Skip to content
Snippets Groups Projects
Commit ddf9cbf4 authored by Jan Frenzel's avatar Jan Frenzel
Browse files

Merge branch 'merge-preview-in-main' into 'main' 

Automated merge from preview to main

See merge request !850
parents d371395b dbf8a112
No related branches found
No related tags found
2 merge requests!882Kraeussl tu dresden.de main patch 02880,!850Automated merge from preview to main
Hide whitespace changes
Inline Side-by-side
Showing
with 355 additions and 24 deletions
doc.zih.tu-dresden.de/docs/archive/hardware_overview_2022.md 0 → 100644
+ 109
− 0
View file @ ddf9cbf4
# HPC Resources
HPC resources in ZIH systems comprise the *High Performance Computing and Storage Complex* and its
extension *High Performance Computing – Data Analytics*. In total it offers scientists
about 60,000 CPU cores and a peak performance of more than 1.5 quadrillion floating point
operations per second. The architecture specifically tailored to data-intensive computing, Big Data
analytics, and artificial intelligence methods with extensive capabilities for energy measurement
and performance monitoring provides ideal conditions to achieve the ambitious research goals of the
users and the ZIH.
## Login and Export Nodes
- 4 Login-Nodes `tauruslogin[3-6].hrsk.tu-dresden.de`
- Each login node is equipped with 2x Intel(R) Xeon(R) CPU E5-2680 v3 with 24 cores in total @
2.50 GHz, Multithreading disabled, 64 GB RAM, 128 GB SSD local disk
- IPs: 141.30.73.\[102-105\]
- 2 Data-Transfer-Nodes `taurusexport[3-4].hrsk.tu-dresden.de`
- DNS Alias `taurusexport.hrsk.tu-dresden.de`
- 2 Servers without interactive login, only available via file transfer protocols
(`rsync`, `ftp`)
- IPs: 141.30.73.\[82,83\]
- Further information on the usage is documented on the site
[Export Nodes](../data_transfer/export_nodes.md)
## AMD Rome CPUs + NVIDIA A100
- 34 nodes, each with
- 8 x NVIDIA A100-SXM4 Tensor Core-GPUs
- 2 x AMD EPYC CPU 7352 (24 cores) @ 2.3 GHz, Multithreading available
- 1 TB RAM
- 3.5 TB local memory on NVMe device at `/tmp`
- Hostnames: `taurusi[8001-8034]`
- Slurm partition: `alpha`
- Further information on the usage is documented on the site [Alpha Centauri Nodes](../jobs_and_resources/alpha_centauri.md)
## Island 7 - AMD Rome CPUs
- 192 nodes, each with
- 2 x AMD EPYC CPU 7702 (64 cores) @ 2.0 GHz, Multithreading available
- 512 GB RAM
- 200 GB local memory on SSD at `/tmp`
- Hostnames: `taurusi[7001-7192]`
- Slurm partition: `romeo`
- Further information on the usage is documented on the site [AMD Rome Nodes](../jobs_and_resources/rome_nodes.md)
## Large SMP System HPE Superdome Flex
- 1 node, with
- 32 x Intel(R) Xeon(R) Platinum 8276M CPU @ 2.20 GHz (28 cores)
- 47 TB RAM
- Configured as one single node
- 48 TB RAM (usable: 47 TB - one TB is used for cache coherence protocols)
- 370 TB of fast NVME storage available at `/nvme/<projectname>`
- Hostname: `taurussmp8`
- Slurm partition: `julia`
- Further information on the usage is documented on the site [HPE Superdome Flex](../jobs_and_resources/sd_flex.md)
## IBM Power9 Nodes for Machine Learning
For machine learning, we have IBM AC922 nodes installed with this configuration:
- 32 nodes, each with
- 2 x IBM Power9 CPU (2.80 GHz, 3.10 GHz boost, 22 cores)
- 256 GB RAM DDR4 2666 MHz
- 6 x NVIDIA VOLTA V100 with 32 GB HBM2
- NVLINK bandwidth 150 GB/s between GPUs and host
- Hostnames: `taurusml[1-32]`
- Slurm partition: `ml`
## Island 6 - Intel Haswell CPUs
- 612 nodes, each with
- 2 x Intel(R) Xeon(R) CPU E5-2680 v3 (12 cores) @ 2.50 GHz, Multithreading disabled
- 128 GB local memory on SSD
- Varying amounts of main memory (selected automatically by the batch system for you according to
your job requirements)
* 594 nodes with 2.67 GB RAM per core (64 GB in total): `taurusi[6001-6540,6559-6612]`
- 18 nodes with 10.67 GB RAM per core (256 GB in total): `taurusi[6541-6558]`
- Hostnames: `taurusi[6001-6612]`
- Slurm Partition: `haswell`
??? hint "Node topology"
![Node topology](misc/i4000.png)
{: align=center}
## 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
- 64 GB RAM (2.67 GB per core)
- 128 GB local memory on SSD
- 4 x NVIDIA Tesla K80 (12 GB GDDR RAM) GPUs
- Hostnames: `taurusi[2045-2108]`
- Slurm Partition: `gpu2`
- Node topology, same as [island 4 - 6](#island-6-intel-haswell-cpus)
## SMP Nodes - up to 2 TB RAM
- 5 Nodes, each with
- 4 x Intel(R) Xeon(R) CPU E7-4850 v3 (14 cores) @ 2.20 GHz, Multithreading disabled
- 2 TB RAM
- Hostnames: `taurussmp[3-7]`
- Slurm partition: `smp2`
??? hint "Node topology"
![Node topology](misc/smp2.png)
{: align=center}
doc.zih.tu-dresden.de/docs/jobs_and_resources/slurm_profiling.md → doc.zih.tu-dresden.de/docs/archive/slurm_profiling.md
+ 2
− 1
View file @ ddf9cbf4
......@@ -70,7 +70,8 @@ More information about profiling with Slurm:
## Memory Consumption of a Job
If you are only interested in the maximal memory consumption of your job, you don't need profiling
at all. This information can be retrieved from within [job files](slurm.md#batch-jobs) as follows:
at all. This information can be retrieved from within
[job files](../jobs_and_resources/slurm.md#batch-jobs) as follows:
```bash
#!/bin/bash
......
doc.zih.tu-dresden.de/docs/index.md
+ 1
− 0
View file @ ddf9cbf4
......@@ -31,6 +31,7 @@ Please also find out the other ways you could contribute in our
## News
* **2023-06-01** [New hardware and complete re-design](jobs_and_resources/architecture_2023.md)
* **2023-01-04** [New hardware: NVIDIA Arm HPC Developer Kit](jobs_and_resources/arm_hpc_devkit.md)
* **2022-01-13** [Supercomputing extension for TU Dresden](https://tu-dresden.de/zih/die-einrichtung/news/supercomputing-cluster-2022)
......
doc.zih.tu-dresden.de/docs/jobs_and_resources/architecture_2023.md 0 → 100644
+ 57
− 0
View file @ ddf9cbf4
# Architectural Re-Design 2023
With the replacement of the Taurus system by the cluster `Barnard` in 2023,
the rest of the installed hardware had to be re-connected, both with
Infiniband and with Ethernet.
![Architecture overview 2023](../jobs_and_resources/misc/architecture_2023.png)
{: align=center}
## Compute Systems
All compute clusters now act as separate entities having their own
login nodes of the same hardware and their very own Slurm batch systems. The different hardware,
e.g. Romeo and Alpha Centauri, is no longer managed via a single Slurm instance with
corresponding partitions. Instead, you as user now chose the hardware by the choice of the
correct login node.
The login nodes can be used for smaller interactive jobs on the clusters. There are
restrictions in place, though, wrt. usable resources and time per user. For larger
computations, please use interactive jobs.
## Storage Systems
### Permananent Filesystems
We now have `/home`, `/projects` and `/software` in a Lustre filesystem. Snapshots
and tape backup are configured. For convenience, we will make the old home available
read-only as `/home_old` on the data mover nodes for the data migration period.
`/warm_archive` is mounted on the data movers, only.
### Work Filesystems
With new players with new software in the filesystem market it is getting more and more
complicated to identify the best suited filesystem for temporary data. In many cases,
only tests can provide the right answer, for a short time.
For an easier grasp on the major categories (size, speed), the work filesystems now come
with the names of animals:
* `/data/horse` - 20 PB - high bandwidth (Lustre)
* `/data/octopus` - 0.5 PB - for interactive usage (Lustre)
* `/data/weasel` - 1 PB - for high IOPS (WEKA) - coming soon
### Difference Between "Work" And "Permanent"
A large number of changing files is a challenge for any backup system. To protect
our snapshots and backup from work data,
`/projects` cannot be used for temporary data on the compute nodes - it is mounted read-only.
Please use our data mover mechanisms to transfer worthy data to permanent
storages.
## Migration Phase
For about one month, the new cluster Barnard, and the old cluster Taurus
will run side-by-side - both with their respective filesystems.
doc.zih.tu-dresden.de/docs/jobs_and_resources/hardware_overview.md
+ 2
− 2
View file @ ddf9cbf4
......@@ -81,7 +81,7 @@ For machine learning, we have IBM AC922 nodes installed with this configuration:
??? hint "Node topology"
![Node topology](misc/i4000.png)
![Node topology](../archive/misc/i4000.png)
{: align=center}
## Island 2 Phase 2 - Intel Haswell CPUs + NVIDIA K80 GPUs
......@@ -105,5 +105,5 @@ For machine learning, we have IBM AC922 nodes installed with this configuration:
??? hint "Node topology"
![Node topology](misc/smp2.png)
![Node topology](../archive/misc/smp2.png)
{: align=center}
doc.zih.tu-dresden.de/docs/jobs_and_resources/hardware_overview_2023.md 0 → 100644
+ 89
− 0
View file @ ddf9cbf4
# HPC Resources
The architecture specifically tailored to data-intensive computing, Big Data
analytics, and artificial intelligence methods with extensive capabilities
for performance monitoring provides ideal conditions to achieve the ambitious
research goals of the users and the ZIH.
