An old benckmark

Estimating the performance of a modern computer is a difficult task and given results are often deceiving: not only clock speed matters; the modern CPUs have multiple cores, some sort of parallelism implemented in each core with sophisticated pipelines, many levels of built-in caches and use all sort of tricks to be faster, as: branch prediction, speculative and out-of-order execution etc.. Another key factor to consider is memory access, and sometimes also the network is important.

Performances can be very different for different applications; to evaluate a computer for your usage you have to test with something enought similar to your application.

In the nineties Alex Bielajew proposed a simple benchmark for EGS4, a Monte Carlo program simulating the transport of radiation in matter. This program was very popular in the nineties among the medical physics groups, and some enhanced versions of this program are in use also today, mainly for simulation and design of medical equipments (EGS5, EGSnrc). The original EGS4 is no more used and the Bielajew benchmark has been forgotten; nevertheless I continued to run that benchmark program on every computer I used from the eighties until 2020.

This benchmark program doesn't have a graphical interface, and doesn't use the parallelism of modern multi-core, multi-threads systems, doesn't use the network or a massive amount of data; it is something similar to many of the programs I run; it was an enought good test for me and can give an idea of the evolution of computer power in all these years.

The following picture summarizes the results. The speed values are relative to the time needed to run the benchmark on a popular mini computer of the old times: the Vax-11/780 (about five hours). The VAX-11/780, commercialized by Digital Equipment in 1977, was one of the first mini-computers available, it had a great success, for its affordable price and good performances; it had a 5MHz clock, and some megabytes of RAM.

Computer speed

EGS4 Benchmark results for my computers, from 1985 up to 2020

The first green points on the left are the Microvax minicomputers I used around 1990. I had a Microvax-II in the eighties that had about the same performance of the Vax-11/780 (not shown in this plot).

The IBM RISC workstations of the nineties (red dots) had a bit better performances, but the Dec-alpha workstations (the little blue dots around 1997) where the faster choiche I had in that period.

Intel CPU became faster in the new century with the Pentium, with a computation speed increased by thousands, compared with the mini computer of ten years before.

The blue circles between 2005 and 2010 are some workstation with Intel Xeon CPU. These are not much faster than common PC of the same time; Xeon, intended for servers, with bigger cache and more cores, are more suited for serving many users and programs, than for running this little benchmark, which is more sensitive to clock speed.

The red triangles are Xeon CPU used for the ENEA CRESCO supercomputer. In the old times of the CRAY systems, supercomputers had special CPU built for the specific supercomputer, with the best technologies available, other systems had cheaper and much less powerful CPU. But today most supercomputer are a grid of hundreds or thousands of commercial CPU, with many cores, connected by a hight performance network: to exploit their power you have to separate your computation into independent parts, to be executed on the different CPU at the same time, in parallel. Not all the problems are suited for parallelization and programming a parallel computer is more an art than an exact science: you have to minimize the data transfer between the CPU, accounting for memory access time, the cache sizes of the specific system and, as in CRESCO, you have to consider that CPU are connected by a network shared among many running programs.
For a simple program, which doesn't use parallelization, a simple PC is a better choice, much cheaper, easy to manage and faster... this was not understood by many of my colleagues...

The yearly increase of CPU speed was greater before 2005: the Moore law, (more an advertising slogan than a real law), telling that the speed of CPU was doubling each year, couldn't cope with thermal problem and current leakage, so maximum clock speed settled a bit below 4 GHz, and performance increase for this benchmark flattened; but we still have an increase in recent years due to better CPU design. The green triangles at the top are the PC and the notebook I bought in 2020, when retired.

An interesting point is the pink dot labeled "ARM" at the bottom right: this is my old cellphone, an Huawey P6 II Pro, with a Kirin 620 ARM CPU; it rates 460 in this performance scale; a supercomputer of the eighties could rate between 20 and 50, but had no graphical capabilities, no wifi, no bluethoot and much less memory.

Today everyone has in his pocket a computer with a computing performance ten or twenty times that of the more powerful million-dollar supercomputers of the eighties. Most of this power is used to operate a graphical interface of extreme complexity, which allow us to send photos of our pet with only some clicks.

The following image is a log-scale plot of the same data; the fast increase in performance in the nineties and the nearly linear increase in performance after 2005 is more visible.

Computer speed

EGS4 Benchmark from 1985 up to 2020, log scale.

All the data of the benchmark are shown in the table below, my data are not uniform, different compilers and operating system can give slightly different results, and some details on computers and compilers used has been forgotten and are not reported in the table.

The first column is the computer nickname, then we have the computer or CPU type; the operating system and compiler (Debian, Centos, Suse are all Linux systems); clock speed; year and the performance, relative to the Vax-11/780 (18510 sec., about five hours).

