[continued from previous message]
programmed and worked with the following computer that was called Altos
586, it was a Unix system, here it is:
https://en.wikipedia.org/wiki/Altos_586
And i have gotten my university level Diploma in Microelectronics and informatics in 1989.
So as you notice that i know how to program in Unix and in Linux and in
Windows too, and as a proof here is my new scalable algorithm invention
that i have also ported to Windows and Linux(and you can download the
zip file from my website and take a look at source code of it):
https://sites.google.com/site/scalable68/new-variants-of-scalable-rwlocks
And you can look at my other Open source software projects here in
my website:
https://sites.google.com/site/scalable68/
And my today new software invention is the following:
You have to know that a Turing-complete system can be proven
mathematically to be capable of performing any possible calculation or
computer program, and bash shell for Linux and Windows are
Turing-complete, and even if bash shell is not python, it is a
minimalist language that is especially designed for administrators of
operating systems, but i have noticed that bash shell is not suited for
for parallel programming, this is why i am enhancing it with my
scalable algorithms so that to support sophisticated parallel
programming on both Linux and Windows that permits it to scale much
better on RAIDs and on multicores. So i am also writing a book about my enhancement to bash shell with my scalable algorithms so that to help
others be efficient in bash shell programming and efficient in operating
system administration, and of course i will sell my book, so i don't
think you need python since python doesn't come with my scalable
algorithms that will enhance bash for Linux and Windows, and i think
operating systems administrators don't need python since it is
not suited for operating system administrators since it is
not a minimalist language as bash for Linux and Windows.
You can read more about bash shell from here:
https://www.infoworld.com/article/2893519/perl-python-ruby-are-nice-bash-is-where-its-at.html
More philosophy about my kind of interests and more about me..
More philosophy of what kind of friends have i ?
I look like a PhD researcher since i am an inventor and i have invented
many scalable algorithms and algorithms, and i am still inventing
algorithms, and this is why my friends are like PhD researchers, here is
one of my friends that is a PhD researcher and Full Professor, he is one
of my best friend, i know him for around 23 years:
https://www.usherbrooke.ca/gelecinfo/fr/departement/profs/khoa-fr/khoa-en/
So notice carefully his webpage:
https://www.usherbrooke.ca/gelecinfo/fr/departement/profs/khoa-fr/khoa-en/
And notice that he is a full professor that is teaching a course
of operational research(that uses sophisticated mathematics),
and it is called the following:
"Performance analysis, probability and queuing, GIF 360"
I have discussed with him a lot on operational research, since i have
also studied operational research, and here is some of my software
projects of operational research:
About capacity planning and queuing theory..
I am a white arab and i think i am smart since i have also
invented many scalable algorithms and algorithms, and i have a
university level Diploma in Microelectronics and informatics, and i am
a software developer, but i have also studied operational research..
And read my following thoughts about Operational research and some of my software projects in Operational research:
I have bought the following book called Performance by Design: Computer Capacity Planning By Example here:
https://www.amazon.ca/Performance-Design-Computer-Capacity-Planning/dp/0130906735
And the book is analyzing the performance of an E-Business Service with
queuing theory, but i think its methodology is error-prone because it
contains many mathematical calculations, so this is why i have decided
to construct another methodology that is much less error-prone and that
is easier and that uses the Jackson network , so my methodology works
with 65% or more of database read transactions, the total of write and
delete database transactions must be 25% or less, and it works too when
it is 65% or above of database write database transactions, so i think
my methodology is suitable to do capacity planning with mathematical
queuing theory of E-Business Services, and i will write a book about it
and explains my methodology, and of course i am taking care of the http
or https overhead and i will provide you with a program too.
And here is my PDQ for Delphi and Freepascal
This is a port by Amine Moulay Ramdane of PDQ version 6.2.0 to Delphi on Windows and to Freepascal on both Windows and Linux, i have also
provided you with two demos, one queuing MM1 demo, and another Jackson
network demo. Also i have provided you with my html tutorial on how to
solve analytically the Jackson network problem provided to you as a PDQ
demo.
You can download it from my website here:
https://sites.google.com/site/scalable68/pdq-for-delphi-and-freepascal
PDQ is an analytic queueing-circuit analyzer made freely available under MIT/X11 license from www.perfdynamics.com
Read more about PDQ here:
http://www.perfdynamics.com/Tools/PDQ.html
And i have also implemented M/M/n queuing model simulation with Object
Pascal, here it is:
https://sites.google.com/site/scalable68/m-m-n-queuing-model-simulation-with-object-pascal
I have also implemented Maxflow algorithm for Delphi and FreePascal,
here it is:
https://sites.google.com/site/scalable68/maxflow-algorithm-for-delphi-and-freepascal
More philosophy about AMD Ryzen Threadripper PRO and Nvidia V100 PCIe
(Volta)..
