search for: panchenko

...propellor doc, the CFI duplication is _necessary_ to represent discontiguous functions, not anything particular to the way Propellor happens to generate those discontiguous functions. And emitting discontiguous functions is a fundamental goal of this, right? On Wed, Oct 2, 2019 at 4:25 PM Maksim Panchenko via llvm-dev < llvm-dev at lists.llvm.org> wrote: > Thanks for clarifying. This means once you move to the next basic block > (or any other basic > > block in the function) you have to execute an entirely new set of CFI > instructions > > except for the common CIE part....

On Wed, Oct 2, 2019 at 8:41 PM Maksim Panchenko via llvm-dev < llvm-dev at lists.llvm.org> wrote: > *Pessimization/overhead for stack unwinding used by system-wide profilers > and > for exception handling* > > Larger CFI programs put an extra burden on unwinding at runtime as more CFI > (and thus native) instructions hav...

Hi all! When compiling the program using opusfile the #include <opus/opusfile.h> generates error that # include <opus_multistream.h> is not found. Actually it should be included as # include <opus/opus_multistream.h> just like the ogg.h in the previous line. A small patch attached. -- Best regards, Alexander -------------- next part -------------- A non-text attachment

Hi All, Our team at Hip-Hop Virtual Machine (http://hhvm.com<http://hhvm.com/>) have been experimenting with using LLVM as a code generator for x86-64. We have been successfully running it for quite some time as a secondary back end. We had to modify our version of LLVM and our mods were based on 3.5 release. At this point we feel our requirements have become stable enough to start

Hello Maksim, On Fri, Oct 18, 2019 at 10:57 AM Maksim Panchenko <maks at fb.com> wrote: > Cool. The new numbers look good. If you run BOLT with jemalloc library > > preloaded, you will likely get a runtime closer to 1 minute. We’ve noticed > that > > compared to the default malloc, it improves the multithreaded > > performance and...

Hello Maksim, On Wed, Oct 16, 2019 at 3:52 PM Maksim Panchenko <maks at fb.com> wrote: > Hi Sri, > > > > I want to clarify one thing before sending a detailed reply: did you > evaluate > > BOLT on Clang built with basic block sections? > In the makefile you reference, > > there are two versions: a “vanilla” and a default...

We are going to be at the llvm-dev meeting the next two days. We will get back to you after that. Sri On Mon, Oct 21, 2019 at 10:07 PM Maksim Panchenko <maks at fb.com> wrote: > Hi Sri, > > > > Thank you for replying to our feedback. 7 out 12 high-level concerns have > been > > answered; 2 of them are fully addressed. The rest are being tracked at the > > following Google doc: > > > > > https://d...

...lock). > > > > *From: *llvm-dev <llvm-dev-bounces at lists.llvm.org> on behalf of James Y > Knight via llvm-dev <llvm-dev at lists.llvm.org> > *Reply-To: *James Y Knight <jyknight at google.com> > *Date: *Wednesday, October 2, 2019 at 1:59 PM > *To: *Maksim Panchenko <maks at fb.com> > *Cc: *"llvm-dev at lists.llvm.org" <llvm-dev at lists.llvm.org> > *Subject: *Re: [llvm-dev] [RFC] Propeller: A frame work for Post Link > Optimizations > > > > I'm a bit confused by this subthread -- doesn't BOLT have the exact s...

..._necessary_ to represent discontiguous functions, not anything particular to the way Propellor happens to generate those discontiguous functions. > > > > And emitting discontiguous functions is a fundamental goal of this, right? > > > > On Wed, Oct 2, 2019 at 4:25 PM Maksim Panchenko via llvm-dev <llvm-dev at lists.llvm.org> wrote: > >> > >> Thanks for clarifying. This means once you move to the next basic block (or any other basic > >> > >> block in the function) you have to execute an entirely new set of CFI instructions > >>...

