RFR: 8292898: [vectorapi] Unify vector mask cast operation [v4]
Xiaohong Gong
xgong at openjdk.org
Wed Sep 28 02:21:21 UTC 2022
On Tue, 27 Sep 2022 03:28:21 GMT, Xiaohong Gong <xgong at openjdk.org> wrote:
>> Since checks related to VecMaskUseAll are decoupled from the main opcode and depends on num and type of elements so one check per intrinsic routine should be ok if its covering the needed trajectories. Infact we are passing VecMaskUseAll back to back to two rountines on Line #2439 and Line # 2452, WDYT ?
>
> Yes, I'm agree that one check is enough.
I'm sorry that the second check on Line-2452 should be kept since the element type and vector length might be different from the first check on Line-2439. So I'd like to keep it as it is.
-------------
PR: https://git.openjdk.org/jdk/pull/10192
More information about the hotspot-compiler-dev
mailing list