search for: crafti

Thanks for your reply. I have a normal (../configure --enable-profiling --disable-optimized --enable-assertions) llvm debug+profile+assert build. I am generating llvm-bitcode using following commands. llvm-gcc -DLINUX_i386 -DSPEC_CPU2000 -O3 -emit-llvm 186.crafty/src/valid.c -c -o 186.crafty/src/valid.bc --- llvm-link 186.crafty/src/*.bc -o 186.crafty/186.crafty.rel.bc and finally: llc

Hello, I am getting the following error while generating code for arm using llc for one of the specint2000 benchmark. Though same works for x86 target. Command => llc -march=arm 186.crafty/186.crafty.rel.bc -o 186.crafty/186.crafty.m5arm.s Error => LLVM ERROR: Couldn't allocate output reg for constraint '{cx}'! Have anyone seen this before? Is there a work around for this?

Hello > Command => llc -march=arm 186.crafty/186.crafty.rel.bc -o > 186.crafty/186.crafty.m5arm.s > Error =>  LLVM ERROR: Couldn't allocate output reg for constraint '{cx}'! > > Have anyone seen this before? It seems you're feeding x86-specific LLVM IR to arm backend. Please don't do that. -- With best regards, Anton Korobeynikov Faculty of Mathematics

Hi, I have looked at the LLVM code generation quality using small test cases and in general it is better than I thought and in some cases better than gcc. However, there are still some gap in SPEC performance. I have not looked at the root cause of those gaps. Anyone who cares about LLVM performance need to take this seriously. For fair comparison, I used -fno-strict-aliasing in gcc to turn off

Thanks David. Unfortunately many of us cannot use GPL v3 gcc so it's hard for us to investigate this. One question, can you tell if gcc is inlining significantly more than llvm? We have reports that this is one of the issue plaguing eon performance. There are also some relatively well known spec optimizations that we haven't implemented. e.g.

Hi, guys, I am comparing the performance of the default scheduler (seems to be the one that minimizes register pressure) with no scheduler (-pre-RA-sched=none), and I got these numbers. The ratio is low_reg_pressure/none, that is, the lower the number, the better the performance with low register pressure: CFP2000/177.mesa/177.mesa 1.00 CFP2000/179.art/179.art

Hi List I am wondering if some of you might know about any free alternative to Crafty Syntax Live and?Help Center Live? Regards Per? -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.centos.org/pipermail/centos/attachments/20090504/8d8eb698/attachment-0004.html>

Perhaps you noticed that LLVM gained a new optimizing register allocator yesterday (r130568). Linear scan is going away, and RAGreedy is the new default for optimizing builds. Hopefully, you noticed because your binaries were suddenly 2% smaller and 10% faster*. Some noticed because LLVM started crashing or miscompiling their code. Greedy replaces a fairly big chunk of the code generator, so

Hi, all I use llvm-gcc -O4 to compile SPEC 2000, some benchmarks can't be built successfully, such as 164.gzip, 175.vpr etc. The error messages are as follows. .. zh.o unlzw.o unpack.o unzip.o util.o zip.o -o gzip bits.o: file not recognized: File format not recognized collect2: ld returned 1 exit status specmake: *** [gzip] Error 1 specmake options 2> options.err |

On 2009-12-23 08:22, Li Shengmei wrote: > > Hi, all > > I use llvm-gcc –O4 to compile SPEC 2000, some benchmarks > can’t be built successfully, such as 164.gzip, 175.vpr etc. > > The error messages are as follows. > > > > …… > > zh.o unlzw.o unpack.o unzip.o util.o zip.o -o gzip > > bits.o: file not recognized: File format not recognized

On Nov 2, 2009, at 3:30 PM, Jon McLachlan wrote: > Hey folks, > > I am hoping that someone might be able to help me better understand > this design decision: For a 64 bit target, index's into GEP's of > arrays are zext up to 64 bit integers, even if the variable itself is > an alloca of only i32. Similarly, on a 32 bit target, index's into > GEP's are

Thank you for the responses! Hi Helmut, I actually prefer moving into a newer version that has all the great new features, but due to policies inside our firm it will be a long process. I find the idea of modifying the new version Samba to start up like the old version. Very crafty! :) Hi Volker, yes we do have a support contract with Red Hat and Oracle. The version we are currently using is

Hey folks, I am hoping that someone might be able to help me better understand this design decision: For a 64 bit target, index's into GEP's of arrays are zext up to 64 bit integers, even if the variable itself is an alloca of only i32. Similarly, on a 32 bit target, index's into GEP's are trunc'd down to 32 bits even if they ultimately reference an alloc'd

Friday I enabled the inlinehint function attribute in the inliner. It mostly affects the performance of -Os compiled code. I have made some measurements on the SPEC test suite to show what it means. I made three runs of then nightly tests. The baseline represents -Os with no inlinehint: make TEST=nightly OPTFLAGS=-Os EXTRA_LOPT_OPTIONS=-inlinehint-threshold=0

While I am waiting for a 1.0 release of Ogg Vorbis, I made a "WAV" folder on my computer and have been regularly ripping CDs into that folder using Exact Audio Copy. Right now that folder has 3.4 GB of wave files in different subfolders. Is there a program in which I could specify this "WAV" folder, and it would go and recursively convert all WAVs into oggs of the same filename

Hello, ALL. I am trying to organize a transparent single sign-on concept for my Active Directory users into Dovecot via IMAP. On the user's desktop I use Thunderbird 6.0 as a mail client (MUA), Windows XP as an operating system. Domain is controlled by Windows 2008 Server SP2 with Active Directory. I have installed on my Mail server Debian GNU/Linux 6.0.2 (Squeeze) and Dovecot 2.0.13 from

Move I/O instruction building to the sub-arch layer. Some very crafty but esoteric macros are used here to get optimized native instructions for port I/O in Linux be writing raw instruction strings. Adding a wrapper layer here is fairly easy, and makes the full range of I/O instructions available to the VMI interface. Also, slowing down I/O is not a useful operation in a VM, so there is a VMI

Move I/O instruction building to the sub-arch layer. Some very crafty but esoteric macros are used here to get optimized native instructions for port I/O in Linux be writing raw instruction strings. Adding a wrapper layer here is fairly easy, and makes the full range of I/O instructions available to the VMI interface. Also, slowing down I/O is not a useful operation in a VM, so there is a VMI

On Thu, Mar 30, 2006 at 04:27:55PM +0530, Pratik Mehta wrote: > I have made few attempts to compile some software packages with llvm. > My approach is to define Make variables as follows : > > export AS=llvm-as > export LD=llvm-ld > export AR=llvm-ar > export CXX=llvm-g++ > > and then run configure and make. > > This approach works with very small code bases

On 01 Sep 2006, at 10:05, Kenneth Hoste wrote: > >> >>> Also, it is possible to tell make only to compile benchmark X? How >>> can I >>> enforce this? >> >> Go into the directory for that benchmark, then run 'make' or >> whatever. > I tried tom compile each of the SPEC CPU2000 benchmarks using the make command is each respective