And I invite you to look at the following spec of AMD Ryzen Threadripper
PRO 3975WX 32-Core CPU that i will buy in the next month:
https://www.techpowerup.com/cpu-specs/ryzen-threadripper-pro-3975wx.c2315
And look carefully at the following benchmark:
https://www.xcelerit.com/computing-benchmarks/insights/benchmarks-intel-xeon-scalable-processor-vs-nvidia-v100-gpu/
So as you are noticing that the spec of Nvidia V100 PCIe (Volta) 16 GB
is 7,014 GFLOPs (double), and AMD Ryzen Threadripper PRO 3975WX 32-Core
CPU is around 6,451.2 GFLOPS, but look carefully at the price of Nvidia
V100 PCIe (Volta) 16 GB that is 7124 US dollars:
https://www.amazon.ca/PNY-TCSV100MPCIE-PB-Nvidia-Tesla-v100/dp/B076P84525/ref=pd_di_sccai_3?pd_rd_w=AmXIj&pf_rd_p=e92f388e-b766-4f7f-aac1-ee1d0056e8fb&pf_rd_r=77B7DWXEVBM5VSXT4NZG&pd_rd_r=27e26b6a-c0a6-4558-8a68-97e286ba6213&pd_rd_wg=HxaUi&pd_rd_i=
B076P84525&psc=1
And look at the price of AMD Ryzen Threadripper PRO 3975WX 32-Core CPU
that is 2790 US dollars:
https://www.newegg.ca/amd-ryzen-threadripper-pro-3975wx/p/N82E16819113677
So i think that AMD Ryzen Threadripper PRO 3975WX 32-Core CPU is
competitive in performance and price for the GFLOPS with Nvidia V100
PCIe (Volta) 16 GB.
I have just read the following interesting article about AVX512
On the dangers of Intel's frequency scaling
https://blog.cloudflare.com/on-the-dangers-of-intels-frequency-scaling/
So as you have just noticed by reading the above article that you have
not to use AVX512, because it heats a lot the CPU cores, so what Intel
is doing is to reduce a lot the speed of the CPU cores, but this is not
good for performance. So what i advice is to avoid AVX2 or AVX512
and choose to use AVX that has not this problem. And AMD Ryzen
Threadripper PRO 3975WX 32-Core that i will buy the next month also
supports AVX2.
More about me and about fault-tolerant computer systems and more..
I am a white arab, and i think i am smart since i have also
invented many scalable algorithms and algorithms..
I have come to Canada when i was 20 years old, and i am living
in Canada Quebec for 32 years and now i am 52 years old , but i am
genetically an athletic guy and i feel that i am still young because
i am more athletic and i am 6 Feet tall, and i am beautiful
from the inside since i am a gentleman type of person and it is also
genetical in me, and i have worked as a software consultant with
some hospitals in USA, and i have worked with some computer hardware
companies and software companies in British Colombia and in New
Brunswick in Canada, and here is more about my education and my Diploma
and more:
My name is Amine Moulay Ramdane, i am a white arab from Morocco, and
i think i am smart since i have also invented many scalable algorithms
and algorithms, and i am a gentleman type of person, and i live in
Quebec Canada since year 1989, i am also a Canadian from Morocco, and
you have seen me writing my thoughts of my political philosophy here,
and now i will talk about my education and my Diploma: my Diploma is a university level Diploma, my school in Morocco where i have studied and
gotten my university level Diploma in Microelectronics and informatics
was under the control of Paris Academie in France (we call it Académie
de Paris), and here it is:
https://translate.google.com/translate?hl=en&sl=auto&tl=en&u=https%3A%2F%2Ffr.wikipedia.org%2Fwiki%2FAcad%25C3%25A9mie_de_Paris
And i have continued to study one more year of applied mathematics in university of Montreal in Quebec Canada, and i have succeeded this one
year in applied mathematics in university of Montreal, so with my
Diploma and this one year of applied mathematics i have studied and
succeeded 3 years at the university level, after that i have studied
Network administration and i have also worked as a network administrator
and as software developer consultant, the name of my company was and is Cyber-NT Communications in Quebec Canada, and around years 2001 and
2002 i have started to implement some of my softwares like PerlZip that
looked like PkZip of PKware software company, but i have implemented it
for Perl , and i have implemented the Dynamic Link Libraries of my
PerlZip that permits to compress and decompress etc. with the
"Delphi"compiler, so my PerlZip software product was very fast
and very efficient, in year 2002 i have posted the Beta version on
internet, and as a proof , please read about it here:
http://computer-programming-forum.com/52-perl-modules/ea157f4a229fc720.htm
And after that i have sold the release version of my PerlZip
product to many many companies and to many individuals around the world,
and i have even sold it to many Banks in Europe, and with that i have
made more money.
