[Bug target/33717] slow code generated for 64-bit arithmetic

[pinskia at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=33717

--- Comment #5 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
#include <stdio.h>
#include <assert.h>

#define rdtscl(low) \
     __asm__ __volatile__ ("rdtsc" : "=a" (low) : : "edx")

int main() {
  unsigned int x[100];
  unsigned int y[100];
  unsigned int z[100];

  long a,b,c;
  size_t i;

  unsigned long long l;

  for (i=0; i<100; ++i) {
    x[i]=0; y[i]=-1;
    z[i]=0;
  }
  x[0]=1;
  rdtscl(a);
  l=0;
  for (i=0; i<100; ++i) {
    l += (unsigned long long)x[i] + y[i];
    z[i]=l;
    l>>=32;
  }
  rdtscl(b);
  printf("C: %ld cycles\n",b-a);

  for (i=0; i<100; ++i)
    assert(z[i]==0);
  assert(l==1);

  rdtscl(a);
  asm volatile(
    "mov (%%esi,%%ecx),%%eax\n"
    "add (%%edi,%%ecx),%%eax\n"
    "mov %%eax,(%%ebx,%%ecx)\n"
    "1:\n"
    "lea 4(%%ecx),%%ecx\n"
    "jecxz 1f\n"
    "mov (%%esi,%%ecx),%%eax\n"
    "adc (%%edi,%%ecx),%%eax\n"
    "mov %%eax,(%%ebx,%%ecx)\n"
    "jmp 1b\n"
    "1:\n"
    : : "S" (x+100), "D" (y+100), "b" (z+100), "c" (-400) : "eax" );

  rdtscl(b);
  printf("asm: %ld cycles\n",b-a);

  for (i=0; i<100; ++i)
    assert(z[i]==0);
  assert(l==1);

}