#pohoiki

[tropic-havens]

Along Puna coast; Kehena-Pohoiki scenic coastal drive, Big Island, Hawai’i

[systemtek]

Intel Builds World’s Largest Neuromorphic System to Enable More Sustainable AI

Intel announced that it has built the world's largest neuromorphic system. Code-named Hala Point, this large-scale neuromorphic system, initially deployed at Sandia National Laboratories, utilizes Intel’s Loihi 2 processor, aims at supporting research for future brain-inspired artificial intelligence (AI), and tackles challenges related to the efficiency and sustainability of today’s AI. Hala Point advances Intel’s first-generation large-scale research system, Pohoiki Springs, with architectural improvements to achieve over 10 times more neuron capacity and up to 12 times higher performance. Hala Point is the first large-scale neuromorphic system to demonstrate state-of-the-art computational efficiencies on mainstream AI workloads. Characterization shows it can support up to 20 quadrillion operations per second, or 20 petaops, with an efficiency exceeding 15 trillion 8-bit operations per second per watt (TOPS/W) when executing conventional deep neural networks. This rivals and exceeds levels achieved by architectures built on graphics processing units (GPU) and central processing units (CPU). Hala Point’s unique capabilities could enable future real-time continuous learning for AI applications such as scientific and engineering problem-solving, logistics, smart city infrastructure management, large language models (LLMs) and AI agents. How It will be Used: Researchers at Sandia National Laboratories plan to use Hala Point for advanced brain-scale computing research. The organization will focus on solving scientific computing problems in device physics, computer architecture, computer science and informatics. “Working with Hala Point improves our Sandia team’s capability to solve computational and scientific modeling problems. Conducting research with a system of this size will allow us to keep pace with AI’s evolution in fields ranging from commercial to defense to basic science,” said Craig Vineyard, Hala Point team lead at Sandia National Laboratories. Currently, Hala Point is a research prototype that will advance the capabilities of future commercial systems. Intel anticipates that such lessons will lead to practical advancements, such as the ability for LLMs to learn continuously from new data. Such advancements promise to significantly reduce the unsustainable training burden of widespread AI deployments. Why It Matters: Recent trendsin scaling up deep learning models to trillions of parameters have exposed daunting sustainability challenges in AI and have highlighted the need for innovation at the lowest levels of hardware architecture. Neuromorphic computing is a fundamentally new approach that draws on neuroscience insights that integrate memory and computing with highly granular parallelism to minimize data movement. In published results from this month’s International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Loihi 2 demonstrated orders of magnitude gains in the efficiency, speed and adaptability of emerging small-scale edge workloads1. Advancing on its predecessor, Pohoiki Springs, with numerous improvements, Hala Point now brings neuromorphic performance and efficiency gains to mainstream conventional deep learning models, notably those processing real-time workloads such as video, speech and wireless communications. For example, Ericsson Research is applying Loihi 2 to optimize telecom infrastructure efficiency, as highlighted at this year’s Mobile World Congress. Hala Point, the world’s largest and Intel’s most advanced neuromorphic system to date, contains 1.15 billion neurons and packages 1,152 Loihi 2 processors produced on Intel 4 process node in a six-rack-unit data center chassis the size of a microwave oven. The system supports up to 1.15 billion neurons and 128 billion synapses distributed over 140,544 neuromorphic processing cores, consuming a maximum of 2,600 watts of power. It also includes over 2,300 embedded x86 processors for ancillary computations. (Credit: Intel Corporation) About Hala Point: Loihi 2 neuromorphic processors, which form the basis for Hala Point, apply brain-inspired computing principles, such as asynchronous, event-based spiking neural networks (SNNs), integrated memory and computing, and sparse and continuously changing connections to achieve orders-of-magnitude gains in energy consumption and performance. Neurons communicate directly with one another rather than communicating through memory, reducing overall power consumption. Hala Point packages 1,152 Loihi 2 processors produced on Intel 4 process node in a six-rack-unit data center chassis the size of a microwave oven. The system supports up to 1.15 billion neurons and 128 billion synapses distributed over 140,544 neuromorphic processing cores, consuming a maximum of 2,600 watts of power. It also includes over 2,300 embedded x86 processors for ancillary computations. Hala Point integrates processing, memory, and communication channels in a massively parallelized fabric, providing a total of 16 petabytes per second (PB/s) of memory bandwidth, 3.5 PB/s of inter-core communication bandwidth, and 5 terabytes per second (TB/s) of inter-chip communication bandwidth. The system can process over 380 trillion 8-bit synapses and over 240 trillion neuron operations per second. Applied to bio-inspired spiking neural network models, the system can execute its full capacity of 1.15 billion neurons 20 times faster than a human brain and up to 200 times faster rates at lower capacity. While Hala Point is not intended for neuroscience modeling, its neuron capacity is roughly equivalent to that of an owl brain or the cortex of a capuchin monkey. Loihi-based systems can perform AI inference and solve optimization problems using 100 times less energy at speeds as much as 50 times faster than conventional CPU and GPU architectures1. By exploiting up to 10:1 sparse connectivity and event-driven activity, early results on Hala Point show the system can achieve deep neural network efficiencies as high as 15 TOPS/W2 without requiring input data to be collected into batches, a common optimization for GPUs that significantly delays the processing of data arriving in real-time, such as video from cameras. While still in research, future neuromorphic LLMs capable of continuous learning could result in gigawatt-hours of energy savings by eliminating the need for periodic re-training with ever-growing datasets. What’s Next: The delivery of Hala Point to Sandia National Labs marks the first deployment of a new family of large-scale neuromorphic research systems that Intel plans to share with its research collaborators. Further development will enable neuromorphic computing applications to overcome power and latency constraints that limit AI capabilities' real-world, real-time deployment. Together with an ecosystem of more than 200 Intel Neuromorphic Research Community (INRC) members, including leading academic groups, government labs, research institutions and companies worldwide, Intel is working to push the boundaries of brain-inspired AI and progressing this technology from research prototypes to industry-leading commercial products over the coming years. Read the full article

