Intelligent computing in extreme environments, including data centers in space
John Clark
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
Amalie Sinclair
via SBSP utilities
You received this message because you are subscribed to the Google Groups "Power Satellite Economics" group.
To unsubscribe from this group and stop receiving emails from it, send an email to power-satellite-ec...@googlegroups.com.
To view this discussion visit https://groups.google.com/d/msgid/power-satellite-economics/CAJPayv23Za0CzstoVUH5S1SbjaHzvLi6GDwafKT5KdkoQOOsvA%40mail.gmail.com.
Keith Lofstrom
> How amazing ... temperatures higher than molten lava ! This discovery indicates whole dimension of information sharing potential,
survival. Bit cells on silicon chips are finite-sized, and
connect externally in large matrices; the bits they store
are huge energies (MANY electron volts) compared to thermal
energies (roughly 0.03 electron volts at room temperature,
0.1 electron volts at 700C). 50 hours is tiny compared to
the 100 years Atmel claims for their NVRAM ... which they
extrapolate from thermal acceleration of charge leakage
above 100C ...in a "normal" environment without ionizing
radiation.
I'm a chip engineer. On a different list, I explained why
silicon non-volatile memory chips (NVRAM) suffers from write
failure more easily than read failure (write involves more
voltage and energy). Also related to large number statistics
and vulnerability to energy damage at the array level.
I'm not saying this memristor technology won't ever work,
but the scale of testing necessary to confidently predict
whole-system integrity for decades of use will require
ten orders of magnitude system size increase, and eight
orders of magnitude "parallel testing time" increase.
MANY chips tested at temperatures MUCH higher than the
700C claimed here.
Otherwise, you don't accelerate the failure rate enough
to observe in finite time (months compared to decades)
you don't find the "rare" gremlins that add up to failure
for large systems with long lifetimes.
Been there, done that; for one of my circuits (a silicon
chip producing 256 immutable ID bits via silicon "magic"),
I tested 300,000 samples for 12 months at 150C, much
hotter than the specified use case. Over that time,
I found 30 errors in 8 different classes, and designed
workarounds for all of them.
Working with Hitachi ULSI in Japan, that would have made
product-level RFID ultra-cheap and secure, and earned us
billions of dollars.
Then came the Sendai earthquake and tsunami; Hitachi
moved ALL their loose capital into their earthmoving
division. Other companies captured the RFID market.
I donated my capital investment to Red Feather, the
Japanese equivalent of Red Cross.
Hence, I did not earn enough money to fund large scale
launch loop experiments. YOU can't buy a $1000 ticket
to Earth escape on a launch loop. Your children will;
other researchers are dabbling with something like the
launch loop (except costly, baroque, and unstable).
I hope to slash away a few orders of magnitude of
impractical and costly "aesthetic symmetry", replacing
that with measurement/computation-rich macro-stability.
Cue the 1994 Coen brothers movie "The Hudsucker Proxy".
All inventor wanna-bes should take lessons from that.
Keith L.
--
Keith Lofstrom kei...@keithl.com
Amalie Sinclair
best wishes Amalie
Apple, Boeing, Citi, Tesla, Meta executives to join Trump's China trip
|
You received this message because you are subscribed to the Google Groups "Power Satellite Economics" group.
To unsubscribe from this group and stop receiving emails from it, send an email to power-satellite-ec...@googlegroups.com.