search for: ctuning

On Jul 6, 2010, at 10:09 AM, Manuel Llosa wrote: > Dear Kenneth, May I ask you if you are implementing your search within > ctuning framework: ctuning.org/ctuning-cc? No, I'm not. I've built my own framework, and since I don't have any experience with the ctuning framework, I don't intend to start using that. There's little gain in it for me. > The thing is that I use it since some time for my thesis to...

On Jul 6, 2010, at 5:04 PM, Manuel Llosa wrote: > Dear Kenneth, I see. Do you plan sharing your framework in open source? > For now, I will continue using ctuning tools (they support LLVM as is but not > some specific things on JIT dynamic recompilation what is my thesis about). > I will like to compare all tools of course and will be happy > to share results although real not until autumn).Look forward > to your results and hopefully keep in t...

Dear Kenneth, I see. Do you plan sharing your framework in open source? For now, I will continue using ctuning tools (they support LLVM as is but not some specific things on JIT dynamic recompilation what is my thesis about). I will like to compare all tools of course and will be happy to share results although real not until autumn).Look forward to your results and hopefully keep in touch. Regards! Manu...

Dear Kenneth, May I ask you if you are implementing your search within ctuning framework: ctuning.org/ctuning-cc? The thing is that I use it since some time for my thesis to optimize code size and compilation time and run time with GCC though they are not using genetic algorithms but some slower hybrid of random exploration and than AI with some fronteer detection. Since rec...

Hello LLVMers, I'm putting together some (extensive) experiments with using a genetic algorithm to construct sets of optimization passes that are as close as optimal in a number of ways, e.g. compilation time, execution time, code size, ... I've figured out which LLVM tools I should use for this (llvm-gcc to obtain bitcode, opt to optimize, llc to obtain assembly, ...), and I'm now

...ation could partially resolve these problems by allowing compiler to explore some alternative decisions, generate code for these new decision paths and take the generated code that is the best for a particular criteria eventually. This approach is not new in the literature, we can mention Milepost/CTuning [http://ctuning.org] among other projects. In this approach, in comparison to Milepost/CTuning, the emphasis is on much finer granularity by changing arbitrary compiler decisions, and not only those based on values of command line options, at any point in translation process. This framework implem...

...explore some alternative decisions, generate > > code > > for these new decision paths and take the generated code that is the > > best > > for a particular criteria eventually. > > > > This approach is not new in the literature, we can mention > > Milepost/CTuning > > [http://ctuning.org] among other projects. In this approach, in > > comparison > > to Milepost/CTuning, the emphasis is on much finer granularity by > > changing > > arbitrary compiler decisions, and not only those based on values of > > command > > lin...

...lems > by allowing compiler to explore some alternative decisions, generate > code > for these new decision paths and take the generated code that is the > best > for a particular criteria eventually. > > This approach is not new in the literature, we can mention > Milepost/CTuning > [http://ctuning.org] among other projects. In this approach, in > comparison > to Milepost/CTuning, the emphasis is on much finer granularity by > changing > arbitrary compiler decisions, and not only those based on values of > command > line options, at any point in translat...

Tobias Grosser wrote: > The way to go is the scoplib format (propably extended by quantified > variables). This format could be extracted from graphite easily and > could also be created in LLVM. > What we need to get back into LLVM is only the new optimized schedule > described e.g. as cloog like scattering functions. These can be parsed > easily. The real code generation

...generate > > > code > > > for these new decision paths and take the generated code that is the > > > best > > > for a particular criteria eventually. > > > > > > This approach is not new in the literature, we can mention > > > Milepost/CTuning > > > [http://ctuning.org] among other projects. In this approach, in > > > comparison > > > to Milepost/CTuning, the emphasis is on much finer granularity by > > > changing > > > arbitrary compiler decisions, and not only those based on values of > &...

On 12/27/09 10:18, ether wrote: > hi Tobi , > > that sounds greate :D > > On 2009-12-27 5:43, Tobias Grosser wrote: >> I already looked into implementing something like Graphite for LLVM. >> However just recently, so I have not released any code yet. As soon as >> some code is available I will post patches. > whats its status? do you need any help? Very

...CALL FOR PAPERS 5th Workshop on Statistical and Machine learning approaches to ARchitecture and compilaTion (SMART 2011) http://cTuning.org/workshop-smart2011 April 2nd or 3rd, 2011, Chamonix, France (co-located with CGO 2011 Conference) ******************************************************************************** The rapid rate of architectural change and the large diversity of architectur...

...g behaviour on the hot/cold samples should be observed. Performance will be evaluated using "test-suite" again, though with one addition. To ensure that the produced code is not over-specialised to the training profiling data an additional set of data will be used. MiDatasets (http://ctuning.org/wiki/index.php/CTools:CBench:Downloads) provides alternatives inputs for the MiBench suite, so that will be used to test this. The next large chunk of work will be to make use of the exisiting path profiling code (PathProfiling.cpp). Superblock Formation will be done via Tail Duplication...

Hi Hans, we have uploaded tarballs for ARM and AArch64 targets: a20ea3fe482e754a61ccb37c67456ad1 clang+llvm-6.0.1-aarch64-linux-gnu.tar.xz f37b132c3dfb3b776524980be5af3a76 clang+llvm-6.0.1-armv7a-linux-gnueabihf.tar.xz and 47a9a9bb02d41581e6804b98918188f6 clang+llvm-7.0.0-aarch64-linux-gnu.tar.xz e639d8f5dc58be5cf44d017fd5eefd6c clang+llvm-7.0.0-armv7a-linux-gnueabihf.tar.xz Yvan On Mon,