Safe Vietnamese Raw Pork Snack

Fermented meat snack is helping researchers develop a safe, all-natural food preservative

From: RMIT University

June 7, 2021 -- Nem Chua is eaten raw but doesn't cause food poisoning when prepared correctly. Food scientists went to explore why - and discovered a powerful new bacteria-killer. A new study reveals the ideal growth conditions to potentially make the bacteriocin at industrial scales.

This traditional Vietnamese meat snack could hold the key to developing a safe and natural food preservative, addressing the twin global problems of food waste and food-borne illnesses.

The fermented pork snack, Nem Chua, is eaten raw but does not cause food poisoning when prepared correctly.

This is because friendly bacteria that thrive in the fermented meat make a special compound that destroys more dangerous bacteria.

Now researchers at RMIT University in Melbourne, Australia, have shown how this natural bacteria-killing compound could be used to keep food fresh for longer.

Food waste is a global issue that costs around $US680 billion annually in industrialised countries, consumes nearly a quarter of the water used in agriculture and produces 8% of global greenhouse emissions.

Food-borne diseases like Listeria or Salmonella affect millions each year and can be life threatening for pregnant women, older people and those who are immunocompromised.

Co-lead researcher Professor Oliver Jones said changes in consumer habits have led to a greater demand for natural alternatives to artificial food preservatives.

"Scientists have known about these bacteria-killing compounds for many years but the challenge is to produce them in large enough quantities to be used by the food industry," said Jones, Associate Dean of Biosciences and Food Technology at RMIT.

"The Nem Chua compound is colourless, odourless, tasteless and very resilient.

"Through this new research, we've identified the right growth conditions that would enable us to make it in large amounts, potentially at industrial scales.

"With further development, we hope this could be an effective, safe and all-natural solution for both food waste and food-borne disease."

Bacteria-killing weapon

A team of RMIT researchers was inspired to investigate Nem Chua for its potential antibacterial properties after travelling to Vietnam and observing people eating the raw meat snack without getting sick, despite the hot and humid climate.

The team, led by Professor Andrew Smith (now at Griffith University) and Dr Bee May, discovered a new type of bacteria-killing compound in Nem Chua.

Plantacyclin B21AG is one of a group of compounds known as bacteriocins, which are produced by bacteria to destroy rival bacterial strains.

Bacteriocins form holes in the membranes of target bacteria. This causes the contents of the cell to leak out -- effectively killing the bacteria.

The problem is most bacteriocins only work against one or two types of bacteria and they are not very stable in different environmental conditions.

Only one -- Nisin, which came to market in the 1960s -- is currently licensed for use as a food preservative, in a market estimated to be worth more than $US513 million in 2020, but this compound is temperature and pH sensitive limiting its use.

Tough and effective

The Nem Chua-derived compound is more robust than Nisin and is effective against a wide range of bacteria even after exposure to a range of environments typical in food processing.

It can survive being heated to 90C for 20 minutes and remains stable across high and low pH levels.

The compound can also destroy a range of disease-causing organisms commonly found in food including potentially life-threating Listeria, which can survive refrigeration and even freezing.

Co-lead researcher Dr Elvina Parlindungan, who completed the new study as part of her PhD research at RMIT, is now a postdoctoral fellow at APC Microbiome, part of University College Cork in Ireland.

"Using bacteriocins as food preservatives effectively means we are turning bacteria's own toxic weapons against them -- harnessing nature's smart solutions to tackle our big challenges," Parlindungan said.

"In the future, these compounds might also be useful as an antibiotic in human medicine."

Researchers at RMIT's School of Science have begun experimenting with methods to further purify the compound and are planning to incorporate it into test food products.

The team is keen to collaborate with potential industry partners to further develop the technology.

