[Bug target/50182] Performance degradation from gcc 4.1 (x86_64)

["xinliangli at gmail dot com" <gcc-bugzilla at gcc dot gnu dot org>]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50182

--- Comment #24 from davidxl <xinliangli at gmail dot com> 2011-10-24 23:00:22 UTC ---
(In reply to comment #23)
> Here is the source preprocessed for gcc47. The test exhibits the 
> slowdown mentioned in comment 11.


The problem can be reproduced with a simplified test case -- basically
depending on how the result value from the inner loop is used in the outer loop
(related to casting), the inner loop code is quite different - in the slow
case, there are two redundant sign extension and a move instructions generated.

# the fast version
gcc -O3 -DFAST_VER bug.cpp

./a.out 
rv=4282167296

test         description   absolute   operations   ratio with
number                     time       per second   test0

 0 "int8_t constant add"   1.05 sec   1523.81 M     1.00

Total absolute time for int8_t constant folding: 1.05 sec

# the slow version:

gcc -O3 bug.cpp
./a.out 
rv=4282167296

test         description   absolute   operations   ratio with
number                     time       per second   test0

 0 "int8_t constant add"   1.57 sec   1019.11 M     1.00

Total absolute time for int8_t constant folding: 1.57 sec


# however, when disabling inlining of check_shifted_sum_1 in the slow case, the
runtime is recovered:

gcc -O3 -DNOINLINE bug.cpp

./a.out 
rv=4282167296

test         description   absolute   operations   ratio with
number                     time       per second   test0

 0 "int8_t constant add"   1.05 sec   1523.81 M     1.00

Total absolute time for int8_t constant folding: 1.05 sec



The inner loop body in faster case:

.L60:
    movzbl    0(%rbp,%rcx), %r9d
    addq    $1, %rcx
    cmpl    %ecx, %ebx
    leal    10(%r8,%r9), %r8d
# SUCC: 4 [91.0%]  (dfs_back,can_fallthru) 5 [9.0%] 
(fallthru,can_fallthru,loop_exit)
    jg    .L60

while for the slow case:

.L60:
    movzbl    (%r12,%rcx), %eax
    movsbl    %r8b, %r8d
    addq    $1, %rcx
    leal    10(%rax), %r9d
    movsbl    %r9b, %r9d
    addl    %r8d, %r9d
    cmpl    %ecx, %ebp
    movl    %r9d, %r8d
# SUCC: 4 [91.0%]  (dfs_back,can_fallthru) 5 [9.0%] 
(fallthru,can_fallthru,loop_exit)
    jg    .L60


The relevant source change:

#ifdef NOINLINE
#define INL __attribute__((noinline))
#else
#define INL inline
#endif

template <typename T, typename T2, typename Shifter>
INL void check_shifted_sum_1(T2 result) {
 T temp = (T)SIZE * Shifter::do_shift((T)init_value);
 if (!tolerance_equal<T>((T&)result,temp))
  printf("test %i failed\n", current_test);
}

#ifdef FAST_VER
#define TYPE u_int32_t
#else
#define TYPE int8_t
#endif


template <typename T, typename Shifter>
__attribute__((noinline)) u_int32_t test_constant(T* first, int count, const
char *label)
{
    int i;
    u_int32_t rv = 0;

    start_timer();

    for (i = 0; i < iterations; ++i) {
        T result = 0;
        for (int n = 0; n < count; ++n) {
            result += Shifter::do_shift( first[n] );
        }
        rv += result;
        check_shifted_sum_1<T, TYPE, Shifter>(result);
    }

    record_result( timer(), label );
    return rv;
}