similar to: [LLVMdev] -fplugin-arg-dragonegg-enable-gcc-optzns impact

Hi Jack, > Now that dragoneegg is robust in its default usage and the dragonegg svn > is moderately stable with -fplugin-arg-dragonegg-enable-gcc-optzns, it is > possible to gauge the impact of that feature. Comparing clang 2.9, FSF gcc 4.5.3svn, > FSF gcc 4.6.0 and dragonegg svn with FSF gcc 4.5.3svn using the himenoBMTxpa benchmark, > the enhancement to code performance from

On Fri, Apr 15, 2011 at 08:53:19AM +0200, Duncan Sands wrote: > Hi Jack, > > > Now that dragoneegg is robust in its default usage and the dragonegg svn > > is moderately stable with -fplugin-arg-dragonegg-enable-gcc-optzns, it is > > possible to gauge the impact of that feature. Comparing clang 2.9, FSF gcc 4.5.3svn, > > FSF gcc 4.6.0 and dragonegg svn with FSF

Hi Jack, thanks for these numbers. Can you also please measure compile times? I'm thinking of enabling gcc optimizations by default, but I don't want to increase compile times, which means choosing a value for the -fplugin-arg-dragonegg-llvm-ir-optimize option that is low enough to get good compile times, yet high enough to get fast code. It would be great if you could play around with

On Thu, Jun 09, 2011 at 08:47:26PM -0400, Jack Howarth wrote: > Duncan, > Here are the complete benchmarks rerun against gcc 4.5.4 built with... > > Using built-in specs. > COLLECT_GCC=gfortran-fsf-4.5 > COLLECT_LTO_WRAPPER=/sw/lib/gcc4.5/libexec/gcc/x86_64-apple-darwin11.0.0/4.5.4/lto-wrapper > Target: x86_64-apple-darwin11.0.0 > Configured with:

hi, I have dragonegg r131864, gcc-4.5 r174052 and llvm r131897. When i tried to make the llvm test-suite, i got a error message: /home/ether/local/gcc-4.5/bin/gcc -fplugin=/home/ether/sources/dragonegg/dragonegg.so -I/home/ether/build/llvm-ts/projects/test-suite/SingleSource/UnitTests/Vector/SSE -I/home/ether/sources/llvm/projects/test-suite/SingleSource/UnitTests/Vector/SSE

Current dragonegg svn has all of the -fplugin-arg-dragonegg-enable-gcc-optzns bugs for usage with -ffast-math -O3 addressed except for those related to PR2314. Using the -fno-tree-vectorize option, we can evaluate the current state of -fplugin-arg-dragonegg-enable-gcc-optzns with the Polyhedron 2005 benchmarks compared to stock dragonegg and stock gcc 4.5.4. The runtime benchmarks below show that

Duncan, Here are the complete benchmarks rerun against gcc 4.5.4 built with... Using built-in specs. COLLECT_GCC=gfortran-fsf-4.5 COLLECT_LTO_WRAPPER=/sw/lib/gcc4.5/libexec/gcc/x86_64-apple-darwin11.0.0/4.5.4/lto-wrapper Target: x86_64-apple-darwin11.0.0 Configured with: ../gcc-4.5.4/configure --prefix=/sw --prefix=/sw/lib/gcc4.5 --mandir=/sw/share/man --infodir=/sw/lib/gcc4.5/info

Hi Jack, thanks for doing this. > Below are the tabulated compile times and executable sizes. > > A) gcc 4.5.4svn using -msse3 -ffast-math -O3 -fno-tree-vectorize > B) gcc 4.5.4svn/dragonegg using -msse3 -ffast-math -O3 -fno-tree-vectorize -fplugin-arg-dragonegg-enable-gcc-optzns > C) gcc 4.5.4svn/dragonegg using -msse3 -ffast-math -O3 -fno-tree-vectorize These numbers really

On Thu, Jun 09, 2011 at 03:44:40PM +0200, Duncan Sands wrote: > Hi Jack, thanks for doing this. > >> Below are the tabulated compile times and executable sizes. >> >> A) gcc 4.5.4svn using -msse3 -ffast-math -O3 -fno-tree-vectorize >> B) gcc 4.5.4svn/dragonegg using -msse3 -ffast-math -O3 -fno-tree-vectorize -fplugin-arg-dragonegg-enable-gcc-optzns >> C)

