Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.programming > #11180 > unrolled thread

Why Energy Is A Big And Rapidly Growing Problem For Data Centers

Back to article view | Back to comp.programming

Contents

  Why Energy Is A Big And Rapidly Growing Problem For Data Centers aminer68@gmail.com - 2020-08-30 13:05 -0700

#11180 — Why Energy Is A Big And Rapidly Growing Problem For Data Centers

Hello,


Why Energy Is A Big And Rapidly Growing Problem For Data Centers

It’s either a breakthrough in our compute engines, or we need to get deadly serious about doubling the number of power plants on the planet.

Read more here:

https://www.forbes.com/sites/forbestechcouncil/2017/12/15/why-energy-is-a-big-and-rapidly-growing-problem-for-data-centers/#1d126295a307

And read the following:

Lightmatter Introduces Optical Processor to Speed Compute for Next-Gen AI

"The Department of Energy estimates that by 2030, computing and communications technology will consume more than 8 percent of the world's power. Transistors, the workhorse of traditional processors, aren't improving; they're simply too hot. Building larger and larger datacenters is a dead end path along the road of computational progress," said Nicholas Harris, PhD, founder and CEO at Lightmatter. "We need a new computing paradigm. Lightmatter's optical processors are dramatically faster and more energy efficient than traditional processors. We're simultaneously enabling the growth of computing and reducing its impact on our planet."

Read more here:

https://www.techpowerup.com/271103/lightmatter-introduces-optical-processor-to-speed-compute-for-next-gen-ai

I am a white arab that is an inventor of many scalable algorithms and
there implementations, and now i will talk about:
"How to beat Moore’s Law ?" and more about: "Energy efficiency"..

How to beat Moore’s Law ?

I think with the following discovery, Graphene can finally be used in
CPUs, and it is a scale out method, read about the following discovery
and you will notice it:

New Graphene Discovery Could Finally Punch the Gas Pedal, Drive Faster CPUs

Read more here:

https://www.extremetech.com/computing/267695-new-graphene-discovery-could-finally-punch-the-gas-pedal-drive-faster-cpus

The scale out method above with Graphene is very interesting, and here
is the other scale up method with multicores and parallelism:

Beating Moore’s Law: Scaling Performance for Another Half-Century

Read more here:

https://www.infoworld.com/article/3287025/beating-moore-s-law-scaling-performance-for-another-half-century.html

More about Energy efficiency..

You have to be aware that parallelization of the software
can lower power consumption, and here is the formula
that permits you to calculate the power consumption of
"parallel" software programs:

Power consumption of the total cores =  (The number of cores) * (
1/(Parallel speedup))^3) * (Power consumption of the single core).


Also read the following about energy efficiency:

Energy efficiency isn’t just a hardware problem. Your programming
language choices can have serious effects on the efficiency of your
energy consumption. We dive deep into what makes a programming language
energy efficient.

As the researchers discovered, the CPU-based energy consumption always
represents the majority of the energy consumed.

What Pereira et. al. found wasn’t entirely surprising: speed does not
always equate energy efficiency. Compiled languages like C, C++, Rust,
and Ada ranked as some of the most energy efficient languages out there,
and Java and FreePascal are also good at Energy efficiency.

Read more here:

https://jaxenter.com/energy-efficient-programming-languages-137264.html

RAM is still expensive and slow, relative to CPUs

And "memory" usage efficiency is important for mobile devices.

So Delphi and FreePascal compilers are also still "useful" for mobile
devices, because Delphi and FreePascal are good if you are considering
time and memory or energy and memory, and the following pascal benchmark
was done with FreePascal, and the benchmark shows that C, Go and Pascal
do rather better if you’re considering languages based on time and
memory or energy and memory.

Read again here to notice it:

https://jaxenter.com/energy-efficient-programming-languages-137264.html


And more about beating Moore's Law with software..

But i think that there is some of the following constraints:

"Modern programing environments contribute to the problem of software bloat by placing ease of development and portable code above speed or memory usage. While this is a sound business model in a commercial environment, it does not make sense where IT resources are constrained. Languages such as Java, C-Sharp, and Python have opted for code portability and software development speed above execution speed and memory usage, while modern data storage and transfer standards such as XML and JSON place flexibility and readability above efficiency."

Read the following:

https://smallwarsjournal.com/jrnl/art/overcoming-death-moores-law-role-software-advances-and-non-semiconductor-technologies

Also there remains the following to also beat Moores's Law:

"Improved Algorithms

Hardware improvements mean little if software cannot effectively use the resources available to it. The Army should shape future software algorithms by funding basic research on improved software algorithms to meet its specific needs. The Army should also search for new algorithms and techniques which can be applied to meet specific needs and develop a learning culture within its software community to disseminate this information."


Thank you,
Amine Moulay Ramdane.

[toc] | [standalone]

Back to top | Article view | comp.programming

csiph-web