Why is Arrays.copyOf 2 times faster than System.arraycopy for small arrays?

Question

I was recently playing with some benchmarks and found very interesting results that I can\'t explain right now. Here is the benchmark:

@BenchmarkMode(Mode.Throug         


        

Answer 1

Your SystemArrayCopy benchmark is not semantically equivalent to arraysCopyOf.

It will be, if you replace

    System.arraycopy(ar, 0, result, 0, length);

with

    System.arraycopy(ar, 0, result, 0, Math.min(ar.length, length));

With this change the performance of both benchmarks will also become similar.

Why is the first variant slower then?

1. Without knowing how length relates to ar.length JVM needs to perform additional bounds check and be prepared to throw IndexOutOfBoundsException when length > ar.length.

2. This also breaks the optimization to eliminate redundant zeroing. You know, every allocated array must be initialized with zeros. However, JIT can avoid zeroing if it sees that the array is filled right after creation. But -prof perfasm clearly shows that the original SystemArrayCopy benchmark spends significant amount of time clearing the allocated array:

    0,84%    0x000000000365d35f: shr    $0x3,%rcx
    0,06%    0x000000000365d363: add    $0xfffffffffffffffe,%rcx
    0,69%    0x000000000365d367: xor    %rax,%rax
             0x000000000365d36a: shl    $0x3,%rcx
   21,02%    0x000000000365d36e: rep rex.W stos %al,%es:(%rdi)  ;*newarray
   

Manual copy appeared faster for small arrays, because unlike System.arraycopy it does not perform any runtime calls to VM functions.