Atomristors, a new single (atomic) layer memristor

Read an article the other day about the “Atomristor: non-volatile resistance  switching in atomic sheets of transition metal dichalcogenides” (TMDs), an ACS publication. The article shows research that discovered an atomic sheet level version of a memristor. The device is an atomic sheet of TMD that is sandwiched between two (gold, silver or graphene) electrodes.

They refer to the device switching non-volatile resistance (NVR) from low to high or vice versa but from our perspective it could just as easily be considered a non-volatile device usable for memory, storage, or electronic circuitry.

Prior to this research, it was believed that such resistance switching could not be accomplished with single atomic, sub-nanometre (0.7nm) sized, sheet of material.

NVR atomristor technological properties

The researchers discovered that NVR switching can occur at different device temperatures, sheet areas, compliance current, voltage sweep rate, and layer thickness. In all five degrees of freedom were tested to show that  TMD atomristors had wide applicability and allowed for significant environmental and electronic variability.

Not only was the effect extremely versatile, the researchers identified multiple materials which could be used for the atomic sheet. In fact, TMD are a class of materials and they showed 4 different TMD materials that had the NVR effect.

Surprisingly, some TMD materials exhibited the NVR effect using unipolar voltages and some using bipolar voltages, and some could use both.

The researchers went a long way to showing that the NVR was due to the atomic sheet. In one instance they specifically used non-lithographic measures to fabricate the devices. This process utilized graphene manufacturing like methods to produce an atomic sheet ontop of gold foil and depositing another gold layer ontop of that.

But they also used standard fabrication techniques to build the atomristor devices as well. Using these different fabrication methods, they were able to show the NVR effect using different electrodes types, testing gold, silver, and graphene, all of which worked similarly.

The paper talked of using atomristors in a software defined radio, as a electronic circuit/cross bar switch, or as a memory/storage device. But they also indicated that it could easily be used in a neuromorphic computer as well, effectively simulating neuron like computations.

There’s much more information in the ACS article.

How does it compare to flash?

As compared to flash, atomristors NVR devices should be able to provide higher levels (bits per mm) of density. And due to the lower current (~1v) required for (bipolar) NVR setting, reading and resetting, there’s a lower probability of leakage of stored charges as they’re scaled down to nm sizes.

And of course it comes in 2d sheets, so it’s just as amenable to 3D arrays as NAND and 3DX is today. That means that as fabs start scaling 3D NAND up in layers, atomristor NVR devices should be able to follow their technology roadmap to be scaled up just as high.

Atomristor computers, storage or switch devices

Going from the “lab” to an IT shop is a multifaceted endeavour that takes a lot of time. There are many steps to needed to get to commercialization and many lab breakthroughs never make it that far because of complexity, economics, and other factors.

For instance, memristors were first proposed in 1971 and HP(E) researchers first discovered material that could produce the memristor effect in 2008. In March 2012, HRL fabricated the first memristor chip on CMOS. In Dec. 2017, >9 years later, at their Discover Conference, HPE showed off “The Machine”, a prototype of a memristor based computer to the public. But we are still waiting to see one on the market for sale.

That being said, memristor technologies didn’t exist before 2008, so the use of these devices in a computer took sometime to be understood. The fact that atomristors are “just” an extremely, thinner version of memristors should help it be get to market faster that original memristor technologies. But how much faster than 9-12 years is anyone’s guess.



Picture Credit(s): All graphics and pictures are from the article in ACS

Better landslide/avalanche/mudslide modeling

Read an article the other week from Scientific American on Looming Landslide Stokes Fears, … about the Rattlesnake Ridge landslide that’s taking place in Washington State in the US. Apparently there’s a fissure that has been slowly widening  and is -slowly causing a landslide in the area.

Of course, recently there’s been significant mudslides in Montecito near  Las Angeles, that have resulted in a number of deaths and destruction of many millions of dollars of property. Now mudslides and landslides are not exactly the same but my guess is by improving our understanding of landslides may also help us better understand mudslides and hopefully, provide a better way to predict the dangers inherent in both. Ditto for snow avalanches.

Science to the rescue

Geologist and geomorphologists from Washington State and the USGS  have been instrumenting Rattlesnake Ridge with over 70 GPS sensors. They are also following the landslide using LIDAR snapshots to map terrain movement to try to better understand that movement over time.

It appears that Rattlesnake Ridge is moving about 1.6 ft/week. There’s a small community at the bottom of the ridge, and in the event of a complete collapse, knowing where and when to evacuate can save lives.

The belief is that the landslide at Rattlesnake Ridge and elsewhere are the result of an interaction of subsurface materials that holds ground in place and surface material moving down the a mountain side. It is the interface between these two layers that determines the rapidity of the landslide and its direction.

Land/snow/mud slides occur all the time

There’s a website called the Watchers that records significant landslides around the world. Aside from Rattlesnake Ridge and Montecito, they list a significant snow avalanche in South East France that cut off a village of 151 people, floods and landslides in the Philippines resulting from hurricane Kai-Tak that killed 26 people, a massive mudslide in Southern Chile which left 3 dead, 15 missing, and a new lake forming in India  after the Gangotri glacier collapsed that rerouted a river flowing from the glacier melt, all of which occurred during December 2017.

Snow avalanches, mudslides, landslides, etc. are all similar activities involving matter moving down a mountainside. The extent, direction and rapidity of its movement, all depend on the surface topology and subsurface and surface materials present in an area.

Knowing when to call an evacuation of the area immediately in a destructive path of a land/mud/snow slide and knowing where that destructive path is going to be is what the team at Rattlesnake Ridge are trying to help find out.




Photo Credit(s): 2104[sic] Washington Landslide by USGS 

Fissure by Ronan Jouve

SR6 Mudslide by Washington State DoT

New techniques shed light on ancient codex & palimpsests

Read an article the other day from New York Times, A fragile biblical text gets a virtual read about an approach to use detailed CT scans combined with X-rays to read text on a codex (double sided, hand bound book) that’s been mashed together for ~1500 years.

How to read a codex

Dr. Seales created the technology and has used it successfully to read a small charred chunk of material that was a copy of the earliest known version of the Masoretic text, the authoritative Hebrew bible.

However, that only had text on one side. A codex is double sided and being able to distinguish between which side of a piece of papyrus or parchment was yet another level of granularity.

The approach uses X-ray scanning to triangulate where sides of the codex pages are with respect to the material and then uses detailed CT scans to read the ink of the letters of the text in space. Together, the two techniques can read letters and place them on sides of a codex.

Apparently the key to the technique was in creating software could model the surfaces of a codex or other contorted pieces of papyrus/parchment and combining that with the X-ray scans to determine where in space the sides of the papyrus/parchment resided. Then when the CT scans revealed letters in planar scans (space), they could be properly placed on sides of the codex and in sequence to be literally read.

M.910, an unreadable codex

In the article, Dr. Seales and team were testing the technique on a codex written sometime between 400 and 600AD that contained the Acts of the Apostles and one of the books of the New Testament and possibly another book.

The pages had been merged together by a cinder that burned through much of the book. Most famous codexes are named but this one was only known as M.910 for the 910th acquisition of the Morgan Library.

M.910 was so fragile that it couldn’t be moved from the library. So the team had to use a portable CT scanner and X-ray machine to scan the codex.

The scans for M.910 were completed this past December and the team should start producing (Coptic) readable pages later this month.

Reading Palimpsests

A palimpsests is a manuscript on which the original writing has been obscured or erased. Another article from UCLA Library News, Lost ancient texts recovered and published online,  that talks about the use of multi-wave length spectral imaging to reveal text and figures that have been erased or obscured from Sinai Palimpsests.  The texts can be read at and total 6800 pages in 10 languages.

In this case the text had been deliberately erased or obscured to reuse parchment or papyrus. The writings are from the 5th to 12th centuries.  The texts were located in St. Catherine’s Monastary and access to it’s collection of ancient and medieval manuscripts is considered 2nd only to that in the Vatican Library.


There are many damaged codexes scurried away in libraries throughout the world today but up until now they were mere curiosities. If successful, this new technique will enable scholars to read their text, translate them and make them available for researchers and the rest of the world to read and understand.

Now if someone could just read my WordPerfect files from 1990’s and SCRIPT/VS files from 1980’s I’d be happy.


Picture credit(s): From NY Times article by Nicole Craine 

Acts of apostles codex

From Sinai Palimpsests Project website

GPU growth and the compute changeover

Attended SC17 last month in Denver and Nvidia had almost as big a presence as Intel. Their VR display was very nice as compared to some of the others at the show.

GPU past

GPU’s were originally designed to support visualization and the computation to render a specific scene quickly and efficiently. In order to do this they were designed with 100s to now 1000s of arithmetically intensive (floating point) compute engines where each engine could be given an individual pixel or segment of an image and compute all the light rays and visual aspects pertinent to that scene in a very short amount of time. This created a quick and efficient multi-core engine to render textures and map polygons of an image.