This work was supported by a PhD scholarship from the Indonesian Endowment Fund for Education (LPDP), part of the Ministry of Finance of the Republic of Indonesia, awarded to Parlindungan.

           https://www.sciencedaily.com/releases/2021/06/210607084619.htm

Amorphous Metal Alloys Liquidmetal and Vitreloy

Liquidmetal and Vitreloy are commercial names of a series of amorphous metal alloys developed by a California Institute of Technology (Caltech) research team and marketed by Liquidmetal Technologies. Liquidmetal alloys combine a number of desirable material features, including high tensile strength, excellent corrosion resistance, very high coefficient of restitution and excellent anti-wearing characteristics, while also being able to be heat-formed in processes similar to thermoplastics. Despite the name, they are not liquid at room temperature.

Liquidmetal was introduced for commercial applications in 2003.  It is used for, among other things, golf clubs, watches and covers of cell phones.

The alloy was the end result of a research program into amorphous metals carried out at Caltech. It was the first of a series of experimental alloys that could achieve an amorphous structure at relatively slow cooling rates.  Amorphous metals had been made before, but only in small batches because cooling rates needed to be in the millions of degrees per second. For example, amorphous wires could be fabricated by splat quenching a stream of molten metal on a spinning disk. Because Vitreloy allowed such slow cooling rates, production of larger batch sizes was possible. More recently, a number of additional alloys have been added to the Liquidmetal portfolio. These alloys also retain their amorphous structure after repeated re-heating, allowing them to be used in a wide variety of traditional machining processes.

Characteristics

Liquidmetal, created by Dr. Atakan Peker, contain atoms of significantly different sizes. They form a dense mix with low free volume. Unlike crystalline metals, there is no obvious melting point at which viscosity drops suddenly. Vitreloy behaves more like other glasses, in that its viscosity drops gradually with increased temperature. At high temperature, it behaves in a plastic manner, allowing the mechanical properties to be controlled relatively easily during casting. The viscosity prevents the atoms moving enough to form an ordered lattice, so the material retains its amorphous properties even after being heat-formed.

The alloys have relatively low softening temperatures, allowing casting of complicated shapes without needing finishing. The material properties immediately after casting are much better than those of conventional metals; usually, cast metals have worse properties than forged or wrought ones. The alloys are also malleable at low temperatures (400 °C or 752 °F for the earliest formulation), and can be molded.  The low free volume also results in low shrinkage during cooling. For all of these reasons, Liquidmetal can be formed into complex shapes using processes similar to thermoplastics, which makes Liquidmetal a potential replacement for many applications where plastics would normally be used.

Due to their non-crystalline (amorphous) structures, Liquidmetals are harder than alloys of titanium or aluminum of similar composition. The zirconium and titanium based Liquidmetal alloys achieved yield strength of over 1723 MPa, nearly twice the strength of conventional crystalline titanium alloys (Ti6Al4V is ~830 MPa), and about the strength of high-strength steels and some highly engineered bulk composite materials (see tensile strength for a list of common materials). However, the early casting methods introduced microscopic flaws that were excellent sites for crack propagation which led to Vitreloy being fragile like glass. Although strong, these early batches shattered easily when struck. Newer casting methods, adjustments of the alloy mixtures and other changes have improved this.

The lack of grain boundaries contributes to the high yield strength (and thereby resilience) exhibited. In a demonstration, a metal sphere dropped on amorphous steel bounced significantly longer than the same metal sphere dropped on crystalline steel.

The lack of grain boundaries in a metallic glass eliminates grain-boundary corrosion—a common problem in high-strength alloys produced by precipitation hardening and sensitized stainless steels. Liquidmetal alloys are therefore generally more corrosion resistant, both due to the mechanical structure as well as the elements used in its alloy. The combination of mechanical hardness, high elasticity and corrosion resistance makes Liquidmetal wear resistant.

Although at high temperatures, plastic deformation occurs easily, almost none occurs at room temperature before the onset of catastrophic failure.  This limits the material's applicability in reliability-critical applications, as the impending failure is not evident. The material is also susceptible to metal fatigue with crack growth. A two-phase composite structure with amorphous matrix and a ductile dendritic crystalline-phase reinforcement, or a metal matrix composite reinforced with fibers of other material can reduce or eliminate this disadvantage.

