On Wed, Aug 12, 2020 at 2:58 PM Ben Craig via SG14 <sg14@lists.isocpp.org> wrote:

Minutes for today’s meeting…

Thanks Ben.
 

 

Ben Craig: Minutes

Staffan Tjernstrom: Chair

Michael Wong

Arthur O'Dwyer

Andrew Lumsdaine

Basit Ayantunde

Billy Baker

connor horman

Derek Haines

Henry Miller

Inbal Levi

Maxime Laine

Muklek Bokth Choudhury

Robert Douglas

Ronen Friedman

Hubert Tong

 

 

Wong: Inverted meetings: maybe once every three or four months while coronavirus is going.  CppCon now fully online.  Kona meeting is in Jeopardy.  Bulgaria, is the next most likely F2F.

 

Ben: Pitch I've heard is that 6 months after sports start is when we'll have a new F2F

 

Inbal: Virtual plenary is in the works

 

Staffan: All we know is that we don't know.

 

 

Wong: Affinity was reviewed in SG1, good to move forward into LEWG.  Low level one needs more discussion.  Now the paper is talking more about interference patterns.  Adjacency locality property work was discussed in an inverted meeting.

 

Staffan: I see us doing what needs to be done to get executors done, maybe these will follow along.

 

Inbal: Technical difficulties with ring buffer meeting yesterday.  Gathering the various inputs for ring buffer.  May want to move some ring buffer things from ring buffer paper to P1958 and P0260.  Need use cases.  Jens suggested that this be a ring span.

 

From Maxime Lainé to Everyone:  01:22 PM

sure, but I can't see any more use cases as those already there sadly.. (perhaps something driver related for networking but seems a bit stretched out)

 

From Inbal Levi to Everyone:  01:25 PM

Jens have suggested something along the lines of ring_span, so that's one direction. But we need to figure out if Guy's popping-strategy (from P0059) is something that is worth importing to P1958

 

Staffan: LEWGI wasn't thrilled with P1958 interface, but didn't hate it either.  LEWGI wanted to see how things differed with ring buffer.

 

Staffan: P0593 implicit object creation.  Adopted in the core language as a DR.  start_lifetime_as isn't in the library yet.  Very confident that it will be in C++23.

 

Staffan: P0593 is important to finance because of pipeline applications, similar to niall's load / unload objects out of memory ideas.

 

Hubert: std::launder won't help with the serialization things.

I think this needs:
"in strict terms without ensuring that the lifetime of an appropriate object has started".
 

start_lifetime_as only lets you claim that there is an object, previous references need to go through std::launder.

 

Staffan: Probably wait to talk about member layout control until Rene is able to make it on.

 

Wong: September is probably the right time to reconnect with Renwick to get forward progress on the paper and implementation.

 

Inbal: Trying to summarize decisions that are made in the low cost exception space for a cppcon talk.

 

Ben: Paper in the works to discuss error handling tradeoffs.  Will send it to Wong and Inbal.

 

Staffan: Big finance concern is just getting C++20 implemented and seeing the impact, like with jthread and the sync primitives. Seeing real at-scale impact with concepts and modules.

 

Wong: How well does the networking proposal work for finance?  Maybe there's an RPC proposal?

 

Staffan: Anything that helps low level timing stability or development throughput is of interest.  In finance, lots of people have the same idea at about the same time, but only the first 50% of people or so will make money on it.

 

Wong: How do contracts feel in your space?

 

Staffan: Vital, just not that everyone has realized that what they are doing is contracts work.

 

Wong: Bloomberg is largely doing it for verification.

 

From Robert Douglas to Everyone:  01:46 PM

Are there any papers in flight, that anyone is aware of, for attributes for hot/cold, a-la likely/unlikely?

 

Robert Douglas: gnu has hot / cold as well.  Has anyone seen a paper along those lines?

 

Staffan: likely / unlikely don't strictly do that, it does help.  Not for data though.