Image rendering required highly parallel computations and as such more compute engines meant faster scene throughput. This led to todays GPUs that have 1000s of cores. In contrast, standard microprocessor CPUs have 10-60 compute cores today.

GPUs today 

Funny thing, there are lots of other applications for many core engines. For example, GPUs also have a place to play in the development and mining of crypto currencies because of their ability to perform many cryptographic operations a second, all in parallel

Another significant driver of GPU sales and usage today seems to be AI, especially machine learning. For instance, at SC17, visual image recognition was on display at dozens of booths besides Intel and Nvidia. Such image recognition  AI requires a lot of floating point computation to perform well.

I saw one article that said GPUs can speed up Machine Learning (ML) by a factor of 250 over standard CPUs. There’s a highly entertaining video clip at the bottom of the Nvidia post that shows how parallel compute works as compared to standard CPUs.

GPU’s play an important role in speech recognition and image recognition (through ML) as well. So we find that they are being used in self-driving cars, face recognition, and other image processing/speech recognition tasks.

The latest Apple X iPhone has a Neural Engine which my best guess is just another version of a GPU. And the iPhone 8 has a custom GPU.

Tesla is also working on a custom AI engine for its self driving cars.

So, over time, GPUs will have an increasing role to play in the future of AI and crypto currency and as always, image rendering.


Photo Credit(s): SC17 logo, SC17 website;

GTX1070(GP104) vs. GTX1060(GP106) by Fritzchens Fritz;

Intel 2nd Generation core microprocessor codenamed Sandy Bridge wafer by Intel Free Press

Quantum computer programming

I was on a vendor call last week and they were discussing their recent technological advances in quantum computing. During the discussion they mentioned a number of ways to code for quantum computers. The currently most popular one is based on the QIS (Quantum Information Software) Kit.

I went looking for a principle of operations on quantum computers. Ssomething akin to the System 360 Principles of Operations Manual that explained how to code for an IBM 360 computer. But there was no such manual.

Instead there is a paper, on the Open Quantum Assembly Language (QASM) that describes the Quantum computational environment and coding language used in QIS Kit.

It appears that quantum computers can be considered a special computational co-proccesor engine, operated in parallel with normal digital computation. This co-processor happens to provide a quantum simulation.

QASM coding

One programs a quantum computer by creating a digital program which describes a quantum circuit that uses qubits and quantum registers to perform some algorithm on those circuits. The quantum circuit can be measured to provide a result  which more digital code can interpret and potentially use to create other quantum circuits in a sort of loop.

There are four phases during the processing of a QIS Kit quantum algorithm.

  1. QASM compilation which occurs solely on a digital computer. QASM source code describing the quantum circuit together with compile time parameters are translated into a quantum PLUS digital intermediate representation.
  2. Circuit generation, which also occurs on a digital computer with access to the quantum co-processor. The intermediate language compiled above is combined with other parameters (available from the quantum computer environment) and together these are translated into specific quantum building blocks (circuits) and some classical digital code needed and used during quantum circuit execution.
  3. Execution, which takes place solely on the quantum computer. The system takes as input, the collection of quantum circuits defined above and runtime control parameters,and transforms these using a high-level quantum computer controller into low-level, real time instructions for the quantum computer building the quantum circuits. These are then executed and the results of the quantum circuit(s) execution creates a result stream (measurements) that can be passed back to the digital program for further  processing
  4. Post-Processing, which takes place on a digital computer and uses the results from the quantum circuit(s) execution and other intermediate results and processes these to either generate follow-on quantum circuits or output ae final result for the quantum algorithm.

As qubit coherence only last for a short while, so results from one execution of a quantum circuit cannot be passed directly to another execution of quantum circuits.  Thus these results have to be passed through some digital computations before they can be used in subsequent quantum circuits. A qubit is a quantum bit.

Quantum circuits don’t offer any branching as such.

Quantum circuits

The only storage for QASM are classical (digital) registers (creg) and quantum registers (qreg) which are an array of bits and qubits respectively.

There are limited number of built-in quantum operations that can be performed on qregs and qubits. One described in the QASM paper noted above is the CNOT   operation, which flips a qubit, i.e., CNOT alb will flip a qubit in b, iff a corresponding qubit in a is on.

Quantum circuits are made up of one or more gate(s). Gates are invoked with a set of variable parameter names and quantum arguments (qargs). QASM gates can be construed as macros that are expanded at runtime. Gates are essentially lists of unitary quantum subroutines (other gate invocations), builtin quantum functions or barrier statements that are executed in sequence and operate on the input quantum argument (qargs) used in the gate invocation.

