Torsten Hoefler 🇨🇭
@thoefler.bsky.social
Professor ETHZ, head of SPCL, Chief Architect ML at CSCS researching large-scale #HPC and #AI systems and #Climate computing - youtube: http://bit.ly/3h1VgIU
Industry reacted quickly.
From lossy packet delivery to reliable multipath spraying: Multipath Reliable Connection (MRC) turns many "Issues at Hyperscale" into engineering solutions.
buff.ly/NH2FvrQ
buff.ly/pueSosc
buff.ly/QpvkyJ0
On the path to Ultra Ethernet. #AI #HPC #Networking
From lossy packet delivery to reliable multipath spraying: Multipath Reliable Connection (MRC) turns many "Issues at Hyperscale" into engineering solutions.
buff.ly/NH2FvrQ
buff.ly/pueSosc
buff.ly/QpvkyJ0
On the path to Ultra Ethernet. #AI #HPC #Networking
September 24, 2026 at 5:26 AM
Industry reacted quickly.
From lossy packet delivery to reliable multipath spraying: Multipath Reliable Connection (MRC) turns many "Issues at Hyperscale" into engineering solutions.
buff.ly/NH2FvrQ
buff.ly/pueSosc
buff.ly/QpvkyJ0
On the path to Ultra Ethernet. #AI #HPC #Networking
From lossy packet delivery to reliable multipath spraying: Multipath Reliable Connection (MRC) turns many "Issues at Hyperscale" into engineering solutions.
buff.ly/NH2FvrQ
buff.ly/pueSosc
buff.ly/QpvkyJ0
On the path to Ultra Ethernet. #AI #HPC #Networking
AI and Mathematicians - all stages of grief on a single panel.
As Turing Award winner Whitfield Diffie put it, "I am very concerned with you people's concern over intellectual property."
A collision of proofs, probability, scaling laws, and strong opinions. An experience! > 27k views in 5 days.
As Turing Award winner Whitfield Diffie put it, "I am very concerned with you people's concern over intellectual property."
A collision of proofs, probability, scaling laws, and strong opinions. An experience! > 27k views in 5 days.
September 22, 2026 at 5:13 AM
AI and Mathematicians - all stages of grief on a single panel.
As Turing Award winner Whitfield Diffie put it, "I am very concerned with you people's concern over intellectual property."
A collision of proofs, probability, scaling laws, and strong opinions. An experience! > 27k views in 5 days.
As Turing Award winner Whitfield Diffie put it, "I am very concerned with you people's concern over intellectual property."
A collision of proofs, probability, scaling laws, and strong opinions. An experience! > 27k views in 5 days.
Want to help shape the future of AI infrastructure?
We're hiring at Microsoft Azure. Our work spans AI systems and networking powering the next generation of intelligent systems.
Looking for exceptional engineers who enjoy tackling hard problems with real-world impact.
Apply here: buff.ly/Myvgeay
We're hiring at Microsoft Azure. Our work spans AI systems and networking powering the next generation of intelligent systems.
Looking for exceptional engineers who enjoy tackling hard problems with real-world impact.
Apply here: buff.ly/Myvgeay
Principal Software Engineer - Networking & Storage Systems | Microsoft Careers
Architect and lead development of robust networking and storage frameworks for large-scale cloud platforms. Own end-to-end technical strategy, making high-impact architectural decisions. Collaborate…
buff.ly
September 18, 2026 at 12:38 PM
Want to help shape the future of AI infrastructure?
We're hiring at Microsoft Azure. Our work spans AI systems and networking powering the next generation of intelligent systems.
Looking for exceptional engineers who enjoy tackling hard problems with real-world impact.
Apply here: buff.ly/Myvgeay
We're hiring at Microsoft Azure. Our work spans AI systems and networking powering the next generation of intelligent systems.
Looking for exceptional engineers who enjoy tackling hard problems with real-world impact.
Apply here: buff.ly/Myvgeay
We keep talking about flop/s.
Maybe we should talk about flop/s per square millimeter.
Maia 200 achieves ~12 Tflop/s FP4 (6 FP8) in just 1 mm², roughly the size of a grain of salt.
When data movement dominates energy consumption, compute density becomes a first-class design objective.
#AI #HPC
Maybe we should talk about flop/s per square millimeter.
