@article{ChristgauSchnor, author = {Christgau, Steffen and Schnor, Bettina}, title = {Comparing MPI Passive Target Synchronization on a Non-Cache-Coherent Shared-Memory Processor}, series = {Mitteilungen - Gesellschaft f{\"u}r Informatik e. V., Parallel-Algorithmen und Rechnerstrukturen, ISSN 0177-0454, 28. PARS-Workshop}, journal = {Mitteilungen - Gesellschaft f{\"u}r Informatik e. V., Parallel-Algorithmen und Rechnerstrukturen, ISSN 0177-0454, 28. PARS-Workshop}, number = {35}, pages = {121 -- 132}, language = {en} } @misc{ChristgauSchnor, author = {Christgau, Steffen and Schnor, Bettina}, title = {MPI Passive Target Synchronization on a Non-Cache-Coherent Shared-Memory Processor}, issn = {1438-0064}, doi = {10.12752/7477}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-74774}, abstract = {MPI passive target synchronization offers exclusive and shared locks. These are the building blocks for the implementation of applications with Readers \& Writers semantic, like for example distributed hash tables. This paper discusses the implementation of MPI passive target synchronization on a non-cache-coherent multicore, the Intel Single-Chip Cloud Computer. The considered algorithms differ in their communication style (message based versus shared memory), their data structures (centralized versus distributed) and their semantics (with/without Writer preference). It is shown that shared memory approaches scale very well and deliver good performance, even in absence of cache coherence.}, language = {en} } @inproceedings{ChristgauEveringhamMikolajczaketal., author = {Christgau, Steffen and Everingham, Dylan and Mikolajczak, Florian and Schelten, Niklas and Schnor, Bettina and Schroetter, Max and Stabernack, Benno and Steinert, Fritjof}, title = {Enabling Communication with FPGA-based Network-attached Accelerators for HPC Workloads}, series = {Proceedings of the SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, SC-W 2023, Denver, CO, USA, November 12-17, 2023}, booktitle = {Proceedings of the SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, SC-W 2023, Denver, CO, USA, November 12-17, 2023}, publisher = {ACM}, doi = {10.1145/3624062.3624540}, pages = {530 -- 538}, abstract = {The use of stand-alone, network-coupled Field Programmable Gate Array (FPGA) accelerators is intended to significantly increase the energy efficiency of HPC applications and thus also of HPC data centers. A loose coupling between the nodes of the HPC data center and the FPGAs is established through the high-speed network of the data center. This allows greater flexibility in combining different nodes and accelerators. Both the resulting energy savings and the increased flexibility through the network connection, enable the economical use of FPGAs. This work presents a communication stack to integrate the so-called Network-attached Accelerator (NAA) into the HPC data center. A low-level Remote Direct Memory Access (RDMA) Application Programming Interface (API) and a high-level Remote Procedure Call (RPC) API is designed on top of the RDMA over Converged Ethernet v2 (RoCEv2) communication stack. The experimental results over 100 Gbps RoCEv2 show that our design and implementation deliver performance close to the theoretical maximum.}, language = {en} }