Uses

Liquidmetal combines a number of features that are normally not found in any one material. This makes them useful in a wide variety of applications.

One of the first commercial uses of Liquidmetal was in golf clubs made by the company, where the highly elastic metal was used in portions of the club face.  These were highly rated by users, but the product was later dropped, in part because the prototypes shattered after fewer than 40 hits.  Since then, Liquidmetal has appeared in other sports equipment, including the cores of golf balls, skis,baseball and softball bats, and tennis racquets.

The ability to be cast and molded, combined with high wear resistance, has also led to Liquidmetal being used as a replacement for plastics in some applications.  It has been used on the casing of late-model SanDisk "Cruzer Titanium" USB flash drives as well as their Sansa line of flash-based MP3 player, and casings of some mobile phones, like the luxury Vertu products, and other toughened consumer electronics.  Liquidmetal was used in the Biolase dental laser Ilase and the Socketmobile ring bar code scanner. Liquidmetal has also notably been used for making the SIM ejector tool of some iPhone 3Gs made by Apple Inc., shipped in the US. This was done by Apple as an exercise to test the viability of usage of the metal.  They retain a scratch-free surface longer than competing materials, while still being made in complex shapes. The same qualities lend it to use as protective coatings for industrial machinery, including  petroleum drill pipes and power plant boiler tubes.

It also replaces titanium in applications ranging from medical instruments and cars to the military and aerospace industry. In military applications, rods of amorphous metals replace depleted uranium in kinetic energy penetrators.  Plates of Liquidmetal were used in the solar wind ion collector array in the Genesis space probe.

                                    https://en.wikipedia.org/wiki/Liquidmetal

Collagen in Connective Tissues

Collagen is the main structural protein in the extracellular matrix found in the body's various connective tissues. As the main component of connective tissue, it is the most abundant protein in mammals, making up from 25% to 35% of the whole-body protein content. Collagen consists of amino acids bound together to form a triple helix of elongated fibril known as a collagen helix.  It is mostly found in connective tissue such as cartilage, bones, tendons, ligaments, and skin.

Depending upon the degree of mineralization, collagen tissues may be rigid (bone) or compliant (tendon) or have a gradient from rigid to compliant (cartilage). Collagen is also abundant in corneas, blood vessels, the gut, intervertebral discs, and the dentin in teeth.  In muscle tissue, it serves as a major component of the endomysium.  Collagen constitutes one to two percent of muscle tissue and accounts for 6% of the weight of strong, tendinous muscles.  The fibroblast is the most common cell that creates collagen.  Gelatin, which is used in food and industry, is collagen that has been irreversibly hydrolyzed.  Collagen has many medical uses in treating complications of the bones and skin.

The name collagen comes from the Greek κόλλα (kólla), meaning "glue", and suffix -γέν, -gen, denoting "producing".  This refers to the compound's early use in the process of creating glue from boiling the skin and tendons of horses and other animals.

Uses of Collagen

Collagen has a wide variety of applications, from food to medical. For instance, it is used in cosmetic surgery and burn surgery.  It is widely used in the form of collagen casings for sausages.

If collagen is subject to sufficient denaturation, e.g. by heating, the three tropocollagen strands separate partially or completely into globular domains, containing a different secondary structure to the normal collagen polyproline II (PPII), e.g. random coils.  This process describes the formation of gelatin, which is used in many foods, including flavored gelatin desserts.  Besides food, gelatin has been used in pharmaceutical, cosmetic, and photography industries. It is also used as a dietary supplement.

