[MAGEEC] LLVM Talk Draft Proposal

[James Pallister]

Hi Simon,

> We will present the latest performance results, which show
> that optimizing for energy is a double win, because such programs are
> almost
> always much faster, and will include examples where energy usage is
> halved and
> speed doubled compared to -O3.
Do we know if MAGEEC can find these sets of optimizations? I can see a
few complaints with saying we can double speed (assuming that this is
coming from the genetic algorithm stuff I did a while ago). It was
actually a genetic algorithm, made heavy use of optimization ordering
and it was with an 'old' version of LLVM (3.1 or 3.2). Also it was on a
Cortex-A8, rather than the embedded platforms we're targeting.

It might be better to say that we've found cases where the potential is
almost 3 times better than -O3, and we expect MAGEEC to get closer to that?

I've attached the graph.

Cheers,
James

On 27/08/14 08:26, Simon Cook wrote:
> Hi all,
>
> Jeremy and I have been working on an abstract for a talk at the
> upcoming LLVM conference. Here is what we have so far.
>
> "Title: Machine Guided Compilation and Compiling to Minimize Energy Usage
>
> Compilers currently optimize for execution time and code size. But in
> a world
> of diminishing battery life, ever larger data centers and nanoscale energy
> scavenging devices, what if the compiler could instead optimize for energy
> efficiency of the compiled code? Imagine having "-Oe" as an option to
> LLVM.
>
> Since June 2013 Embecosm and the University of Bristol, supported by
> the UK
> Technology Strategy Board have developed the Machine Guided Energy
> Efficient
> Compliation system. MAGEEC (www.mageec.org <http://www.mageec.org>)
> uses machine learning to train a
> compiler on the combinations of compiler optimizations which will
> minimize the
> energy consumed by the compiled program. The original target of the
> project was
> to reduce the energy of compiled code by 40% compared to optimized
> code today.
>
> Unlike previous projects, MAGEEC is completely generic, capable of
> working with
> any compiler and target. It can optimize for any criterion, not just
> energy
> efficiency as we have used, and can be integrated with any machine
> learning
> approach. The project is entirely free and open source, with the code
> and all
> project design materials freely available online.
>
> In July 2014, the first complete version of the MAGEEC infrastructure was
> released, supporting both GCC and LLVM, and is now undergoing
> refinement and
> evaluation.  To support energy efficiency optimization, the project has
> developed its own low-cost (approx $50) energy measurement board,
> capable of
> sampling voltage and current up to 6 million times per second to an
> accuracy of
> better than 1%.  Training also requires a large pool of benchmark
> programs, and
> as part of this project we have also developed a new standard free and
> open
> source benchmark suite, BEEBS (www.beebs.eu <http://www.beebs.eu>),
> suitable for use with low energy
> deeply embedded systems.
>
> In this talk we will explain the detailed design of MAGEEC, comparing the
> challenges in developing for LLVM and GCC.  This will include the
> details of
> the integration with the machine learning system, allowing it to
> control the
> pass manager, and which allows us to select the best optimizations on
> a per
> function basis.  We will present the latest performance results, which
> show
> that optimizing for energy is a double win, because such programs are
> almost
> always much faster, and will include examples where energy usage is
> halved and
> speed doubled compared to -O3.
>
> We will conclude with a demonstration of MAGEEC in action on ARM
> processors,
> using the energy measurement board to measure the energy savings
> achieved."
>
>
> We're attempting to cover the entire history of the work we've done so
> far, as we don't have the benefit of having done a couple of talks
> previously for background information. If anyone has any thoughts
> before we submit this, that would be great. In particular, James, the
> graphs you had a few months ago with data from trying different passes
> with opt, have we quoted have the correct decrease in energy/execution
> time?
>
> Many thanks,
> Simon
>
>
> _______________________________________________
> mageec mailing list
> mageec at mageec.org
> http://mageec.org/cgi-bin/mailman/listinfo/mageec

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mageec.org/pipermail/mageec/attachments/20140829/da505442/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: evolve for core energy.pdf
Type: application/pdf
Size: 25922 bytes
Desc: not available
URL: <http://mageec.org/pipermail/mageec/attachments/20140829/da505442/attachment-0001.pdf>