similar to: [LLVMdev] major dragonegg improvement

Seems very likely to be related to Andy's SCEV-unroll-loops changes. --Owen On Sep 6, 2011, at 11:56 AM, Jack Howarth wrote: > I'm not certain yet which commit in the last couple of days caused this, > but the current llvm/dragonegg svn shows a major improvement in the runtime > of the xplor-nih testsuite when xplor-nih is built with FSF gcc 4.6.1 and the > dragonegg plugin

Try -mllvm -disable-unroll-scev if you're curious. There can be some luck involved. If you have the bitcode for the important function, I may be able to convert it into a test case to avoid regressing. I usually grab the unoptimized bitcode as follows: -emit-llvm -mllvm -disable-llvm-optzns -o module.bc -Andy On Sep 6, 2011, at 12:03 PM, Owen Anderson wrote: > Seems very likely to be

Is the new EH scheme completely compatible with the existing linker in Xcode 4.1? I am finding that today's changes break the ability to link xplor-nih with dragonegg under FSF gcc 4.6.2... de-g++46 -c thread.cc -O3 -ffast-math -funroll-loops -g -DX_MMAP_FLAGS=0 -DFORTRAN_INIT -fno-common -DDARWIN -D_REENTRANT -DNDEBUG -I/Users/howarth/xplor-nih-2.27/vmd/

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

What exactly are the current limitations for using -O4 to create shared libraries with llvm/llvm-gcc-4.2 2.5? I tried a build of xplor-nih at -O4 with llvm-gcc, llvm-g++ and llvm-gfortran. The build fails to link shared libraries with errors such as... Building xplor-nih for platform: Darwin_9_x86 [ -d /Users/howarth/xplor-nih-2.21/bin.Darwin_9_x86/ ] || mkdir

With current dragonegg svn, the Polyhedron 2005 benchmarks all now pass when using the compiler plugin under FSF gcc 4.6.1 on x86_64-apple-darwin11. The differences between the runtime and compile times when using the same plugin under FSF gcc 4.5.4svn are small. Once new vector_select feature is available in llvm and -fplugin-arg-dragonegg-enable-gcc-optzns supports -ftree-vectorizer we might see

After trying the recommended use of -O4 -fvisibility=hidden to compile xplor-nih with full LTO optimizations, I discovered three symbols become undefined... llvm-gcc-4 -O4 -fvisibility=hidden -o xplor xplor.o \ \ -L. -lxplorCmd -lxplor -L/Users/howarth/xplor-nih-2.21/bin.Darwin_9_x86/ -lfft -lintVar -lvmd -lpy -lswigpy-xplor -ltclXplor -lswigtcl8-xplor -lnmrPot -lcommon -lmarvin \

Le 25 janv. 09 à 06:01, Jack Howarth a écrit : > After trying the recommended use of -O4 -fvisibility=hidden to > compile xplor-nih with full LTO optimizations, I discovered three > symbols become undefined... > > llvm-gcc-4 -O4 -fvisibility=hidden -o xplor xplor.o \ > \ > -L. -lxplorCmd -lxplor -L/Users/howarth/xplor-nih-2.21/ > bin.Darwin_9_x86/ -lfft -lintVar

Duncan, With the commit from http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20121203/158488.html, the Polyhedron 2005 benchmarks complete again on x86_64-apple-darwin12. The result are similar to what were seen with FSF gcc 4.6.2svn and llvm/dragonegg 3.0 (which was the last release that passed pb05) http://lists.cs.uiuc.edu/pipermail/llvmdev/2011-October/044091.html. Jack

Hi Jack, thanks for these numbers. > With the commit from http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20121203/158488.html, > the Polyhedron 2005 benchmarks complete again on x86_64-apple-darwin12. The result are similar to what > were seen with FSF gcc 4.6.2svn and llvm/dragonegg 3.0 (which was the last release that passed pb05) >

Attached are the Polyhedron 2005 benchmark results for current llvm/dragonegg svn on x86_64-apple-darwin11 built against Xcode 4.3.2 and FSF gcc 4.6.3. The benchmarks for -msse3 and -msse4 appear identical (at least for degg+optnz). This is fortunate since there seems to be a bug in -msse4 on 2.33 GHz (T7600) Intel Core 2 Duo Merom (http://llvm.org/bugs/show_bug.cgi?id=12434).

