[Bug tree-optimization/98694] New: GCC produces incorrect code for loops with -O3 for skylake-avx512 and icelake-server

["vsevolod.livinskij at frtk dot ru" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98694

            Bug ID: 98694
           Summary: GCC produces incorrect code for loops with -O3 for
                    skylake-avx512 and icelake-server
           Product: gcc
           Version: 11.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: vsevolod.livinskij at frtk dot ru
  Target Milestone: ---

The reproducer is a bit big, but I was not able to reduce it further.
Reproducer:

// func.cpp
#include <algorithm>

extern short var_1, var_29, var_89;
extern unsigned var_2, var_11;
extern bool var_4;
extern long var_6;
extern char var_7;
extern int var_8, var_10;
extern short arr_206[10][14][13][21][14] __attribute__((aligned));
extern int arr_257[];

long f(long l) { return 0 > l ? 0 : l; }

void test() {
  var_11 = var_6;
  for (char a = 0; a < (char)var_2; a = 6)
    for (int b = 0; b < var_2; b = ~0)
      for (int c = 0; c < 2; c = var_1)
        for (bool d = 0; d < var_4; d = 1)
          var_29 = f(~var_6);
  for (short e = 0; e < short(var_6); e = var_6) {
    for (; 0 < (int)var_6;)
      ;
    for (char g = 0; g < 4; g++)
      for (; std::min(var_7 / 405077347810ULL, (unsigned long long)9);
           var_7 += 2)
        for (char h = 0; h < (char)var_8; h += 4)
          for (short i = 0; i < (var_4 && var_6) + 13; i++) {
            arr_206[0][g][0][h][i] = var_6;
            var_89 = std::min(var_4 ?: 709U, (unsigned)var_4);
          }
    for (short j = 0; j < var_2; j += 4)
      for (int k = 0; k < 5U; k = var_10)
        arr_257[k] = var_6;
  }
}

// driver.cpp
#include <stdio.h>

short var_1 = (short)7531;
unsigned int var_2 = 187158918U;
bool var_4 = (bool)1;
unsigned long long int var_6 = 10263287916162477044ULL;
signed char var_7 = 0;
long long int var_8 = 21;
unsigned int var_10 = 3309705747U;
unsigned int var_11 = 222967114U;
short var_29 = (short)-22723;
short var_89 = (short)-19017;
short arr_206 [10] [14] [13] [21] [14] __attribute__((aligned));
int arr_257 [5];

void test();

int main() {
    test();
    for (size_t i_0 = 0; i_0 < 5; ++i_0)
        printf("%d ", arr_257 [i_0]);
    printf("\n");
}

Error:

>$ g++ -march=skylake-avx512 func.cpp driver.cpp -O2 && sde -skx -- ./a.out 
-2039714828 0 0 0 0 
>$ g++ -march=skylake-avx512 func.cpp driver.cpp -O3 && sde -skx -- ./a.out 
27636 0 0 0 0

gcc version 11.0.0 20210113 (8fc183ccd0628465205b8a88c29ab69bfe74a08a)