Opaque gates are quantum gates whose circuits (code) have yet to be defined. Opaque gates have a physical implementation may yet be possible but whose definition is undefined. Essentially these operate as place holders to be defined in a subsequent circuit execution or perhaps something the quantum circuit creates in real time depending on gate execution (not really sure how this would work).

In addition to builtin quantum operations,  there are other statements like the measure  or  reset statement. The reset statement sets a qubit or qreg qubits to 0. The measure statement copies the state of a qubit or qreg into a digital bit or creg (digital register).

There is one conditional command in QASM, the If statement. The if statement can compare a creg against an integer and if equal execute a quantum operation. There is one “decision”  creg, used as an integer.  By using IF statements one can essentially construct a case statement in normal coding logic to execute quantum (circuits) blocks.

Quantum logic within a gate can be optimized during the compilation phase so that they may not be executed (e.g., if the same operation occurs twice in a gate, normally the 2nd execution would be optimized out) unless a barrier statement is encountered which prevents optimization.

Quantum computer cloud

In 2016, IBM started offering quantum computers in its BlueMix cloud through the IBM Quantum (Q)  Experience. The IBM Q Experience currently allows researchers access to 5- and 16-qubit quantum computers.

There are three pools of quantum computers: 1 pool called IBMQX5, consists of 8 16-qubit computers and 2 pools of 5 5-qubit computers, IBMQX2 and IBMQX4. As I’m writing this, IBMQX5 and IBMQX2 are offline for maintenance but IBMQX4 is active.

Google has recently released the OpenFermion as open source, which is another software development kit for quantum computation (will review this in another post). Although Google also seems to have quantum computers and has provided researchers access to them, I couldn’t find much documentation on their quantum computers.

Two other companies are working on quantum computation: D-Wave Systems and Rigetti Computing. Rigetti has their Forest 1.0 quantum computing full stack programming and execution environment but I couldn’t easily find anything on D-Wave Systems programming environment.

Last month, IBM announced they have  constructed a 50-Qubit quantum computer prototype.

IBM has also released 20-Qubit quantum computers for customer use and plans to offer the new 50-Qubit computers to customers in the future.


Picture Credit(s): Quantum Leap Supercomputer,  IBM What is Quantum Computing Website

QASM control flow, Open Quantum Assembly Language, by A. Cross, et al

IBM’s newly revealed 50-Qubit Quantum Processer …,  Softcares blog post

Blockchain, open source and trusted data lead to better SDG impacts

Read an article today in Bitcoin magazine IXO Foundation: A blockchain based response to UN call for [better] data which discusses how the UN can use blockchains to improve their development projects.

The UN introduced the 17 Global Goals for Sustainable Development (SDG) to be achieved in the world by 2030. The previous 8 Millennial Development Goals (MDG) expire this year.

Although significant progress has been made on the MDGs, one ongoing determent to  MDG attainment has been that progress has been very uneven, “with the poorest and economically disadvantaged often bypassed”.  (See WEF, What are Sustainable Development Goals).

Throughout the UN 17 SDG, the underlying objective is to end global poverty  in a sustainable way.

Impact claims

In the past organizations performing services for the UN under the MDG mandate, indicated they were performing work toward the goals by stating, for example, that they planted 1K acres of trees, taught 2K underage children or distributed 20 tons of food aid.

The problem with such organizational claims is they were left mostly unverified. So the UN, NGOs and other charities funding these projects were dependent on trusting the delivering organization to tell the truth about what they were doing on the ground.

However, impact claims such as these can be independently validated and by doing so the UN and other funding agencies can determine if their money is being spent properly.

Proving impact

Proofs of Impact Claims can be done by an automated bot, an independent evaluator or some combination of the two . For instance, a bot could be used to analyze periodic satellite imagery to determine whether 1K acres of trees were actually planted or not; an independent evaluator can determine if 2K students are attending class or not, and both bots and evaluators can determine if 20 tons of food aid has been distributed or not.

Such Proofs of Impact Claims then become a important check on what organizations performing services are actually doing.  With over $1T spent every year on UN’s SDG activities, understanding which organizations actually perform the work and which don’t is a major step towards optimizing the SDG process. But for Impact Claims and Proofs of Impact Claims to provide such feedback but they must be adequately traced back to identified parties, certified as trustworthy and be widely available.

The ixo Foundation

The ixo Foundation is using open source, smart contract blockchains, personalized data privacy, and other technologies in the ixo Protocol for UN and other organizations to use to manage and provide trustworthy data on SDG projects from start to completion.

Trustworthy data seems a great application for blockchain technology. Blockchains have a number of features used to create trusted data:

  1. Any impact claim and proofs of impacts become inherently immutable, once entered into a blockchain.
  2. All parties to a project, funders, services and evaluators can be clearly identified and traced using the blockchain public key infrastructure.
  3. Any data can be stored in a blockchain. So, any satellite imagery used, the automated analysis bot/program used, as well as any derived analysis result could all be stored in an intelligent blockchain.
  4. Blockchain data is inherently widely available and distributed, in fact, blockchain data needs to be widely distributed in order to work properly.


The ixo Protocol

The ixo Protocol is a method to manage (SDG) Impact projects. It starts with 3 main participants: funding agencies, service agents and evaluation agents.

  • Funding agencies create and digitally sign new Impact Projects with pre-defined criteria to identify appropriate service  agencies which can do the work of the project and evaluation agencies which can evaluate the work being performed. Funding agencies also identify Impact Claim Template(s) for the project which identify standard ways to assess whether the project is being performed properly used by service agencies doing the work. Funding agencies also specify the evaluation criteria used by evaluation agencies to validate claims.
  • Service agencies select among the open Impact Projects whichever ones they want to perform.  As the service agencies perform the work, impact claims are created according to templates defined by funders, digitally signed, recorded and collected into an Impact Claim Set underthe IXO protocol.  For example Impact Claims could be barcode scans off of food being distributed which are digitally signed by the servicing agent and agency. Impact claims can be constructed to not hold personal identification data but still cryptographically identify the appropriate parties performing the work.
  • Evaluation agencies then take the impact claim set and perform the  evaluation process as specified by funding agencies. The evaluation insures that the Impact Claims reflect that the work is being done correctly and that the Impact Project is being executed properly. Impact claim evaluations are also digitally signed by the evaluation agency and agent(s), recorded and widely distributed.

The Impact Project definition, Impact Claim Templates, Impact Claim sets, Impact Claim Evaluations are all available worldwide, in an Global Impact Ledger and accessible to any and all funding agencies, service agencies and evaluation agencies.  At project completion, funding agencies should now have a granular record of all claims made by service agency’s agents for the project and what the evaluation agency says was actually done or not.

Such information can then be used to guide the next round of Impact Project awards to further advance the UN SDGs.

Ambly project

The Ambly Project is using the ixo Protocol to supply childhood education to underprivileged children in South Africa.

It combines mobile apps with blockchain smart contracts to replace an existing paper based school attendance system.

The mobile app is used to record attendance each day which creates an impact claim which can then be validated by evaluators to insure children are being educated and properly attending class.


Blockchains have the potential to revolutionize financial services, provide supply chain provenance (e.g., diamonds with Blockchains at IBM), validate company to company contracts (Ethereum enters the enterprise) and now improve UN SDG attainment.

Welcome to the new blockchain world.

Photo Credit(s): What are Sustainable Development Goals, World Economic Forum;

IXO Foundation website

Ambly Project webpage

Magnonics for configurable electronics

Read an article today in ScienceDaily on [a] New way to write magnetic info … that discusses research done at Imperial College Of London that used a magnetic force microscope (small magnetic probe) to write magnetic fields onto a dense array of nanowires.

Frustrated metamaterials needed

The original research is written up in a Nature article Realization of ground state in artificial kagome spin ice via topological defect driven magnetic writing  (paywall). Unclear what that means but the paper abstract discusses geometrically frustrated magnetic metamaterials.  This is where the physical size or geometrical properties of the materials at the nanometer scale restricts or limits the magnetic states that material can exhibit.

Magnetic storage deals with magnetic material but there are a number of unique interactions of magnetic material when in close (nm) proximity to one another and the way nanowire geometrically frustrated magnetic metamaterials can be magnetized to different magnetic moments which can be exploited for other uses.  These interactions and magnetic moments can be combined to provide electronic circuitry and data storage.

I believe the research provides a proof point that such materials can be written, in close proximity to one another using a magnetic force microscope.

Why it’s important

The key is the potential to create  magnonic circuitry based on the pattern of moments writen into an array of nanowires. In doing so, one can fabricate any electrical circuit. It’s almost like photolithography but without fabs, chemicals, or laser scanners.