Nickname Computer or CPU System and compiler Clock (MHz) Year Relative Speed
ebo421 Microvax II 630 VAX-VMS 5 1985 1
ebomv1 Microvax 3100/80 VAX-VMS 50 1993 8
astbo4 Microvax 4000/90A VAX-VMS 30 1991 29
axpbo6 DEC alpha 21064a VAX-VMS 200 1993 57
axpbo6 DEC alpha 21064a DU 4.0A 200 1993 65
eboal1 DEC alpha 3000/300 VAX-VMS 150 1993 32
eboal1 DEC alpha 3000/300 DU 4.0A 150 1993 38
eboals DEC alpha 21164 DU 4.0B 300 1995 155
maros DEC alpha 21164/400 DU 4.0D 400 1997 237
vega DEC alpha 21164/433 433 1997 267
graphlab SGI octane MIPS R10000 IRIX 6 195 1997 131
risc990 IBM RISC 6000/990 AIX 60 1993 42
risc590 IBM Risc 6000/595 AIX 135 1995 84
info251 IBM R6000/260 power3 AIX 200 1998 116
lanlook Intel 486 Debian 66 1992 4
bofi77A Pentium Pro 200 Linux 200 1995 67
spike Pentium Pro 200 Debian 200 1995 66
diaf3 Intel Pentium 166 Debian 166 1996 41
diaf Pentium II-266Mhz Debian 266 1997 94
bofi77B Pentium II-300 Linux 300 1997 106
nessie AMD K6-200 Debian 200 1997 50
bofi76 AMD K6-3d-300 Linux 300 1998 70
alpc Pentium II-350 Linux 350 1998 126
bofi77C Pentium II-400 Linux 400 1998 144
hercules Pentium II-400 Linux 400 1998 144
bofi79 Pentium II-Xeon 450 Linux 450 1998 162
diaf-II Pentium III-500 Linux 500 1999 178
diaf3-II AMD Athlon Suse 7.2 1330 2000 544
nica AMD K7-800 Athlon Linux 800 2000 317
ebo530 AMD K7-1.33 Athlon Debian 2.2 1330 2000 487
ebots1 Pentium 4 Linux 2000 2001 516
ebots2 AMD Athlon XP 1600+ Suse 8 1400 2001 577
monval02 AMD Athlon XP 2000+ Suse 8 1666 2002 666
eborsk6 AMD Athlon XP 2000+ Suse 8.1 1674 2002 685
shenron Pentium IV Debian 3.0 2200 2002 625
diaf-III AMD Athlon XP BartonDebian 3.0
g77 3.3.5
1837 2003 685
powerg5 powerpc 970 Mac OS-X darwin 8 2300 2003 636
asu Asus V6V
Intel Pentium M 740
Ubuntu 6.06.1
g77 3.4.6
1730 2005 964
winter HP Proliant ML530 GS
Intel Xeon 5150
Ubuntu 6.06
g77 3.4.6
1860 2006 1267
agile AMD 64 X2 Debian 4.0
g77 3.4.6
1400 2006 1371
fafnir AMD Athlon 64 X2 5600+ Debian 4.0
g77 3.4.6
2815 2006 1661
fafnir AMD Athlon 64 X2 5600+ Debian 8
gfortran 4.9.2
2800 2006 1574
cidm HP Proliant M350 G5
Xeon 5420
Ubuntu 8.04
g77 3.4.6
2500 2007 2050
cidm HP Proliant M350 G5
Xeon 5420
Ubuntu 8.04
gfortran 4.2.4
2500 2007 2100
main AMD Phenom II X4 955 Debian 5.0
gfortran 4.3.2
3200 2008 1990
main AMD Phenom II X4 955 Debian 8,
gfortran 4.9.2
3200 2008 2061
soniv Sony Vaio VPCF11M1E
Intel i5-M520
Ubuntu 10.04
gfortran 4.4.3
2400 2010 2682
toshi Toshiba Portege R700
Intel I5-M560
Debian 6
gfortran 4.4.5-8
2600 2010 2848
nos HP proliant ML350 G6
Intel Xeon E5520
Ubuntu 10.04
gfortran 4.4.3
2270 2009 2373
nos HP proliant ML350 G6
Intel Xeon E5520
gfortran 4.9.2
2270 2009 2249
cresco 3 AMD Opteron 6234 Centos 6.3
gfortran 4.8.2
4799 2011 1595
cresco 4 Intel Xeon E5-2665 Centos 6.3
gfortran 4.8.2
4800 2012 2314
cresco 5 Intel Xeon E5-2630 Centos 6.4
2300 2012 3402
cresco 6 Intel Xeon Platinum 8160 Centos-7.3
gfortran 7.3.0
2100 2017 2560
acercons Acer Travelmate P2510-M
Intel Core i5-6200U
Debian 8
gfortran 4.9.2
2300 2015 3329
fuji Intel Core i7-6700 Debian 9
gfortran 6.3.0
3400 2016 4535
last Intel Core i7-7700 Debian 9
gfortran 6.3.0
3600 2017 4850
panglong Intel Core i5-9400F Debian 10
gfortran 8.3.0
2900 2019 5500
tianlong Intel Core i3-8145U Debian 10
gfortran 8.3.0
2100 2020 5140
huawey Huawey CAM-L21
kirin 620
Android 6
gfortran 8.2.0
1200 2018 460

For details on the EGS4 benchmark see: