search for: csibe

Hi all, We did some benchmarks on code size with clang, gcc 4.5, and open64. Clang performed second in the test. The benchmark is CSiBE. Clang can't compile the linux kernel (some inline asm not supported) and replaypc (error: use of unknown builtin '__builtin_next_arg'). The concrete results are attached. -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail...

On Apr 19, 2010, at 3:11 AM, Zhongxing Xu wrote: > Hi all, > > We did some benchmarks on code size with clang, gcc 4.5, and open64. Clang performed second in the test. The benchmark is CSiBE. Clang can't compile the linux kernel (some inline asm not supported) and replaypc (error: use of unknown builtin '__builtin_next_arg'). The concrete results are attached. Nice, I don't have access to CSiBE. Out of curiosity, why aren't llvm -O2 numbers included? Would you be...

Is anyone using CSiBE ? http://www.inf.u-szeged.hu/csibe/ What things are people using for code size benchmarks for clang/llvm? tia. Reed -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20131115/7097624f/attachment.html>

On Mon, Apr 19, 2010 at 3:11 AM, Zhongxing Xu <xuzhongxing at gmail.com> wrote: > Hi all, > > We did some benchmarks on code size with clang, gcc 4.5, and open64. Clang > performed second in the test. The benchmark is CSiBE. Clang can't compile > the linux kernel (some inline asm not supported) and replaypc (error: use of > unknown builtin '__builtin_next_arg'). The concrete results are attached. That error looks extremely strange; where is the call to __builtin_next_arg coming from? -Eli

(NPM: new pass manager; LPM: legacy pass manager) In a first quick experiment today I compared code-size of the LMP vs. the NMP for the CSiBE benchmark (and some other), and this shows code-size increases with the NPM that would probably be unacceptable for us. So, now I am wondering how/if we need to mitigate this, and have a bunch of questions. As I've noticed quite some activity around the NPM recently, I am first of all curious...

...> - Late outlining provides a geomean of 4.65% reduction, with a largest > improvement of ~51% and largest regression of ~6.4%. > > - Spec 2006(X86_64) > > - Early+Late outlining provides a geomean reduction of 2.08%. > > - Late outlining provides 2.09%. > > - CSiBE(AArch64) > > - Early+Late outlining shows geomean reduction of around 3.5%. > > - Late outlining shows 3.1%. > > * Compile Time: > > Compile time was tested under test-suite with a multisample of 5. > > - Early+Late outlining > > - Many improvements with...

...ent of ~67% and largest regression of ~7.5%. - Late outlining provides a geomean of 4.65% reduction, with a largest improvement of ~51% and largest regression of ~6.4%. - Spec 2006(X86_64) - Early+Late outlining provides a geomean reduction of 2.08%. - Late outlining provides 2.09%. - CSiBE(AArch64) - Early+Late outlining shows geomean reduction of around 3.5%. - Late outlining shows 3.1%. * Compile Time: Compile time was tested under test-suite with a multisample of 5. - Early+Late outlining - Many improvements with > 40% compile time reduction. - Few regression...

I am looking for some scripts that let me compare , for size, gcc and llvm for mips16/32 and get some kind of function by function comparison and maybe a list of which ones are bigger in llvm and other statistics. Not rocket science but maybe someone already has exactly what I'm looking for. Tia. Reed

...at implements communication between these two processes through temporary files. At this point mechanism is applied to two optimizations: Inliner and Loop Invariant Code Motion. Supported platform is MIPS32r2. Despite small number of instrumented points we got improvements on some test files from CSiBE benchmark. Here are the promising results: jpeg-6b/jidctflt.c -10.2% OpenTCP-1.0.4/system.c -6.7% libmspack/test/chmd_md5.c -5.8% flex-2.5.31/regex.c -4.8% We plan to apply this framework to more compiler phases and to some other target architectures. It is expected to give better...

...that each package has not been corrupted or tampered with, examine only the md5sum with the following command: rpm --checksig --nogpg <filename> 8. References: http://www.securityfocus.com/templates/archive.pike?list=1&date=2000-03-22&msg=Pine.LNX.4.21.0003231428110.13143-100000@csibe.fazekas.hu http://www.securityfocus.com/templates/archive.pike?list=1&date=2000-06-15&msg=Pine.LNX.4.10.10006201453090.1812-200000@apollo.aci.com.pl Copyright(c) 2000 Red Hat, Inc. -- ---------------------------------------------------------------------- Please refer to the information...