[scienza-magia]

Sistema neuromorfico per robot e intelligenza artificiale

Hala Point Intel ha creato il sistema neuromorfico più grande al mondo. Intel ha presentato Hala Point, il primo sistema neuromorfico del settore con 1,15 miliardi di neuroni, ideato per rendere possibile un’AI più sostenibile. Hala Point comprende 1152 processori Loihi 2 in uno chassis per datacenter da sei unità rack delle dimensioni di un forno a microonde. Intel ha annunciato la costruzione del più grande sistema neuromorfico al mondo, nome in codice Hala Point. Si tratta di un sistema su larga scala che utilizza il processore Intel Loihi 2, il quale applica principi informatici ispirati al cervello, quali reti neurali spiking (SNN) asincrone e basate su eventi, memoria e calcolo integrati e connessioni sparse e in continua evoluzione, per ottenere miglioramenti di ordini di grandezza in termini di consumo energetico e prestazioni. I neuroni comunicano direttamente tra loro anziché comunicare attraverso la memoria, riducendo il consumo energetico complessivo.

Intel Loihi 2 Hala Point rappresenta un potenziamento della prima generazione Pohoiki Springs, con numerosi miglioramenti nell'architettura per ottenere una capacità neuronale oltre dieci volte più elevata e prestazioni fino a 12 volte superiori. Hala Point comprende 1152 processori Loihi 2 in uno chassis per datacenter da sei unità rack delle dimensioni di un forno a microonde. Il sistema supporta fino a 1,15 miliardi di neuroni e 128 miliardi di sinapsi distribuiti su 140.544 core di elaborazione neuromorfica che consumano un massimo di 2600 Watt di potenza. Il sistema include inoltre oltre 2300 processori x86 per calcoli ausiliari.

Hala Point, caratteristiche tecniche Hala Point integra canali di calcolo, memoria e comunicazione in una struttura massivamente parallelizzata, fornendo un totale di 16 petabyte al secondo (PB/s) di ampiezza di banda di memoria, 11 PB/s di ampiezza di banda di comunicazione inter-core e 5,5 TB/s di larghezza di banda di comunicazione tra chip. Il sistema può elaborare oltre 380mila miliardi di operazioni sinaptiche a 8 bit al secondo e oltre 240mila miliardi di operazioni neuronali al secondo. Applicato a modelli di rete neurale di ispirazione biologica, il sistema può eseguire la sua piena capacità di 1,15 miliardi di neuroni 20 volte più velocemente di un cervello umano e fino a 200 volte più velocemente a capacità inferiori. Sebbene Hala Point non sia destinato alla modellazione neuroscientifica, la sua capacità neuronale è più o meno equivalente a quella del cervello di un gufo o della corteccia di una scimmia cappuccino.

Secondo Intel, i sistemi basati su Loihi possono eseguire l'inferenza IA e risolvere problemi di ottimizzazione utilizzando 100 volte meno energia, a velocità fino a 50 volte superiori, rispetto alle architetture CPU e GPU convenzionali. Sfruttando la connettività sparsa fino a 10:1 e l'attività basate su eventi, Hala Point può supportare 30 milioni di miliardi (quadrillion) di operazioni al secondo, o 30 petaops, con un'efficienza che supera fino a 15 TOPS/W senza richiedere la raccolta dei dati di input in batch, un metodo ottimizzazione comune per le GPU che ritarda notevolmente l'elaborazione dei dati che arrivano in tempo reale, come i video provenienti dalle telecamere. Mentre sono ancora in fase di ricerca, i futuri LLM neuromorfici capaci di apprendimento continuo potrebbero portare a gigawattora di risparmio energetico, eliminando la necessità di riqualificazione periodica con dataset in continua crescita. "Il costo in temini di potenza di calcolo degli attuali modelli di intelligenza artificiale sta aumentando a ritmi insostenibili. L'industria ha bisogno di approcci fondamentalmente nuovi che consentano la scalabilità. Per questo motivo abbiamo sviluppato Hala Point, che combina l'efficienza del deep learning con nuove funzionalità di apprendimento e ottimizzazione ispirate al cervello. Ci auguriamo che la ricerca con Hala Point porti a scoperte rivoluzionarie nell'efficienza e nell'adattabilità della tecnologia IA su grande scala", ha dichiarato Mike Davies, direttore del Neuromorphic Computing Lab di Intel Labs.

Hala Point, caratteristiche tecniche Hala Point sarà utilizzato in primis dai ricercatori dei Sandia National Laboratories per la ricerca informatica avanzata. Gli scienziati si concentreranno sulla risoluzione di problemi di calcolo scientifico relativi alla fisica dei dispositivi, all'architettura dei computer e all'informatica. "Lavorare con Hala Point in Sandia fornisce al nostro team la preziosa capacità di risolvere problemi di modellazione scientifica. Condurre ricerche con un sistema di queste dimensioni ci consentirà di ricercare capacità di calcolo, di modellazione, simulazione e analisi dei dati per tenere il passo con l'evoluzione dell'intelligenza artificiale", ha dichiarato Craig Vineyard, Hala Point Team Lead dei Sandia National Laboratories. Attualmente, Hala Point è un prototipo di ricerca che migliorerà le capacità dei futuri sistemi disponibili in commercio. Intel prevede di apprendere informazioni che porteranno a scoperte di utilizzo pratico, come la capacità dei Large Language Model (LLM) di apprendere continuamente da nuovi dati. Tali scoperte promettono di ridurre in modo significativo l'insostenibile onere formativo che la crescita esponenziale dell'IA porta con sé. Read the full article

[jcmarchi]

Intel Develops Largest Neuromorphic System for Eco-Friendly AI Advancements

New Post has been published on https://thedigitalinsider.com/intel-develops-largest-neuromorphic-system-for-eco-friendly-ai-advancements/

Intel Develops Largest Neuromorphic System for Eco-Friendly AI Advancements

Intel has recently announced the creation of Hala Point, the world’s largest neuromorphic system, marking a significant step towards more sustainable and efficient artificial intelligence. Deployed initially at Sandia National Laboratories, Hala Point uses Intel’s advanced Loihi 2 processor and builds on the success of its predecessor, Pohoiki Springs, by offering substantial improvements in architecture. This enhancement boosts neuron capacity by more than tenfold and performance by up to twelve times.

“The computing cost of today’s AI models is rising at unsustainable rates. The industry needs fundamentally new approaches capable of scaling. For that reason, we developed Hala Point, which combines deep learning efficiency with novel brain-inspired learning and optimization capabilities. We hope that research with Hala Point will advance the efficiency and adaptability of large-scale AI technology,” said Mike Davies, director of the Neuromorphic Computing Lab at Intel Labs.

Hala Point distinguishes itself by being the first large-scale neuromorphic system capable of demonstrating state-of-the-art computational efficiencies on mainstream AI workloads. It can support up to 20 quadrillion operations per second, or 20 petaops, and offers unprecedented efficiency exceeding 15 trillion 8-bit operations per second per watt (TOPS/W) when executing conventional deep neural networks.

Researchers at Sandia National Laboratories will use Hala Point for advanced brain-scale computing research, focusing on scientific computing problems across various domains such as device physics, computer architecture, and informatics. “Working with Hala Point improves our Sandia team’s capability to solve computational and scientific modeling problems. Conducting research with a system of this size will allow us to keep pace with AI’s evolution in fields ranging from commercial to defense to basic science,” stated Craig Vineyard, Hala Point team lead at Sandia National Laboratories.

While Hala Point remains a research prototype, Intel envisions its lessons will significantly enhance future commercial systems’ capabilities, notably enabling large language models to learn continuously from new data and reducing the training burden of AI deployments.

The drive for increasingly large deep learning models has exposed significant sustainability challenges within AI, necessitating innovation at the fundamental levels of hardware architecture. Neuromorphic computing, inspired by neuroscience, integrates memory and computing within a highly parallel framework to minimize data movement. This approach has demonstrated remarkable gains in efficiency, speed, and adaptability, as evidenced by Loihi 2’s performance at this month’s International Conference on Acoustics, Speech, and Signal Processing (ICASSP).

Hala Point integrates 1,152 Loihi 2 processors and supports up to 1.15 billion neurons and 128 billion synapses, distributed over 140,544 neuromorphic processing cores, within a six-rack-unit data center chassis. Its massively parallelized fabric offers significant memory bandwidth and communication speeds, providing a robust foundation for bio-inspired spiking neural network models.

Intel’s ongoing development of neuromorphic systems like Hala Point aims to address power and latency constraints that currently limit the real-world deployment of AI. With the continued collaboration of the Intel Neuromorphic Research Community (INRC), Intel is committed to advancing this brain-inspired technology from research prototypes to commercial products.

[kinialohaguy]

Alooohaaa Friday

Aloha kākou and Happy Aloha Friday. Getting ready for a nice weekend. Got the grocery shopping done early so I can stay home and watch the Trump Rally tomorrow at Des Moines, Iowa. Plus, I can do a little yard work. Who am I kidding? I got a stack of yard work to do. Kīlauea Volcano Update: Summit Inflation Continues. Warning Siren Testing in Hilo Set for Friday. Virtual Meeting Held on Pohoiki…

[esandersonucc]

Story: Growing Memories

November 13, 2022 Isaiah 65:17-25Luke 21:5-19 Last week’s story was about a kolea who came back from a summer in Alaska to find Pohoiki completely changed by lava. It was a hard thing to accept that this is how an island grows. He saw a landscape that had been green and growing transformed into one that was rocky and barren. He might have taken more comfort if he’d talked with a tree – though…

[damienawai808]

How da @romerocreations play #funk Small kine sample of #organicislandmusic I’m brewing up for you! #maui #mauimusic #mauimusician #mauimusicians #hawaii #romerocreations #pohoiki #kalapana #hilo #mokukeawe #ukulele (at Paukukalo, Hawaii) https://www.instagram.com/p/CAkGE-WDKZY/?igshid=1q7biam8qi3yp

[hikereyes]

FOTO MOKU - December 15, 2018 - Line of freshly planted coconuts on the new black sand beach at Pohoiki.  The eruption in Puna this year advanced to the very edge of this park, then stopped.  A grand beach of very new black sand quickly built up.

by HikerEyes

[petri808]

Was nice and empty the beach 🔥 I didn’t even tan as much as I wanted to lol. Oh well, for another day. Got pics of a guy surfing 🏄 #pohoiki #pohoikibeach #kalapana #blacksandbeach #bigisland #bigislandhawaii https://www.instagram.com/p/BxTiYztlTyL/?utm_source=ig_tumblr_share&igshid=1u97zyx3o4g6f

[thebabelgraphic]

[bio-child]

collapsed lava tube

[johnsjohnsoniii]

🌺🌋🌴 Quarantine Quickies #022🌺🌋🌴 In Hawaii some of the quarantine rules are loosening up. There are more people out and about. People are starting to look around and assess the changes. What will be like it used to be? What is changed forever? What is changed for a little bit longer? Those are the questions we will be facing as we open up again. Hopefully we ramp up testing capacity so we can test everyone getting off or onto a plane so we can ensure that we are not importing or exporting anything but aloha. Here is a picture of Pohoiki after the lava quit flowing and the longshore currents rearranged the landscape. In the center you see Pohoiki boat ramp. Now Pohoiki Pond is probably a more accurate description. In the distance you can see the flow that obliterated so much land and emptied into the sea, where the waves and current deposited it to form new beach where the ramp used to be. This image is dedicated to the Kanahele family of the Big Island. They make amazing jewelry, and many of the men of this family serve to protect the public as EMTs, firemen, and lifeguards. Miss you guys and can't wait to see the ohana next year. #onebreathphoto #underwaterphotography #volcano #pohoiki #isiaachale #bigisland #madeofocean #hawaii #hawaiilife #hawaiistagram #aloha #bigisland #naturelovers #natgeo #海 #自然 #nakedplanet #earthpix #fucovid #fucovid19 #pele (at Pohoiki, Hawaii) https://www.instagram.com/p/B_1rnsYgq-b/?igshid=cxi5x3ka0ipg

[b9r6a7d7d8a-blog]

Can we go Back PLEASE!!!! 💔💔💔💔💔💔 #nevergonnabethesame #pohoiki #home https://www.instagram.com/p/B4o0vselnFy9SiLtQ46oNof83LDs6suiSvz_Ak0/?igshid=yoqnl8e26m2h

[merrilyali]

Standing on the #blacksandbeach off #fissure8 in #Pohoiki that used to be #ocean ah-MAZE-balls to be standing on the newest part of the #bigislandhawaii & the last photo notice the foot button. https://www.instagram.com/p/Bzuw6BBp7-2/?igshid=80o1t2ac0q5p

[psychedelightful]

Gaycation day 3, pohoiki part 1 #pohoiki #lavaflow #kalapana #redroad #isaachale #pahoa #puna #luckywelivehi #luckywelivehawaii #hilife #bigisland #hawaii #vacation #gaycation @purdymoon (at Pohoiki, Hawaii) https://www.instagram.com/p/Bv59FoMFCcO_MHoy8ey77X2y_pcusZK0FKquWM0/?utm_source=ig_tumblr_share&igshid=1nj692rxy0qf0