Collagen adhesive was used by Egyptians about 4,000 years ago, and Native Americans used it in bows about 1,500 years ago. The oldest glue in the world, carbon-dated as more than 8,000 years old, was found to be collagen – used as a protective lining on rope baskets and embroidered fabrics, to hold utensils together, and in crisscross decorations on human skulls.  Collagen normally converts to gelatin, but survived due to dry conditions. Animal glues are thermoplastic, softening again upon reheating, so they are still used in making musical instruments such as fine violins and guitars, which may have to be reopened for repairs – an application incompatible with tough, synthetic plastic adhesives, which are permanent.  Animal sinews and skins, including leather, have been used to make useful articles for millennia.

Gelatin-resorcinol-formaldehyde glue (and with formaldehyde replaced by less-toxic pentanedial and ethanedial) has been used to repair experimental incisions in rabbit lungs.

                https://en.wikipedia.org/wiki/Collagen#Uses

One Job in Twenty Was Seen as Useless

The so-called ‘bullshit jobs theory’ – which argues that a large and rapidly increasing number of workers are undertaking jobs that they themselves recognize as being useless and of no social value – contains several major flaws, argue researchers from the universities of Cambridge and Birmingham.

From: Cambridge University

June 3, 2021 -- Even so, writing in Work, Employment and Society, the academics applaud its proponent, American anthropologist David Graeber, who died in September 2020, for highlighting the link between a sense of purpose in one’s job and psychological wellbeing.

Graeber initially put forward the concept of ‘bullshit jobs’ – jobs that even those who do them view as worthless – in his 2013 essay The Democracy Project. He further expanded this theory in his 2018 book Bullshit Jobs: A Theory, looking at possible reasons for the existence of such jobs.

Jobs that Graeber described as bullshit (BS) jobs range from doormen and receptionists to lobbyists and public relations specialists through to those in the legal profession, particularly corporate lawyers and legal consultants.

Dr Magdalena Soffia from the University of Cambridge and the What Works Centre for Wellbeing, one of the authors of the article, said: “There’s something appealing about the bullshit jobs theory. The fact that many people have worked in such jobs at some point may explain why Graeber’s work resonates with so many people who can relate to the accounts he gives. But his theory is not based on any reliable empirical data, even though he puts forward several propositions, all of which are testable.”

To test Graeber’s propositions, the researchers turned to the 2005–2015 European Working Conditions Surveys (EWCS), examining reasons that led to respondents answering ‘rarely’ or ‘never’ to the statement: ‘I have the feeling of doing useful work’. The surveys – taken in 2005, 2010 and 2015 – gather measures on the usefulness of the job, workers’ wellbeing and objective data on the quality of work. The number of respondents grew from over 21,000 in 2005 to almost 30,000 in 2015.

According to Graeber, somewhere between 20% and 50% of the workforce – possibly as many as 60% - are employed in BS jobs. Yet the EWCS found that just 4.8% of EU workers said they did not feel they were doing useful work. The figure was slightly higher in the UK and Ireland, but still only 5.6% of workers.

Graeber also claimed that the number of BS jobs has been ‘increasing rapidly in recent years’, despite presenting no empirical evidence. Again the researchers found no evidence to support this conjecture – in fact, the percentage of people in BS jobs fell from 7.8% in 2005 to just 4.8% in 2015 – exactly the opposite of Graeber’s prediction.

His next hypothesis was that BS jobs are concentrated in particular professions, such as finance, law, administration and marketing, and largely absent in others, such as those linked to public services and manual labour. “Many service workers hate their jobs; but even those who do are aware that what they do does make some sort of meaningful difference in the world . . . [Whereas] we can only assume that any office worker who one might suspect secretly believes themselves to have a bullshit job does, indeed, believe this,” he wrote.

When the researchers ranked the occupations by the proportion of people who rated their job as rarely or never useful, they found no evidence for the existence of occupations in which the majority of workers feel their work is not useful.

The authors found that workers in some occupations, such as teachers and nurses, generally see themselves as doing useful jobs, while sales workers are above average in the proportion rating their job as not useful (7.7%). Even so, most of the results contradict Graeber’s assertion. For example, legal professionals and administration professionals are all low on this ranking, and jobs that Graeber rates as being examples of essential non-BS jobs, such as refuse collectors (9.7%) and cleaners and helpers (8.1%), are high on this scale.

Not everything that Graeber suggested was wrong, however. He argued, for example, that BS jobs are a form of ‘spiritual violence’ that lead to anxiety, depression and misery among workers. The team found strong evidence between the perception of one’s job as useless and an individual’s psychological wellbeing, albeit a correlation rather than necessarily a causal link. In the UK in 2015, workers who felt their job was not useful scored significantly lower on the World Health Organisation Well-Being Index than those who felt they were doing useful work (a mean average of 49.3 compared with 64.5). There was a similar gap across other EU nations.

Dr Alex Wood from the University of Birmingham said: “When we looked at readily-available data from a large cohort of people across Europe, it quickly became apparent to us that very few of the key propositions in Graeber’s theory can be sustained – and this is the case in every country we looked at, to varying degrees. But one of his most important propositions – that BS jobs are a form of ‘spiritual violence’ – does seem to be supported by the data.”

Given that, in absolute terms, a substantial number of people do not view their jobs as useful, what then leads to this feeling? The team found that those individuals who felt respected and encouraged by management were less likely to report their work as useless. Conversely, when employees experience management that is disrespectful, inefficient or poor at giving feedback, they were less likely to perceive their work as useful.

Similarly, individuals who saw their job as useful tended to be able to use their own ideas at work – an important element for feeling that your job provides you with the ability to make the most of your skills – was correlated with a perception of usefulness. There was a clear relationship between the extent to which people felt that they had enough time to do their job well and their rating of the usefulness of their job, suggesting that one source of feeling a job to be useless is the pace at which one is working, affecting the ability to realise one’s potential and capabilities. Other factors correlated with feeling that a job was worthwhile included support by managers and colleagues and the ability to influence important decisions and the direction of an organization.

Professor Brendan Burchell from the University of Cambridge said: “Although the data doesn’t always support David Graeber’s claims, his insightful and imaginative work played an important role in raising awareness of the harms of useless jobs. He may have been way off the mark with regards how common BS jobs are, but he was right to link people’s attitudes towards their jobs to their psychological wellbeing, and this is something that employers – and society as a whole – should take seriously.

“Most importantly, employees need to be respected and valued if they in turn are to value – and benefit psychologically as well as financially from – their jobs.”

https://www.cam.ac.uk/research/news/one-in-twenty-workers-are-in-useless-jobs-far-fewer-than-previously-thought

Active Early Learning Affects the Adult Brain

Fralin Biomedical Research Institute, University of Pennsylvania scientists reveal effects of early learning that last decades

From Virginia Tech

May 31, 2021 -- An enhanced learning environment during the first five years of life shapes the brain in ways that are apparent four decades later, say Virginia Tech and University of Pennsylvania scientists writing in the June edition of the Journal of Cognitive Neuroscience.

The researchers used structural brain imaging to detect the developmental effects of linguistic and cognitive stimulation starting at six weeks of age in infants. The influence of an enriched environment on brain structure had formerly been demonstrated in animal studies, but this is the first experimental study to find a similar result in humans.

“Our research shows a relationship between brain structure and five years of high-quality educational and social experiences,” said Craig Ramey, professor and distinguished research scholar with the Fralin Biomedical Research Institute at VTC and principal investigator of the study. “We have demonstrated that in vulnerable children who received stimulating and emotionally supportive learning experiences, statistically significant changes in brain structure appear in middle age.”

The results support the idea that early environment influences the brain structure of individuals growing up with multirisk socioeconomic challenges, said Martha Farah, director of the Center for Neuroscience & Society at Penn and first author of the study. 

“This has exciting implications for the basic science of brain development, as well as for theories of social stratification and social policy,” Farah said. 