Maia 200 achieves ~12 Tflop/s FP4 (6 FP8) in just 1 mm², roughly the size of a grain of salt.
When data movement dominates energy consumption, compute density becomes a first-class design objective.
#AI #HPC
September 14, 2026 at 5:00 AM
Digital for Good: What if climate predictions could be generated 1,000× more efficiently and with 1,000× less CO₂?
In this interview, Fanny Lehmann and the ESFM team explain how AI foundation models are transforming weather forecasting.
buff.ly/Il8H4Td
buff.ly/yRF5Txv
#ClimateAI #AIforScience
In this interview, Fanny Lehmann and the ESFM team explain how AI foundation models are transforming weather forecasting.
buff.ly/Il8H4Td
buff.ly/yRF5Txv
#ClimateAI #AIforScience
September 9, 2026 at 5:00 AM
Digital for Good: What if climate predictions could be generated 1,000× more efficiently and with 1,000× less CO₂?
In this interview, Fanny Lehmann and the ESFM team explain how AI foundation models are transforming weather forecasting.
buff.ly/Il8H4Td
buff.ly/yRF5Txv
#ClimateAI #AIforScience
In this interview, Fanny Lehmann and the ESFM team explain how AI foundation models are transforming weather forecasting.
buff.ly/Il8H4Td
buff.ly/yRF5Txv
#ClimateAI #AIforScience
Send your best papers to SC Asia before the end-of-month deadline! 🚀
SC Asia is among the flagship international forums for breakthroughs in supercomputing, AI infrastructure, system architecture, networking, quantum, cloud and scientific computing.
buff.ly/3C7EUpz
#SCAsia #Supercomputing #HPC
SC Asia is among the flagship international forums for breakthroughs in supercomputing, AI infrastructure, system architecture, networking, quantum, cloud and scientific computing.
buff.ly/3C7EUpz
#SCAsia #Supercomputing #HPC
September 7, 2026 at 5:02 AM
Send your best papers to SC Asia before the end-of-month deadline! 🚀
SC Asia is among the flagship international forums for breakthroughs in supercomputing, AI infrastructure, system architecture, networking, quantum, cloud and scientific computing.
buff.ly/3C7EUpz
#SCAsia #Supercomputing #HPC
SC Asia is among the flagship international forums for breakthroughs in supercomputing, AI infrastructure, system architecture, networking, quantum, cloud and scientific computing.
buff.ly/3C7EUpz
#SCAsia #Supercomputing #HPC
Most filtered vector search benchmarks rely on outdated datasets.
SPCL student Patrick presents arxiv-for-fanns: a new benchmark with 2.7M modern embeddings concludes: There is no universally best filtered ANN algorithm.
📖 buff.ly/hHvx0bl
📽️ buff.ly/r1ERkxb
#VectorSearch #RAG #ANN #Databases
SPCL student Patrick presents arxiv-for-fanns: a new benchmark with 2.7M modern embeddings concludes: There is no universally best filtered ANN algorithm.
📖 buff.ly/hHvx0bl
📽️ buff.ly/r1ERkxb
#VectorSearch #RAG #ANN #Databases
September 2, 2026 at 5:35 AM
Most filtered vector search benchmarks rely on outdated datasets.
SPCL student Patrick presents arxiv-for-fanns: a new benchmark with 2.7M modern embeddings concludes: There is no universally best filtered ANN algorithm.
📖 buff.ly/hHvx0bl
📽️ buff.ly/r1ERkxb
#VectorSearch #RAG #ANN #Databases
SPCL student Patrick presents arxiv-for-fanns: a new benchmark with 2.7M modern embeddings concludes: There is no universally best filtered ANN algorithm.
📖 buff.ly/hHvx0bl
📽️ buff.ly/r1ERkxb
#VectorSearch #RAG #ANN #Databases
Nothing beats chatting and traveling with president Ramos-Horta, talking to the next generation in Timor-Leste, and discussing deep topics about #AI for education and development with Turing Awardees and Nobel Laureates on tropical islands.
buff.ly/n0V8ikW
buff.ly/n0V8ikW
August 31, 2026 at 4:58 AM
Nothing beats chatting and traveling with president Ramos-Horta, talking to the next generation in Timor-Leste, and discussing deep topics about #AI for education and development with Turing Awardees and Nobel Laureates on tropical islands.
buff.ly/n0V8ikW
buff.ly/n0V8ikW
We presented how Maia 200's Software-Define Dataflow delivers highest inference performance for production LLMs in Microsoft's fleet at #HotChips26 today. We also released the full paper with many details on arXiv: buff.ly/KJ8yMOp
And a blog post: buff.ly/TsrPppe
And a blog post: buff.ly/TsrPppe
August 26, 2026 at 11:10 AM
We presented how Maia 200's Software-Define Dataflow delivers highest inference performance for production LLMs in Microsoft's fleet at #HotChips26 today. We also released the full paper with many details on arXiv: buff.ly/KJ8yMOp
And a blog post: buff.ly/TsrPppe
And a blog post: buff.ly/TsrPppe
Check out SPCL's Tommaso explaining REPS for efficient packet spraying in Ethernet!
Developed in collaboration with Microsoft and now part of Ultra Ethernet, REPS delivers adaptive, load balancing and failure mitigation. Already powering large-scale AI clusters!
📺 buff.ly/sBLvG87
Developed in collaboration with Microsoft and now part of Ultra Ethernet, REPS delivers adaptive, load balancing and failure mitigation. Already powering large-scale AI clusters!
📺 buff.ly/sBLvG87
REPS: Recycled Entropy Packet Spraying for Adaptive Load Balancing and Failure Mitigation
REPS Visualizer: https://tommasobonato.github.io/reps-fat-tree-viz/
Paper Title: REPS: Recycled Entropy Packet Spraying for Adaptive Load Balancing and Failure Mitigation
Speaker: Tommaso…
www.youtube.com
August 24, 2026 at 5:15 AM
Check out SPCL's Tommaso explaining REPS for efficient packet spraying in Ethernet!
Developed in collaboration with Microsoft and now part of Ultra Ethernet, REPS delivers adaptive, load balancing and failure mitigation. Already powering large-scale AI clusters!
📺 buff.ly/sBLvG87
Developed in collaboration with Microsoft and now part of Ultra Ethernet, REPS delivers adaptive, load balancing and failure mitigation. Already powering large-scale AI clusters!
📺 buff.ly/sBLvG87
This Thursday at Hot Interconnects #HOTI26: "Demystifying NVSHMEM". Learn how the old #HPC PGAS and symmetric heap concepts nicely accelerate GPU communications 🚀
Reminiscient of our earlier dCUDA paper that turns 10 years now! Great to see concepts productized 🤗
buff.ly/K4aRYqz
buff.ly/Z9mHPso
Reminiscient of our earlier dCUDA paper that turns 10 years now! Great to see concepts productized 🤗
buff.ly/K4aRYqz
buff.ly/Z9mHPso
August 17, 2026 at 5:00 AM
This Thursday at Hot Interconnects #HOTI26: "Demystifying NVSHMEM". Learn how the old #HPC PGAS and symmetric heap concepts nicely accelerate GPU communications 🚀
Reminiscient of our earlier dCUDA paper that turns 10 years now! Great to see concepts productized 🤗
buff.ly/K4aRYqz
buff.ly/Z9mHPso
Reminiscient of our earlier dCUDA paper that turns 10 years now! Great to see concepts productized 🤗
buff.ly/K4aRYqz
buff.ly/Z9mHPso
"Messages matter packets don't" - learn how our work on Multipath Reliable Connection (MRC) at #HOTI26 shifts to an application-centric view.
Join us online next Wednesday 1pm PDT with Rip Sohan (AMD) and Eric Spada (BRCM)!
A bigstep towards Ultra Ethernet!
buff.ly/K4aRYqz
buff.ly/NIZXU9A
Join us online next Wednesday 1pm PDT with Rip Sohan (AMD) and Eric Spada (BRCM)!
A bigstep towards Ultra Ethernet!
buff.ly/K4aRYqz
buff.ly/NIZXU9A
August 14, 2026 at 5:00 AM
"Messages matter packets don't" - learn how our work on Multipath Reliable Connection (MRC) at #HOTI26 shifts to an application-centric view.
Join us online next Wednesday 1pm PDT with Rip Sohan (AMD) and Eric Spada (BRCM)!
