Intel’s Aurora Supercomputer Tops AI Performance Charts, Setting New Standards

Intel, Argonne National Laboratory, and HPE announced at ISC High Performance 2024 that the Aurora supercomputer has achieved exascale computing, making it the fastest AI system dedicated to open science, with Intel emphasizing the importance of open ecosystems in driving AI-accelerated HPC and paving the way for future discoveries, while also highlighting the impressive configuration and capabilities of Aurora, and discussing the role of Intel's Xe GPU architecture, oneAPI software tools, and Tiber Developer Cloud in advancing HPC and AI, and the deployment of new supercomputers utilizing Intel technologies for breakthroughs in various fields.

Intel's collaboration with Argonne National Laboratory and HPE has resulted in the world's fastest AI system dedicated to open science.
The Aurora supercomputer is designed as an AI-centric system, enabling researchers to leverage generative AI models for accelerated scientific discovery.
Intel's suite of software tools, including the Intel oneAPI DPC++/C++ Compiler and optimized AI frameworks, fosters an open ecosystem for developers, promoting flexibility and scalability across various devices and form factors.

At the ISC High Performance 2024 event, Intel made a announcement in collaboration with Argonne National Laboratory and Hewlett Packard Enterprise (HPE). They revealed that the Aurora supercomputer has achieved exascale computing, reaching a stunning 1.012 exaflops. This makes Aurora the fastest AI system in the world dedicated to open science, with an impressive 10.6 AI exaflops.

Intel emphasized the importance of open ecosystems in driving AI-accelerated high-performance computing (HPC). Ogi Brkic, Intel’s vice president and general manager of Data Center AI Solutions, highlighted the significance of this achievement, stating that the Aurora supercomputer will pave the way for future discoveries. From understanding climate patterns to unraveling the mysteries of the universe, supercomputers like Aurora play a crucial role in solving complex scientific challenges that can benefit humanity.

Aurora was designed as an AI-centric system right from the start, enabling researchers to leverage generative AI models for accelerated scientific discovery. Argonne National Laboratory has already made significant progress in AI-driven research using this supercomputer. They have successfully mapped the human brain’s 80 billion neurons, enhanced high-energy particle physics with deep learning, and accelerated drug design and discovery through machine learning, among other achievements.

The Aurora supercomputer boasts an impressive configuration, with 166 racks, 10,624 compute blades, 21,248 Intel Xeon CPU Max Series processors, and 63,744 Intel Data Center GPU Max Series units. It is one of the largest GPU clusters in the world. Additionally, Aurora features an Ethernet-based supercomputing interconnect with 84,992 HPE slingshot fabric endpoints, further enhancing its capabilities.

While Aurora secured second place on the high-performance LINPACK (HPL) benchmark, it broke the exascale barrier at 1.012 exaflops using only 87% of the system’s nodes. It also achieved the third spot on the high-performance conjugate gradient (HPCG) benchmark at 5,612 Teraflops per second (TF/s) with 39% of the machine. The HPCG benchmark provides insights into communication and memory access patterns, which are crucial in real-world HPC applications.

At the core of the Aurora supercomputer lies the Intel Data Center GPU Max Series, built on the Intel Xe GPU architecture. This architecture features specialized hardware optimized for both AI and HPC tasks, such as matrix and vector compute blocks. The parallel processing capabilities of the Xe architecture excel in managing the complex matrix-vector operations involved in neural network AI computation. These compute cores play a pivotal role in accelerating matrix operations essential for deep learning models.

Intel’s suite of software tools, including the Intel oneAPI DPC++/C++ Compiler, performance libraries, and optimized AI frameworks and tools, complements the Xe architecture. This fosters an open ecosystem for developers, characterized by flexibility and scalability across various devices and form factors.

During a special session at ISC 2024, CEO Andrew Richards of Codeplay, an Intel company, addressed the growing demand for accelerated computing and software in HPC and AI. He emphasized the importance of oneAPI, which offers a unified programming model across diverse architectures. Built on open standards, oneAPI empowers developers to write code that seamlessly runs on different hardware platforms without extensive modifications or vendor lock-in.

Intel Tiber Developer Cloud is also expanding its compute capacity with new state-of-the-art hardware platforms and service capabilities. This allows enterprises and developers to evaluate the latest Intel architecture, innovate and optimize AI models and workloads quickly, and deploy AI models at scale. The new hardware includes previews of Intel Xeon 6 E-core and P-core systems, as well as large-scale clusters based on Intel Gaudi 2 and Intel Data Center GPU Max Series.

The deployment of new supercomputers utilizing Intel Xeon CPU Max Series and Intel Data Center GPU Max Series technologies further demonstrates Intel’s commitment to advancing HPC and AI. These systems, such as CMCC’s Cassandra, ENEA’s CRESCO 8, TACC, and UKAEA, will enable breakthroughs in climate change modeling, fusion energy research, data analysis in biology, and simulations on various materials.