## Overview
From the users' perspective, there are separate clusters, all of them with their subdomains:
| Name | Description | Year| DNS |
| --- | --- | --- | --- |
| **Barnard** | CPU cluster |2023| n[1001-1630].barnard.hpc.tu-dresden.de |
| **Romeo** | CPU cluster |2020|i[8001-8190].romeo.hpc.tu-dresden.de |
| **Alpha Centauri** | GPU cluster |2021|i[8001-8037].alpha.hpc.tu-dresden.de |
| **Julia** | single SMP system |2021|smp8.julia.hpc.tu-dresden.de |
| **Power** | IBM Power/GPU system |2018|ml[1-29].power9.hpc.tu-dresden.de |
They run with their own Slurm batch system. Job submission is possible only from
their respective login nodes.
All clusters have access to these shared parallel filesystems:
| Filesystem | Usable directory | Type | Capacity | Purpose |
| --- | --- | --- | --- | --- |
| Home | `/home` | Lustre | quota per user: 20 GB | permanent user data |
| Project | `/projects` | Lustre | quota per project | permanent project data |
| Scratch for large data / streaming | `/data/horse` | Lustre | 20 PB | |
| Scratch for random access | `/data/rabbit` | Lustre | 2 PB | |
These mount points are planned (September 2023):
| Filesystem | Mount Point | Type | Capacity |
| --- | --- | --- | --- |
| Scratch for random access | `/data/weasel` | WEKA | 232 TB |
| Scratch for random access | `/data/squirrel` | BeeGFS | xxx TB |
## Barnard - Intel Sapphire Rapids CPUs
- 630 diskless nodes, each with
- 2 x Intel Xeon CPU E5-2680 v3 (52 cores) @ 2.50 GHz, Multithreading enabled
- 512 GB RAM
- Hostnames: `n1[001-630].barnard.hpc.tu-dresden.de`
- Login nodes: `login[1-4].barnard.hpc.tu-dresden.de`
## AMD Rome CPUs + NVIDIA A100
- 34 nodes, each with
- 8 x NVIDIA A100-SXM4 Tensor Core-GPUs
- 2 x AMD EPYC CPU 7352 (24 cores) @ 2.3 GHz, Multithreading available
- 1 TB RAM
- 3.5 TB local memory on NVMe device at `/tmp`
- Hostnames: `taurusi[8001-8034]` -> `i[8001-8037].alpha.hpc.tu-dresden.de`
- Login nodes: `login[1-2].alpha.hpc.tu-dresden.de`
- Further information on the usage is documented on the site [Alpha Centauri Nodes](alpha_centauri.md)
## Island 7 - AMD Rome CPUs
- 192 nodes, each with
- 2 x AMD EPYC CPU 7702 (64 cores) @ 2.0 GHz, Multithreading available
- 512 GB RAM
- 200 GB local memory on SSD at `/tmp`
- Hostnames: `taurusi[7001-7192]` -> `i[7001-7190].romeo.hpc.tu-dresden.de`
- Login nodes: `login[1-2].romeo.hpc.tu-dresden.de`
- Further information on the usage is documented on the site [AMD Rome Nodes](rome_nodes.md)
## Large SMP System HPE Superdome Flex
- 1 node, with
- 32 x Intel Xeon Platinum 8276M CPU @ 2.20 GHz (28 cores)
- 47 TB RAM
- Configured as one single node
- 48 TB RAM (usable: 47 TB - one TB is used for cache coherence protocols)
- 370 TB of fast NVME storage available at `/nvme/<projectname>`
- Hostname: `taurussmp8` -> `smp8.julia.hpc.tu-dresden.de`
- Further information on the usage is documented on the site [HPE Superdome Flex](sd_flex.md)
## IBM Power9 Nodes for Machine Learning
For machine learning, we have IBM AC922 nodes installed with this configuration:
- 32 nodes, each with
- 2 x IBM Power9 CPU (2.80 GHz, 3.10 GHz boost, 22 cores)
- 256 GB RAM DDR4 2666 MHz
- 6 x NVIDIA VOLTA V100 with 32 GB HBM2
- NVLINK bandwidth 150 GB/s between GPUs and host
- Hostnames: `taurusml[1-32]` -> `ml[1-29].power9.hpc.tu-dresden.de`
- Login nodes: `login[1-2].power9.hpc.tu-dresden.de`
doc.zih.tu-dresden.de/docs/jobs_and_resources/migration_2023.md 0 → 100644
+ 80
− 0
View file @ ddf9cbf4
# Migration 2023
## Brief Overview over Coming Changes
All components of Taurus will be dismantled step by step.
### New Hardware
The new HPC system "Barnard" from Bull comes with these main properties:
* 630 compute nodes based on Intel Sapphire Rapids
* new Lustre-based storage systems
* HDR Infiniband network large enough to integrate existing and near-future non-Bull hardware
* To help our users to find the best location for their data we now use the name of
animals (size, speed) as mnemonics.
More details can be found in the [overview](/jobs_and_resources/hardware_overview_2023).
### New Architecture
Over the last decade we have been running our HPC system of high heterogeneity with a single
Slurm batch system. This made things very complicated, especially to inexperienced users.
To lower this hurdle we now create homogenous clusters with their own Slurm instances and with
cluster specific login nodes running on the same CPU. Job submission is possible only
from within the cluster (compute or login node).
All clusters will be integrated to the new Infiniband fabric and have then the same access to
the shared filesystems. This recabling requires a brief downtime of a few days.
[Details on architecture](/jobs_and_resources/architecture_2023).
### New Software
The new nodes run on Linux RHEL 8.7. For a seamless integration of other compute hardware,
all operating system will be updated to the same versions of OS, Mellanox and Lustre drivers.
With this all application software was re-built consequently using GIT and CI for handling
the multitude of versions.
We start with `release/23.04` which is based on software reqeusts from user feedbacks of our
HPC users. Most major software versions exist on all hardware platforms.
## Migration Path
Please make sure to have read [Details on architecture](/jobs_and_resources/architecture_2023) before
further reading.
The migration can only be successful as a joint effort of HPC team and users. Here is a description
of the action items.
|When?|TODO ZIH |TODO users |Remark |
|---|---|---|---|
| done (May 2023) |first sync /scratch to /data/horse/old_scratch2| |copied 4 PB in about 3 weeks|
| done (June 2023) |enable access to Barnard| |initialized LDAP tree with Taurus users|
| done (July 2023) | |install new software stack|tedious work |
| ASAP | |adapt scripts|new Slurm version, new resources, no partitions|
| August 2023 | |test new software stack on Barnard|new versions sometimes require different prerequisites|
| August 2023| |test new software stack on other clusters|a few nodes will be made available with the new sw stack, but with the old filesystems|
| ASAP | |prepare data migration|The small filesystems `/beegfs` and `/lustre/ssd`, and `/home` are mounted on the old systems "until the end". They will *not* be migrated to the new system.|
| July 2023 | sync `/warm_archive` to new hardware| |using datamover nodes with Slurm jobs |
| September 2023 |prepare recabling of older hardware (Bull)| |integrate other clusters in the IB infrastructure |
| Autumn 2023 |finalize integration of other clusters (Bull)| |**~2 days downtime**, final rsync and migration of `/projects`, `/warm_archive`|
| Autumn 2023 ||transfer last data from old filesystems | `/beegfs`, `/lustre/scratch`, `/lustre/ssd` are no longer available on the new systems|
### Data Migration
Why do users need to copy their data? Why only some? How to do it best?
* The sync of hundreds of terabytes can only be done planned and carefully.
(/scratch, /warm_archive, /projects). The HPC team will use multiple syncs
to not forget the last bytes. During the downtime, /projects will be migrated.
* User homes are relatively small and can be copied by the scientists.
Keeping in mind that maybe deleting and archiving is a better choice.
* For this, datamover nodes are available to run transfer jobs under Slurm.
### A Graphical Overview
(red: user action required):
![Migration timeline 2023](../jobs_and_resources/misc/migration_2023.png)
{: align=center}
doc.zih.tu-dresden.de/docs/jobs_and_resources/misc/architecture_2023.drawio 0 → 100644
+ 1
− 0
View file @ ddf9cbf4
<mxfile host="Electron" modified="2023-06-05T08:54:45.184Z" agent="5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/20.8.10 Chrome/106.0.5249.199 Electron/21.3.5 Safari/537.36" etag="-HTyYpm7KikI7TLmpzGH" version="20.8.10" type="device"><diagram name="Seite-1" id="tXkwnWAt3AUjisLzzv1-">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</diagram></mxfile>
\ No newline at end of file
doc.zih.tu-dresden.de/docs/jobs_and_resources/misc/architecture_2023.png 0 → 100644
+ 0
− 0
View file @ ddf9cbf4
doc.zih.tu-dresden.de/docs/jobs_and_resources/misc/architecture_2023.png

43.2 KiB

doc.zih.tu-dresden.de/docs/jobs_and_resources/misc/migration_2023.png 0 → 100644
+ 0
− 0
View file @ ddf9cbf4
doc.zih.tu-dresden.de/docs/jobs_and_resources/misc/migration_2023.png

205 KiB

doc.zih.tu-dresden.de/docs/jobs_and_resources/overview.md
+ 7
− 5
View file @ ddf9cbf4
# HPC Resources and Jobs
ZIH operates a high performance computing (HPC) system with more than 60.000 cores, 720 GPUs, and a
flexible storage hierarchy with about 16 PB total capacity. The HPC system provides an optimal
ZIH operates high performance computing (HPC) systems with more than 90.000 cores, 500 GPUs, and
a flexible storage hierarchy with about 20 PB total capacity. The HPC system provides an optimal
research environment especially in the area of data analytics and machine learning as well as for
processing extremely large data sets. Moreover it is also a perfect platform for highly scalable,
data-intensive and compute-intensive applications.
......@@ -58,12 +58,12 @@ automatically select a suitable partition depending on your memory and GPU requi
**MPI jobs:** For MPI jobs typically allocates one core per task. Several nodes could be allocated
if it is necessary. The batch system [Slurm](slurm.md) will automatically find suitable hardware.
Normal compute nodes are perfect for this task.
**OpenMP jobs:** SMP-parallel applications can only run **within a node**, so it is necessary to
include the [batch system](slurm.md) options `-N 1` and `-n 1`. Using `--cpus-per-task N` Slurm will
start one task and you will have `N` CPUs. The maximum number of processors for an SMP-parallel
program is 896 on partition `julia`, see [partitions](partitions_and_limits.md).
program is 896 on partition `julia`, see [partitions](partitions_and_limits.md) (be aware that
the application has to be developed with that large number of threads in mind).