A bigstep towards Ultra Ethernet!
buff.ly/K4aRYqz
buff.ly/NIZXU9A
Join us online next Wednesday 1pm PDT with Rip Sohan (AMD) and Eric Spada (BRCM)!
A bigstep towards Ultra Ethernet!
buff.ly/K4aRYqz
buff.ly/NIZXU9A
At #ModSim26, Jeff Vetter highlighted DOE's ambitious goal: 150-250 fault-tolerant logical qubits by 2028 at ≤10⁻⁸ logical error rate.
The science is remarkable, but the real story is that #Quantum computing is becoming an engineering discipline - excited to share some new architecture ideas soon.
The science is remarkable, but the real story is that #Quantum computing is becoming an engineering discipline - excited to share some new architecture ideas soon.
August 13, 2026 at 3:01 PM
Hal Finkel highlights at #ModSim26 how the U.S. Department of Energy will converge #HPC, simulation, and #AI pushing 20% of its budget into compute infrastructure.
Looking forward to my panel on how Agentic AI will reshape science, engineering, and discovery.
#AI #AgenticAI #Accelerate #Science
Looking forward to my panel on how Agentic AI will reshape science, engineering, and discovery.
#AI #AgenticAI #Accelerate #Science
August 12, 2026 at 4:20 PM
Hal Finkel highlights at #ModSim26 how the U.S. Department of Energy will converge #HPC, simulation, and #AI pushing 20% of its budget into compute infrastructure.
Looking forward to my panel on how Agentic AI will reshape science, engineering, and discovery.
#AI #AgenticAI #Accelerate #Science
Looking forward to my panel on how Agentic AI will reshape science, engineering, and discovery.
#AI #AgenticAI #Accelerate #Science
It seems like “linear attention” now means almost anything—as long as there’s an O(L) somewhere in the paper 🙃. Linear compute? Memory capacity? Memory traffic? Those are three different bills, and our accelerators pay all of them 💰️.
My plea: show me all three: buff.ly/Yd35IUv
My plea: show me all three: buff.ly/Yd35IUv
August 10, 2026 at 5:27 AM
It seems like “linear attention” now means almost anything—as long as there’s an O(L) somewhere in the paper 🙃. Linear compute? Memory capacity? Memory traffic? Those are three different bills, and our accelerators pay all of them 💰️.
My plea: show me all three: buff.ly/Yd35IUv
My plea: show me all three: buff.ly/Yd35IUv
Honored that our paper won the 2025 IEEE TPDS Best Paper Award!
buff.ly/4AiBN0S
The main idea is to use differential analysis on dependence graphs to causally determine root causes of performance issues.
Credits to Yuyang for the hard work, Jidong for leadership, and to all of our co-authors!
buff.ly/4AiBN0S
The main idea is to use differential analysis on dependence graphs to causally determine root causes of performance issues.
Credits to Yuyang for the hard work, Jidong for leadership, and to all of our co-authors!
July 27, 2026 at 5:25 AM
Honored that our paper won the 2025 IEEE TPDS Best Paper Award!
buff.ly/4AiBN0S
The main idea is to use differential analysis on dependence graphs to causally determine root causes of performance issues.
Credits to Yuyang for the hard work, Jidong for leadership, and to all of our co-authors!
buff.ly/4AiBN0S
The main idea is to use differential analysis on dependence graphs to causally determine root causes of performance issues.
Credits to Yuyang for the hard work, Jidong for leadership, and to all of our co-authors!
Reposted by Torsten Hoefler 🇨🇭
Happy Birthday, Jack J. Dongarra! Dongarra received the #ACMTuringAward in 2021 for his pioneering contributions to numerical algorithms and libraries that have enabled high-performance computational software to keep pace with exponential hardware improvements. youtu.be/Oe9LRKoE6L0?...
July 18, 2026 at 4:03 PM
Happy Birthday, Jack J. Dongarra! Dongarra received the #ACMTuringAward in 2021 for his pioneering contributions to numerical algorithms and libraries that have enabled high-performance computational software to keep pace with exponential hardware improvements. youtu.be/Oe9LRKoE6L0?...