The mixed-precision AI benchmark results achieved by Aurora will serve as the foundation for Intel’s next-generation GPU for AI and HPC, code-named Falcon Shores. Falcon Shores will leverage the next-generation Intel Xe architecture combined with the best features of Intel Gaudi. This integration will provide a unified programming interface for developers.

Early performance results on Intel Xeon 6 with P-Cores and MCR memory show significant improvements, delivering up to 2.3x performance improvement for real-world HPC applications like NEMO compared to the previous generation. This solidifies Intel Xeon as the preferred host CPU choice for HPC solutions.

About Our Team

Our team comprises industry insiders with extensive experience in computers, semiconductors, games, and consumer electronics. With decades of collective experience, we’re committed to delivering timely, accurate, and engaging news content to our readers.

Background Information

About Intel:

Intel Corporation, a global technology leader, is for its semiconductor innovations that power computing and communication devices worldwide. As a pioneer in microprocessor technology, Intel has left an indelible mark on the evolution of computing with its processors that drive everything from PCs to data centers and beyond. With a history of advancements, Intel's relentless pursuit of innovation continues to shape the digital landscape, offering solutions that empower businesses and individuals to achieve new levels of productivity and connectivity.

Latest Articles about Intel

Technology Explained

CPU: The Central Processing Unit (CPU) is the brain of a computer, responsible for executing instructions and performing calculations. It is the most important component of a computer system, as it is responsible for controlling all other components. CPUs are used in a wide range of applications, from desktop computers to mobile devices, gaming consoles, and even supercomputers. CPUs are used to process data, execute instructions, and control the flow of information within a computer system. They are also used to control the input and output of data, as well as to store and retrieve data from memory. CPUs are essential for the functioning of any computer system, and their applications in the computer industry are vast.

Latest Articles about CPU

GPU: GPU stands for Graphics Processing Unit and is a specialized type of processor designed to handle graphics-intensive tasks. It is used in the computer industry to render images, videos, and 3D graphics. GPUs are used in gaming consoles, PCs, and mobile devices to provide a smooth and immersive gaming experience. They are also used in the medical field to create 3D models of organs and tissues, and in the automotive industry to create virtual prototypes of cars. GPUs are also used in the field of artificial intelligence to process large amounts of data and create complex models. GPUs are becoming increasingly important in the computer industry as they are able to process large amounts of data quickly and efficiently.

Latest Articles about GPU

HPC: HPC, or High Performance Computing, is a type of technology that allows computers to perform complex calculations and process large amounts of data at incredibly high speeds. This is achieved through the use of specialized hardware and software, such as supercomputers and parallel processing techniques. In the computer industry, HPC has a wide range of applications, from weather forecasting and scientific research to financial modeling and artificial intelligence. It enables researchers and businesses to tackle complex problems and analyze vast amounts of data in a fraction of the time it would take with traditional computing methods. HPC has revolutionized the way we approach data analysis and has opened up new possibilities for innovation and discovery in various fields.

Latest Articles about HPC

P-Cores: P-Cores (Performance Cores) are a type of processor technology developed by Intel that is designed to improve the performance of computer systems. This technology is based on the concept of multi-core processors, which are processors that contain multiple cores or processing units. P-Cores are designed to increase the speed and efficiency of computer systems by allowing multiple cores to work together in parallel. This technology is used in a variety of applications, including gaming, video editing, and data analysis. P-Cores are also used in servers and other high-performance computing systems. The technology is also used in mobile devices, such as smartphones and tablets, to improve battery life and performance. P-Cores are an important part of the computer industry, as they allow for faster and more efficient computing.

Latest Articles about P-Cores

Teraflops: Teraflops, or trillion floating point operations per second, is a measure of computing speed and power. It is used to describe the performance of supercomputers and high-end computer processors. To put it simply, a teraflop is equivalent to one trillion calculations per second. This incredible speed allows for complex and data-intensive tasks to be completed in a fraction of the time it would take a regular computer. In the computer industry, teraflops are used for a variety of applications such as weather forecasting, scientific research, and artificial intelligence. They also play a crucial role in the development of advanced video games and virtual reality experiences. With the continuous advancement of technology, the use of teraflops is expected to increase, leading to even faster and more efficient computing capabilities.

Latest Articles about Teraflops

Xeon: The Intel Xeon processor is a powerful and reliable processor used in many computer systems. It is a multi-core processor that is designed to handle multiple tasks simultaneously. It is used in servers, workstations, and high-end desktop computers. It is also used in many embedded systems, such as routers and switches. The Xeon processor is known for its high performance and scalability, making it a popular choice for many computer applications. It is also used in many cloud computing applications, as it is capable of handling large amounts of data and providing high levels of performance. The Xeon processor is also used in many scientific and engineering applications, as it is capable of handling complex calculations and simulations.