At first I thought this could be a denser storage device, but the potential is much greater if electronic circuitry could be constructed without having to fabricate semiconductors. It would seem ideal for testing out circuitry before manufacturing. And ultimately if it could be scaled up, the manufacture/fabrication of electronic circuitry itself could be done using these techniques.

Speed, endurance, write limits?

There was no information in the public article about the speed of writing the “frustrated magnetic metamaterials”. But an atomic force microscope can scan 150×150 micrometers in several minutes. If we assume that a typical chip size today is 150×150 mm, then this would take 1E6 times several minutes, or ~2K days. With multiple scanning force microscopes operating concurrently we could cut this down by a factor of 10 or 100 and maybe someday 1000. 2 days to write any electronic circuit on the order of todays 23nm devices with nanowires and magnetic force microscopes would be a significant advance

Also there was no mention of endurance, write limits or other characteristics we have learned to love with Flash storage. But the assumption is that it can be written multiple times and that the pattern stays around for some amount of time.

How magnetics generate electronic circuits

Neither Wikipedia page, the public article or the paywall articles’ abstract describes how Magnonics can supply electronic circuitry. However both the abstract and the public article discuss applications for this new technology in hardware based neural networks using arrays of densely packed nanowires.

Presumably, by writing different magnetic patterns in these nanowire metamaterials, such patterns can be used to simulate hardware connected neurons. This means that the magnetic information can be overwritten because it can be trained. Also, such magnetic circuits can be constructed to: a) can create different path for electrons to flow through the material; b) can restrict or enhance this electronic flow, and c) can integrate across a number of inputs and determine how electronic flow will proceed from a simulated neuron.

If magnonics can do all that,  it’s very similar to electronic gates today in CPU, GPUs and other electronic circuitry. Maybe it cannot simulate every gate or electronic device that’s found in todays CPUs but it’s a step in the right direction. And magnonics is relatively new. Silicon transistors are over 70 years old and the integrated circuit is almost 60 years old. So in time, magnonics could very well become the next generation of chip technology.

Writing speed is a problem. Maybe if they spun the nanowire array around the magnetic force microscope…


Photo Credits:  Real space observation of emergent magnetic monopoles … Nature article

Realization of ground state in artificial kagome spin ice via topological defect driven magnetic writing, Nature article


Scratch file use in HPC @ORNL, a statistical analysis

Attended SC17 (Supercomputing Conference) this past week and I received a copy of the accompanying research proceedings. There are a number of interesting papers in the research and I came across one, Scientific User Behavior and Data Sharing Trends in a Peta Scale File System by Seung-Hwan Lim, et al from Oak Ridge National Laboratory (ORNL) and the use of files at the Oak Ridge Leadership Computing Facility (OLCF) which was very interesting.

The paper statistically describes the use of a Scratch files in a multi PB file system (Lustre) at OLCF from January 2015 to August 2016. The OLCF supports over 32PB of storage, has a peak aggregate of over 1TB/s and Spider II (current Lustre file system) consists of 288 Lustre Object Storage Servers, all interconnected and connected to all the supercomputing cluster of  servers via an InfiniBand network. Spider II supports all scratch storage requirements for active/queued jobs for the Titan (#4 in Top 500 [super computer clusters worldwide] list) and other clusters at ORNL.

ORNL uses an HPSS (High Performance Storage System) archive for permanent storage but uses the Spider II file system for all scratch files generated and used during supercomputing applications.  ORNL is expecting Spider III (2018-2023) to host 10 billion files.

Scratch files are purged from Spider II after 90 days of no access.The paper is based on metadata analysis captured during scratch purging process for 500 days of access.

The paper displays a number of statistics and metrics on the use of Spider II:

  • Less than 3% of projects have a directory depth >15, the maximum directory depth was recorded at 432, with most projects having a shallow (<10) directory depth.
  • A project typically has 10X the files that a specific researcher has and a median file count/researcher is 2000 files with a median project having 20,000 files.
  • Storage system performance is actively managed by many projects. For instance, 20 out of 35 science domains manually managed their Lustre cluster configuration to improve throughput.
  • File count continues to grow and reached a peak of 1B files during the time being analyzed.
  • On average only 3% of files were accessed readonly, 10% of files updated (read-write) and 76% of files were untouched during a week period. However, median and maximum file age was 138 and 214 days respectively, which means that these scratch files can continue to be accessed over the course of 200+ days.

There was more information in the paper but one item missing is statistics on scratch file size distribution a concern.

Nonetheless, in paints an interesting picture of scratch file use in HPC application/supercluster environments today.