rdtsc, too many cycles

Question

#include <stdio.h>
static inline unsigned long long tick() 
{
        unsigned long long d;
        __asm__ __volatile__ ("rdtsc" : "=A" (d) );
        return d;
}

int main()
{
        long long res;
        res=tick();

        res=tick()-res;
        printf("%d",res);
        return 0;
}

I have compiled this code with gcc with -O0 -O1 -O2 -O3 optimizations. And I always get 2000-2500 cycles. Can anyone explain the reason for this output? How to spend these cycles?

First function "tick" is wrong. This is right.

Another version of function "tick"

static __inline__ unsigned long long tick()
{
  unsigned hi, lo;
  __asm__ __volatile__ ("rdtsc" : "=a"(lo), "=d"(hi));
  return ( (unsigned long long)lo)|( ((unsigned long long)hi)<<32 );
}

This is assembly code for -O3

 .file  "rdtsc.c"
.section    .rodata.str1.1,"aMS",@progbits,1
.LC0:
    .string "%d"
    .text
    .p2align 4,,15
.globl main
    .type   main, @function
main:
    leal    4(%esp), %ecx
    andl    $-16, %esp
    pushl   -4(%ecx)
    pushl   %ebp
    movl    %esp, %ebp
    subl    $40, %esp
    movl    %ecx, -16(%ebp)
    movl    %ebx, -12(%ebp)
    movl    %esi, -8(%ebp)
    movl    %edi, -4(%ebp)
#APP
# 6 "rdtsc.c" 1
    rdtsc
# 0 "" 2
#NO_APP
    movl    %edx, %edi
    movl    %eax, %esi
#APP
# 6 "rdtsc.c" 1
    rdtsc
# 0 "" 2
#NO_APP
    movl    %eax, %ecx
    movl    %edx, %ebx
    subl    %esi, %ecx
    sbbl    %edi, %ebx
    movl    %ecx, 4(%esp)
    movl    %ebx, 8(%esp)
    movl    $.LC0, (%esp)
    call    printf
    movl    -16(%ebp), %ecx
    xorl    %eax, %eax
    movl    -12(%ebp), %ebx
    movl    -8(%ebp), %esi
    movl    -4(%ebp), %edi
    movl    %ebp, %esp
    popl    %ebp
    leal    -4(%ecx), %esp
    ret
    .size   main, .-main
    .ident  "GCC: (Debian 4.3.2-1.1) 4.3.2"
    .section    .note.GNU-stack,"",@progbits

This is CPU

processor   : 0
vendor_id   : GenuineIntel
cpu family  : 15
model       : 4
model name  : Intel(R) Xeon(TM) CPU 3.00GHz
stepping    : 3
cpu MHz     : 3000.105
cache size  : 2048 KB
fdiv_bug    : no
hlt_bug     : no
f00f_bug    : no
coma_bug    : no
fpu     : yes
fpu_exception   : yes
cpuid level : 5
wp      : yes
flags       : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss constant_tsc up pebs bts pni
bogomips    : 6036.62
clflush size    : 64

Answer 1

I've tried your code on several Linux distros running on different Intel CPUs (admittedly all more recent than the Pentium 4 HT 630 you appear to be using). In all those tests I got values between 25 and 50 cycles.

My only hypothesis that's consistent with all the evidence is that you're running your operating system inside a virtual machine rather than on bare metal, and TSC is getting virtualized.