Nils Blach
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nils Blach has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Maciej Besta
ETH Zurich, Zurich, Switzerland
3 shared publications - Torsten Hoefler
ETH Zurich, Zurich, Switzerland
3 shared publications - Robert Gerstenberger
ETH Zurich, Zurich, Switzerland
2 shared publications - Aidan O. Mahony
Dell Technologies, Cork, Ireland
1 shared publication - Ales Kubicek
ETH Zurich, Zurich, Switzerland
1 shared publication - Berke Egeli
ETH Zurich, Zurich, Switzerland
1 shared publication
Latest Publications
- Top Cited Papers
- 12 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 10967-10989
Demystifying Chains, Trees, and Graphs of Thoughts
The field of natural language processing (NLP) has witnessed significant progress in recent years, with a notable focus on improving large language models’ (LLM) performance through innovative prompting techniques. Among these, prompt engineering coupled with structures has emerged as a promising paradigm, with designs such as Chain-of-Thought, Tree of Thoughts, or Graph of Thoughts, in which the overall LLM reasoning is guided by a structure such as a graph. As illustrated with numerous examples, this paradigm significantly enhances the LLM’s capability to solve numerous tasks, ranging from logical or mathematical reasoning to planning or creative writing. To facilitate the understanding of this growing field and pave the way for future developments, we devise a general blueprint for effective and efficient LLM reasoning schemes. For this, we conduct an in-depth analysis of the prompt execution pipeline, clarifying and clearly defining different concepts. We then build the first taxonomy of structure-enhanced LLM reasoning schemes. We focus on identifying fundamental classes of harnessed structures, and we analyze the representations of these structures, algorithms executed with these structures, and many others. We refer to these structures as reasoning topologies, because their representation becomes to a degree spatial, as they are contained within the LLM context. Our study compares existing prompting schemes using the proposed taxonomy, discussing how certain design choices lead to different patterns in performance and cost. We also outline theoretical underpinnings, relationships between prompting and other parts of the LLM ecosystem such as knowledge bases, and the associated research challenges. Our work will help to advance future prompt engineering techniques.
- 12 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 10967-10989
Top Cited PapersDemystifying Chains, Trees, and Graphs of Thoughts
The field of natural language processing (NLP) has witnessed significant progress in recent years, with a notable focus on improving large language models’ (LLM) performance through innovative prompting techniques. Among these, prompt engineering coupled with structures has emerged as a promising paradigm, with designs such as Chain-of-Thought, Tree of Thoughts, or Graph of Thoughts, in which the overall LLM reasoning is guided by a structure such as a graph. As illustrated with numerous examples, this paradigm significantly enhances the LLM’s capability to solve numerous tasks, ranging from logical or mathematical reasoning to planning or creative writing. To facilitate the understanding of this growing field and pave the way for future developments, we devise a general blueprint for effective and efficient LLM reasoning schemes. For this, we conduct an in-depth analysis of the prompt execution pipeline, clarifying and clearly defining different concepts. We then build the first taxonomy of structure-enhanced LLM reasoning schemes. We focus on identifying fundamental classes of harnessed structures, and we analyze the representations of these structures, algorithms executed with these structures, and many others. We refer to these structures as reasoning topologies, because their representation becomes to a degree spatial, as they are contained within the LLM context. Our study compares existing prompting schemes using the proposed taxonomy, discussing how certain design choices lead to different patterns in performance and cost. We also outline theoretical underpinnings, relationships between prompting and other parts of the LLM ecosystem such as knowledge bases, and the associated research challenges. Our work will help to advance future prompt engineering techniques.
- Open Access
- 17 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 345-357
PolarStar: Expanding the Horizon of Diameter-3 Networks
We present PolarStar, a novel family of diameter-3 network topologies derived from the star product of low-diameter factor graphs. PolarStar gives the largest known diameter-3 network topologies for almost all radixes, thus providing the best known scalable diameter-3 network. Compared to current state-of-the-art diameter-3 networks, PolarStar achieves 1.3x geometric mean increase in scale over Bundlefly, 1.9x over Dragonfly, and 6.7x over 3-D HyperX. PolarStar has many other desirable properties, including a modular layout, large bisection, high resilience to link failures and a large number of feasible configurations for every radix. We give a detailed evaluation with simulations of synthetic and real-world traffic patterns and show that PolarStar exhibits comparable or better performance than current diameter-3 networks.
- 17 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 345-357
Open AccessPolarStar: Expanding the Horizon of Diameter-3 Networks
We present PolarStar, a novel family of diameter-3 network topologies derived from the star product of low-diameter factor graphs. PolarStar gives the largest known diameter-3 network topologies for almost all radixes, thus providing the best known scalable diameter-3 network. Compared to current state-of-the-art diameter-3 networks, PolarStar achieves 1.3x geometric mean increase in scale over Bundlefly, 1.9x over Dragonfly, and 6.7x over 3-D HyperX. PolarStar has many other desirable properties, including a modular layout, large bisection, high resilience to link failures and a large number of feasible configurations for every radix. We give a detailed evaluation with simulations of synthetic and real-world traffic patterns and show that PolarStar exhibits comparable or better performance than current diameter-3 networks.
- Open Access
- 11 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-18
The Graph Database Interface: Scaling Online Transactional and Analytical Graph Workloads to Hundreds of Thousands of Cores
Graph databases (GDBs) are crucial in academic and industry applications. The key challenges in developing GDBs are achieving high performance, scalability, programmability, and portability. To tackle these challenges, we harness established practices from the HPC landscape to build a system that outperforms all past GDBs presented in the literature by orders of magnitude, for both OLTP and OLAP workloads. For this, we first identify and crystallize performance-critical building blocks in the GDB design, and abstract them into a portable and programmable API specification, called the Graph Database Interface (GDI), inspired by the best practices of MPI. We then use GDI to design a GDB for distributed-memory RDMA architectures. Our implementation harnesses onesided RDMA communication and collective operations, and it offers architecture-independent theoretical performance guarantees. The resulting design achieves extreme scales of more than a hundred thousand cores. Our work will facilitate the development of next-generation extreme-scale graph databases.
- 11 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Open AccessThe Graph Database Interface: Scaling Online Transactional and Analytical Graph Workloads to Hundreds of Thousands of Cores
Graph databases (GDBs) are crucial in academic and industry applications. The key challenges in developing GDBs are achieving high performance, scalability, programmability, and portability. To tackle these challenges, we harness established practices from the HPC landscape to build a system that outperforms all past GDBs presented in the literature by orders of magnitude, for both OLTP and OLAP workloads. For this, we first identify and crystallize performance-critical building blocks in the GDB design, and abstract them into a portable and programmable API specification, called the Graph Database Interface (GDI), inspired by the best practices of MPI. We then use GDI to design a GDB for distributed-memory RDMA architectures. Our implementation harnesses onesided RDMA communication and collective operations, and it offers architecture-independent theoretical performance guarantees. The resulting design achieves extreme scales of more than a hundred thousand cores. Our work will facilitate the development of next-generation extreme-scale graph databases.