[LLVMdev] Polyhedron 2005 results for dragonegg 3.3svn
baldrick at free.fr
Thu May 23 07:01:40 PDT 2013
On 23/05/13 15:53, Jack Howarth wrote:
> On Thu, May 23, 2013 at 03:40:00PM +0200, Duncan Sands wrote:
>> Hi Jack,
>> On 23/05/13 15:37, Jack Howarth wrote:
>>> 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 skews the geometric mean
>>> of the run time to much higher values.
>> I also didn't hook up LLVM's new fast-math optimizations yet, which I expect to
>> make a big difference.
> Is current dragonegg 3.3svn configured to enable llvm vectorization like clang or do we still have to
> manually pass those flags with -fplugin-arg-dragonegg-llvm-option? Also can the new fast-math optimizations
> be manually enabled in dragonegg via flags to -fplugin-arg-dragonegg-llvm-option as well?
no, like -fast-math, the autovectorizer is not turned on. This is because I
want the testsuite to be building with no failures again before turning on
additional optimizations. There is no way to turn on the fast-math
More information about the llvm-dev