From faed07d7bee4a5d3b80cde8f603125ac2cb49bc0 Mon Sep 17 00:00:00 2001
From: Emicia <veronika.scholz@tu-dresden.de>
Date: Fri, 1 Oct 2021 10:34:55 +0200
Subject: [PATCH] Fix spelling

---
 .../docs/software/distributed_training.md     | 10 +++---
 doc.zih.tu-dresden.de/wordlist.aspell         | 31 +++++++++++++++++++
 2 files changed, 36 insertions(+), 5 deletions(-)

diff --git a/doc.zih.tu-dresden.de/docs/software/distributed_training.md b/doc.zih.tu-dresden.de/docs/software/distributed_training.md
index 05c266d9e..128eee8c8 100644
--- a/doc.zih.tu-dresden.de/docs/software/distributed_training.md
+++ b/doc.zih.tu-dresden.de/docs/software/distributed_training.md
@@ -13,7 +13,7 @@ each device has a replica of the model and computes over different parts of the
 2. model parallelism:
 models are distributed over multiple devices.
 
-In the folowing we will stick to the concept of data parallelism because it is a widely-used
+In the following we will stick to the concept of data parallelism because it is a widely-used
 technique.
 There are basically two strategies to train the scattered data throughout the devices:
 
@@ -183,7 +183,7 @@ synchronize gradients and buffers.
 The tutorial can be found [here](https://pytorch.org/tutorials/intermediate/ddp_tutorial.html).
 
 To use distributed data parallelism on ZIH systems please make sure the `--ntasks-per-node`
-parameter is equal to the number of GPUs you useper node.
+parameter is equal to the number of GPUs you use per node.
 Also, it can be useful to increase `memory/cpu` parameters if you run larger models.
 Memory can be set up to:
 
@@ -277,13 +277,13 @@ In the example presented installation for TensorFlow.
 Adapt as required and refer to the Horovod documentation for details.
 
 ```bash
-HOROVOD_GPU_OPERATIONS=NCCL HOROVOD_WITH_TENSORFLOW=1 pip install --no-cache-dir horovod\[tensorflow\] 
+HOROVOD_GPU_OPERATIONS=NCCL HOROVOD_WITH_TENSORFLOW=1 pip install --no-cache-dir horovod\[tensorflow\]
 
 horovodrun --check-build
 ```
 
-If you want to use OpenMPI then specify `HOROVOD_GPU_ALLREDUCE=MPI`. 
-To have better performance it is recommended to use NCCL instead of OpenMPI.  
+If you want to use OpenMPI then specify `HOROVOD_GPU_ALLREDUCE=MPI`.
+To have better performance it is recommended to use NCCL instead of OpenMPI.
 
 ##### Verify that Horovod works
 
diff --git a/doc.zih.tu-dresden.de/wordlist.aspell b/doc.zih.tu-dresden.de/wordlist.aspell
index 3bfbeea4f..9fcd006a1 100644
--- a/doc.zih.tu-dresden.de/wordlist.aspell
+++ b/doc.zih.tu-dresden.de/wordlist.aspell
@@ -1,9 +1,11 @@
 personal_ws-1.1 en 203 
+ALLREDUCE
 Altix
 Amdahl's
 analytics
 anonymized
 APIs
+awk
 BeeGFS
 benchmarking
 BLAS
@@ -13,8 +15,13 @@ ccNUMA
 centauri
 citable
 conda
+config
+CONFIG
+cpu
 CPU
+cpus
 CPUs
+crossentropy
 CSV
 CUDA
 cuDNN
@@ -24,9 +31,13 @@ dataframes
 DataFrames
 datamover
 DataParallel
+dataset
+ddl
 DDP
 DDR
 DFG
+dir
+distr
 DistributedDataParallel
 DockerHub
 EasyBuild
@@ -47,22 +58,30 @@ GFLOPS
 gfortran
 GiB
 gnuplot
+gpu
 GPU
 GPUs
+gres
 hadoop
 haswell
 HDFS
+hiera
+horovod
 Horovod
+horovodrun
 hostname
 HPC
 HPL
+hvd
 hyperparameter
 hyperparameters
 icc
 icpc
 ifort
 ImageNet
+img
 Infiniband
+init
 inode
 Itanium
 jobqueue
@@ -80,11 +99,13 @@ lsf
 lustre
 Mathematica
 MEGWARE
+mem
 MiB
 MIMD
 Miniconda
 MKL
 MNIST
+modenv
 Montecito
 mountpoint
 mpi
@@ -99,7 +120,11 @@ multithreaded
 NCCL
 Neptun
 NFS
+nodelist
+NODELIST
 NRINGS
+ntasks
+NUM
 NUMA
 NUMAlink
 NumPy
@@ -134,10 +159,15 @@ PowerAI
 ppc
 PSOCK
 Pthreads
+pty
+PythonAnaconda
+pytorch
+PyTorch
 queue
 randint
 reachability
 README
+resnet
 Rmpi
 rome
 romeo
@@ -175,6 +205,7 @@ SUSE
 TBB
 TCP
 TensorBoard
+tensorflow
 TensorFlow
 TFLOPS
 Theano
-- 
GitLab