And after that i have continued to work like a software developer
consultant and network administrator, the name of my company was and is Cyber-NT Communications,
Here is my company in Quebec(Canada) called Cyber-NT Communications,
i have worked as a software developer and as a network administrator,
read the proof here:
https://opencorporates.com/companies/ca_qc/2246777231
Also read the following part of a somewhat old book of O'Reilly called
Perl for System Administration by David N. Blank-Edelman, and you will
notice that it contains my name and it speaks about some of my Perl modules:
https://www.oreilly.com/library/view/perl-for-system/1565926099/ch04s04.html
And you can find my Open source software projects here in my website:
https://sites.google.com/site/scalable68/
More philosophy about HP NonStop to x86 Server Platform fault-tolerant
computer systems and more..
I am white arab and i think i am smart since i have also invented many
scalable algorithms and algorithms..
Now HP to Extend HP NonStop to x86 Server Platform
HP announced in 2013 plans to extend its mission-critical HP NonStop
technology to x86 server architecture, providing the 24/7 availability
required in an always-on, globally connected world, and increasing
customer choice.
Read the following to notice it:
https://www8.hp.com/us/en/hp-news/press-release.html?id=1519347#.YHSXT-hKiM8
And today HP provides HP NonStop to x86 Server Platform, and here is
an example, read here:
https://www.hpe.com/ca/en/pdfViewer.html?docId=4aa5-7443&parentPage=/ca/en/products/servers/mission-critical-servers/integrity-nonstop-systems&resourceTitle=HPE+NonStop+X+NS7+%E2%80%93+Redefining+continuous+availability+and+scalability+for+x86+data+sheet
So i think programming the HP NonStop for x86 is compatible with x86 CPU architecture programming, so my following methodolody is working
correctly, read it carefully since i have just extended my thoughts:
Here is my next powerful computer..
In the next month i will buy a powerful computer with the following
powerful CPU:
AMD Ryzen Threadripper PRO 3975WX 32-Core 3.5 GHz
https://www.newegg.ca/amd-ryzen-threadripper-pro-3975wx/p/N82E16819113677
So my computer that i will buy in the next month will cost me around 9 thousands dollars, since i want to do some testing with the above CPU
that comes with 32 cores and 8 memory channels, since i have invented
many scalable algorithms and algorithms and i am writing two books about parallelism and concurrency that i will sell and i have invented some
powerful tools for parallelism and concurrency that i will sell too etc.
So as you are noticing i am also buying a 3,499 US dollars CPU from USA
to make the USA economy works better.
Here is some benchmarks that shows a less powerful Threadripper 3970x
AMD CPU with 4 channels of memory:
https://www.pugetsystems.com/labs/hpc/HPC-Parallel-Performance-for-3rd-gen-Threadripper-Xeon-3265W-and-EPYC-7742-HPL-HPCG-Numpy-NAMD-1717/
Also my next AMD Ryzen Threadripper PRO 3975WX 32-Core 3.5 GHz can be configured to work as 4 NUMA nodes, and the accessing time of far memory
will be slower than accessing time of near memory by 1.6x times. So as
you are noticing that my scalable algorithms such as my scalable MLock
will work correctly, since what is important is scalability even if
accessing time of far memory will be slower than accessing time of near
memory by 1.6x times on my next AMD Ryzen Threadripper PRO 3975WX
32-Core 3.5 GHz.
About smartness and about MCS Lock and more..
I have just read the following article from ACM:
Scalability Techniques for Practical Synchronization Primitives
https://queue.acm.org/detail.cfm?id=2698990
Notice how they are speaking about one of the best scalable Lock that we
call MCS lock, but i think that CLH and MCS locks are not smart since
those scalable Locks are like intrusive, since they have to hide the
required parameter to be passed, this is why i think i am smart since i
have invented a scalable Lock that is better than MCS Lock since my
scalable Lock doesn't require any parameter to be passed, just call the
Enter() and Leave() methods and that's all, here it is, read carefully
about it in my website here:
https://sites.google.com/site/scalable68/scalable-mlock
I have also just enhanced it more and i will post it soon.
I have also invented many other scalable algorithms and algorithms..
Here is some of them:
https://sites.google.com/site/scalable68/scalable-reference-counting-with-efficient-support-for-weak-references
https://sites.google.com/site/scalable68/scalable-rwlock
https://sites.google.com/site/scalable68/new-variants-of-scalable-rwlocks
https://groups.google.com/forum/#!topic/comp.programming.threads/VaOo1WVACgs
https://sites.google.com/site/scalable68/an-efficient-threadpool-engine-with-priorities-that-scales-very-well
Thank you,
Amine Moulay Ramdane.
--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)