as played on a vertical 7x6 board. This takes about 10 minutes
on contemporary PCs.
WWW: http://homepages.cwi.nl/~tromp/c4/fhour.html
PR: ports/105778
Submitted by: trasz <trasz at pin.if.uz.zgora.pl>
benchmark kernels. With one executable, all of the supported
benchmarks, or a subset specified by the command line, can be run.
The rules, such as time measurement (including a repetitive call
of the kernels for better clock synchronization), message lengths,
selection of communicators to run a particular benchmark (inside
the group of all started processes) are program parameters.
WWW: http://www.intel.com/cd/software/products/asmo-na/eng/cluster/mpi/219848.htm
PR: ports/105665
Submitted by: trasz <trasz at pin.if.uz.zgora.pl>
Revision 1.3 of patch-ad worked around the problem, that only one writer
is allowed to allow a partition through GEOM. The fix was not complete,
leading to the file position not been incremented during reads and writes,
thus not testing sequential performance, but performance of cached reads
and writes, in general.
This fix makes rawio report reasonable sequential performance again,
but I'm still very suspicious with regard to randomized start positions
working. The results do not show the expected variation of sequential
read/write performance. I have not had time to look into this any deeper,
though, and thus decidied to not delay the commit any further ...
on single systems and clusters of systems. It is a command-line
based tool that grew out of the UNIX world and has been ported to
run in Windows environments as well. It is designed to provide
consistent and reproducible performance measurements of disk I/O
traffic. There are three basic components to xdd that include the
xdd program itself, a timeserver program, and a gettime program.
The timeserver and gettime programs are used to synchronize the
clocks of xdd programs simultaneously running across multiple
computer systems.
WWW: http://www.ioperformance.com/
PR: ports/100833
Submitted by: Gerhard Gonter <g.gonter at ieee.org>
- A printf format specified a long operand but received an offset_t value.
- The random numbers for large seek ranges were computed without regard
for operator precedence and could become negative (for file sizes larger
than 4GB, which was a wrong test for "large", since it did not account
for the chunk size).
The problems were found by etc at fluffles dot net (Enlightenment). Thanks
for the detailed report. Guess there aren't many Bonnie users with multi-
terabyte RAID systems; these bugs had been found long ago, else ...
create common testing platform to run predefined GTK+ widgets (opening
comboboxes, toggling buttons, scrolling text yms.) and this way define the speed
of device/platform.
WWW: http://gtkperf.sourceforge.net
PR: ports/96162
Submitted by: Andreas Kohn <andreas@syndrom23.de>
- Honor build environment CC and CFLAGS
- OPTIONS to support threading using pthreads
PR: ports/92714
Submitted by: Jeffrey H. Johnson <CPE1704TKS@bellsouth.net>