The study follows children who have continuously participated in the Abecedarian Project, an early intervention program initiated by Ramey in Chapel Hill, North Carolina, in 1971 to study the effects of educational, social, health, and family support services on high-risk infants. 

Both the comparison and treatment groups received extra health care, nutrition, and family support services; however, beginning at six weeks of age, the treatment group also received five years of high quality educational support, five days a week, 50 weeks a year.

When scanned, the Abecedarian study participants were in their late 30s to early 40s, offering the researchers a unique look at how childhood factors affect the adult brain.

“People generally know about the potentially large benefits of early education for children from very low resource circumstances,” said co-author Sharon Landesman Ramey, professor and distinguished research scholar with the Fralin Biomedical Research Institute and the Virginia Tech College of Science. “The new results reveal that biological effects accompany the many behavioral, social, health, and economic benefits reported in the Abecedarian Project. This affirms the idea that positive early life experiences contribute to later positive adjustment through a combination of behavioral, social, and brain pathways.”

During follow-up examinations, structural MRI scans of the brains of 47 study participants were conducted at the Fralin Biomedical Research Institute Human Neuroimaging Lab. Of those, 29 individuals had been in the group that received the educational enrichment focused on promoting language, cognition, and interactive learning. 

The other 18 individuals received the same robust health, nutritional, and social services supports provided to the educational treatment group, and whatever community childcare or other learning their parents provided.  The two groups were well matched on a variety of factors such as maternal education, head circumference at birth, and age at scanning.

Analyzing the scans, the researchers looked at brain size as a whole, including the cortex, the brain’s outermost layer, as well as five regions selected for their expected connection to the intervention’s stimulation of children’s language and cognitive development. 

Those included the left inferior frontal gyrus and left superior temporal gyrus, which may be relevant to language, and the right inferior frontal gyrus and bilateral anterior cingulate cortex, relevant to cognitive control. A fifth, the bilateral hippocampus, was added because its volume is frequently associated with early life adversity and socioeconomic status.

The researchers determined that those in the early education treatment group had increased size of the whole brain, including the cortex. 

Several specific cortical regions also appeared larger, according to study co-authors Read Montague, professor and director of the Human Neuroimaging Lab and Computational Psychiatry Unit at the Fralin Biomedical Research Institute, and Terry Lohrenz, research assistant professor and member of the institute’s Human Neuroimaging Laboratory. 

The scientists noted the group intervention treatment results for the brain were substantially greater for males than for females. The reasons for this are not known, and were surprising, since both the boys and girls showed generally comparable positive behavioral and educational effects from their early enriched education. The current study cannot adequately explain the sex differences.  

“When we launched this project in the 1970s, the field knew more about how to assess behavior than it knew about how to assess brain structure,” said Craig Ramey, who is also a professor in the Virginia Tech College of Science. “Because of advances in neuroimaging technology and through strong interdisciplinary collaborations, we were able to measure structural features of the brain. The prefrontal cortex and areas associated with language were definitely affected; and to our knowledge, this is the first experimental evidence on a link between known early educational experiences and long-term changes in humans.”

“We believe that these findings warrant careful consideration and lend further support to the value of ensuring positive learning and social-emotional support for all children – particularly to improve outcomes for children who are vulnerable to inadequate stimulation and care in the early years of life,” Craig Ramey said.

The study was supported by a Principal Research Fellowship from the Wellcome Trust, Virginia Tech, the School of Arts and Sciences Research Fund, University of Pennsylvania, and the William N. Sternberg Fund for Human Information-Processing Research.

       https://vtx.vt.edu/articles/2021/05/learning-fralinbiomed-06012021.html

Advanced Method for AI Generation of Images

Applications include fields from autonomous robotics to AI training

From:  North Carolina State University

June 1, 2021 -- At issue is a type of AI task called conditional image generation, in which AI systems create images that meet a specific set of conditions. For example, a system could be trained to create original images of cats or dogs, depending on which animal the user requested. More recent techniques have built on this to incorporate conditions regarding an image layout. This allows users to specify which types of objects they want to appear in particular places on the screen. For example, the sky might go in one box, a tree might be in another box, a stream might be in a separate box, and so on.