On Tue, Apr 03, 2012 at 09:26:38AM +0200, Duncan Sands wrote: > Hi Jack, > >> Attached are the Polyhedron 2005 benchmark results for current llvm/dragonegg svn >> on x86_64-apple-darwin11 built against Xcode 4.3.2 and FSF gcc 4.6.3. > > thanks for the numbers. How does this compare to LLVM 3.0 - were there any > regressions? The results from just before

On Tue, 3 Apr 2012 08:57:51 -0400 Jack Howarth <howarth at bromo.med.uc.edu> wrote: > On Tue, Apr 03, 2012 at 09:26:38AM +0200, Duncan Sands wrote: > > Hi Jack, > > > >> Attached are the Polyhedron 2005 benchmark results for current > >> llvm/dragonegg svn on x86_64-apple-darwin11 built against Xcode > >> 4.3.2 and FSF gcc 4.6.3. > > >

Hi Jack, > Attached are the Polyhedron 2005 benchmark results for current llvm/dragonegg svn > on x86_64-apple-darwin11 built against Xcode 4.3.2 and FSF gcc 4.6.3. thanks for the numbers. How does this compare to LLVM 3.0 - were there any regressions? Ciao, Duncan. The benchmarks > for -msse3 and -msse4 appear identical (at least for degg+optnz). This is fortunate > since

Below are the results for the Polyhedron 2005 benchmarks compiled with llvm/compiler-rt/dragonegg 3.3svn at r182439 against current FSF gcc 4.7.3svn and 4.8.1svn. The only major bug remaining in the dragonegg 3.3svn support for gcc 4.8.x is http://llvm.org/bugs/show_bug.cgi?id=15980 which results in unresolved symbols for _iround and _iroundf in the aermod and rnflow testcases. Note that this

With the case-insensitive file system patch from http://llvm.org/bugs/show_bug.cgi?id=9656#c15 applied to dragonegg 2.9, the following Polyhedron 2005 benchmarks are seen on x86_64-apple-darwin10 under gcc 4.5.3svn using the dragonegg plugin... ================================================================================ Date & Time : 8 Apr 2011 19:52:56 Test Name :

The Polyhedron 2005 benchmark results for dragonegg svn at r141492 using FSF gcc 4.6.2svn measured on x86_64-apple-darwin11 are listed below. The benchmarks used the optimizaton flags... -msse4 -ffast-math -funroll-loops -O3 in all cases. The use of -fplugin-arg-dragonegg-enable-gcc-optzns to allow for autovectorization from the FSF gcc front-end only produces a single run-time regression,

Hi Chris, >> PS: With -fplugin-arg-dragonegg-enable-gcc-optzns the LLVM optimizers are run at >> the following levels: >> >> Command line option LLVM optimizers run at >> ------------------- ---------------------- >> -O1 tiny amount of optimization >> -O2 or -O3 -O1 >> -O4 or -O5

On Oct 8, 2011, at 12:05 PM, Duncan Sands wrote: > PS: With -fplugin-arg-dragonegg-enable-gcc-optzns the LLVM optimizers are run at > the following levels: > > Command line option LLVM optimizers run at > ------------------- ---------------------- > -O1 tiny amount of optimization > -O2 or -O3 -O1 > -O4 or -O5

Duncan, With r182593, the dragonegg 3.3 branch now completely passes the Polyhedron 2005 benchmarks using the FSF gcc 4.8.1svn compiler. Thanks. Jack Tested on x86_apple-darwin12 Compile Flags: -ffast-math -funroll-loops -O3 de-gfortran47: /sw/lib/gcc4.7/bin/gfortran -fplugin=/sw/lib/gcc4.7/lib/dragonegg.so -specs=/sw/lib/gcc4.7/lib/integrated-as.specs de-gfortran48: