Η Intel ανακοίνωσε αυτή την εβδομάδα ότι πρόκειται να δημιουργήσει δύο νέα τμήματα στο εσωτερικό της που θα επικεντρωθούν ξεχωριστά στην ανάπτυξη λογισμικού και στο high-end computing και τα γραφικά.
Η εταιρεία επίσης έκανε γνωστό ότι οι Sandra Rivera και Raja Koduri θα αναλάβουν νέους ηγετικούς ρόλους εντός της εταιρείας, στο δυναμικό της οποίας εντάχθηκαν και δύο βετεράνοι από τον τεχνολογικό κλάδο, οι Nick McKeown και Greg Lavender. Ο τελευταίος προέρχεται από την VMWare όπου και υπηρετούσε την εταιρεία από τις θέσεις του Senior Vice President και CEO (Chief Executive Officer). Στην Intel, αναλαμβάνει τους ρόλους Senior Vice President, CTO (Chief Technology Officer) και General Manager του τμήματος Software and Advanced Technology Group (SATG).
O Raja Koduri θα ηγηθεί του τμήματος Accelerated Computing Systems and Graphics (AXG) της Intel που φιλοδοξεί να ανταγωνιστεί την Nvidia καθώς η προσφορά της τελευταίας στο high-performance computing και στα κέντρα δεδομένων έχει κερδίσει σημαντικό έδαφος σε σχέση με την Intel, κυρίως μετά την άνοδο λογισμικού τεχνητής νοημοσύνης και μηχανικής μάθησης. Ο Raja Koduri είχε εργαστεί στο παρελθόν στην Apple ωστόσο έγινε περισσότερο γνωστός από την θητεία του στην AMD, από την οποία και αποχώρησε το 2017 για να ενταχθεί στην Intel.
Οι Sandra Rivera, Raja Koduri, Nick McKeown και Greg Lavender θα αναφέρονται απευθείας στον CEO της Intel, Pat Gelsinger. Αξίζει να αναφέρουμε επίσης ότι ο Navin Shenoy, που ήταν υπεύθυνος του τμήματος Datacenter και AI πριν το αναλάβει η Sandra Rivera αποχωρεί από την Intel στις 6 Ιουλίου.
Αν και όπως είναι γνωστό, η Intel τα τελευταία χρόνια αντιμετώπισε -και συνεχίζει να αντιμετωπίζει- πολλά προβλήματα στην κατασκευή των επεξεργαστών της σε κλίμακα 10nm και κάτω, εντούτοις για τους νέους επεξεργαστές γραφικών της (GPUs) πρόκειται να ακολουθήσει διαφορετική προσέγγιση, αξιοποιώντας το know-how και την παραγωγική ικανότητα της γνωστής εταιρείας TSMC (Taiwan Semiconductor Manufacturing Company) για να μπορέσει να ανταγωνιστεί αποτελεσματικότερα την προσφορά της Nvidia.
Ένας από τους λόγους που η Nvidia κέρδισε σημαντικό έδαφος έναντι της Intel ήταν ότι παρείχε σε προγραμματιστές και developers λογισμικού όλα τα εργαλεία που χρειάζονταν για να συντάσσουν κώδικα ειδικά για τα chips και από ότι φαίνεται, αυτή θα είναι και το βασικό έργο της νέας ομάδας του Greg Lavender. Η Intel έκανε γνωστό άλλωστε ότι εργάζεται σε εργαλεία λογισμικού για την ανάπτυξη εφαρμογών για νέους τύπους chips όπως είναι αυτά που βασίζονται στην αρχιτεκτονική ανοιχτού κώδικα RISC-V. Η εταιρεία μάλιστα φαίνεται να έχει κινηθεί και για την εξαγορά της SiFive, πρωτοπόρου στον συγκεκριμένο τομέα. insomniagr
Customers Select Intel to Accelerate Research and Help Solve Scientific Challenges
Intel is the foundation of high performance computing (HPC) – from the workstation to the cloud to the backbone of the Top500. At SC20, Intel’s Trish Damkroger, vice president and general manager of HPC at Intel, shows how Intel and its partners are building the future of HPC today through hardware and software technologies that accelerate the broad deployment of advanced HPC systems. (Credit: Intel Corporation)
Intel’s SC20 Content: HPCwire website
Keynote Slides: “Building the Future Today with HPC”
Intel’s Key SC20 News Highlights:
- The upcoming 3rd Gen Intel® Xeon® Scalable processors (code-named “Ice Lake”) will deliver increased performance for high performance computing (HPC) workloads through higher memory bandwidth, a new core architecture, increased processor cores and faster input/output.
