[vector] RFR: Unify VectorMaskCmp shape between x86 and aarch64

[Vladimir Ivanov]

Thanks, Yang.

Best regards,
Vladimir Ivanov

On 08.04.2020 09:22, Yang Zhang wrote:
> Hi Vladimir
> 
> I verified this patch on aarch64, vector api tests are passed.
> It looks good to me.
> 
> 19473 instruct vcmeq4I(vecX dst, vecX src1, vecX src2, immI cond)
> You add one input parameter "immI cond", but don't use it. I will create another patch to use " immI cond" to combine compare operations.
> 
> Regards
> Yang
> 
> 
> 
> -----Original Message-----
> From: panama-dev <panama-dev-bounces at openjdk.java.net> On Behalf Of Vladimir Ivanov
> Sent: Tuesday, April 7, 2020 9:38 PM
> To: panama-dev <panama-dev at openjdk.java.net>
> Subject: [vector] RFR: Unify VectorMaskCmp shape between x86 and aarch64
> 
> http://cr.openjdk.java.net/~vlivanov/panama/vector/vcmp/webrev.00/
> 
> Get rid of platform-specific differences in VectorMaskCmp.
> 
> Testing: jdk/incubator/vector tests
> 
> The patch is against vectorIntrinsics branch.
> 
> Best regards,
> Vladimir Ivanov
>