similar to: [LLVMdev] Benchmarking for automatic parallelization project

On Thu, 2011-12-08 at 11:53 +0800, 陳韋任 wrote: > > I am looking appropriate Benchmarking for the assessment of automatic > > parallelization project. What Benchmarking do you suggest me? > > Do you mean auto-parallelization or auto-vectorization? If it's the latter, I > sugguest you find scientific or graphic applications. For auto-vectorization, look at:

Hi Hal, > For auto-vectorization, look at: > http://polaris.cs.uiuc.edu/~garzaran/doc/pact11.pdf > http://polaris.cs.uiuc.edu/~maleki1/TSVC.tar.gz > > If you're looking for auto-parallelization, I can ask around. Thanks for the sharing. If that doesn't bother you too much, I would like to know auto-parallelization benchmarks. :p Just curious. I was thinking that

> I am looking appropriate Benchmarking for the assessment of automatic > parallelization project. What Benchmarking do you suggest me? Do you mean auto-parallelization or auto-vectorization? If it's the latter, I sugguest you find scientific or graphic applications. I don't think there is auto-parallelization benchmark, however. Regards, chenwj -- Wei-Ren Chen (陳韋任) Computer

Ralf, et al., Attached is the latest version of my autovectorization patch. llvmdev has been CC'd (as had been suggested to me); this e-mail contains additional benchmark results. First, these are preliminary results because I did not do the things necessary to make them real (explicitly quiet the machine, bind the processes to one cpu, etc.). But they should be good enough for discussion.

On Sat, 2011-10-29 at 12:30 -0500, Hal Finkel wrote: > Ralf, et al., > > Attached is the latest version of my autovectorization patch. llvmdev > has been CC'd (as had been suggested to me); this e-mail contains > additional benchmark results. > > First, these are preliminary results because I did not do the things > necessary to make them real (explicitly quiet the

On Sat, 2011-10-29 at 14:02 -0500, Hal Finkel wrote: > On Sat, 2011-10-29 at 12:30 -0500, Hal Finkel wrote: > > Ralf, et al., > > > > Attached is the latest version of my autovectorization patch. llvmdev > > has been CC'd (as had been suggested to me); this e-mail contains > > additional benchmark results. > > > > First, these are preliminary

On Sat, 2011-10-29 at 15:16 -0500, Hal Finkel wrote: > On Sat, 2011-10-29 at 14:02 -0500, Hal Finkel wrote: > > On Sat, 2011-10-29 at 12:30 -0500, Hal Finkel wrote: > > > Ralf, et al., > > > > > > Attached is the latest version of my autovectorization patch. llvmdev > > > has been CC'd (as had been suggested to me); this e-mail contains > >

Dear Neda, Please explain in more detail what you are trying to do and what is not working. I do not understand what llvm-prof does that you don't like or what you want llvm-prof to do. -- John T. On 9/7/11 1:38 AM, neda 8664 wrote: > hi > I changed llvm-prof and make it, but when use profile.pl > <http://profile.pl> ,i could not see any change in result. > > >

I've study their work carefully. My problem is the implementation of threads in llvm after partitionning. I want to have information about how to implement producer/consumer thread in llvm. I do not know where I should start in llvm for code generation and create thread and insert produce and consume statement . -------------- next part -------------- An HTML attachment was scrubbed... URL:

Hi, All I want to implement DSWP Which is used for parallelization of loops. For this purpose, the loop was replaced with a new basic block in main function. And new functions were created and basic blocks of Loop assigned to them.I have checked blocks and branches for Succ and Pred relation and I have not found any problems. However I get the following error: * **opt:

I am changing structure of loops, I used std::vector<> but i get same error, I can’t use FunctionPass :( On Mon, Dec 12, 2011 at 8:03 PM, John Criswell <criswell at illinois.edu>wrote: > On 12/12/11 10:25 AM, neda 8664 wrote: > > Thank you for your reply > Yes, I change them, so what should I do for another loops? > > > I don't really know what you should

On 12/12/11 10:25 AM, neda 8664 wrote: > > Thank you for your reply > > Yes, I change them, so what should I do for another loops? I don't really know what you should do since I don't know what your code does. All I know is that it's changing the function's control-flow graph. If you're not modifying the structure of the loops in the function, then you can

When I SSH using protocol 1 from a Debian box running OpenSSH 2.9p2-4 to a sparc.sunos5 box running vanilla OpenSSH 2.9.1, after a little while (of inactivity?) I get the following message on the client terminal: Disconnecting: protocol error: rcvd type 98 Looking further, this message is actually caused by the SSH daemon. However, I'm at a loss to determine why sshd is doing this. I attach

Greetings, I am setting up Dovecot 1.0.15 on my home Fedora Core 8 pc ONLY to access my mail archives across several mail clients. No access from the internet is possible or needed here. I cannot log in with any client, the login always fails. The reason, as I understand, is that when dovecot starts it doesn't read any user name from the userdb file, so when I try to login it doesn't

I am MSc student and my thesis subject is "parallelization of sequential program in thread level to run on multi-core processors". I want automatically parallelize sequential program in thread level to run on multi-core processors with software pipelining. I've use LLVM to code analysis and translate code to IR, I could extract PDG graph form IR code and convert it to SCCDAG and

Greetings Everyone, A group in my office is designing/integrating what I would loosly label as an "embedded system". In that, it performs a dedicated task and is not a general purpose workstation or server. It operates in a harsh environment, particularly a questionable power environment and they are extremely concerned about inadvertent shutdown and recovery. They were totally

Hi, I have a data.frame which contains timeseries from several different locations, which I want to compare against each other for example calculating RMSE, or normalized mean bias of each location against the others. An example of this is the cor function where I can put in a data.frame and get the correlation of each location compared to the others in the data.frame eg.

Dear, all. I am pulling my hair because I could not find any error messsages that could point me to a fix to my problem. The directory I want to share was mounted on /home with drbd and heartbeat but then my users could not access any shares / their home directories. However, if I set up shares else where on my box like share under /opt or /usr/local, then the same users would be able to access

Thank you for your reply Yes, I change them, so what should I do for another loops? On Mon, Dec 12, 2011 at 7:54 PM, neda 8664 <neda8664 at gmail.com> wrote: > Thank you for your reply > > Yes, I change them, so what should I do for another loops? > > On Mon, Dec 12, 2011 at 7:42 PM, John Criswell <criswell at illinois.edu>wrote: > >> On 12/12/11 9:59 AM,

I'm attempting to upgrade to kernel-smp-2.4.21-27.0.4.EL (x86_64) on a Dell 1850. The new kernel is panicing on reboot. When comparing against the current working kernel, I just noticed that we're currently running the "UP" kernel: [root at polaris root]# uname -srvp Linux 2.4.21-27.0.2.EL #1 SMP Wed Jan 19 11:49:43 CST 2005 x86_64 First question... why is the kernel