eax, (%esp)
call __ZNSo5flushEv
jmp L2 // no test
With mymanual inlining of std::endl, -O2:
L3:
movl %ebx, 28(%esp)
movl 28(%esp), %eax
addl $715827883, %ebx
movl $LC0, (%esp)
movl %eax, 4(%esp)
call _printf
movl $10, 4(%esp)
movl $__ZSt4cout, (%esp)
call __ZNSo3putEc
movl $__ZSt4cout, (%esp)
call __ZNSo5flushEv
cmpl $-1431655764, %ebx
jne L3
xorl %eax, %eax
One difference between these two is that %esi is used in the original , and %ebx in the second version; is there any difference in semantics defined between %esi and %ebx in general? (I don't know much about x86 assembly).