Lines Matching +full:multi +full:- +full:system
4 All the tests are executed using the "Run" script in the top-level directory.
11 hostname-2007-09-23-01
14 If you want to generate both the basic system index and the graphics index,
18 If your system has more than one CPU, the tests will be run twice -- once
23 Since the tests are based on constant time (variable work), a "system"
25 A "gindex" run on a dual-core machine will do 2 "system" passes (single-
26 and dual-processing) and one "graphics" run, for a total around one and
38 Run [ -q | -v ] [-i <n> ] [-c <n> [-c <n> ...]] [test ...]
42 -q Run in quiet mode.
43 -v Run in verbose mode.
44 -i <count> Run <count> iterations for each test -- slower tests
47 -c <n> Run <n> copies of each test in parallel.
49 The -c option can be given multiple times; for example:
51 ./Run -c 1 -c 4
53 will run a single-streamed pass, then a 4-streamed pass. Note that some
54 tests (currently the graphics tests) will only run in a single-streamed pass.
56 The remaining non-flag arguments are taken to be the names of tests to run.
59 When running the tests, I do *not* recommend switching to single-user mode
61 and it's not realistic (unless your system will actually be running in this
62 mode, of course). However, if using a windowing system, you may want to
64 so that randomly-churning background processes don't randomise the results
83 system The original Unix system tests (not all are actually
87 misc Various non-indexed tests
91 system:
93 whetstone-double Double-Precision Whetstone
94 syscall System Call Overhead
96 context1 Pipe-based Context Switching
99 fstime-w File Write 1024 bufsize 2000 maxblocks
100 fstime-r File Read 1024 bufsize 2000 maxblocks
102 fsbuffer-w File Write 256 bufsize 500 maxblocks
103 fsbuffer-r File Read 256 bufsize 500 maxblocks
105 fsdisk-w File Write 4096 bufsize 8000 maxblocks
106 fsdisk-r File Read 4096 bufsize 8000 maxblocks
108 shell1 Shell Scripts (1 concurrent) (runs "looper 60 multi.sh 1")
109 shell8 Shell Scripts (8 concurrent) (runs "looper 60 multi.sh 8")
110 shell16 Shell Scripts (8 concurrent) (runs "looper 60 multi.sh 16")
113 2d-rects 2D graphics: rectangles
114 2d-lines 2D graphics: lines
115 2d-circle 2D graphics: circles
116 2d-ellipse 2D graphics: ellipses
117 2d-shapes 2D graphics: polygons
118 2d-aashapes 2D graphics: aa polygons
119 2d-polys 2D graphics: complex polygons
120 2d-text 2D graphics: text
121 2d-blit 2D graphics: images and blits
122 2d-window 2D graphics: windows
137 "looper 30 dc < dc.dat", using your system's copy of "dc")
138 hanoi Recursion Test -- Tower of Hanoi
139 grep Grep for a string in a large file, using your system's
143 The following pseudo-test names are aliases for combinations of other
147 and whetstone-double
150 whets Alias for whetstone-double
151 whetstone Alias for whetstone-double
154 speed Runs the arithmetic and system groups
157 system Runs oldsystem plus shell1, shell8, and shell16
158 fs Runs fstime-w, fstime-r, fstime, fsbuffer-w,
159 fsbuffer-r, fsbuffer, fsdisk-w, fsdisk-r, and fsdisk
163 the oldsystem group, plus dhry2reg, whetstone-double,
167 2d-rects, 2d-ellipse, 2d-aashapes, 2d-text, 2d-blit,
168 2d-window, and ubgears
181 of a Unix-like system; hence, multiple tests are used to test various
182 aspects of the system's performance. These test results are then compared
183 to the scores from a baseline system to produce an index value, which is
185 values is then combined to make an overall index for the system.
187 Since 1995, the baseline system has been "George", a SPARCstation 20-61
189 were set at 10.0. (So a system which scores 520 is 52 times faster than
191 sense, there's no particular reason to update the base system, so for the
214 a system.
217 for these tests are separate from the basic system index. This seems
218 like a sensible division, since the graphics performance of a system
224 system's x11perf command (which must be installed and in the search
232 run and displays the average frames-per-second.
234 On multi-CPU systems, the graphics tests will only run in single-processing
245 If your system has multiple CPUs, the default behaviour is to run the selected
246 tests twice -- once with one copy of each test program running at a time,
248 this with the "-c" option; see "Detailed Usage" above.) This is designed to
251 - the performance of your system when running a single task
252 - the performance of your system when running multiple tasks
253 - the gain from your system's implementation of parallel processing
256 of two runs on a dual-processor system, one in single-processing mode, one
257 dual-processing:
260 -------------------- ------ ------ ----
264 File Copy 1024 759.4 595.9 -22%
265 File Copy 256 535.8 438.8 -18%
266 File Copy 4096 1261.8 1043.4 -17%
268 Pipe-based Switching 326.8 1229.0 276%
272 System Call Overhead 944.2 1445.5 53%
273 -------------------- ------ ------ ----
276 As expected, the heavily CPU-dependent tasks -- dhrystone, whetstone,
277 execl, pipe throughput, process creation -- show close to 100% gain when
280 The Pipe-based Context Switching test measures context switching overhead
283 but it seems to be consistent on my system. I think this may be an issue
286 The System Call Overhead shows a lesser gain, presumably because it uses a
287 lot of CPU time in single-threaded kernel code. The shell scripts test with
288 8 concurrent processes shows no gain -- because the test itself runs 8
290 is run in single-stream mode. The same test with one process per copy
294 multi-processing. That there's no gain is to be expected, since the tests
304 --------------
306 The multi-processing mode is implemented at the level of test iterations.
319 once. This is probably not very useful for testing multi-CPU performance.
331 it is set to en_US.UTF-8, foir example, then text is treated as being
332 encoded in UTF-8, which is more complex and therefore slower. Setting
345 system; but we also report the character mapping and collation order which
359 system's compiler, the performance of the compiler will inevitably impact
361 system, you probably care about its overall speed, which may well depend
375 The C test is very dubious -- it tests the speed of compilation. If you're
376 running the exact same compiler on each system, OK; but otherwise, the
378 anything about the speed of your system, since the compiler may simply be
379 spending more time to super-optimise the code, which would actually make it
382 This will be particularly true on architectures like IA-64 (Itanium etc.)
386 Some tests are even more dubious in terms of host-dependency -- for example,
392 Another age-old issue is that of the benchmarks being too trivial to be
394 wide-ranging flow path analyses, the danger of parts of the benchmarks
398 give a reasonable measure of overall system performance; but the results