@HPCpodcast with Shahin Khan and Doug Black

Special guest David Kanter of ML Commons joins Shahin Khan and Doug Black to discuss AI performance metrics. AI is everywhere and destined to run on everything from devices to big systems. So, in addition to the well-known MLPerf benchmark for AI training, ML Commons provides a growing suite of benchmarks and data sets for other aspects of AI such as inference, storage, and safety. David is a founder, board member of ML Commons and the head of MLPerf benchmarks. David has more than 16 years of experience in semiconductors computing and machine learning. He was a founder of a microprocessor and compiler startup. He was also at Astor Data Systems and has consulted for NVIDIA, Intel, KLA, Applied Materials, Qualcomm, Microsoft, and others.   OrionX Editorial TeamThe OrionX editorial team manages the content on this website. The post @HPCpodcast-91: David Kanter of ML Commons on AI Performance Measurement appeared first on OrionX.net.

– India rising – High Bandwidth Memory (HBM) in short supply – Novel accelerator architectures – CHIPS Act funds Extreme Ultra Violet (EUV) lithography technology in the US   OrionX Editorial TeamThe OrionX editorial team manages the content on this website. The post HPC News Bytes – 20241104 appeared first on OrionX.net.

– TSMC delivers good news for chip manufacturing in the US – Denmark builds AI supercomputer with Eviden and Nvidia – White House tasks NNSA/DOE with assessing AI risk for National Security   OrionX Editorial TeamThe OrionX editorial team manages the content on this website. The post HPC News Bytes – 20241028 appeared first on OrionX.net.

– Exascale Day, Zettascale, Avogadro’s Number – Did a Chinese quantum computer crack military grade encryption? – The great Rear admiral Dr. Grace Hopper – The First Computer Bug – Hyperion Research innovation award – Q2B Conference   OrionX Editorial TeamThe OrionX editorial team manages the content on this website. The post HPC News Bytes – 20241021 appeared first on OrionX.net.

– AMD’s new CPU, GPU, DPU, NIC – Foxconn’s big supercomputer at Hon Hai Kaohsiung Center in Taiwan – AI drives Nobel Prizes in Physics and Chemistry – Yann LeCun’s take on AGI   OrionX Editorial TeamThe OrionX editorial team manages the content on this website. The post HPC News Bytes – 20241014 appeared first on OrionX.net.

– IDC report on datacenter energy use and growth – NTT Research on the state of optical computing – AI experts weigh in on the future impact of AI   OrionX Editorial TeamThe OrionX editorial team manages the content on this website. The post HPC News Bytes – 20241007 appeared first on OrionX.net.

– Intel Xeon 6, Gaudi 3, MRDIMM, AMX – Intel 3 Fab, TSMC, Samsung, Chip subsidies – AMD Turin, AMD UDNA – Quantum update   OrionX Editorial TeamThe OrionX editorial team manages the content on this website. The post HPC News Bytes – 20240930 appeared first on OrionX.net.

In this discussion, Patrick Caporale, Executive Director and Chief I/O Architect at Lenovo, dives into the impact of memory-centric architectures on high-performance computing. He explores the CPU-Memory-I/O gap, innovations in I/O and storage solutions, and the importance of advanced caching strategies. Patrick also highlights the integration challenges posed by rapid chip advancements from major players like Nvidia, Intel, and AMD. The conversation emphasizes how collaboration between vendors and clients is crucial for navigating these technological shifts effectively.

– AI-fueled M&A rumors: Intel, Qualcomm, Ampere – Three Mile Island resurrected to feed GPUs for Microsoft – Beyond GPUs lie specialized chiplets   OrionX Editorial TeamThe OrionX editorial team manages the content on this website. The post HPC News Bytes – 20240923 appeared first on OrionX.net.

Rick Stevens and Mike Papka of Argonne National Lab join the discussion, bringing their expertise in high-performance computing. They dive into the challenges and innovations surrounding the Aurora supercomputer, particularly in areas like AI applications and reliability. The duo examines the shift from traditional computing architectures to GPU-based systems and the importance of power management in data centers. They also explore the integration of cloud computing and the transformative potential of quantum technologies, affirming the future of Exascale and AI in science.