A successful week at #ICML26 is nearing its end:
Learn about (1) weather model scaling laws from Yuejiang, (2) near-optimal quantization from Jiale, (3) sparse data scaling laws from Boqian, (4) a cool algorithm for sparse training from Qiao, and (5) process reward agents from Jiwoong, Tomasz et al
Learn about (1) weather model scaling laws from Yuejiang, (2) near-optimal quantization from Jiale, (3) sparse data scaling laws from Boqian, (4) a cool algorithm for sparse training from Qiao, and (5) process reward agents from Jiwoong, Tomasz et al
July 9, 2026 at 3:25 PM
A successful week at #ICML26 is nearing its end:
Learn about (1) weather model scaling laws from Yuejiang, (2) near-optimal quantization from Jiale, (3) sparse data scaling laws from Boqian, (4) a cool algorithm for sparse training from Qiao, and (5) process reward agents from Jiwoong, Tomasz et al
Learn about (1) weather model scaling laws from Yuejiang, (2) near-optimal quantization from Jiale, (3) sparse data scaling laws from Boqian, (4) a cool algorithm for sparse training from Qiao, and (5) process reward agents from Jiwoong, Tomasz et al
The actual #AI and #HPC accelerators are the building blocks: various precision matrix and vector units and high-bandwidth memory will define the future of accelerated computation much more than #GPUs vs. #CPUs. Also opening the door for highly-efficient software-defined dataflow.
Three HPC Gurus Ask: Do We Still Need GPUs?
Yes, that simple question is, in the modern Nvidia world that has come to dominate AI training and t ...
buff.ly
July 8, 2026 at 4:53 AM
It was great attending the 75th Lindau Nobel Laureate Meeting last week. I'm very much looking forward to deliver the Heidelberg Plenary Lecture in #AI next year at the 76th!
Congratulations to both Peter and Nikolaus for receiving those special honors.
Congratulations to both Peter and Nikolaus for receiving those special honors.
July 6, 2026 at 5:12 AM
It was great attending the 75th Lindau Nobel Laureate Meeting last week. I'm very much looking forward to deliver the Heidelberg Plenary Lecture in #AI next year at the 76th!
Congratulations to both Peter and Nikolaus for receiving those special honors.
Congratulations to both Peter and Nikolaus for receiving those special honors.
ADIA Lab in Abu Dhabi is looking for a Senior Computational Scientist in Trustworthy #AI to lead a world-class research program. If you have a PhD, 5+ years of experience, and a strong publication record in top-tier venues like #NeurIPS and #ICML, then go and check it out!
Apply:
Apply:
ADIA Lab - Senior Computational Scientist - Trustworthy AI - Abu Dhabi Investment Authority
ADIA Lab, an independent research institution based in Abu Dhabi specializing in data science, artificial intelligence, and computational sciences, is seeking a Senior Computational Scientist with a…
buff.ly
July 4, 2026 at 6:03 PM
Big congrats to our Racklette team for the 1st prize in the #ISC26 student cluster competition.
Switzerland is back, very proud of this repeated success!! Thanks to Hussein and CSCS for the strong support.
Look at that big golden trophy for the future leaders in #AI and #HPC!
Switzerland is back, very proud of this repeated success!! Thanks to Hussein and CSCS for the strong support.
Look at that big golden trophy for the future leaders in #AI and #HPC!
June 25, 2026 at 4:56 PM
Saverio presents the #ISC26 Hans Meuer award paper. Selecting and tuning collective operations is not simple. Need to consider various systems effects, for example, load on global vs. local links and different phases. Also using ATLAHS #HPC for selection
isc-hpc.com/isc-high-per...
isc-hpc.com/isc-high-per...
June 24, 2026 at 9:36 AM
Saverio presents the #ISC26 Hans Meuer award paper. Selecting and tuning collective operations is not simple. Need to consider various systems effects, for example, load on global vs. local links and different phases. Also using ATLAHS #HPC for selection
isc-hpc.com/isc-high-per...
isc-hpc.com/isc-high-per...
This year's Jack Dongarra award goes to Devesh Tiwari. He starts his talk with an hommage to Jack and then lures the audience into quantum computing. Well done 😀.
June 24, 2026 at 8:59 AM
This year's Jack Dongarra award goes to Devesh Tiwari. He starts his talk with an hommage to Jack and then lures the audience into quantum computing. Well done 😀.