RFR: 8227505: SuperWordLoopUnrollAnalysis may lead to over loop unrolling

Jie Fu fujie at loongson.cn
Wed Aug 21 08:59:24 UTC 2019


Hi Vivek,

Updated: http://cr.openjdk.java.net/~jiefu/8227505/webrev.03/
Please see comments inline.

On 2019/8/20 上午11:44, Deshpande, Vivek R wrote:
> Hi All
>
> I tested this patch with small test which adds byte arrays.
> for (int i = 0; i < NUM; i++) {
>                  data[i] = (byte)(data2[i] + data3[i]);
> }
>
> Since the loop unrolled to half than earlier, the maximum vector length could not be used and generated 256 bit long vector instructions instead of maximum available 512 bits.
I've asked my manager for an AVX-512 machine.
But it will take some time to get it.

So could you please share me the performance of your test case on your  
AVX-512 machine?


> Also the loop did not get unrolled after vectorization.  I have given the generated code below.

Fixed. Thanks.


Any comments?

Thanks a lot.
Best regards,
Jie




More information about the hotspot-compiler-dev mailing list