long
当你使用s时,我的 JVM 对内部循环做了这个非常简单的事情:
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 */
int
当您使用s时,它很难作弊;首先有一些我不声称理解但看起来像展开循环的设置:
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 */
然后展开循环本身:
0x00007f3dc290b640: add $0xfffffffffffffff0,%ecx
0x00007f3dc290b643: mov %ecx,0x258(%r10)
0x00007f3dc290b64a: cmp %r11d,%ecx
0x00007f3dc290b64d: jg 0x00007f3dc290b640
然后是展开循环的拆解代码,它本身就是一个测试和一个直接循环:
0x00007f3dc290b64f: cmp $0xffffffffffffffff,%ecx
0x00007f3dc290b652: jle 0x00007f3dc290b662
0x00007f3dc290b654: dec %ecx
0x00007f3dc290b656: mov %ecx,0x258(%r10)
0x00007f3dc290b65d: cmp $0xffffffffffffffff,%ecx
0x00007f3dc290b660: jg 0x00007f3dc290b654
因此,对于整数来说,它的速度提高了 16 倍,因为 JIT 将int
循环展开了 16 次,但根本没有展开long
循环。
为了完整起见,这是我实际尝试过的代码:
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;
}
}
程序集转储是使用选项生成的-XX:+UnlockDiagnosticVMOptions -XX:+PrintAssembly
。请注意,您需要弄乱您的 JVM 安装才能让这项工作也为您服务;您需要将一些随机共享库放在正确的位置,否则它将失败。