Lines Matching +full:run +full:- +full:time
1 Version 5.1.3 -- 2011-01-13
18 3. Do "Run" to run the system test; "Run graphics" to run the graphics
19 tests; "Run gindex" to run both.
21 You will need perl, as Run is written in perl.
47 a space, it should now run (previously it failed).
59 * In pgms/tst.sh, changed "sort -n +1" to "sort -n -k 1"
75 why runlevel 1 produced odd results -- runlevel 1 doesn't set LANG, and
76 hence reverts to ASCII, whereas most people use a UTF-8 encoding, which is
86 I also added the "grep" and "sysexec" tests. These are non-index tests,
89 these useful. They aren't in any of the main test groups; do "Run grep
90 sysexec" to run them.
93 -------------
112 As before, each test is run for 3 or 10 iterations. However, we now discard
117 for a test run to see the discarded scores.
119 Made the tests compile and run on x86-64/Linux (fixed an execl bug passing
127 -------------
148 All the work I've done on this release is Linux-based, because that's
149 the only Unix I have access to. I've tried to make it more OS-agnostic
151 by /usr/bin/time. However, it's possible that portability has been damaged.
158 The big change has been to make the tests multi-CPU aware. See the
161 * Completely rewrote Run in Perl; drastically simplified the way data is
167 ignored for the index and wasted about 10 minutes per run (see fstime.c).
172 hostname-date-sequence.
180 -------------
182 The index is still based on David Niemi's SPARCstation 20-61 (rated at 10.0),
188 * The Pipe-based Context Switching test (context1) was being dropped
193 in single-copy mode). I made up the baseline score for this by
197 SPECIFICATIONS" section of Run.
212 perlbench and poll added as "exhibition" (non-index) benchmarks.
240 - The biggest change is to put a lot more operating system-oriented
241 tests into the index. I experimented for a while with a decibel-like
246 "George", certain SPARCstation 20-61 with 128 MB RAM, a SPARC Storage
251 avoiding the skew that was once possible (e.g. a Pentium-75 which got
258 I am finding new SPARCs running Solaris 2.4 getting about 15-20, and
259 my 486 DX2-66 Compaq running Linux 1.3.45 got a 9.1. It got
262 over 20 on the OS-oriented benchmarks. The Pentium-75 running
265 - It is difficult to get a modern compiler to even consider making
272 - fstime: this had some bugs when compiled on modern systems which return
287 - Instead of 1,2,4, and 8-shell benchmarks, went to 1, 8, and 16 to
288 give a broader range of information (and to run 1 fewer test).
290 done with 16 at a time on slow systems, so there are some significant
299 well-compiled some of the common shell utilities like grep, sed, and
302 twice as high as 486es due to their 64-bit bus). Small, sometimes
303 broken shells like "ash-linux" do particularly well here, while big,
306 - "dc" is a somewhat iffy benchmark, because there are two versions of
310 - Execl is a somewhat troubling benchmark in that it yields much higher
315 - Arithoh is really more an indicator of the compiler quality than of
316 the computer itself. For example, GCC 2.7.x with -O2 and a few extra
321 notably the fstime suite; and with how long it takes to run. But I think
323 time.
325 If anyone has ideas on how to make these benchmarks faster, lower-variance,
327 hesitate to e-mail me.
333 your system is BSD or SysV. (It uses the output format of time (1)
337 ---
348 for the time request by the benchmark administration script
349 (Run). As soon as the clock is started, the test is run with a
352 and the program terminates. Since the time resolution, signal
354 precise time that was requested, the test program is also run
355 from the time (1) command. The real time value returned from time
358 overhead time that is not taken into account, therefore the
373 --
383 --
390 The file access tests have been reversed so that the test is run
391 for a fixed time. The amount of data transfered (written, read,
399 supposed to do it. Or, simpler yet, just run the benchmarks from
402 The options to Run have not been checked in a while. They may no
403 longer function. Next time, I'll get back on them. There needs to
404 be another option added (next time) that halts testing between
406 before the next test or iteration is run. This can cause
411 queue space. The default set in the Run script is 1024 bytes.
414 Time, System Time, and Real Time. Generally, in reporting, we
415 plan on using the Real Time values with the benchs run with one