...: *llvm-dev <llvm-dev-bounces at lists.llvm.org> on behalf of James Y >>> Knight via llvm-dev <llvm-dev at lists.llvm.org> >>> *Reply-To: *James Y Knight <jyknight at google.com> >>> *Date: *Wednesday, October 2, 2019 at 1:59 PM >>> *To: *Maksim Panchenko <maks at fb.com> >>> *Cc: *"llvm-dev at lists.llvm.org" <llvm-dev at lists.llvm.org> >>> *Subject: *Re: [llvm-dev] [RFC] Propeller: A frame work for Post Link >>> Optimizations >>> >>> >>> >>> I'm a bit confuse...

...ang-based C++ Tooling, Daniel Jasper - Google, Manuel Klimek - Google Session #8: October 30 2:00-3:30 Salon III & IV LLVM for a managed language: what we've learned, Sanjoy Das - Azul Systems, Philip Reames - Azul Systems LLVM back end for HHVM/PHP, Brett Simmers - Facebook, Inc., Maksim Panchenko - Facebook, Inc Session #9: October 30 2:00-3:30: Salon I & II Throttling Automatic Vectorization: When Less Is More, Vasileios Porpodas - University of Cambridge LoopVersioning LICM, Ashutosh Nema - AMD Session #10: October 30 4:30-6:00 Salon III & IV Compiling large, real-world codebas...

...functions, not anything particular to the way Propellor happens to generate those discontiguous functions. > > > > > > > > And emitting discontiguous functions is a fundamental goal of this, right? > > > > > > > > On Wed, Oct 2, 2019 at 4:25 PM Maksim Panchenko via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > > >> > > > >> Thanks for clarifying. This means once you move to the next basic block (or any other basic > > > >> > > > >> block in the function) you have to execute an entirely n...

On 9/8/15, 9:35 AM, "Philip Reames" <listmail at philipreames.com> wrote: >On 09/04/2015 11:36 AM, Brett Simmers via llvm-dev wrote: >> On 9/4/15 1:12 AM, Sanjoy Das via llvm-dev wrote: >>> Specifically on "Location records" -- >>> >>> Is it legal for the optimizer to drop the `!locrec` metadata that you >>> attach to

Actually, you're supposed to add /usr/include/opus to your include path. That's why the includes don't have the "opus/" prefix. Cheers, Jean-Marc On 31/08/17 05:20 AM, Alexander Panchenko wrote: > Hi all! > When compiling the program using opusfile the > > #include <opus/opusfile.h> > > generates error that > > # include <opus_multistream.h> > > is not found. Actually it should be included as > > # include <opus/opus_multistrea...

...39;t have the "opus/" prefix. Hi! But that's uncommon: You also don't put /usr/include/sys into your include path, but you still write #include <sys/stat.h> (for example). Regards, Ulrich > > Cheers, > > Jean-Marc > > On 31/08/17 05:20 AM, Alexander Panchenko wrote: >> Hi all! >> When compiling the program using opusfile the >> >> #include <opus/opusfile.h> >> >> generates error that >> >> # include <opus_multistream.h> >> >> is not found. Actually it should be included as >&...

Greetings! I have successfully installed and configured nut package. All i want now is to power off ups. If i run upsmon -c fsd as root - everything goes fine, system and ups gracefully shutting down. If i unplug power cable from an ups, then system is down, but ups still on load. Any help would be appreciated. Debian Lenny x86 ups.conf [ippon] driver = megatec port = /dev/ttyS0

On 9/3/15, 3:34 PM, "Mehdi Amini" <mehdi.amini at apple.com<mailto:mehdi.amini at apple.com>> wrote: Hi, On Sep 3, 2015, at 1:38 PM, Maksim Panchenko via llvm-dev <llvm-dev at lists.llvm.org<mailto:llvm-dev at lists.llvm.org>> wrote: Hi All, Our team at Hip-Hop Virtual Machine (http://hhvm.com<http://hhvm.com/>) have been experimenting with using LLVM as a code generator for x86-64. We have been successfully running it for qu...

Greetings, We, at Google, recently evaluated Facebook’s BOLT, a Post Link Optimizer framework, on large google benchmarks and noticed that it improves key performance metrics of these benchmarks by 2% to 6%, which is pretty impressive as this is over and above a baseline binaryalready heavily optimized with ThinLTO + PGO. Furthermore, BOLT is also able to improve the performance of binaries