[aarch64-port-dev ] [11u] RFR (S) 8212043: AArch64: Add floating-point Math.min/max intrinsics

[Andrew Haley]

On 13/02/2021 09:13, Andrew Haley wrote:
> On 25/01/2021 20:15, Dmitry Chuyko wrote:
>> Intrinsics: http://cr.openjdk.java.net/~dchuyko/8212043/webrev.11u.01/
>>
>> Graal test: http://cr.openjdk.java.net/~dchuyko/8215687/webrev.11u.00/
>>
>> jtreg test: http://cr.openjdk.java.net/~dchuyko/8218550/webrev.11u.00/
>>
>> Testing: aarch64 build, tier1, tier2, Graal HotspotTest (with Graal 
>> enabled) - fails because of ECB, TestFpMinMaxIntrinsics.
>>
>> I'd be grateful if you take x86 part.
> 
> From what I can remember there wasn't much improvement, and may
> actually have been a regression with some code.

It also looks intrusive and significantly risky.

-- 
Andrew Haley  (he/him)
Java Platform Lead Engineer
Red Hat UK Ltd. <https://www.redhat.com>
https://keybase.io/andrewhaley
EAC8 43EB D3EF DB98 CC77 2FAD A5CD 6035 332F A671