Duncan, Below are the tabulated compile times and executable sizes. A) gcc 4.5.4svn using -msse3 -ffast-math -O3 -fno-tree-vectorize B) gcc 4.5.4svn/dragonegg using -msse3 -ffast-math -O3 -fno-tree-vectorize -fplugin-arg-dragonegg-enable-gcc-optzns C) gcc 4.5.4svn/dragonegg using -msse3 -ffast-math -O3 -fno-tree-vectorize Compile time (seconds) Benchmark A) stock B) gcc 4.5.4/ C)

Hi ether, > I have dragonegg r131864, gcc-4.5 r174052 and llvm r131897. When i > tried to make the llvm test-suite, i got a error message: ... > cc1: error: invalid option '-fplugin-arg-dragonegg-disable-llvm-optzns' > cc1: error: Fail to initialize plugin /home/ether/sources/dragonegg/dragonegg.so this is my fault: you now need to use

On Thu, Jun 09, 2011 at 03:44:40PM +0200, Duncan Sands wrote: > Hi Jack, thanks for doing this. > >> Below are the tabulated compile times and executable sizes. >> >> A) gcc 4.5.4svn using -msse3 -ffast-math -O3 -fno-tree-vectorize >> B) gcc 4.5.4svn/dragonegg using -msse3 -ffast-math -O3 -fno-tree-vectorize -fplugin-arg-dragonegg-enable-gcc-optzns >> C)

> I'll try this after I repeat the initial benchmarks with --enable-checking=release. Thanks! Don't forget to do a release build of LLVM too, i.e. configure with --enable-optimized --disable-assertions Building dragonegg will the use the same options. Ciao, Duncan.

On 4/9/2011 6:09 AM, Duncan Sands wrote: > Hi Jack, thanks for the numbers. Any chance of analysing why gcc does better on > those where it does much better than dragonegg? > > Ciao, Duncan. Also, does -fplugin-arg-dragonegg-enable-gcc-optzns get Dragonegg to match GCC performance where GCC was faster? Marcus

Duncan, Is this expected for x86_64-apple-darwin12 under Xcode 5? Using current llvm/compiler-rt/clang/polly/testsuite with dragonegg 3.4 branch, I see the warnings... % /sw/lib/gcc4.8/bin/gcc-4 -fplugin=/sw/lib/gcc4.8/lib/dragonegg.so -specs=/sw/lib/gcc4.8/lib/integrated-as.specs -fplugin-arg-dragonegg-enable-gcc-optzns -Ofast himenoBMTxpa.c himenoBMTxpa.c: In function ‘main’:

I was quite surprised to find that dragonegg svn can now compile all of xplor-nih (which is a complex mix of c, c++ and fortran that is a regression magnet for FSF gcc). The xplor-nih package was compiled at -O3 -ffast-math -funroll-loops for all three compilers. The xplor testsuite passed without regressions and benchmarked as follows... dragonegg svn with llvm 2.9 and FSF gcc 4.5.3svn Total

On Thu, Nov 21, 2013 at 07:37:46PM -0500, Jack Howarth wrote: > Duncan, > Is this expected for x86_64-apple-darwin12 under Xcode 5? Using current > llvm/compiler-rt/clang/polly/testsuite with dragonegg 3.4 branch, I see > the warnings... > > % /sw/lib/gcc4.8/bin/gcc-4 -fplugin=/sw/lib/gcc4.8/lib/dragonegg.so -specs=/sw/lib/gcc4.8/lib/integrated-as.specs

> Is there anything I can do to make the build more verbose so I can debug this? make VERBOSE=1

The new dragonegg 2.9 sources fail to build against either FSF gcc 4.5.2 or 4.5.3svn (with the i386_static.diff patch applied) on x86_64-apple-darwin10. In both cases, the build fails as... GCC=/sw/lib/gcc4.5/bin/gcc-4 LLVM_CONFIG=/sw/bin/llvm-config make CPPFLAGS="-DENABLE_LTO -I/sw/include" Compiling utils/TargetInfo.cpp <command-line>: warning: "__STDC_LIMIT_MACROS"

Despite the commit of... ------------------------------------------------------------------------ r135371 | lattner | 2011-07-18 00:25:32 -0400 (Mon, 18 Jul 2011) | 2 lines untested patch to de-constify llvm::Type, patch by David Blaikie! current dragonegg svn at r135391 still fails to compile against FSF gcc 4.5.3 with the failure... In file included from