similar to: [LLVMdev] -march and -mtune options on x86

Which options are you seeing that cause the largest difference, and on which targets? As Chandler mentioned there has been a large amount of variation in x86 targets, and there are certain optimizations that can be done, on say a Pentium (scheduling instructions which are pairable and non-dependent so the U and V pipelines are saturated without contention, for example) that don't make sense

Let me describe more precisely what I am doing and why the results I got may help improve LLVM's performance on modern x86-64 processors regardless of the front end (GCC, Clang or DragonEgg). I am running ALL my tests on an Intel Xeon E5540 processor, which is an x86-64 Nehalem processor. The OS is a 64-bit version of Ubuntu. So, I am running all my tests on the same x86-64 machine and am

On Mon, Jan 16, 2012 at 12:29 AM, Ghassan Shobaki <ghassan_shobaki at yahoo.com > wrote: > Let me describe more precisely what I am doing and why the results I got > may help improve LLVM's performance on modern x86-64 processors regardless > of the front end (GCC, Clang or DragonEgg). > > I am running ALL my tests on an Intel Xeon E5540 processor, which is an > x86-64

Hi, We are using LLVM 2.9 (with the llvm-gcc front end) to compile and run the SPEC CPU2006 benchmarks on x86. We are compiling and running the benchmarks on a an Intel Xeon E5540 processor running Ubuntu 10.10 (64-bit version). For the native x86-64 target, we are using the following command-line arguments: -O3 -march=core2 -mtune=core2 and are getting compile-time errors on the gamess and

Hi, We are currently in the process of upgrading from LLVM 2.9 to LLVM 3.3. We are working on instruction scheduling (mainly for register pressure reduction). I have been following the llvmdev mailing list and have learned that a machine instruction (MI) scheduler has been implemented to replace (or work with?) the selection DAG (SD) scheduler. However, I could not find any document that

Sent from my iPhone On Jun 28, 2013, at 2:38 PM, Ghassan Shobaki <ghassan_shobaki at yahoo.com> wrote: > Hi, > > We are currently in the process of upgrading from LLVM 2.9 to LLVM 3.3. We are working on instruction scheduling (mainly for register pressure reduction). I have been following the llvmdev mailing list and have learned that a machine instruction (MI) scheduler has been

Thank you for the answers! We are currently trying to test the MI scheduler. We are using LLVM 3.3 with Dragon Egg 3.3 on an x86-64 machine. So far, we have run one SPEC CPU2006 test with the MI scheduler enabled using the option -fplugin-arg-dragonegg-llvm-option='-enable-misched:true' with -O3. This enables the machine scheduler in addition to the SD scheduler. We have verified this by

Hi Andy, Please see my in-line answers below. Regards -Ghassan ________________________________ From: Andrew Trick <atrick at apple.com> To: Ghassan Shobaki <ghassan_shobaki at yahoo.com> Cc: "llvmdev at cs.uiuc.edu" <llvmdev at cs.uiuc.edu> Sent: Friday, September 23, 2011 8:02 PM Subject: Re: [LLVMdev] Pre-Allocation Schedulers in LLVM On Sep 23, 2011, at

Hi, We are currently working on revising a journal article that describes our work on pre-allocation scheduling using LLVM and have some questions about LLVM's pre-allocation scheduler. The answers to these question will help us better document and analyze the results of our benchmark tests that compare our algorithm with LLVM's pre-allocation scheduling algorithm. First, here is a

Hi Renato, Please see my answers below. Thanks -Ghassan ________________________________ From: Renato Golin <renato.golin at linaro.org> To: Ghassan Shobaki <ghassan_shobaki at yahoo.com> Cc: Andrew Trick <atrick at apple.com>; "llvmdev at cs.uiuc.edu" <llvmdev at cs.uiuc.edu> Sent: Thursday, September 19, 2013 5:30 PM Subject: Re: [LLVMdev] Experimental

On 19 September 2013 17:25, Ghassan Shobaki <ghassan_shobaki at yahoo.com>wrote: > Ghassan: You have made me so curious to try other benchmarks in our future > work. Most academic publications on CPU performance though use SPEC. You > can even find some recent publications that are still using SPEC CPU2000! > When I was at AMD in 2009, performance optimization and benchmarking

On 17 September 2013 19:04, Ghassan Shobaki <ghassan_shobaki at yahoo.com>wrote: > We have done some experimental evaluation of the different schedulers in > LLVM 3.3 (source, BURR, ILP, fast, MI). The evaluation was done on x86-64 > using SPEC CPU2006. We have measured both the amount of spill code as well > as the execution time as detailed below. > Hi Ghassan, This is an

On Sep 29, 2012, at 2:43 AM, Ghassan Shobaki <ghassan_shobaki at yahoo.com> wrote: > Hi, > > We are currently working on revising a journal article that describes our work on pre-allocation scheduling using LLVM and have some questions about LLVM's pre-allocation scheduler. The answers to these question will help us better document and analyze the results of our benchmark

Thank you for the answers, Jakob! That's really informative for someone who is still new to LLVM like me. Please see my responses below. -Ghassan  ________________________________ From: Jakob Stoklund Olesen <stoklund at 2pi.dk> To: Ghassan Shobaki <ghassan_shobaki at yahoo.com> Cc: "llvmdev at cs.uiuc.edu" <llvmdev at cs.uiuc.edu> Sent: Tuesday, August 16,

Dear All, I have been trying to compile a package for windows that we have written. Since R version 3.0.0 the package doesn't compile any more. (On Linux the package compiles without errors). The error specifically says: gcc -m32 -I"C:/PROGRA~1/R/R-30~1.0/include" -DNDEBUG -I"d:/RCompile/CRANpkg/extralibs64/local/include" -O3 -Wall -std=gnu99 -mtune=core2 -c

Hi Andy, We have done some experimental evaluation of the different schedulers in LLVM 3.3 (source, BURR, ILP, fast, MI). The evaluation was done on x86-64 using SPEC CPU2006. We have measured both the amount of spill code as well as the execution time as detailed below. Here are our main findings: 1. The SD schedulers significantly impact the spill counts and the execution times for many

Hi there, I'm having trouble to compile the R + C/C++ codes for this project from Yahoo folks on latent factor models: https://github.com/yahoo/Latent-Factor-Models#readme After downloading the package from the site, I could not successfully *make* the files. Here is the message: ====================================================================================== sh-4.1$ make R CMD

I'm going to using RInside on windows enviroment. I installed all tools and packages according to Dirk's instruction. My R installation reside in d:\hli\programfiles\R-3.2.2. There's no problems with folders with spaces. The rtools is installed in d:\hli\programfiles\Rtools and MinGW in d: \hli\programfiles\MinGW. The R_HOME is set to d:\hli\programfiles\R-3.2.2. I

Hello all, I'm trying to build R 32bit from source in a Windows 64 machine. I have followed the steps in "R Installation and Adiministration" ( http://cran.r-project.org/doc/manuals/R-admin.html#Getting-the-source-files) or at least I think I did everything described. I am not sure if I have installed the libjpeg, libtiff and libpng files though. I have upzipped them in the

So, when the MI scheduler is enabled, will SD scheduling be totally disabled or the SD scheduler will be automatically set to do source scheduling? -Ghassan ________________________________ From: Andrew Trick <atrick at apple.com> To: llvmdev at cs.uiuc.edu Cc: Ghassan Shobaki <ghassan_shobaki at yahoo.com> Sent: Thursday, September 26, 2013 9:24 AM Subject: Re: [LLVMdev]