performance - Why is long slower than int in x64 Java?

Question

I'm running Windows 8.1 x64 with Java 7 update 45 x64 (no 32 bit Java installed) on a Surface Pro 2 tablet.

The code below takes 1688ms when the type of i is a long and 109ms when i is an int. Why is long (a 64 bit type) an order of magnitude slower than int on a 64 bit platform with a 64 bit JVM?

My only speculation is that the CPU takes longer to add a 64 bit integer than a 32 bit one, but that seems unlikely. I suspect Haswell doesn't use ripple-carry adders.

I'm running this in Eclipse Kepler SR1, btw.

public class Main {

    private static long i = Integer.MAX_VALUE;

    public static void main(String[] args) {    
        System.out.println("Starting the loop");
        long startTime = System.currentTimeMillis();
        while(!decrementAndCheck()){
        }
        long endTime = System.currentTimeMillis();
        System.out.println("Finished the loop in " + (endTime - startTime) + "ms");
    }

    private static boolean decrementAndCheck() {
        return --i < 0;
    }

}

Edit: Here are the results from equivalent C++ code compiled by VS 2013 (below), same system. long: 72265ms int: 74656ms Those results were in debug 32 bit mode.

In 64 bit release mode: long: 875ms long long: 906ms int: 1047ms

This suggests that the result I observed is JVM optimization weirdness rather than CPU limitations.

#include "stdafx.h"
#include "iostream"
#include "windows.h"
#include "limits.h"

long long i = INT_MAX;

using namespace std;


boolean decrementAndCheck() {
return --i < 0;
}


int _tmain(int argc, _TCHAR* argv[])
{


cout << "Starting the loop" << endl;

unsigned long startTime = GetTickCount64();
while (!decrementAndCheck()){
}
unsigned long endTime = GetTickCount64();

cout << "Finished the loop in " << (endTime - startTime) << "ms" << endl;



}

Edit: Just tried this again in Java 8 RTM, no significant change.

Answer 1

My JVM does this pretty straightforward thing to the inner loop when you use longs:

0x00007fdd859dbb80: test   %eax,0x5f7847a(%rip)  /* fun JVM hack */
0x00007fdd859dbb86: dec    %r11                  /* i-- */
0x00007fdd859dbb89: mov    %r11,0x258(%r10)      /* store i to memory */
0x00007fdd859dbb90: test   %r11,%r11             /* unnecessary test */
0x00007fdd859dbb93: jge    0x00007fdd859dbb80    /* go back to the loop top */

It cheats, hard, when you use ints; first there's some screwiness that I don't claim to understand but looks like setup for an unrolled loop:

0x00007f3dc290b5a1: mov    %r11d,%r9d
0x00007f3dc290b5a4: dec    %r9d
0x00007f3dc290b5a7: mov    %r9d,0x258(%r10)
0x00007f3dc290b5ae: test   %r9d,%r9d
0x00007f3dc290b5b1: jl     0x00007f3dc290b662
0x00007f3dc290b5b7: add    $0xfffffffffffffffe,%r11d
0x00007f3dc290b5bb: mov    %r9d,%ecx
0x00007f3dc290b5be: dec    %ecx              
0x00007f3dc290b5c0: mov    %ecx,0x258(%r10)   
0x00007f3dc290b5c7: cmp    %r11d,%ecx
0x00007f3dc290b5ca: jle    0x00007f3dc290b5d1
0x00007f3dc290b5cc: mov    %ecx,%r9d
0x00007f3dc290b5cf: jmp    0x00007f3dc290b5bb
0x00007f3dc290b5d1: and    $0xfffffffffffffffe,%r9d
0x00007f3dc290b5d5: mov    %r9d,%r8d
0x00007f3dc290b5d8: neg    %r8d
0x00007f3dc290b5db: sar    $0x1f,%r8d
0x00007f3dc290b5df: shr    $0x1f,%r8d
0x00007f3dc290b5e3: sub    %r9d,%r8d
0x00007f3dc290b5e6: sar    %r8d
0x00007f3dc290b5e9: neg    %r8d
0x00007f3dc290b5ec: and    $0xfffffffffffffffe,%r8d
0x00007f3dc290b5f0: shl    %r8d
0x00007f3dc290b5f3: mov    %r8d,%r11d
0x00007f3dc290b5f6: neg    %r11d
0x00007f3dc290b5f9: sar    $0x1f,%r11d
0x00007f3dc290b5fd: shr    $0x1e,%r11d
0x00007f3dc290b601: sub    %r8d,%r11d
0x00007f3dc290b604: sar    $0x2,%r11d
0x00007f3dc290b608: neg    %r11d
0x00007f3dc290b60b: and    $0xfffffffffffffffe,%r11d
0x00007f3dc290b60f: shl    $0x2,%r11d
0x00007f3dc290b613: mov    %r11d,%r9d
0x00007f3dc290b616: neg    %r9d
0x00007f3dc290b619: sar    $0x1f,%r9d
0x00007f3dc290b61d: shr    $0x1d,%r9d
0x00007f3dc290b621: sub    %r11d,%r9d
0x00007f3dc290b624: sar    $0x3,%r9d
0x00007f3dc290b628: neg    %r9d
0x00007f3dc290b62b: and    $0xfffffffffffffffe,%r9d
0x00007f3dc290b62f: shl    $0x3,%r9d
0x00007f3dc290b633: mov    %ecx,%r11d
0x00007f3dc290b636: sub    %r9d,%r11d
0x00007f3dc290b639: cmp    %r11d,%ecx
0x00007f3dc290b63c: jle    0x00007f3dc290b64f
0x00007f3dc290b63e: xchg   %ax,%ax /* OK, fine; I know what a nop looks like */

then the unrolled loop itself:

0x00007f3dc290b640: add    $0xfffffffffffffff0,%ecx
0x00007f3dc290b643: mov    %ecx,0x258(%r10)
0x00007f3dc290b64a: cmp    %r11d,%ecx
0x00007f3dc290b64d: jg     0x00007f3dc290b640

then the teardown code for the unrolled loop, itself a test and a straight loop:

0x00007f3dc290b64f: cmp    $0xffffffffffffffff,%ecx
0x00007f3dc290b652: jle    0x00007f3dc290b662
0x00007f3dc290b654: dec    %ecx
0x00007f3dc290b656: mov    %ecx,0x258(%r10)
0x00007f3dc290b65d: cmp    $0xffffffffffffffff,%ecx
0x00007f3dc290b660: jg     0x00007f3dc290b654

So it goes 16 times faster for ints because the JIT unrolled the int loop 16 times, but didn't unroll the long loop at all.

For completeness, here is the code I actually tried:

public class foo136 {
  private static int i = Integer.MAX_VALUE;
  public static void main(String[] args) {
    System.out.println("Starting the loop");
    for (int foo = 0; foo < 100; foo++)
      doit();
  }

  static void doit() {
    i = Integer.MAX_VALUE;
    long startTime = System.currentTimeMillis();
    while(!decrementAndCheck()){
    }
    long endTime = System.currentTimeMillis();
    System.out.println("Finished the loop in " + (endTime - startTime) + "ms");
  }

  private static boolean decrementAndCheck() {
    return --i < 0;
  }
}

The assembly dumps were generated using the options -XX:+UnlockDiagnosticVMOptions -XX:+PrintAssembly. Note that you need to mess around with your JVM installation to have this work for you as well; you need to put some random shared library in exactly the right place or it will fail.