Scalable Parallel Computing Lab, SPCL @ ETH Zurich Courses

Can We Build an AI Climate Scientist?

Explore how artificial intelligence can revolutionize climate science research and modeling to address global environmental challenges.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

Parallele Programmierung

Erlernen Sie parallele Programmierung mit umfassenden Vorlesungen der ETH Zürich, die fortgeschrittene Konzepte und Techniken für effiziente Mehrprozessor-Systeme abdecken.

• YouTube
• 21 hours 57 minutes
• Self-Paced
• Free Video

Computing the Full Earth System at 1km Resolution

Discover groundbreaking Earth system simulation at unprecedented 1km resolution using 8192-20480 GPUs, achieving 145.7x time compression for atmosphere, ocean, and land interactions.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

Uno - A One-Stop Solution for Inter- and Intra-Data Center Congestion Control and Reliable Connectivity

Discover Uno, a unified system tackling inter- and intra-datacenter congestion control challenges with fair rate management, erasure coding, and adaptive routing for improved flow completion times.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

PerfDojo - Automated ML Library Generation for Heterogeneous Architectures

Discover PerfDojo, an automated ML library generation system using LLMs and reinforcement learning to optimize performance across diverse CPU and GPU architectures without hardware-specific knowledge.

• YouTube
• 17 minutes
• Self-Paced
• Free Video

Chameleon - Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models

Discover Chameleon, a heterogeneous accelerator system combining LLM and vector search accelerators for efficient Retrieval-Augmented Language Models with up to 3.18× throughput improvements.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

FPsPIN - An FPGA-based Open-Hardware Research Platform for Processing in the Network

Explore FPsPIN, an FPGA-based platform for network processing that reduces latency by 96% through smart NIC offloading and MPI datatype processing optimization.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

EDAN - Towards Understanding Memory Parallelism and Latency Sensitivity in HPC

Discover EDAN, a novel tool analyzing memory parallelism and latency sensitivity in HPC applications through execution DAG generation from runtime instruction traces.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

ARMing GPUs for Impactful Science with the GH200 Superchip and True Exascale

Explore NVIDIA's GH200 Superchip architecture, analyzing its complex memory system and demonstrating revolutionary large-scale scientific computing applications.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

What is AI for Science - Models, Data, and Computation

Discover how AI for Science unifies traditional modeling with data-driven techniques through high-performance computing to accelerate scientific progress and human advancement.

• YouTube
• 17 minutes
• Self-Paced
• Free Video

ARMing GPUs - On the Memory Subsystem of Grace Hopper GH200

Explore the memory subsystem of Grace Hopper GH200 superchips, analyzing data movement patterns and memory placement strategies in tightly coupled heterogeneous systems.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

Offloaded MPI Message Matching - An Optimistic Approach

Explore optimistic tag matching for MPI message delivery using SmartNICs to free CPU resources while maintaining performance in high-performance computing environments.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

LLAMP - Assessing Network Latency Sensitivity Tolerance of HPC Applications with Linear Programming

Discover LLAMP, a novel toolchain using linear programming to assess HPC applications' network latency tolerance efficiently without specialized hardware or simulators.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Reasoning Language Models Will Solve All Our Problems - Given the Right Machines

Discover how reasoning language models could potentially solve complex problems with sufficient computational power and explore scaling strategies for cloud systems.

• YouTube
• 17 minutes
• Self-Paced
• Free Video

Finding Relevant Items Using Approximate Nearest Neighbor Search Algorithms

Explore algorithms for nearest neighbor search, from KD-Trees to modern approaches like HNSW and IVF-PQ, understanding their applications and performance tradeoffs.

• YouTube
• 22 minutes
• Self-Paced
• Free Video