RFR: 8361582: AArch64: Some ConH values cannot be replicated with SVE [v4]
Bhavana Kilambi
bkilambi at openjdk.org
Wed Aug 13 10:23:16 UTC 2025
On Tue, 12 Aug 2025 09:50:21 GMT, Andrew Haley <aph at openjdk.org> wrote:
> > HI @theRealAph Thanks a lot for your comment. I feel it is a good idea to modify `loadConH` to move a constant instead of doing an `ldr` from the constant pool (it could probably get us some performance benefit as well). However, the scope of this ticket was to mainly fix the JTREG errors that >16B SVE machines were running into due to illegal immediates being passed to the `sve_dup` instruction. Would it be acceptable if I push this fix first and then create a follow up task to work on optimizing `loadConH`? I can create a new JBS ticket and assign it to myself and tag it here as well if that helps. Thank you!
>
> Well, yes, but I'm proposing a simpler and better fix to the problem. Sure, if you want to do this in two steps go ahead.
Apologies, I thought I could change just the replicate backend nodes to be able to generate the `mov` to a scratch reg -> `dup` to replicate the value but missed the point that I can't still get rid of the `loadConH` node that loads the immediate from the constant pool. If we want to change `loadConH` to instead generate a `mov` of an immediate to a scratch register, then we might have to change the `dst` from being a `vRegF` to a `iRegI` -
`instruct loadConH(vRegF dst, immH con) %{`
which I am not in favour of as the scalar FP16 operations still expect the value to be in an FPR. I will work on this on a follow up JBS ticket. Thanks.
If this is acceptable, could I please get another round of review of the updated patch?
-------------
PR Comment: https://git.openjdk.org/jdk/pull/26589#issuecomment-3183158689
More information about the hotspot-compiler-dev
mailing list