diff --git a/doc.zih.tu-dresden.de/docs/archive/system_taurus.md b/doc.zih.tu-dresden.de/docs/archive/system_taurus.md index 413f7a53dba94e5ea7fdd0285eee0942f5e25c80..1a0d8cda206f3817f828e37ee5f40554d8a9eac9 100644 --- a/doc.zih.tu-dresden.de/docs/archive/system_taurus.md +++ b/doc.zih.tu-dresden.de/docs/archive/system_taurus.md @@ -37,7 +37,7 @@ users and the ZIH. ## Island 2 Phase 2 - Intel Haswell CPUs + NVIDIA K80 GPUs - 64 nodes, each with - - 2 x Intel(R) Xeon(R) CPU E5-E5-2680 v3 (12 cores) @ 2.50 GHz, Multithreading disabled + - 2 x Intel(R) Xeon(R) CPU E5-2680 v3 (12 cores) @ 2.50 GHz, Multithreading disabled - 64 GB RAM (2.67 GB per core) - 128 GB local memory on SSD - 4 x NVIDIA Tesla K80 (12 GB GDDR RAM) GPUs diff --git a/doc.zih.tu-dresden.de/docs/software/gpu_programming.md b/doc.zih.tu-dresden.de/docs/software/gpu_programming.md index 5de6a12d965c768ab9bc1edc4cecfb7294f5a717..dc45a045cafbbd2777845fbb7a648fd542e82345 100644 --- a/doc.zih.tu-dresden.de/docs/software/gpu_programming.md +++ b/doc.zih.tu-dresden.de/docs/software/gpu_programming.md @@ -4,7 +4,25 @@ The full hardware specifications of the GPU-compute nodes may be found in the [HPC Resources](../jobs_and_resources/hardware_overview.md#hpc-resources) page. -Each node uses a different modules(modules.md#module-environments): +Note that the clusters may have different [modules](modules.md#module-environments) available: + +E.g. the available CUDA versions can be listed with + +```bash +marie@compute$ module spider CUDA +``` + +Note that some modules use a specific CUDA version which is visible in the module name, +e.g. `GDRCopy/2.1-CUDA-11.1.1` or `Horovod/0.28.1-CUDA-11.7.0-TensorFlow-2.11.0`. + +This especially applies to the optimized CUDA libraries like `cuDNN`, `NCCL` and `magma`. + +!!! important "CUDA-aware MPI" + + When running CUDA applications using MPI for interprocess communication you need to additionally load the modules + that enable CUDA-aware MPI which may provide improved performance. + Those are `UCX-CUDA` and `UCC-CUDA` which supplement the `UCX` and `UCC` modules respectively. + Some modules, like `NCCL`, load those automatically. ## Using GPUs with Slurm