- Customers, including the Max Planck Computing & Data Facility and the Korea Meteorological Administration, select 3rd Gen Intel Xeon Scalable processors to accelerate their HPC applications.
- Argonne National Laboratory leveraging Intel® Xe-HP GPUs and Intel® oneAPI toolkits to accelerate exascale application development.
- Partners, including AWS, Penguin Computing and Advantech, are verified to deploy HPC-optimized Intel® Select Solutions, which help enable customers to deploy and manage HPC workloads.
SANTA CLARA, Calif., Nov. 17, 2020 – At Supercomputing 2020 (SC20), Intel highlighted how the company’s hardware and software technologies are enabling the future of high performance computing (HPC). Companies around the world are selecting Intel® XPUs (CPUs, GPUs, FPGAs and accelerators) and oneAPI programming environment to accelerate the development and deployment of advanced computing systems.
3rd Gen Intel® Xeon® Scalable Processors (code-named “Ice Lake”)
In her keynote presentation to kickoff SC20, Trish Damkroger, vice president and general manager of High Performance Computing at Intel, highlighted Intel’s upcoming Ice Lake server processors that deliver performance-optimized features for a range of HPC workloads. Increased memory bandwidth, a new high-performance Sunny Cove core architecture, increased processor core count and support for PCIe Gen4 will help customers solve scientific challenges across different disciplines, including life sciences, material science and weather modeling.
More: Intel at Supercomputing 2020 (Press Kit)
Early testing demonstrates that two socket systems using 32-core Ice Lake processors can deliver higher performance on specified workloads at half the core count when compared to competitive x86 systems with 64-core processors. Customers running life sciences and financial services applications can expect to see higher performance on workloads such as NAMD molecular dynamics simulation (up to 1.2 times)1, Monte Carlo simulations (up to 1.3 times)2, and LAMMPS molecular modeling simulation (up to 1.2 times)3 compared to competitive x86 systems featuring twice as many cores as a 32-core Ice Lake processor-based system.
Several customers are adopting Ice Lake to address their next-generation HPC needs, including:
- Korea Meteorological Administration, which selected Ice Lake server processors to power its Supercomputer No. 5. The system will deliver 50 petaflops performance to help study weather and climate change and enable more reliable and actionable forecasting relative to its current system.
- The Max Planck Computing and Data Facility, which will adopt Ice Lake for use in its new Raven system. The Raven system will deliver 9 petaflops performance and enable groundbreaking research in physics, bioscience, theoretical chemistry and more.
- The National Institute of Advanced Industrial Science and Technology (AIST), which will use Ice Lake to power its AI Bridging Green Cloud Infrastructure system being added to its AI Data Center Building. The system is expected to deliver a theoretical peak performance of half-precision floating-point operations of 850 petaflops.
- The University of Tokyo and Osaka University, which are the first Japanese universities to leverage Ice Lake. The University of Tokyo’s 2.4 petaflops system and Osaka University’s greater than 8 petaflops system will be used for general research and data analytics.
- Oracle which will deploy Ice Lake within its Oracle Cloud Infrastructure to power its X9 Generation HPC cloud instance, targeted at computationally intensive workloads such as crash simulation, seismic analysis and electronic design automation.
Damkroger also highlighted some of the recent supercomputing projects that target Intel’s latest Xeon processors, future Xeon processors, memory and artificial intelligence (AI) technologies to advance science and research:
- Barcelona Supercomputing Center is leveraging Intel® Optane® persistent memory and Xeon Scalable processors to accelerate HPC applications using heterogeneous memory architectures. Its researchers found Optane persistent memory uses 10 times less power than DRAM and double-digit increases in performance for several applications.
- LIQID and Intel are collaborating to provide the world’s largest composable supercomputer for the U.S. Department of Defense. LIQID’s platform consists of Intel Xeon Platinum 9200 CPUs and is being used to create software-defined servers on demand for the DoD’s AI-infused workloads – driving up resource utilization and AI performance.
- Los Alamos National Laboratory’s Crossroads supercomputer will enable scientists at Lawrence Livermore, Los Alamos and Sandia National Laboratories to support the Stockpile Stewardship Program, current and planned weapons Life Extension Program activities, and future predictive weapons research and calculations. The system will feature Intel’s upcoming Sapphire Rapids processor and deliver four times greater system performance and enable easier code portability than its predecessor, the Trinity system.
- Lawrence Livermore National Laboratory is leveraging the latest Intel Xeon Scalable processors in its Ruby supercomputer to perform functions for the National Nuclear Security Administration (NNSA) and support the Laboratory’s COVID-19 research.
0 Post a Comment:
إرسال تعليق