Intelligent computing in extreme environments, including data centers in space

[John Clark]

There was an article in the March 26, 2026 issue of the journal science that I found particularly interesting: 

High-temperature memristors enabled by interfacial engineering

They invented a memory AND processing device that can operate at temperatures over 700 °C, can store data for over 50 hours at that scorching heat, and is also at least as fast as conventional devices. One of the inventors said :

 "Creating high-operating-temperature accelerators could enable intelligent computing in extreme environments, including space applications or data centres".

That made me wonder if resistance to heat would also mean it was resistant to cosmic rays of the sort it would receive in space, so I asked Gemini and this is what he she or it said: 

==

Gemini:  " The article you linked, "High-temperature memristors enabled by interfacial engineering" (published in Science, March 2026), describes a major breakthrough in electronics designed for extreme environments.

Summary of the Article

The research team, led by J. Joshua Yang at the University of Southern California, developed a new type of memristor—a nanoscale component that acts as both memory and a processor—that can operate reliably at temperatures up to 700°C (1,300°F). This is significantly hotter than molten lava and far surpasses the ~200°C limit where traditional silicon chips fail.

• The Design: The device is a "sandwich" of three materials: Tungsten (W) on top, Hafnium Oxide (HfOx) in the middle, and Graphene on the bottom.

• The Breakthrough: In traditional chips, high heat causes atoms from the metal electrodes to "leak" or diffuse into the insulating layers, creating a short circuit. The researchers used graphene as a bottom electrode because its atomic structure is extremely stable. It acts as an "interfacial barrier" that prevents tungsten atoms from migrating into the other layers, even at extreme temperatures.

• Performance: The chip maintained an ON/OFF ratio (for data storage) for over 50 hours at 700°C and survived over one billion switching cycles. This makes it the most stable high-temperature memory device ever recorded.

Does Heat Resistance Equal Radiation Resistance?

Your question touches on a key challenge in "extreme environment" engineering. While high-temperature resistance and radiation resistance are technically different, they are closely related, particularly for the materials used in this study.

1. The Physics of "Atomic Migration"

In space, radiation (like protons and heavy ions) damages electronics by knocking atoms out of their crystal lattice, a process called displacement damage. High heat causes a similar problem: atoms vibrate so much they drift out of place (thermal diffusion).

• The Link: The "interfacial engineering" (using graphene to block atoms from moving) that makes this chip heat-resistant also makes it more robust against radiation-induced displacement. Because the interface is designed to be "atomically stubborn," it is much harder for radiation to cause the kind of material leakage that usually kills space-grade chips.

2. Thermal Annealing (The "Healing" Effect)

There is a unique phenomenon where being hot can actually help a device survive radiation. In a process called thermal annealing, the high temperature provides enough energy for atoms that were knocked out of place by radiation to "settle" back into their correct positions.

• Because this memristor is designed to operate at 700°C, it could potentially "self-heal" radiation damage in real-time, whereas a standard chip would simply accumulate defects until it failed.

3. The Tardigrade Connection (Biology vs. Electronics)

You likely noticed a parallel with tardigrades (water bears). In biology, resistance to high temperatures (and desiccation) almost always confers resistance to radiation.

• Why? Both heat and radiation damage cells in the same way: by creating reactive oxygen species (free radicals) and breaking DNA strands. Tardigrades evolved proteins like Dsup (Damage Suppressor) to protect their DNA from drying out; these same proteins happen to shield the DNA from space radiation.

• In Electronics: The logic is similar. By choosing materials like Tungsten (highest melting point) and Graphene (strongest atomic bonds), the engineers have selected materials that are inherently "stiff" against any kind of energy—whether that energy comes from a heat lamp or a cosmic ray.

Conclusion

For this specific article, yes, the resistance to high temperatures is a strong indicator of high radiation resistance. The use of graphene as a diffusion barrier specifically targets the "movement of atoms" which is the primary failure point for both heat and radiation in nanoscale electronics. This makes this technology a prime candidate for missions to the surface of Venus or for logic systems located near nuclear reactors."

   John K Clark    See what's on my list at  Extropolis

[John Clark]

On Mon, May 11, 2026 at 11:44 AM Amalie Sinclair <ana...@yahoo.com> wrote:

> How amazing ... temperatures higher than molten lava ! This discovery indicates whole dimension of information sharing potential, via SBSP utilities  

A memristor would be extremely useful even if you didn't consider its enormous resistance to heat and radiation. A memristor is a two-terminal gadget whose electrical resistance changes based on the history of the voltage applied to it, so it can be used as a non-volatile memory device. But that's not all, If you arrange memristors in a "crossbar array" you can perform vector-matrix multiplication much faster than we can today because it can do it in a single step. And today it can take 1000 times more energy to move information across a chip than performing the actual calculation, but memristors don't have that problem because the memory and the processing are already at the same spot.

Vector-matrix multiplication is not the only sort of computation so a memristor would not be good at every sort of problem, like those that use Boolean Logic with a lot of if-then branching. You'd still need to have some CPUs with MOSFET NAND and NOR gates, but when it comes to AI the chief bottleneck does not come from the messy logic of branching code, it comes from the high energy usage and slow processing of matrix multiplication. And that is exactly what memristors are very good at. 

 John K Clark

[Giulio Prisco]

USC press release here:
https://viterbischool.usc.edu/news/2026/03/usc-scientists-build-a-memory-chip-that-survives-temperatures-hotter-than-lava/

> --
> You received this message because you are subscribed to the Google Groups "extropolis" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to extropolis+...@googlegroups.com.
> To view this discussion visit https://groups.google.com/d/msgid/extropolis/CAJPayv0xCQu8EtgGGbEPBE4gEQAfVhdZ-ydrq1aU-b87r1f1eQ%40mail.gmail.com.