<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Wed, Sep 6, 2017 at 3:24 AM, Filip Pizlo <span dir="ltr"><<a href="mailto:fpizlo@apple.com" target="_blank">fpizlo@apple.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span><br>
<br>
> On Sep 5, 2017, at 10:51 AM, Olmstead, Don <<a href="mailto:Don.Olmstead@sony.com" target="_blank">Don.Olmstead@sony.com</a>> wrote:<br>
><br>
> We have plans to add a JSC-Only windows bot in the very near future. Would that have any bearing on the state of JIT in Windows?<br>
<br>
</span>Not really.<br>
<br>
Because of the poor state of that code, I think we should rip it out.<br>
<br>
Also maintaining the 32_64 value representation is no value for us.<br></blockquote><div><br></div><div>I think keeping Windows support would be good. I believe Sony folks are working on Windows improvement, and it would be fine if they can keep watching JSC on Windows.</div><div>And it means that we can keep WebKit fast at major latest architectures including macOS / Linux / Windows (with 64bit CPUs), which is fine.</div><div><br></div><div>My largest concern about dropping JIT for various platforms is that LLInt performance would be not good compared to JIT-ed environment.</div><div>We could remove DFG for 32bit (not sure). But I think PolyIC can be critical for performance.</div><div>JS performance largely depends on this feature.</div><div><br></div><div>BTW, I strongly agree that newer feature should focus on 64bit architecture. (I'm opposed to adding 32bit support to FTL).</div><div><br></div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<span class="m_-507056909724016277m_1117288000753458065HOEnZb"><font color="#888888"><br>
-Filip<br>
</font></span><div class="m_-507056909724016277m_1117288000753458065HOEnZb"><div class="m_-507056909724016277m_1117288000753458065h5"><br>
<br>
><br>
> -----Original Message-----<br>
> From: webkit-dev [mailto:<a href="mailto:webkit-dev-bounces@lists.webkit.org" target="_blank">webkit-dev-bounces@lis<wbr>ts.webkit.org</a>] On Behalf Of Filip Pizlo<br>
> Sent: Tuesday, September 5, 2017 8:37 AM<br>
> To: Adrian Perez de Castro <<a href="mailto:aperez@igalia.com" target="_blank">aperez@igalia.com</a>><br>
> Cc: <a href="mailto:webkit-dev@lists.webkit.org" target="_blank">webkit-dev@lists.webkit.org</a><br>
> Subject: Re: [webkit-dev] Bring back ARMv6 support to JSC<br>
><br>
> There isn’t anyone maintaining the 32-not JIT ports to the level of quality we have in our 64-not ports. Making 32-bit use the 64-bit cloop would be a quality progression for actual users of 32-bit.<br>
><br>
> -Filip<br>
><br>
>>> On Sep 5, 2017, at 8:02 AM, Adrian Perez de Castro <<a href="mailto:aperez@igalia.com" target="_blank">aperez@igalia.com</a>> wrote:<br>
>>><br>
>>> On Tue, 5 Sep 2017 16:38:09 +0200, Osztrogonác Csaba <<a href="mailto:oszi@inf.u-szeged.hu" target="_blank">oszi@inf.u-szeged.hu</a>> wrote:<br>
>>><br>
>>> [...]<br>
>>><br>
>>> Maybe it will be hard to say good bye to 32-bit architecutres for<br>
>>> many people, but please, it's 2017 now, the first ARMv8 SoC is out 4<br>
>>> years ago, the first AMD64 CPU is out 14 years ago.<br>
>><br>
>> While it's true that amd64/x86_64 has been around long enough to not<br>
>> have to care (much) about its 32-bit counterpart; the same cannot be said about ARM.<br>
>> It would be great to be able to say that 32-bit ARM is well dead, but<br>
>> we are not there yet.<br>
>><br>
>> If we take x86_64 as an example, it has been “only” 10 years since the<br>
>> last new 32-bit CPU was announced and until 3-4 years ago it wasn't<br>
>> uncommon to see plently of people running 32-bit userlands. If things<br>
>> unroll in a similar way in the ARM arena, I would expect good 32-bit<br>
>> ARM support being relevant at least for another 3-4 years before the need starts to fade away.<br>
>><br>
>> If something, I think it may make more sense to remove 32-bit x86<br>
>> support, and have the 32-bit ARM support around for some more time.<br>
>><br>
>> Cheers,<br>
>><br>
>><br>
>> --<br>
>> Adrián 🎩<br>
>><br>
>> ______________________________<wbr>_________________<br>
>> webkit-dev mailing list<br>
>> <a href="mailto:webkit-dev@lists.webkit.org" target="_blank">webkit-dev@lists.webkit.org</a><br>
>> <a href="https://lists.webkit.org/mailman/listinfo/webkit-dev" rel="noreferrer" target="_blank">https://lists.webkit.org/mailm<wbr>an/listinfo/webkit-dev</a><br>
> ______________________________<wbr>_________________<br>
> webkit-dev mailing list<br>
> <a href="mailto:webkit-dev@lists.webkit.org" target="_blank">webkit-dev@lists.webkit.org</a><br>
> <a href="https://lists.webkit.org/mailman/listinfo/webkit-dev" rel="noreferrer" target="_blank">https://lists.webkit.org/mailm<wbr>an/listinfo/webkit-dev</a><br>
______________________________<wbr>_________________<br>
webkit-dev mailing list<br>
<a href="mailto:webkit-dev@lists.webkit.org" target="_blank">webkit-dev@lists.webkit.org</a><br>
<a href="https://lists.webkit.org/mailman/listinfo/webkit-dev" rel="noreferrer" target="_blank">https://lists.webkit.org/mailm<wbr>an/listinfo/webkit-dev</a><br>
</div></div></blockquote></div><br></div></div>