From 13f08fedb6ffb56117b1e73cfd72c29a3d201b52 Mon Sep 17 00:00:00 2001 From: Peter Teuben Date: Mon, 20 Nov 2023 16:31:46 -0500 Subject: [PATCH] upd --- man/man5/bench.5 | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/man/man5/bench.5 b/man/man5/bench.5 index eb382ed78..a38ee86fb 100644 --- a/man/man5/bench.5 +++ b/man/man5/bench.5 @@ -1,4 +1,4 @@ -.TH BENCH 5NEMO "31 August 2023" +.TH BENCH 5NEMO "20 November 2023" .SH "NAME" bench \- various NEMO benchmarks @@ -14,6 +14,12 @@ nemobench COMMAND There are several methods to compare the performance of NEMO on different processors or environments: .RS 2 + +.IP 0. +The command \fBmake bench5\fP from the $NEMO directory runs a small number of benchmarks designed +to each takae 5 seconds on a given CPU. An average \fIspeed\fP is then computed to compare different +compilers and/or CPU's, an idea simular to the \fIgeekbench\fP suite of tests. + .IP 1. The command \fBmake bench\fP from the $NEMO directory runs a standard benchmark of about a dozen selected NEMO programs. It should run in about 30 seconds on a ~2020 computer. A short @@ -21,12 +27,16 @@ table (see below in RESULTS) lists results from some recent computers. .IP 2. Various \fBBenchfile\fP filles scattered through the $NEMO source tree contain benchmarks. There is -no wrapper like "make check" has for Testfile's +no wrapper like "make check" has for Testfile's .IP 3. Selected man pages have some examples. Over time these should be moved into the Benchfile in the source directory where this program is maintained. Some are mentioned below in this man page. +.RS -2 +.PP +Unless otherwise noted, benchmarks are always performed at the max power settings of a laptop. + .SH "NEMOBENCH5" The NEMOBENCH5 benchmark (cd $NEMO;make bench5) runs a number (currently 6) N-body codes all calibrated to @@ -60,16 +70,18 @@ i5-10400H 700 Dell Precision 3351 (astroumd) AMD EPYC 7302 @ 3.0GHz 630 lma 1000/ 28000 Intel Core i9-9900X - geminid 1214 / 9467 Xeon Gold 5218 @ 2.30 GHz 761 unity/node99 1100 / 8610 -i5-10210U CPU @ 1.60 GHz 732 X1Y4 1029 / 3194 +i5-10210U @ 1.60 GHz 732 X1Y4 1029 / 3194 Xeon(R) Silver 4114 @ 2.20GHz - terra 777 / 10213 -i7-8550U CPU @ 1.80 GHz 548 T480 (1600) 696 / 1935 +i7-8550U @ 1.80 GHz 548 T480 (1600) 696 / 1935 Xeon E-2186G 3.80 GHz - aurora 1313 / 6721 i7-3820QM @ 2.70 GHz 498 MacBookPro (Retina, Mid 2012) -i7-3820 CPU @ 3.60 GHz 414 dante 833 / 3693 -Xeon(R) CPU E3-1280 @ 3.50 GHz 384 chara 828 / 3117 -i7-3630QM CPU @ 2.40 GHz 429 T530 (1200) 762 / 3006 +i7-3820 @ 3.60 GHz 414 dante 833 / 3693 +Xeon(R) E3-1280 @ 3.50 GHz 384 chara 828 / 3117 +i7-3630QM @ 2.40 GHz 429 T530 (1200) 762 / 3006 Xeon E5-2623 v4 @ 2.60 GHz - kraken 782 / 5800 Xeon X5550 @ 2.67 GHz 256 sdp 566 / 3938 +AMD Opteron(tm) 6380 234 yorp (2023) + .fi A typical output of bench5 might look as follows: @@ -164,7 +176,7 @@ The \fBbench8\fP measures how well your CPU performs simple OpenMP algorithm as more cores are employed. This can be an effective way to determine how well your CPU adjusts under increased power demands, for example laptops with thermal protection will scale down their cpu frequency as more cores are -employed. +employed or as a long benchmark heats up the CPU. .nf scaling2 umax=20000 np=1 iter=20