The new work builds on those techniques to give users more control over the resulting images, and to retain certain characteristics across a series of images.

"Our approach is highly reconfigurable," says Tianfu Wu, co-author of a paper on the work and an assistant professor of computer engineering at NC State. "Like previous approaches, ours allows users to have the system generate an image based on a specific set of conditions. But ours also allows you to retain that image and add to it. For example, users could have the AI create a mountain scene. The users could then have the system add skiers to that scene."

In addition, the new approach allows users to have the AI manipulate specific elements so that they are identifiably the same, but have moved or changed in some way. For example, the AI might create a series of images showing skiers turn toward the viewer as they move across the landscape.

"One application for this would be to help autonomous robots 'imagine' what the end result might look like before they begin a given task," Wu says. "You could also use the system to generate images for AI training. So, instead of compiling images from external sources, you could use this system to create images for training other AI systems."

The researchers tested their new approach using the COCO-Stuff dataset and the Visual Genome dataset. Based on standard measures of image quality, the new approach outperformed the previous state-of-the-art image creation techniques.

"Our next step is to see if we can extend this work to video and three-dimensional images," Wu says.

Training for the new approach requires a fair amount of computational power; the researchers used a 4-GPU workstation. However, deploying the system is less computationally expensive.

"We found that one GPU gives you almost real-time speed," Wu says.

"In addition to our paper, we've made our source code for this approach available on GitHub. That said, we're always open to collaborating with industry partners."

         https://www.sciencedaily.com/releases/2021/06/210601135751.htm

New “Flatland” Computer Memory Approach

Currently being explored by the McKelvey School of Engineering at Washington University in St. Louis

May 21, 2021 -- Computers have a hierarchy of memory, with the memory closest to the processor performing the fastest but storing the least amount of data. Improved technology is flattening out the hierarchy, but the current practical tools and theory to understand it are not designed for this “flatland” terrain. 

Kunal Agrawal, associate professor of computer science in the McKelvey School of Engineering at Washington University in St. Louis, is joining a team of collaborators who seek to understand how the structure of memory is changing and develop new theoretical models and algorithms for the new subsystems with a four-year, $1.2 million grant from the National Science Foundation. She is collaborating with Michael Bender, professor of computer science at Stony Brook University; Martin Farach-Colton, professor of computer science at Rutgers University and lead investigator; and Jeremy Fineman, Provost's Distinguished Associate Professor and Wagner Term Chair in Computer Science at Georgetown University. Washington University’s portion of the grant is $299,997.

In this theoretical project, Agrawal and collaborators will investigate how to manage memory resources to ensure the best performance.

“Computers have many processors and cores that are all accessing this memory system, and they are fighting over the resources because some levels of the memory hierarchy are shared,” Agrawal said. “These cores could be running independent applications, the same parallel application or it could be a combination. We want to get the best performance that we can in all of these scenarios.”

“Parallelism is here to stay,” Agrawal said. “Now we have eight cores on a machine, but as we get more and more cores, this work becomes more relevant.”

While this is not a new field, it is more important now because of the changing properties of the different types of memory. The team will look at the new kinds of memory coming online: some that are fast, some that read fast but write slow, and some that can only do a certain number of writes before the memory is useless, Agrawal said.

The researchers also will look at streaming and semi-streaming applications for large data sets. 

“Previously, streaming applications often used a one-pass algorithm where you read the data only once because it was too big,” she said. “Now, you can afford to do more than one read, and this makes a big difference in algorithm design.” 

The team will build new theoretical models to help them learn how to use the memory to solve problems.

https://engineering.wustl.edu/news/2021/Exploring-the-flatland-of-computer-memory.html