Hello Dear LLVM Developers and Users
I would like to complain about scientific inaccuracy of the paper
http://hal.inria.fr/docs/00/35/45/77/PDF/RR-6799.pdf written by
Nicolas Geoffray, Gaël Thomas, Charles Clément, Bertil Folliot, Gilles
Muller and presentation done by Nicolas Geoffray on LLVM conference
supported by Google:
http://llvm.org/devmtg/2008-08/Geoffray_VMKitProject.pdf
They provide comparison of their system that uses LLVM, with our
system Portable.NET that uses LibJIT for Just-In-Time compilation.
All measures in this paper have been done for Portable.NET 0.7.4,
which does not use LibJIT as its engine. However, the author provides
results of Portable.NET 0.7.4. as results of LibJIT. The Portable.NET
0.7.4 uses a dynamic compiler, which has nothing in common with the
project and development of LibJIT. We are very upset with these papers
and that there are such "researchers" in your group. Portable.NET
0.7.4 was released 3 years ago. LibJIT have been developed during the
last 3 years. We require that you remove this paper and this
presentation and make official excuses not only in this maillist but
also on the next conferences when you talk about LLVM.
Thanks,
Kirill
Hello Dear LLVM Developers and Users
Hi Kirill,
Please talk to Nicholas about this, thanks!
-Chris
Hi Chris,
Just in case that this information does not get corrupted I want to
point to the issue:
In http://llvm.org/devmtg/2008-08/Geoffray_VMKitProject.pdf it is on
page 21: "VMKit, Mono, PNet", Array bounds checks.
In http://hal.inria.fr/docs/00/35/45/77/PDF/RR-6799.pdf it is on page
17: "We compare N3 with Mono [9] version 1.2.6, and PNet version 0.7.4
[2], which uses libjit as dynamic compiler...."
This statement is false. PNet version 0.7.4 has not been using LibJIT.
It has been using an unroller.
"The PNet performance show that libjit has very few optimizations and
does not compete against robust compilers."
In fact any amateur in Just-In-Time compilers, and Virtual Machine
engines, by just looking at this benchmark on the next page "Figure 7:
PNetMark results (higher is better)", can tell that PNet engine used
to take these measures has not been a Just-In-Time compiler. However,
the authors of the paper insist.
This benchmark definitely does not tell anything about LibJIT, as
LibJIT has not been used. In fact, we started development of LibJIT as
an answer to such benchmarks issues.
I can suggest the authors of these papers to use a real industrial VM
engine to compare. For instance, check Microsoft .NET or if you cannot
do this "for legal reason" try Java HotSpot. But not a 5 years old
version, although even that should give you more objective results
that you can understand what these benchmark mean in fact.
Thanks,
Kirill
Dear all,
First, sorry for all that noise. I know you guys *just don't care*TM, but this requires some clarification. I won't say more than what's in this email.
The VMKit paper dates from early 2008. It compares VMKit with pnet 0.7.4 and not the latest release (0.8.0) because we were not able to get any information to build it correctly at the time; the website that hosted libjit was broken, i.e. http://www.southern-storm.com.au. That said, here's the info that we have on the pnet website:
January 15-01-2006: DotGNU Portable.NET 0.7.4 and libjit 0.0.6 released!
New versions of Portable.NET and libjit are available. Far too many new features and bug fixes to list them here, see the announcement which includes a full list of new features and bug fixes. You can get it from the download page.
December 03-12-2005: Portable.NET and libjit progress
Work on libjit (A JIT designed to be independent of any particular virtual machine bytecode format or language) has resumed again and we are gearing towards using it in Portable.NET soon. Recently, there have also been donations which will be distributed amongst developers who contribute code to get libjit finished and hook it into Portable.NET's runtime engine.
Maybe it's our mistake if we misinterpreted the informations given on that webpage. From our understanding, libjit and pnet were merged in 0.7.4. Now that we all know pnet and libjit are two separate, alive, projects, we will stop refering to pnet only. The VMKit paper got rid of libjit references. As for the LLVM developer meeting presentation, there is no mention of libjit.
End of the story.
Nicolas
Kirill Kononenko wrote:
Dear all,
This new version of the paper at:
http://hal.archives-ouvertes.fr/docs/00/36/53/37/PDF/RR-6799.pdf
get ride of libJIT. Now my question is the how scientific is this
research if instead of using libJIT it simply decided to remove this
information all together? Also how object is Related Work in this
context?
Thanks,
Kirill
Dear all,
This new version of the paper at:
got ride of libJIT. Now my question is the how scientific is this
research and research paper if instead of using libJIT and
Portable.NET JIT:
authors of "VMKit: a Substrate for Virtual Machines by Nicolas
Geoffray — Gaël Thomas— Charles Clément —Bertil Folliot — Gilles
Muller" simply decided to decided remove research information all
together? Also how objective is Related Work part of this research
paper in this context?
Thanks,
Kirill
Kirill, this has nothing to do with llvm. Please stay on topic or your future postings will be moderated.
-Chris
Hi Chris
How does this has nothing to do with llvm? Is not the VMKit project an
official part of LLVM?
Thanks,
Kirill
You're asking about a paper not hosted on our web site or in the project, go hassle Nicholas off-line. Also, your massive spamming of GCC, mono, perl, etc demonstrates that you are not interested in contributing to any of these projects. You are now moderated.
-Chris