 

Staffan: finance ends up living in a weird world where the most common things need to be marked "unlikely" for performance.

 

From Me to Everyone:  01:50 PM

Timur Doumler is also trying to drag an assume attribute back from contracts

 

From connor horman to Everyone:  01:52 PM

I'd be interested in seeing that as well.

 

Robert Douglas: I usually see this for error handling functions that are marked both as unlikely and cold.

 

Wong: Could use a paper exploring this.

 

From Inbal Levi to Everyone:  01:53 PM

Yes. But to my humble understanding, the support is vague.

 

From Maxime Lainé to Everyone:  01:53 PM

hot/cold pragmas/markers seems a bit out of language, more of a compiler feature, but I'm open for discussion as well

 

From Inbal Levi to Everyone:  01:53 PM

P1774R3

 

Staffan: Would like to have an offline discussion talking about hot / cold.

 

Actions:

* Wong to talk with Renwick

* Staffan + Robert to talk about object layout

* Revisit object layout space when Rene is on the call

 

From: SG14 <sg14-bounces@lists.isocpp.org> On Behalf Of Matthew Butler via SG14
Sent: Wednesday, August 12, 2020 10:14 AM
To: Low Latency:Game Dev/Financial/Trading/Simulation/Embedded Devices <sg14@lists.isocpp.org>
Cc: Matthew Butler <mbutler@laurellye.com>
Subject: [EXTERNAL] Re: [SG14] SG14 Aug 12 meeting

 

Me as well.

 

On Wed, Aug 12, 2020 at 9:10 AM René Ferdinand Rivera Morell via SG14 <sg14@lists.isocpp.org> wrote:

Same for me.

On Wed, Aug 12, 2020, 11:07 AM Guy Cpp via SG14 <sg14@lists.isocpp.org> wrote:

Apologies: I won't be able to attend this month's meeting. Have a great time!

 

Cheers,
G

 

On Tue, 11 Aug 2020 at 17:06, Tjernstrom, Staffan via SG14 <sg14@lists.isocpp.org> wrote:

Topic: SG14 Low Latency Monthly

This meeting is Finance focused and is chaired by Staffan Tjernström.

Hi,

Michael Wong is inviting you to a scheduled Zoom meeting.

Topic: SG14 monthly Apr 2020-Oct 2020

Time: Jun 11, 2020 02:00 AM Eastern Time (US and Canada) 6 UTC
    Jun 11, 2020 02:00 AM 6UTC
    Jul 8, 2020 02:00 PM 18 UTC
    Aug 12, 2020 02:00 PM 18 UTC
    Sep 9, 2020 02:00 PM 18 UTC
    Oct 7, 2020 02:00 PM 18 UTC

Join from PC, Mac, Linux, iOS or Android:

    Password: 013549

Or iPhone one-tap :
    US: +13462487799,,819108882# or +14086380968,,819108882#
Or Telephone:
    Dial(for higher quality, dial a number based on your current location):
        US: +1 346 248 7799 or +1 408 638 0968 or +1 646 876 9923 or +1
669 900 6833 or +1 253 215 8782 or +1 301 715 8592 or +1 312 626 6799
 or 877 853 5247 (Toll Free)
    Meeting ID: 819 108 882
    Password: 013549
    International numbers available: https://iso.zoom.us/u/abhaIjFKLZ

Or Skype for Business (Lync):
    https://iso.zoom.us/skype/819108882

Agenda:

1. Opening and introductions

1.1 Roll call of participants

1.2 Adopt agenda

1.3 Approve minutes from previous meeting, and approve publishing
 previously approved minutes to ISOCPP.org

1.4 Action items from previous meetings

2. Main issues (125 min)

2.1 General logistics

Inverted meeting frequency?

CPPCON logistics
CPPCON Embedded Track: Ben Saks
future C++ Standard meetings:

2.2 Paper reviews

2.2.1 any other proposal for reviews?