...; > > > > At this point mechanism is applied to two optimizations: Inliner and > > Loop > > Invariant Code Motion. Supported platform is MIPS32r2. > > > > Despite small number of instrumented points we got improvements on > > some test > > files from CSiBE benchmark. Here are the promising results: > > > > jpeg-6b/jidctflt.c -10.2% > > OpenTCP-1.0.4/system.c -6.7% > > libmspack/test/chmd_md5.c -5.8% > > flex-2.5.31/regex.c -4.8% > > Very interesting. Out of curiosity, any slowdowns? jidctflt.c is optimized due to...

...re is obviously already a binding here. > > At this point mechanism is applied to two optimizations: Inliner and > Loop > Invariant Code Motion. Supported platform is MIPS32r2. > > Despite small number of instrumented points we got improvements on > some test > files from CSiBE benchmark. Here are the promising results: > > jpeg-6b/jidctflt.c -10.2% > OpenTCP-1.0.4/system.c -6.7% > libmspack/test/chmd_md5.c -5.8% > flex-2.5.31/regex.c -4.8% Very interesting. Out of curiosity, any slowdowns? > > We plan to apply this framework to more compiler phas...

Attention all List Members: We are in the process of migrating all Red Hat lists from the current list manager software/server running qmail/Smartlist to a new server running postfix and GNU Mailman (*). Within the next week you will receive more information about this migration including information on how to access your membership, including subscribe/unsubscribe information and instructions on

...point mechanism is applied to two optimizations: Inliner and > > > Loop > > > Invariant Code Motion. Supported platform is MIPS32r2. > > > > > > Despite small number of instrumented points we got improvements on > > > some test > > > files from CSiBE benchmark. Here are the promising results: > > > > > > jpeg-6b/jidctflt.c -10.2% > > > OpenTCP-1.0.4/system.c -6.7% > > > libmspack/test/chmd_md5.c -5.8% > > > flex-2.5.31/regex.c -4.8% > > > > Very interesting. Out of curiosity, any slowdown...

...ns). The code size benchmarking results provided are: * LLVM Test Suite - X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* * Spec 2006 - X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* * Clang - X86_64(Mac OS) * llvm-tblgen - X86_64(Mac OS) * CSiBE - AArch64 * The machine outliner currently only supports X86_64 and AArch64. Full Code Size Results: https://goo.gl/ZBjHCG --- Algorithmic differences with the Machine Outliner ---- There was a lot of confusion on how exactly the algorithm I am proposing differs from what is...

...e code size benchmarking results provided are: > * LLVM Test Suite > X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* > * Spec 2006 > X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* > * Clang > X86_64(Mac OS) > * llvm-tblgen > X86_64(Mac OS) > * CSiBE > AArch64 > * The machine outliner currently only supports X86_64 and AArch64. > > Full Code Size Results: > https://goo.gl/ZBjHCG <https://goo.gl/ZBjHCG> > > --- Algorithmic differences with the Machine Outliner ---- > > There was a lot of confusion...

...* LLVM Test Suite > > - X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* > > * Spec 2006 > > - X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* > > * Clang > > - X86_64(Mac OS) > > * llvm-tblgen > > - X86_64(Mac OS) > > * CSiBE > > - AArch64 > > * The machine outliner currently only supports X86_64 and AArch64. > > Full Code Size Results: > https://goo.gl/ZBjHCG > > --- Algorithmic differences with the Machine Outliner ---- > > There was a lot of confusion on how exactly the a...

...vided are: >> * LLVM Test Suite >> X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* >> * Spec 2006 >> X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* >> * Clang >> X86_64(Mac OS) >> * llvm-tblgen >> X86_64(Mac OS) >> * CSiBE >> AArch64 >> * The machine outliner currently only supports X86_64 and AArch64. >> >> Full Code Size Results: >> https://goo.gl/ZBjHCG <https://goo.gl/ZBjHCG> >> >> --- Algorithmic differences with the Machine Outliner ---- >> >>...

...Suite >>> X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* >>> * Spec 2006 >>> X86_64, X86*, AArch64, Arm1176jzf-s*, Arm1176jzf-s-thumb* >>> * Clang >>> X86_64(Mac OS) >>> * llvm-tblgen >>> X86_64(Mac OS) >>> * CSiBE >>> AArch64 >>> * The machine outliner currently only supports X86_64 and AArch64. >>> >>> Full Code Size Results: >>> https://goo.gl/ZBjHCG <https://goo.gl/ZBjHCG> >>> >>> --- Algorithmic differences with the Machine Outliner...