SG14/SG19 features/issues/defects:

https://docs.google.com/spreadsheets/d/1JnUJBO72QVURttkKr7gn0_WjP--P0vAne8JBfzbRiy0/edit#gid=0

These are more status updates than full-blown reviews this time around.

Affinity https://github.com/cplusplus/papers/issues?q=is:issue+P1436

System topology discovery https://github.com/cplusplus/papers/issues?q=is:issue+P1795

Ring Buffer https://github.com/cplusplus/papers/issues?q=is:issue+P0059

Object Creation https://github.com/cplusplus/papers/issues?q=is:issue+P0593

Member layout control https://github.com/cplusplus/papers/issues?q=is:issue+P1605

Discuss future direction of detreministic C++ exception group :

Low-cost Deterministic C++ Exceptions for Embedded Systems
<
https://www.research.ed.ac.uk/portal/files/78829292/low_cost_deterministic_C_exceptions_for_embedded_systems.pdf>

Low-cost
Deterministic C++ Exceptions for Embedded Systems James Renwick James
Renwick et al.

2.3 Domain-specific discussions

2.3.1 SIG chairs

   - Embedded Programming chairs: Ben Craig, Wouter van Ooijen and Odin
   Holmes, John McFarlane  

   - Financial/Trading chairs: Staffan Tjernström, Carl Cooke, Neal Horlock,
   Mateusz Pusz, Clay Trychta,
   - Games chairs: Rene Riviera, Guy Davidson and Paul Hampson
   - Linear Algebra chairs: Bob Steagall, Mark Hoemmen, Guy Davidson

2.4 Other Papers and proposals

2.5 Future F2F meetings:

2.6 future C++ Standard meetings:
https://isocpp.org/std/meetings-and-participation/upcoming-meetings

- 2020-11: (New York, tentative) Cancelled.
- 2021-02-22 to 27: Kona, HI, USA

3. Any other business
Reflector
https://lists.isocpp.org/mailman/listinfo.cgi/sg14
As well as look through papers marked "SG14" in recent standards committee
paper mailings:
http://open-std.org/jtc1/sc22/wg21/docs/papers/2015/
http://open-std.org/jtc1/sc22/wg21/docs/papers/2016/

Code and proposal Staging area
https://github.com/WG21-SG14/SG14
4. Review

4.1 Review and approve resolutions and issues [e.g., changes to SG's
working draft]

4.2 Review action items (5 min)

5. Closing process

5.1 Establish next agenda

5.2 Future meeting

Time: Sep 9, 2020 02:00 PM Eastern Time (US and Canada) : Security: Mathew
Butler

Time: Oct 14, 2020 02:00 PM Eastern Time (US and Canada): Games: Rene

 

 

Kind Rgds

Staffan Tj.

pp Michael Wong

 

 



IMPORTANT: The information contained in this email and/or its attachments is confidential. If you are not the intended recipient, please notify the sender immediately by reply and immediately delete this message and all its attachments. Any review, use, reproduction, disclosure or dissemination of this message or any attachment by an unintended recipient is strictly prohibited. Neither this message nor any attachment is intended as or should be construed as an offer, solicitation or recommendation to buy or sell any security or other financial instrument. Neither the sender, his or her employer nor any of their respective affiliates makes any warranties as to the completeness or accuracy of any of the information contained herein or that this message or any of its attachments is free of viruses.

_______________________________________________
SG14 mailing list
SG14@lists.isocpp.org
https://lists.isocpp.org/mailman/listinfo.cgi/sg14

_______________________________________________
SG14 mailing list
SG14@lists.isocpp.org
https://lists.isocpp.org/mailman/listinfo.cgi/sg14

_______________________________________________
SG14 mailing list
SG14@lists.isocpp.org
https://lists.isocpp.org/mailman/listinfo.cgi/sg14

_______________________________________________
SG14 mailing list
SG14@lists.isocpp.org
https://lists.isocpp.org/mailman/listinfo.cgi/sg14