Partitions with GPUs are best suited for **repetitive** and **highly-parallel** computing tasks. If
you have a task with potential [data parallelism](../software/gpu_programming.md) most likely that
......@@ -71,7 +71,9 @@ you need the GPUs. Beyond video rendering, GPUs excel in tasks such as machine
simulations and risk modeling. Use the partitions `gpu2` and `ml` only if you need GPUs! Otherwise
using the x86-based partitions most likely would be more beneficial.
**Interactive jobs:** Slurm can forward your X11 credentials to the first node (or even all) for a job
**Interactive jobs:** An interactive job is the best choice for testing and development. See
[interactive-jobs](slurm.md).
Slurm can forward your X11 credentials to the first node (or even all) for a job
with the `--x11` option. To use an interactive job you have to specify `-X` flag for the ssh login.
## Interactive vs. Batch Mode
......
doc.zih.tu-dresden.de/docs/misc/migration2023.drawio 0 → 100644
+ 1
− 0
View file @ ddf9cbf4
<mxfile host="Electron" modified="2023-06-22T11:44:28.169Z" agent="5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/20.8.16 Chrome/106.0.5249.199 Electron/21.4.0 Safari/537.36" etag="Y2qdBmcmrf7lYsppJ_dS" version="20.8.16" type="device"><diagram name="Seite-1" id="-EQ8Qw6o7c4L1Kgc9zBM">7b1bd+LIsrb7a3qMvS+6hkCSXb6kDFXN/Cwo2jB70jffwDKWMRi8ABdIF/u373gjMqXUwYd216nniu61emLZCBGZGREZERnPL/75/fHTdvZwG22u56tf2t718Re/+0u7/T7w6b+4kMqFVuu0JVeS7eLaXCsuXC6yubnomauPi+v5rvSH+81mtV88lC/Gm/V6Hu9L12bb7eZQ/rObzar8qQ+zZF67cBnPVvWrfyyu97f2a5ycFb/4bb5Ibs1Hv2+fyi/uZ/aPzTfZ3c6uNwfnkt/7xT/fbjZ7eXV/PJ+vIDwrF3nfxyd+mz/Ydr7ev+oNib/5+Oefp91o++unXw/xye3q4de23OXLbPVovvB+9rh93K02yWL9S/gh+PXkl5Aun6zoMz5cbelVglfyVwv6i9DzWu/eveO/8n79BQ9x8j+P+FIfxvxHxc/P3eb06dv8vrmfb153l/dP36WzeridvXyX3f3D+9p7//W4WrzivfcreoSnPp9+6dyAJ8Q+tbNsu3lcX88xUB79+nC72M8vH2YxfnugdUXXbvd0A7/bopez1SJZ0+vV/AY3u1msVueb1WbLt/JvQvyL65v13rku/9D13X67Wc6d35zwP/ljuTPKTLIv8+1+fnQumRn2aU5Ds9+m9Cfmt+1TM9vtevfMzwdn8ZyYa7fOusn/cGYWbJLfu5jT9MJM678wxYNWTdzza1rj5sfNdn+7STbr2apXXP1QXL3YbB6M4O/m+31qVNTscb8pD8v8uNj/x3k9xWi+C81P3aMZXP4htT+s6Rv+x/3BeRd+LN7GPxXvu+5AudGP6816Llc+LiAY/n15PlVmyElwevL+tGkm+K3AD4PnZsJu87iN589I+8To6Nk2me+f+TvfaB4MxbMTaztfzfaLL2V1/NUnyUlND9Jtbunmv7TPeRl/fNhu7sjA7PILu83N/kASemYxt15ezD/16s2t8Eurt/3NFm9bF+/3W7yn/8zFe9q0eFePJKE51unuOl+zV/N5ckNL+COM9H/xug1+9Lptn7xh3caP2y+5/H/yRVwZ/6vW9fWN1zTOLe/UP5v/rWX5/pXLsh3+VMsyCFR3fz/d/dpJ8pPp7vfP6+54O9vHt//Nqvr0R6tqG6LRZfo9lunZP3OZhu/fMEnKq/RvTBnv+06ZeDXb7RZxadY0KJJvavNfO09C76eaJ2dN6px2yff/d7aNb/Hx/72q3H9trOubqfJWq0H8Nuj4YbZdz7bXz4UxbdS39WvQGPXl3zkh1urvd/PtlwUNnRMF/YaBzpubdhw3DfL1ydVJ+JUGOWy/MaB5+s3s9d9Txd4PsN6tr2u9365VW+1/pvm1z13Wq9ez/YzDlNvdV9arP2Rp/fioRXCqS+vNS8v/hy4t/5mltYn3mwekMP/5i+vHh/LfEhLUxSWTNPiHLq6gaXH9iLzaj3EW3//oRdcKawOwnh8g13S3n98bqffXN4v14mq2pt2B91v397Z1ch3pkwj2ZRGXRWlmvCt3c8m68TEJdk7XP0Cgi3i26phf3C+ur3m1N41pJVRDGz2rMRoqYP76iHnlETupD1guDHfA/G82YPVMNEqWnhuwj93f/5eMVjsMXxqt1vvwe45WPfXYieP5w362jusKrG4frme721yjOYOF659nexqAtYjOK6IZtgytXRP3kxJ+0Ro4AgwbZru99mqjYT7h82ZBT+IETMrD59uf7S3EDpp3FUNTu9HJmff8jcRO1m7EY5x/7b+R3axr1dp2zOYu2v9EO3ZScR6bFlr7e9qxdn2h3Sy2uz0rxnWMOc66cHND/4lm+C70bz2z8ff1oglG/Q2t+BUGKHhfXklNWaTva7fsjUtLoiL83e3sAS8X91x0+2G2e5CS3ZvFEdL5YH7R5ZXkd+RHWklfkl/aH46ooDz/3D0Lrv44JNf3/07j9urL1Z23iC6DQ3/xYXV1P/jy56fV45+Zt/j3v3//dDFOFv3fBt70j3A5/eP45ep+cta/D7/0797T/c7vjtn1fZzMP7V2V+uIfnPrXf/WOblIz/xrP368zqLHK/9f64usf4i6nS+x/+eaPsWf/fG7N+t6i8F4iU/d/PnHaj37bXTWv5t40Xlf7nyY/uf3Tf/Tnw9Xnw5n/UXkRcuPn36f9Bf9T/SX914S3cXti7vJcdidhhfd3mOUTVrD8SSZpp19NO48Rt3IH3TjXXSOn5PHaBzT3y53w/PgMMimaZSWr/Pr7oheJ8nVeedw0e0k0fkhG5wHfnQ3PQzOP9z1u53d8DIIB+OkPTjvBBd3vWzQHaX0+fS64w26k6zPr3s+3S8sXf90wP0O/W5Ez90Joyw64jPoeY8RPVOUxd7wEr/n9weDca91ce7h/fQ6CSvXj/w9uqNWlH7Y4bkiPPO5V3vei/HycTietgZ3k+SCv+/IH9xN6bo8Gz1n0Jf70XefHAeXh32TLC7G5eeeLz7s+92E7hEfB3T/i+7Eu7hbeoO7UdD/FNHfx4+DcRQOFvSd6P5RGrQH49FxcH5oQz6Du367ch2v/UE28qKF8526ffr7UUjj3MJ9SYb+Bb7fXcfvd6f0fXoevZ/GL3ocZLE/HNPf4DVmU+V6Pq53Md4XRN0+fQbkhGcdkTwTfKY8U3fpkzzbZizbJP+MPtcbjmPIjl7H9KxLZ1wh69qz7gdpQPMyOQ4Wnf1gERyj7jKNFpAxPxfNjX4i96vcm+ZVfu9zL6X7HOk5DhHk+dsmubrE/J2S/Ec0tknLzCX+PJpLZt6zHNIoW+7w2Zj3eA73uvsczrynvwvoeWieX8o8ovu2oy7JPe1AJkeM7UXXkYPIpxXdVa7n8un7/D6Sp3lW+nmSYRz5M50xuxhPzbqcVq7/DbmT7AZpo9xbg27Pu5C5WJ1/ezNX2vQ8mCsn/U9eQp9P9xgdaSwyWrvZcDzyZM73DrRGMvqdL2vG1QVYU/hOo8p1sw4zPHvxnaJsRJ/RJ/3Sg6xoXHgd02f1EqzViJ/zYPRAjO/Ja3iQ9QLSI871/LtkJIcDrYMsgp6BnHI9ueR57+oAvH/YjdLBZadJN9CzT935sq8977kXkj7Adzz2WY/ROs2m7UJ3RTS3rA5OWtF4UugkVxbQae5zy9yn+Zc80vej92EO03y5i8NIPns/uMRcjbPI6h7IZdwnXXkgHTUhHTo9Vq7jdUrrH/Pd0T29EPotIjtj5lWL53g3TvvdEXQGzffejuVI8x5jy6/Hk5TWR+l6oXvw+9iLWNdgbU1ofncy+hvRPeaZBpjD5zSHu0uaZ+Xrjffl65iXPfrsfAzwvO0o63j0ffHdvWGXdQzN077H68WRQ3HvUQB7Uej+/oF1dpdsntX9NC5k1WFPSBeb7yKfdyD5Zmb+430tWeOQV0Kve5XrzrO487/6XVhOE7Ld/QRyGYzJrp7LuJEeCwa57KCj3Ov5eKb8+7s4oPHm+c/zZNw3+ofHzafnIPnws4b0u8p1flZag4lX1j+1ecJzcHAXkR3u8DgOsH4WZfnmcsgSXhcNc3Av82VKnx/l+ofGnt4XBbB9ZB/pNemzu8R/hd2lZ5oEjXb3btKu213IW3Sb2N1JOBxD11ft7pRkNWqwu3L9jXa3PRz3jw12l673vLr+Lz2r0f9LkX/N7sIfarS7JJPp17e7pDOG5012V56jYnehXzzrv5nvEUZ1uytyqNvdinz+qt2lMaM12mB33yb3kt0tyb1sd8vzr9Hu0nckuffpu+C7RnSPKKT3FHoni1JX79B6zIzeSWnNVq6btdxdBg16J4uyxNU7Rzy3Wccp2SGzVun5HN1c2JGe+11E72Sjw/Dc0TvdiHQT+/v2mSAL6Oiwcq3pnge2o5fk65NdHOa+Pj9ru0HXy/ds1PVRANl8A11fkrmj6/+6zB1dX5Z5oesbZf5qXb9s0vM09x1d4Or5LApKep58IbkP+QPj6RMyj4NC/zfKvE12ICv2Vj0vYhsywb6Q9DR8MPKNUpZ9vmccpKLnHd8PPhTtd+Ksct34XdN0WPJxIporcQofxHwn+G2kh2Oah/DNIvjKZn9MNieDrKr7Zrme67GM9Eh3SePZM3o+94tDkb/r87FfnFn/texnVu5b+JlYP66f2TbzvsHPxPdt9jNpfoUv+JmpPAfta6GHaIzJDrdzP5Pn2FLW8bkHvUq+K2wy6TpaP/g7scejDHq02EOVfEyS/zTjcYW+hwygMxcd6Defnsa1Ac5n4L7LsLSvxfPRuA/HkZH7iOe0iYPgvSnNIdhXuvfoQN/NFxvcp2eFrmi4J+sJkvldlOVzvnjGPeluGtcO5F3sy0UW9rOK64WsMZ9D0tchr09jV9keQPfgOxhdiXVFa4rsVRLIWmH/hmzRZEefDT/6EF1a+zsNae7UP491TOk74HPIf+7Qvj56pHWURXfT1JVp+X7G78nvh+ekOQf/xuylZC7Qc8JP4PuQfs+iBlnn1xvuyzqmNB/k+y9pfKBj+FnJf4j9BnmTvqF1lLINrs6zvcyNKdnZpRO/6QeIF9F18iWTHemyA/mmx4Hod7kn6TPHp2F/QHya/nFYuW5sfOrqtsKn6WMvWool0PvFp0HsyMQMomySxxJ4PrjXKz4NjV/q+DQ0F0ZB4dOMQpYFPyvpycuSf2n2+lE1flZ7Vp5vdx08a5MfaW1czY+M7hwb99X8yJLMXT/yr8vcid+4MnfjN00y/wt+JOmdSWP8pnzfwo8kv7Pt+JH0vB3Yz7YZ62LcSG9X597zcp8eB6mj0zPS6fRZLD/aX5F/QfvMyWtiByG99htjB4ix1mMHh2G358YO6Pl6rebYweSJ2MHkzbEDxD2bfEneF182+JLd5Bhdur7klPa0ifVtAvHj8VyTNuTl+NOFn1qWw77yzOzHkx478LOS/i30PH8XWguRmfssC4zFjuMgkEtavu4+izP3a99F9uK0Fi47GENaFyMv90XJJ7AyKvmouF7M/ZJ/RvMEY0myiR25i39Xlbu7t3+j3F2fEnH8VrNPWZZDs08ZtfB50GeDBcuJ/KOefDbvGbDnTrzCzorfInZ25A2NnR10I8QN2P5EeJ4GOxvlcUu2X2T/aA2wr0D7ti7rVOijpHo/XK/YWdIXSyt3T2Qq8VXWlXdmf4lnHE+sj1T1PdqNNjbrHF/j00Qi89p9S9/9q/o0haxdn+YNsia/vl/4nQurs5ctdwzK/mPhIxh5I47VzuWdJT7sE3wR+m6twley1xvu6/iQUREfLnww9pHI16X/L/wXmuu5DEr3TsvzvOKLidzJt4dt6CFeGBgfm3z5iclNRdjL0rNw3Jt1Pn/vy0N6gXVEa9bsb0PyHVq8H81ofLplPYO8Kc3NlrWxJHNak7TvIRvDegb7EHlvClvofA7dGz7nyBnP3pHWd4i4uJF9hvwi6TmeI/xexOTIptG9fewBRP8nKesd6JGs71X1S/UZ5btPaf+5hI6geYccal/0jvmOooPc+06Dkk4f90jfLBGnd3T65ED6hObWhJ55ZGME+A60LqOWiUeyTEn2iFvSZyOuOTWftyR7MNo1fB5s6RH7R1of1j/AfTH3jn2+D/kOXeitqqx7iBs8JesAc2Ng4gM8dt0+4gj4TDxnQLbUY19vAZ0OHVW+/naZY+51jhKfj6EHWkY2lXs3yZ3WAv2/6PT+l8/J5n386aM3O/+w/Hz5L8QNUrFBPcQ+aC+MfW8/HbIcaf9NdhBxFvq+IeYT+zmiE8nPSmg8Ysy9lNdjl8aXY0zYJ0FmtA+h/RFyWaTPyL/ukF/FMjiyH7RAjIV8OOihbJSyPlsEtIePPL5G6xE5M7rPIWLd0qe11glZb91N/Yi/64TeS3/H+w4rPx5jyRfR/cjPxneDnqZ7d0LjI5I/Nwkkdkx+BX0P+k6kzxLSg5jfqBGYhpL3n2J+h5HEeo6SI+G8XBtjMBx32mYcofs8I3/od7KHiYd1QXPdG3QT+M30nuhAz+QbOx/Q+s9gq4f4Ha9XjiVhTtKcWx5lT0jrReapvZY/95XoJPIBOi27v7zgXB3tFehn+jyye3EiccWE84C0j0hlfsEG0B7xjv0m0v+xrK8u2aVxbycyG/nGXmFt0tww+RKytXwdtgMxARlTWjuxjYPtaWxgY/xI7GQxh0TvZvxe8qMGlzKvaL+FcSfbB5nQ/OF9ttgE53dN98J+icavI7kMvhfGcJQNRAcjLtOSsaGxyEbGltPa41wJ5uIIeS/4QWQ7SXfS+2kuhGzjzXvo82h8RsiFsIxJB9F8ga8q81reP4WObHGdSZfzmSTvBHOU70ky9DmmJv4c6X38bMcNv49bomPxzBNf3k86sUtzn+8/OgxkH/lI9vBo6jPMfflZU/IpDxyzxdqWax7pgXaEWNklfp+k8qwj2nf10gt5xjDP49E8jNjHiVuypgr58essDk1sEbG6I/YmLA+y2Szvu05oYqP0jKTz+Fr+WWw3EZNjuXbjFvtkLEOyuV3ch3SxeT/JIEAMN5chP2sPcsezlmVo9CetY+P/L+Er0d8urY1J2aZkrE8PvIYk50b6f8mxU8Q3MV9pTcG3or0jdBCNfRbLmGcSF+T1nnFOlO5D6+quw7E8mvOtSGRO+jnCejO6q2f9AfjsmehYxBangcgCaxVjPzWvoWeSymvEHEd2T81yjniNk54Z8+/hc2KfBP2LvSyu+cilDtlfWcIu8jWSK8/RAeTKOjw+InYk34HsxiXsF/Jt0OH8vQKJBWOvSnab5oCsTcRhyaeydQLQ6zRv2Vby3hVzgffc9FkxxqXFeRkaF9FtEd4vz5nFLd6jsP/SyTAX6L0h9nkSz+q3ZS7RGJDNEL/QkS2PRS7DPeuAMfmwaaPOoPkRBxyL6cJGwu/Ds5i6sAXmfw8xMujQo8TtET+huYY6Auji7iSVvVBE+mN5lLkScS1UMVdGRs5x26xF6FTJh6ZsI0Izh/CdcI/6fKF1QXrI5llpT+rYZIm52XgUcjFe05qldeaZvRvmzYHlDL2XoT4B++QO6fR8zWLNPblmyV8Jh5eVNTvuwyfnzyK9gVzsI/ZFduxpLUkcB759tiS/PMnr0ETXx8Y/J91yNwlsjAs1M/CNI9ERB7O2YL+P5hkOA/ZD8bkjus/IyQGyvQ1ofqX5/RaYWxPx1fBeu3fG3nDcFx+G9gjiY/H8DyRG35N5hBgoXrOuwNrty2d3Ryn7shhTqVcr5qnxWaxP6axtjFmbnl/8oC7XcrnjSXNlYnQ12TaOuz+hi+0437HNKuyY6PYjvqdjx8RPvZM1NkDtznlVB8MnGdnxDBATLetgzi9BH7Rk/k8yWwdJ90E9hI94Oeviu34+1sXv8D6ay8ivmNpG7H1pz3MUez1Fvhpyw3jteB50I6+YVxHGCrVB+F7kR5AcFqxDaX6yjqN1LTqOfH/UohXzWfYThyKei/0vahX49UF05KGQf/17OONm5T6V3GrFJqLeC/ltM9eMf7o8GL/C2oh94X9hvXdaqLMSnUm2RXzZNvK3nO9K8d367KuJ/zuxe+yM4/hS20m+KenpIr4Qkk2DbyE5KPY3+thLwV6Y55vYtRCw/8f7ish7w1po8fj8qLUgf0P7s6i6Jo5st161JsS3k/GIUuOXkIxio8+muOfTfgnGNuscIrYfkD3nNjnmwvbDyDviffAS+2fYmQPPXbItEe0HBuyro8atJ3M86/li7zHHR2aOL1PxW5ZZxHbP9VWhs/OaESOfij98N0WeshWldZ8bvxsg57CwtlXGyuhl+t5940ctPauD6Rlkv7VAHLZTHnvHXpt5fmTfz9p7tjPxEXt3kwvz7TyHXaM1WJ3nJTkX9X78nUKbz8c8R07NyPgYiT+AXGc4YF+J1pjdD2Xkv8MOiG0O5Plj+MZp1Y4Pun342Zn4Bz0z9yeoa7T7qWMxz3O/hPMt5BcFhV7pvcWGH+0+gcbo2JcxPRh50jgmMmfxnnFk9A50HutB2gv2U+MvIW+XyB6InkVsakhzKMB8Le0x/pYNpz152YaTbum0BgvXhstncLy+iBW1Jdc/DWidhDx3MV5p2R9y56TkxLAn7nl2z4faBPMa/nBb5NWR3AC+L+d3ef5ifR7FRiTtYeFvsrzzcWV9sPQxx2UOTT3UK4r/u0RuIs395vPC56X7FHOL54bxn7uS10PNAskcujbPd7DPMp6aWjjxWWTP0guj3LeOYKNzPc36zH4O+5DJEfpT9JTdc7APS3q1X/jXlx3XF91X5vHekZ/NxbH8833XndhzM8/zuezYVWuH7R6Gx+nC7vtkbiB3GrD+L/yx3H5Hl3YfPnH24Rz7hK6W+jmzp+e1dYn65J67Zz5W9+ID7IsRV+J4QMVXyef39DjMa65h23tmnznh2Cjv3c/dvXySYV7lc3wscSYaBw9r1figHnKvbpwg6tb29KL7EX8ya3bA+grfPYEukXthT2L0kKx7jrVBF3uDIh+QxzPqOgbjifzbqDSezp4JOSH4Jm3ys0PHp8aeB/FA46eNjiIzfoZQ/AOSxThydCz55vm+0vgS2EOkvJZ80mnWlwjhi8rf9tOS34Q6BOM3Ne+tyZ6OeyX9a+acsctLz9hM5H1C2SPTXkv8gupn2DV/QKxHbMGoLfF71LbFsM35/g/zCT7xM+td6uh5fqNuytbhsE+GmG9o/OCA99G0nydd45n1m5l4oMQounb9sq7Bd8WeJ2O/rryXhl+Wmn13yv6H8z15bGxsNfezpr5r+yU/kzwiZj287DT+Ta6Lu1PHPxhZ/8CT/XyDH+w8g7G7pLM6fv49xpxbs7EK38R1caYicH1UR/dxzZapxUv5HETqxEgz7FtGgYkFmfhdnPE5B+sTdyPHLk3bTs3dETVgOMNE+3MnvgSd3PfE3+qI786+Rs/4adV10K/EAWTscl9DdBnOUsG287iRfEr73dIaML4x9B9sguT+MF6kZ2Wd2RiSiSvw3pG+X68l+6d8TZj8VGlN0L0T7BVzP05iSajzcNfDhOZkL2ywf15xjfdeUi/HsSKMUQIba+NbKeuBbscrrQOMezep2Dzy6SR+nq8/2ZtMjoP6GkijbtRo75rjSU/M+xf94dFL/nDxeWYvRfr+UJ/ryP327JqF/J1937RY90VMOWA/rjbPJ0bXG/uAvEA2MtdGWd8891Dmrq0BQA3EEXlUu7c3djDhvcEY9dxLW7dp7F2vsreZeCaGhprrp/c2xf49M7FMD/t2s7fxSvEou3/Pa3jZnqUVPwN7A9J3skd/wf+o5QB4r9/ge/Bnd6ctsy49XsOXxXOLbMlm3k0kPoH42tM5gJTj8fBDU8dvyEbtwWXZZ+Dzm+O+3edKXL+QZa5D5Vkh634mcxG5o8j1CWTtcCy0lNvg++H8p+MnpEPMjZqfELM+GeTrAPtb+xpy6tu8vc2HmNh1YuNRaWWvavfe6dPxKJsT4HiURzqlHo+SdVuWqZsTwPe9Q0wJtelRKScgsRmjZ3hdwke2e74oGNRyAhK3duK8O9Ezud9SxEDyfeRTMZB8b0j+15L0e99cp73PpdXPHdge1l82XjtA7HeB/NuSr+Xxz5TGsYu6Ivw9zu2yD0x+IvZDfZxpbEOW9N4QtdelPOoCe4KR+ColWXH8hOeHo59RL84/I49Mf5+aeSS5EdwXNV9Z5Ogp8U/s2WTOY3d7+V6Ex53jRoj/2f10v+yb2P2wjYtLHIDrRcy8FduX50I5R/s34hRcW2FszvI4EJ/X53rphfVBOLdcxMkcW3TFtW0lfSnx6THOQcf0mVInWdOvXO/Zc/Tr1MS3c/2KPUtg8rxWvyIXH8ietDF2lOtXs/ZYv1au1WJHrDsWldgRzlXinF71einHyjG+Y24PTZ7hdbqV8wxl3YqaaLEdPs738ZiYPEOEPHgWG5+vj7xpNuD8i9mnXML3jlOb+4tEh2aojTMx0NperIjrLY0tnZp4Cu81q/nhpj2Y+Lr8vZy5y7Gcmv5sSy3AyM5ja7OqryVenc9v3hPvbQzH6Ic87zZEnKoxn9M3OdjIH/49fYv4jjeo5mCtvs2Qv3Z9ZNSujPJxKHKwPeQzzf5mWor7VXxkn+vaJX/plXVr7nPWc7BFvD+PYdiaitL1vDZgamNDvujgODR1X4HE0cr6PBLdxnsWJ1ZYxDTrudWgnFstz9lKvjffZ75R33pN+tbuoV6lb+GLpoW+pe8UPpH/sPlF3i/07Th37b6P42pN+Q+7BztE45q+RczBt/ah0Ld13z/Xt4X+zM/iD1E7afMK3Xye2phsXosBXQH7Ij5ppy35L/jRU9/s7Wj/2Sn7ddgjsrwjH2eenHgU1h59V/YJQ8i9iM32d7nvk/sD4kPJa6MbOJ7B59Er1524cDfXBV9X55pc4Cv9WdEFC9efjQrfNa9pGUH/mJoW2m9LjbgTbzZz8dzEj+HbyJxCvNHsV5CLj6r+LOvGhpqWA9fxSa1FSZ+iDgn738Zal2dzrT2jBzqkQxp1bVbLnd8l7SKGxzYXfQlsfjuPu9scZynunuvSaSXuPnXtXfvCzXXj3EhZz5K/Ex+kRkTiSO5+spL3EL3RdfKQhd4o+cCvyHvUfVt679Tko1y/lvdO7NdOvAa/NjB+7YHPDHI8MvILv3Zi/dq0wa/1n/FrvULPTkKTe8T+N0VNpNGdOHucx/ZyX7UcY3fztrY2x9a6lGNui8b4eh63kbOH5GPgzGmzXxteFPt2cy1O7X5qKHuZul+bxxumQZ5/G/f8ev4tCvm8XLHvqcTVbPxfaoEkZjDKpL6wEhOT87QYj6Opm0d+l/XHEOeb5YwkYh1hEUfNY9zYZ+ykVrZn9NcU8RJ5/3hp7T3bb+g0mk+eyRE6MbFqPY1j08qxY9SIpmY/4cZ5OF7AdSLWtolfcJTY8Sg0a9rxO3qI73J+jdZdKGuJa5LYnlu/gHOaC6c2Kr9m4mRj1mX2vHJrgHrfRZO/BR85bg+7Uyv/o5wpSHJ/a9Ds9z5XU2j3D4WPKDYkYDsnujarxRMk7+C9nHeg/c8djVcWWxl7QxOvItsjMr7rpSaW56Hez7WfUru7PJrcJv0+DqyOlbjRFLlKz6wVHzG0UuzE1JHUYgfGD+A9Qx6D5PyNP+T4PdZCrx7TSqs+wCiTOKORF8/ZUdrgA2RlH6BXsfV9c9569IIPILECttt5Pq3fkudLUrsHrn22jKnIr2vqHkwMR9aqqQValGJP7l6Aay7JxuMsRNXHkjNEZOsk3uvOaZv36ByHklP2OG4lY1bTu7nPyr3OanrXNznbjOtwjd7lPfXLetc3ebBQ+molNb1rfoZ9MLWf5Afe9V/r16LmxDffiXRiLDU4pBPlPCh89uVh2Kxzg2Jf20eMPrt4vkYO+fVDkcdozq8PxJc95OfvRV8HyIcZP7dt9TXOT0UmhyE180/mMJz9WZ7DcOslihyG2W+8KY8nvoHxt9DHINmJ3YsqOtjJVYjNy+cUx3HuuK4KzxXg7+pxPt5TlPcINb1biYeL3g2KGPv0mNdyZ0lga7mj8lra5zEM8W/hN2auv2jsYUh+vPE3J8dKLXdeo174vbkuKccR3PhNLY7rvmY/28lzTFIb26W5xLkisRWm9mQ8Dcr6uVR7UtLPxl5K7YndM2Z8zrK59qQav+0WNfOlvANsWx4X6z+lo1FXIjqa/DxTp97Cd5G52wsHlbxDhPln4jhyXrgX1PMLhV5mHbco62XyJdqFXp6msofqHe1eB7U1kveYHCXGBfuH/G/P1CpOWtb+Sv8Gqefu53sezs3b/F49zyC9I7CXa0nModAnUb2eO0M9r/gaiAmQ/jexUPT+cc6e8H4DdRDinyPfavJ0XT6Pa3OL5pzL8oA56uQUoWNwpjR1dDLOu4f2rCv3q3gq95bHqrBPzOst7f4rkDrfpviG0ZVd7p1S9YVT7LdyX5j90XItWp7LbMzldGTva2pB89wbcrmZrV/knJOxoZ0iv0y+OulD+j4TX8azZEcrNQM9OcfT7Qel2ln0UOKep6zHM7eGV/S4m3/rZKgDKsUA2e+WWFbFXzmWcnBurcBfixVL/pd9heq5HLsue7Z+VnRMd/lCTZA9m8M1+WmtJojeh/jYa2qCanI2vjRqlK2tLWp6pugd0c71+l3veX8aZ0ruJjaObJ9PapZlHdtzJOJP8xx6dRy5lPtsrCNclGqVvUquLq+/ajrDY9a6m68Lh7l/7dYTSv1VXkNeq5eV+ZfXUyA2lnHtm62NKeWyJSbXtzW18CuObNulJ4Yzx2Osfe81MTnuGcYxuf43yn/kceQ3njGDbJfFupScboa1WT5j5nzn8hyu1AOYPP15Zf7ijLvRoaTDUpMb8fM8Wd0v8Rr8ktbgsikHEn3LuVvE4uo13qnslYxs0+q85bpBN5dz4HgP7dfsXpFjV2U5YK947P+2WVxkwf/5/NuH2+tPSfJn11twfRyPyQQ9GXao2WFfOosze5af1k9AfyN1zNxDjPVEyjWz2TSUGA3ZDLJH5nxlm3sOXUq/CD6bL+cB8JyHvLZQevtkcn65b3oF8HmlNJI+bDwfpAdMz9Q5mrPocqYSZ/ECs8dHnKpleiWhX1aLfV45hw/bZepwpy0ZZ5y9HGXsg3GMZuINzRlkxBo5Bp/CP5J6yQHbefTYwHlrkk93iXmFs1g4p926yHv6TCvXJcZJ77U1CiHLB+fKyD8fol5hPGkVeaikJfmYSd6PKkItOHSM9IVr8blp06uE3ou6TO6twj0W8p54Sz5/yZ+ZcWzJ530z64aliYGhzhXxsCVqjY62hn44npoz5zQPM+4zkFn/QPbDpna9i752fN4afiVq2rE2Qs4Pk9+Dnr44X+z0yITNQc0kPifgsxP0HMhlDOXssfQmk77eOKuMHFFaxK6T9sDx6Qd5DgVnaadm3z+x542hm8lejtqmVyN8Np9jPNyzZekjL8Fn6tATCDpZ9i28j0evlqKXRc/0LCrm2BA+oIkz07xsSY2TnCGHH885MvS25fpy9HVYptxbimMztE+Te3AfOu7xJ/1K25XrJjexTO05+SHfC+fWaGzuEvaxB1keWw8G0jOxVcT8sU6jA9eu8BzBPmRaniPcy2Vi/dwj+7f0d5Lfi6Snxrhvz0qRvCa8549Y34+4H9+Aez137B5X1nEXZyGMH5mvOzz/BPsarGX4jH7EfacS1L0Fpndk/vw893l+2r66qE9F70bz/Bnv38264Fo08/yxrS/LRJ59v6hzRrwn8uSMVmcvfSZj6Ausc+g69nm4l0wX+RM+D4+5d3Rzi6hNH2SS9yady/FzqZPs8/4fNbFGZuGA8xodEx8ozeUD9w4857Ou9NlS54/YH9fAIM/RjeHrJzKHR3gec9YZ/UQQdxodaU0eOf7K+gD9TRGj4fPThW5GzeMdemnFnP8dsL80TUQvx6Ymo+PjXEkkfQ9SqR2v6OTuJOC8iDlPa8ec9THXSGO8of/Rj2Uq9eXdYh2Z+cD9z3kddeN2VMQ0Rc9dBlyPOZSzY1YP+5IL5lg/9HAo8a8Ecyo08TTuVYY+/uXrRZ7a7tVkLY1S6ZWOMeujN55nxiyw/S9oHplzHT0v4j54JOPLA/opcgwL+fJcjxf9JvyI9fxUennJWm0N7NnXrvt7e/9+S2L47Je2ZC33joPC5h24RxLpgwu2MagrjXyTU0Yfy1B6t7G+N/0SJjhPjBxiaPoykAw60mNJ+n60h/Ys3pjnibHt6MHCvXkgfxo30omynlrIX9H40n5yVLLH6JUxwD6N4xySIxxUrvP6x7ka2xdYbCWN0Si0tTcmfouzOXx2cMg6E+sXtqWH/VRgelSY65iT07bU6KHuI++75rFcMukhiHmO2FvNjxCbH/BZcvF1yX/ps4xwHoSezcZqQrZnlx+66HWInt6IrSCvyOOLcxNZnGBucB8JjuMs+edBl89bZFHeYycyvbrynnDwIX3EbNE7QPSQyQ3CHmdL6Ykxxucm2F+3JOcTS882mtMD7sGP83ixzadiHcHH8eUcjvgP6C8F/3zIOZRJavrNNlw3Nofr1Kb5c0IOOLMv/e3hIyMPErG9jxAn5ZgD5tAI/hl8B9hXklHH5OCmHudLup3AxNV3ZM+QC4UuSIbIhXH/qL5f0i8cC2Gf3+yd4iPHSBFnQR2e1My1OP9IvjHnUmlfgDMaphcN4iRHqcmOcXbav7DnaLDnXXAMH7o2Ff9qwnG7nAWAM6pcT4A+Y7RmF8KJOTD75XMCig3+72sQfE6C03eWT2RpgQ38W7/97vT0e2J8mgjiivFRjI9ifBTjoxgfxfgoxkcxPorxUYyPYnwU46MYH8X4KMZHMT6K8VGMj2J8FOOjGB/F+CjGRzE+ivGRdJ9ifJ7wKRXjU7KxivFRjI9ifBTjoxifnWJ8FOOjGB/F+NSPUijGRzE+ivFRjI9ifMqt5RTjoxgfxfgoxkcxPorxUYyPYnwU46MYH8X4KMZHMT6K8VGMj2J8bFtdxfgoxkcxPorxUYyPYnwU46MYH8X4KMZHMT6K8bHxDMX4RIrxUYyPYnysX6sYH8X47BTjoxgfxfgoxkcxPorxuVCMj2J8FOOjGB/F+CjGRzE+ivFRjE8xrorxUYyPYnx2ivFRjI9ifBTjoxgfxfgoxkcxPhf/5Rgf/6yO8Tn9CTA+7RrGBzCe+w19M7q83lzPdzWuz3bzuL4GwKfrkXAOt4v9/PJhFuO3h+3sga7d7u/pMbotQH9Wi2RNr1fzG/oyH24Wq9X5ZrXZ8q38m5ubdhzT9d1+u1nOnd9cn1ydhCdfR/hh2ytJ3vfrkm+deN9T7r7ikxSfpPgkxScpPknxSYpPUnyS4pMUn9RRfJLikxSfpPgkxScpPknxSYpPUnyS4pMUn6T4JMUnKT5J8UnOsyg+SfFJik9SfJLikxSfpPgkxScpPknxSYpPUnyS4pMUn6T4JMUnKT5J8UmR4pMUn6T4JMUnKT5J8UmKT1J8kuKTFJ+k+KTEtl1TfJLikxSfpPgkxScpPknxSYpPUnyS4pMUn9S4B9spPknxSYpPUnyS4pPcmhbFJyk+SfFJik9SfJLikxSfpPgkxScpPknxSYpPUnyS4pMUn9RXfJLikxSfpPgkxScpPknxSYpPUnyS4pMUnyRrXvFJik9SfNJO8UmKT1J80ssEnxO/hk9qgvh8d3xSWMP4zPhdv30+x1febu7m8X5HL5P5Hg8Qx/Mdftxv6D8fZtv1bHtdA//QBy8edvOX2UpfQbBBOyxJNfAa0EjtZrGG30ysJzWxPu7mWwhudj17IEmerACTutrSqwSv9vRcAFbt4u3iYV9HVr1apDUO1cePPv2T/+YPI5b2V8KCnZbJVMFJXfxnYV30wTcT/emTot/Pd5jDdeGv5wdIe3OzP5As/jGyzwX7zNT/VrL/9/a3287Z5nPXv3/IHg+bu0EU/dpq1WV3ncwvzY+b7f52k2zWs1WvuPqhuHqx2TwYSd7N9/v0cpHhbbNHUjYlOc+Pi/1/QG97F5qfpoblhtfdo/tDan5wuW3X85vZI8+BZDu7XtAI1H8TP26/MCKu0FP4LqWhahi93eZxG8+fm5/v5Q/3sy1U6ktku/rgb+er2X7xpfwkX38ZvX9yGT1s5w+8TKrLaLa+5sGfbbHMGOrW9u4XJOP9YrOmv5rdY8Gsr3YPPDrxHJrQozV3/39n2/gWX+qfsvbCqt5rMjuthsV3+q0UX1A35ZsVBuTjJYZh87jez695/syuf92sV2lN1vTV988Jdb1ZzysryVyqMBIhxkU8W3XM5fvF9fXqqTEswxi/hkfwvgJLbBiatvc9YYnBWW1oxOQ0Dc1hSzL6Kcdmu9nLSva7Z19prE5a5bFqv//RYxW+xYaV5fQ3LJp9PS1Zt2aLRlLfpvmb8IPzLvxYvI1/Kt533dluN4diitCVjwuI6fkl+KJts/70K21bzaL+KGNnn7u2Puluz1qnYtxbL1uon4IcGzbZqSZybPubLbC6Mtyl65iuXOG5/+z/9g2UX0wSnG9/uGlqn1S8hrOG0fC/p7o7qU/9TgzHbLYmSWAS0Pf2/r8AzzifLxs2pjVtcj3b3eZrwhkzXP8829M4rPlK22v2zl4p9Rd1hyPTsEGk9tqrVYz5hM+bxXrvDKlXWWDVoIJoTfOuYrRqNzo5e+FGolVrN+Jhz7/222dCywvfYPlK26TvZvjyKRevZrvdIi7ZsGcDSy/asJPTV9qws5Ofyoa1vJN/zPAZv8V753lBxXch8b/kvdBPn+fbBYkNGv1nmhGnP9eMsPHmf9CMKM+Gk3/uXGi92kx9n8lwUg+L7meP28fdapMs1r+EH4JfT34Juw2Baf6rBf3Fqee13r17x3/l/cq+wcn/PG7wR7/TU26KH5+7y/un79JZPdzOXr7L7v7hfe29/3pcLV7xXpqm4YenPp9+6dzgSVffe9nVr+y5q55/iH9xfVNEHum6/NO0Izjhf76SD1qJXJ2Er9wRtLxv5YSe1idnMRJ5kunpsbVzuPVr0DiH+XfOvKv+fjffflnQUDpT4xuO/g/Z9716lL9ZfPJ9PSfWtNM40Z3GUzuNysI9a711p/E+fP5G33in8b4eAagN9u529oCXi/tZwhv53cM8hjxvFkeM2Afziy6nGfyO/Nj+uPuS0EQ6QpWff+6eBVd/HJLr+3+ncXv15erOW6Amqb/4sLq6H3z589Pq8c/MW/z7379/uhgni/5vA2/6R7ic/nH8cnU/Oevfh1/6d1ITcMyu7+Nk/qm1u1pH9Jtb7/q3zslFeuZf+/HjdRY9Xvn/Wl+gMrzb4foB+hR/9sfv3qzrLdBlkH7e/PnHaj37bXTWR8XReV/ufJj+5/dN/9OfD1efDmf9ReRFy4+ffp/0F/1P9Jf36CEfo74T9VV8djfKJuDLSd0k1yZHlpm6d1m3zJPNpqkwZKoM3JE9U2b5UOjX7Ufo72FqaYaoSR8nqPkJuP9MF31GDIu2ywzGgM8Wc62gcz3nFkVt5kNk0TGvXzEcYDm/xu+3fZgC7mHA5ylL1w0Xd1RlX9aeF3WA6A0lPcTxfUe+qY3kZzM9BRq4vWVZXIzLzy1nA5KAz05y7yn0TMKZkVHwCoY9+I/tynXD8xx5dYY9emlOWwXD3jBTawz7mM/D1Xmmcv2NDHuMZbuBYe9Lr58qA7P0rIalnvDZ+jp7NPakLq/h3ui78LXZozTv+UxDjT0qz1Fhj+IsVXtg+Ys5j7bOHpUe/XX2aFk+f5U9GnPtZBN79E1yLzHsS3IvM+zL86+RYY9+NeZMCHoRo8+pZ85wHAwj2zdcO0cXJNKPgHu/1HUEzoSVuIDCyM7yfohdXsf0WT3Ukx65Z+rC8sBxDrDTwAnH9fy7lNnYkFOuJ825HkcH4P3oSYtzOw26wc/rxcpM7+J5hemN73jsNzK9I1NbV2d6l2TRzPSm+ZfgzAnqL7l2MMI5Dcv0fp7/il49x8p1w5/n+V7lv+I8mMt/RV+NtJn/OnqC/zpydM9f478OUV+/KF9vvC9fx7zspahBN2MgvNqs48kZkYlXnJ3oe7xeHDkU9x4FeX+egkOKnq+Bcw4SvZBhT5ifYc7htaQXlpxZtWxZWeMjOZN116tcd56lxMWsfBeW04TPDDMbb9zxBpZ5BiZrLjvoKPd6Pp6p1DUzd05435gn0v/EjpsvfCx+VvRGqVzPubJeWf/U5sleeLXRYWB6+wywfhZl+eZycPiylTloznGAsRg5/BycX4rAAgGDEWe9PPQveIXdxVmUoNHu4lxdze5C3qLbxO4a1nnN7jIPssHuyvU32l0+i9Rgd5kJ2cSedp7V6P/lYdDM/G6hNruJ+T3AGZuvzvyetp5gfrfyGvES85vG8zy3u/ge4INU7a7IoW53K/L5y8zvEGdkm7jcb5J7ye6W5F62u+X512h36TsG3IeHv2skZ78Xjt7JotTVO7QeM6N3LOPduW7WctdhjRd6J8v7ConeAbc9MesY52zNWu21Xd1c2JGe+11E72Sjgz2bY87/CO+nzPZmPnkT77tyz4I7TXZxmPv6/KztBl0v37NR10eBy53/irq+JPMSl/uvytzR9WWZF7q+Ueav1vXLJj3vRa4ucPV8VvScYT3PDLoa57sic5fz3SjzCue75wm7lPsfHJlt3WW21525J+8Z+WyB2b8Z3y+QnitxVrlu/K5pOiz5ODijEafS44i/k+llFIc4WwQ+C/oyiN9HNgdnPWr7Zrme67FsinOBWd67ppv7xcImLPl87Bdn1n8t+5mV+xZ+Jvftc/zMtpn3DX4mvm+znwn+1At+ZirPgT68MbO6h+hfYP1MnmNLWcfCFse5eU96hHUC6StRMNiLPVTJxxSOuTkL6DDMhaedRa4NcD4D912GpX0ts79xzt+e/RnxnDZxEJd9nnEvhDH5DHyffiB9lBvu6XC/X8NZN+edm/jtviPrr8hZTw5RA2e99HkOZ918h4Jbzn1ecTYb/V6K71++n/F7ykz7glcO/cJzgZ6Tz8bF0g85ixpknV9vuK/Dtc/PtjIPPoi6wrkEF5J7ONXljd5PWcFeL82zfZULLzoGzDnwXaYB81RwRhznLEW/yz3lLN/e9QfEp+kfh5Xrxsanrm4rfJr+0bK07fPR+8WnQezIxAz4THjX8Q/c6xWfhsYvdXwa9IYKCp9mFLIs+Flj8Itc/9Ls9aNq/Kz2rIZXfxg2+5HWxtX8yOjOsXFfzY8sydz1I/+6zJ34jStzN37TJPO/4Ef66G3WFL8p37fwI8EFdfxIet4O7GfbjHUxbjjDWpl7z8t9ehykjk4HT53PP5L8uC8jevZPXhM7kHOITbEDxFjrsQP0snFjB230gW6OHUyeiB1M3hw7QNyzyZfkffFlgy/ZTY6mV6HxJafol2F9m7wfA93LML4a/NSyHPaVZzZngKMDP6swkY2e5+/SMr1f90YWzIGT3rgTw/QqrrvP4sz92neRvTj6WnTMedSRl/uiY+5pVvdRcb2Y+yX/bMqsZMgmduQu/l1V7u7e/o1yd33KFvPCGn3KshyafUqc6cT64T7g0veR5qdhF3qy5068ws6K3yJ2duQNjZ1Fn5WBicNHBb+sZGejPG7J9ovsX5SIr4AztKxToY+S6v1wvWJnSV8srdw9kanEV1lX3pn9JZ5xPLE+UtX3aDfa2KxzfI1PE4nMa/ctffev6tMUsnZ9mjfImtm4uT+wsDp72XLHoOw/Fj6CkTfiWO1c3uiTn0lPTPpurcJXstcb7uv4kFERHy58MOnjhp5efuG/9Jml03DvtDzPK76YyB0sM+HCZui5w+ONHqUmNxVhL0vPspQz/dxbjr63MASwZgxnGvyZuMX7UfQQ6Jb1jPTUWbasjSWZGzYX96rG2LXNe7m3q/M5LekHNHLGE31V+iHi4kb2GfKLpOd4jvB7u33Tow99CxD7ga6Q/oy2j0NVv1SfUb77NJC+CX3mIwqnrviOooPc+06Dkk7nvlRLxOldHuhhKFypjHnb4kPiO6DPVMvEI1vSXxX6l/vU+TlPAj1eutw7pvp5sKXoSQaugfUPcF/MvSP3p+U+PtBbVVmjR92Tsg4wN/IeZhi7bj8VThbr94BsqZczkDLoqPL1t8scc69zNOf1oQdaRjaVezfJPUG/V190ev/L52TzPv700Zudf1h+vvwX4gap2CD0wD/QXhj7XvQ4Yf2AHgVH5qZZTn3RywO9JcCKNL3WI5/7o3GMCfsk6ftD+oVzWaTPyL/mHg6QwZH9IGZh94QTnZle48yHBuMVfR178H/RGx89R03/V/SzdZkWTm/4PK7FY9w2/bUC7mMhOp/uzbyJtvSzmAQSO0aPfumfNkRPtUx6UUOXSt6f+9iEhud5lBwJ5+XQjykAd8iMI3Sf4aR2oN/Rv8kzfTm8AXgH3J8iOgzHsW/sfEDrPxNeTM+sV44lJZZpYnqUHAwr0l7Ln/tKdJLt31n0rOyOWoYpJH0yOLaTeMIKsr1QRtJz8i7Oe/dKb0yyS2Pu94Xet76xV1ib6dDmUcjWmt5mGccEZEwz9PHKe39mzMr2I7GTxRwSvZvxe9EryfS4GnC/jB56AtU41s7vmu6F/dIjeCK238yA6zxG2cD22Xqyr1/0N/r6CV9c+vr1j/2i/2Kr3NevkbMBnwo9mnJeifT1kz64Zc5GxH2pbF9K6dX3ZF/KlHxK2zO6ZVi8zKyIpK8f/d7yXPJ+w1XOhumnFD/P0Kj174tE3uCwGv5tte9klaWBvKxhSjdwi7gPH/d/eZLR7srQ7eecSh9z9OF3+jmn0lunc6xzi5ae9OsFe6HKiRuhH6HDiWMGjPB6hM1A8u1YLmYrZ2xUelc398W2HOcSZyPvjVt+XWIJsZyFE5NY9hd8zrZwQZbYy3K/bORShW2wzKS/sfQaNkwQ6FfLYw0a+EZhmW+EvSp6jkmvq4Zew23MW+ljgz1JwbAaIHacOnyEnPezlOcEE3FRY32Gwpo1rM+C5V1ivBV9snMZ7lkHjJnT0KQzaH7EAcdiurCR8PvwLJOChzwGo1548xK3575f3BOI+2N2J6nshbhP7dHtNe4wBVtV5jzqMQbjUaXfes7rrs+XnHVRsLrz7zOeuvGo13Lnbc9J9KV0mC35mg2iRtaY4d8IX6i8ZsF9votsn9hjwb8ZlXt/v4k7X+uLD/t9HFq+pmEh5IyZPAfI9hYs3jS/H/rOdSdelPfcNHtn7A3HJV5oie/FHA/DXBnitTDOgsgwW4RJa8ZU6tUOT7Mi87Wdcs9H7pM64r52A8u1kvEM0FPP5Z+8zDPqmx6oxo6Jbj8a9m+V1Zn1n2R1Ci8q7/t72dD3l+OhvZbM/4nt7Vcw122/67t+PtbF7/A+msvjnh3rvC9zqf81yUr6EqLnVuS5XCXL/IjK7Fman6zjpA8z970Gd7ncA1562ecsOWHxlXvAF/Kvfw9n3BrZablNRL2X6X19ED5pAzO7YEwYvdEBn91lEAk7bcyMA45fCCvI+r8Tu8fODC8HtZ3km04yJ74Qkk2DbyE5KPY3mFPeHto+wlxnwmshMLxRn/3xv74WCm7qj1gL8jfpoBtV14TbV/iFNSG+nekrnBq/5IA+56LPpmG9F7bjl5xz/1fb5zqU2kj2hw+mF7TDV15i/8ycA567T/GVC/6nF2UjM8ctZwC8+RKPt9b/WuRT8YfvpshTtqK07nPn/L2cLfEcK/stTFbsCR17X2NXoV9qv9av35nnJTkX9X78ncKih38f+VzfyPgYpZZdRftS9pXQW3TZxEKxDDX4xmnVjjsslKPtlf0KhpplkASFXum9xYYf7T4BfehNH/6DkSeNY+L0+rfMxpzfgR7sab3XOz3LZZlh18jveJMNn7QHdbZNK+99/QTbhsa+Lbn+aUDrxPSsToT94fhD7pw0vYm5J77d86E2oV/mhnJ/Svks5oOaa+B5LQ0bgVlAhW9WMG6Oog+WPua4zKEp+uQb/3eJ3ITLMc19XrBkXBZQ7j93Ja+HmgVw8UjX5vkOywCMcj5KkuSs1dy3jmCjcz0dLRq5dpaBZ/YchgPIMQ/jX192XF+0ibGUc1cLdlyS5PuuO7HnZp7nc9mxqznLxmG3ezknImeqCLvgeU7ExNmH57yrghNh2AWv4UQMhMNseqpXfJWC0Xi0vVRp7j7aXujoi4nYKO/dzw/lHv3oC2rneM6Z4B7lB+OD1njFUfcJdhviT3m//pyr1+L+483cYtsv3xsU+YBnGG4YT+TfRqXxdPZMyAnBNwHHNXR8aux5EA80ftroaPrY4xnCgeFNSS9oq2N77WJfaXwJ7CFyrlPOYA/hi8rf9tOS34Q6hLcwp+6sXWaWTSJrqhMODRfY+AXVz7Br/oBYj9iCUVvi98L0LZiHScE5e3q9Wz5GhQPDPlnGXMicVzfimDfpGstSy0w8UGIUXbt+Wdfgu2LPkw3Pa3tp+GVpI8eSbasTW3V5MI7tt8wpxKyFS1z/G4fn4/gHI+sfeLKfb/CDnWewrDUwevPvMebcmo1V+JYhh32f66M6us/01+X8esrnIMpcH+gIy1a1fLeMzznkzLXIsUvTgu0D1skC82ZE/keFk9nte4ZlIr47+xo946dV10GNu8ZjV+Gu4SwVbHuZu2b2u6U1kHMyCwapjBd6H3f2TgzJsqUsc7gl+6d8TZj8VGlNWM5TmceGPuql9TDhXuUN9s8rrhkmJurlOFaEMUq4f/VFwcpm+1FaBxj3blKxeXV+tOxNJsdBfQ2kUTdqtHfN8aQn5v2L/vDoJX+4+Lyc5cr9+itzHbnfnl2zoXAVirxHwQh/ihVj5/lkV+JXIS+Qc+1GhhvJDFrPqQHwmF9217F7gpxVXGPlda2961X2NhPPxNBQc/303qbYv1uenId9u9nbeNGiYf+e1/CyPUsrfkaJQfOC/1HLAfBe/1Ws7emxztomm3k3eS1ru8Ib47xFe3BZ9hn4/KblbyNOellhDhodatg+yGUb/g1yR5HrE+wqrO1i/3uJmMHU9RPSIeZGzU+IWZ80cwaFe27y9jYfYmLXiY1HpZW9apVF1RCPsjkBjkeBTdPIoarxX2uMxwp70OQEJDZj9AyvS/jIds8XMS+1zpRcunHeneiZ3G8pYiD5PvKpGMgzfO0KD9ZlbA+EiQ1fkK9VGNu+6LuOZ2I54I14BWN7ahnbWQNjO3iGsd1y9DPqxfln5hqB1WDi95wbwX1R85VFjp4S/8SeTRZ+RS/fi+Q87rupcMNrrD+HPWXj4hIHyKKCj1llbLf/XpyCayuMzVkeB+Lz+lwvvbA+COeWiziZY4uYqVvWlxKfHuMcdEyfKXWSNf3K9Z49R79OTXw716/YsxhOSa5fmXMle9LG2FGuX83aY/1aufYV2Wkc4zvm9tDkGV6nWznPUNatqIkW2+ELV7PIM+R8s5yxK3yTfJ9iOdAm9xc1M7TLOds8rrc0tnRq4ik5b6ymQyt7sN1f4Ka1pRZgZOdxwXktv5Z4dT6/Dc/PxHCMfsjzbkPEqRrzOYaXR/7u8O/pW8R3vEEjU7fH/EzmdhT6lmQ0ysehyMEyN97sb6aluN/TbOLEK+vW3Oes52CLeH8ew7A1FaXrZeYfYkO+6OA4NHVfgcTRyvpcGIWyZ3FihUVMs55bDcq51fKcreR7833mG/Wt16Rvcw73a/QtfNG00Lf0ncIn8h+HnAPctbUGkrN5JWP7EI1r+hYxB9/ah0Lf1n3/XN8W+jM/iz9kJtzInmey87TMhc45lZNAfFJmuxwlzyV8VIxxlHbKft0LnMqB1A2EkHsRm83Z7WnhD4gPVeYQI57B59Er16vceNYFX1fnmlzgK/1Z0QUL15+NCt81r2kZQf+Ymhbab0uNuBNvNnPR8JQjZgJLTUuEWqqCaV31Z1k3NtS0HLiOrxvV9CnqkLD/bax1eTbX2jN6oEM6pFHXZhfV3Pld0i5ieGxzmQtl8tt53N3mOGvcbNal00rcferau/aFm+vGuZGynm2B5yg1IhJHcveTlbxHYJl+eR6y0BslH/gVeY+6b0vvzRnwjl/Leyf2aydeg18bGL9WePccjwTzzPq1E+vXpg1+rf+MX+sVenYSmtyjxyzRcd/GzZk3b2N7ua9ajrG7eVtbm2NrXcoxt0VjfD2P28jZQ/IxcOa02a8NL4p9u7kWp3Y/NZS9TN2vzeMNhptZ5mU7+bco5PNyxb6nElez8X+pBZKYwSiT+sJKTEzO02I8jqZuHvld1h9DnG+WM5KIdYRFHDWPcWOfYbikPaO/poiXyPvHS2vv2X5Dpw3B4ErdOGZsdL5bT+PYtHLsuC3cORs7zuM8HC/gOhFr28QvOErseBSaNe34HT3Edzm/RusulLXENUlsz61fwDnNhVMblV8zcbIx6zJ7Xrk1QL3vosnfgo8ct4fdqZX/Uc4UJLm/NWj2e5+rKbT7h8JHNOx6tnOia7NaPEHyDt7LeQdwGMFMi62MvaGJV5HtERnf9VITywPL0Hftp9TuLo8mt+mB3Wh1rMSNpshVGtbx0kcMrRQ7MXUktdiB8QN4z5DHIDl/4w85fo+10KvHtNKqDzDKJM5o5FVnse/y2oOSD9Cr2Pq+OW89esEHkFgB2+08n9ZvyfMlqd0D1z5bxlTk1zV1DyaGI2s1Z4Dva99Z9gJcc0k2PhQefMnHkjNEYCBKXMaZ0zbv0TkOJafMzFnDI6/p3dxn5V5nNb3rm5xtxnW4Ru/ynvplveubPFgofbWSmt41P8M+mNpP8gPv+q/1a1Fz4pvvRDoxlhoc0olyHjRijuywWecGxb62jxh9dvF8jZzPjOQ8j9GcXx+IL3vIz9+Lvg6QDzN+btvqa5yfikwOQ2rmn8xhOPuzPIfh1ksUOQyz33hTHk98A+NvoY9BshO7F1V0sJOrEJuXzymO49xxXRWeK8Df1eN8vKco7xFqercSDxe9GxQx9ukxr+XOksDWckfltdTEaM9cf9HYw5D8eONvTo6VWu68Rr3we3NdUo4juPGbWhzXfc1+tpPnmKQ2tktziXNFYitM7cl4GpT1c6n2pKSfjb2U2hO7Z8z4nGVz7Uk1ftstauZLeQfmHdu4WP8pHY26EtHR5OeZOvUWvovM3V44qOQdwDc1uaudnBfuBfX8QqGXWcctynqZfIl2oZenqeyhwLXN9y8mVzg5Soyrw1zr4bhnahUnLWt/pX+D1HP38z0P5+Ztfq+eZ5DeEdjLtSTmUOiTqF7PnaGeV3wNxARI/5tYKHr/OGdPeL+BOgjxz5FvNXk65od2bG7RnHNZHjBHnZwidAzOlKaOTsZ599CedeV+FU/l3vJYFfaJeb2l3X8FUufbFN8wurLLvVOqvnCK/VbuC3eXtVq0PJfZmMvpyN7X1ILmuTfkci33ucs5J2NDO0V+mXx10ofg2fsyniU7WqkZ6Mk5nm4/KNXOoocS9zxlPZ65Nbyix938WydDHVApBsh+t8SyKv7KsZSDc2sF/lqsWPK/7CtUz+XYddmz9bOiY7rLF2qC7NkcrslPazVB9D7Ex15TE1STs/GlUaNsbW1R0zNF74h2rtfves/70zhTcjexcWT7fFKzLOvYniMRf5rn0KvjyKXcZ2Md4aJUq+xVcnV5/VXTGR6z1t18XTjM/Wu3nlDqr/Ia8lq9rMy/vJ4CsbGMa99sbUwply0xub6tqYVfcWTbLj0xnDkeY+17r4nJcc8wjsn1v1H+I48jv/GMGWS7LNal5HQzrM3yGTPnO5fncKUewOTpzyvz94450mZ+YB/Efomf58nqfonX4Je0BpdNOZDoW87dIhZXr/FOZa9kZJtW5y3XDbq5nAPHe2i/ZveKHLsqywF7xWP/t83iIgv+z+ffPtxef0qSP7veguvjeEwm6MmwQ80O+9JZnNmz/LR+AvobqWPmHmKsJ1Kumc2mocRomDvvmfOVbe45dCn9IvhsvpwHwHMe8tpC6e2TyfnlvukVwOeV0kj6sPF8kB4wPb/GfE/5LF5g9viIU7VMryT0y2qxzyvn8GG7TB3utCXjjLOXo4x9MI7RTLxhwZE/cAw+hX8k9ZIDtvPosYHz1iSf7hLzCmexcE67dZH39JlWrkuMk95raxRClg/OlZF/PkS9wnjSKvJQSUvyMZO8HxX47LwvMox3PjdtepXQe1GXyb1VuMdC3hNvyecv+TMzji35vG9m3bA0MTDUuSIetkSt0dHW0A/HU3PmnOZhxn0GMusfyH7Y1K530deOz1vDr0RNO9ZGyPlh8nvQ0xfni50embA5qJnE5wR8doKeA7mMoZw9lt5k0tcbZ5WRI0qL2HXSHjg+/SDPoeAs7dTs+yf2vDF0M9nLUdv0aoTP5nOMh3u2LH3kJfhMHXoCQSfLvoX38ejVUvSy6JmeRcUcG8IHNHFmmpctqXGSM+Tw4zlHht62XF+Ovg7LlHtLcWyG9mlyD+5Dxz3+pF9pu3Ld5CaWqT0nP+R74dwajc1dwj72IMtj68FAeia2ipg/1ml04NoVniPYh0zLc4R7uUysn3tk/5b+TvJ7kfTUGPftWSmS14T3/BHr+xH34xtwr+eO3ePKOu7iLITxI/N1h+efYF+DtQyf0Y+471SCurfA9I7Mn5/nPs9P21cX9ano3WieP+P9u1kXXItmnj+29WWZyLPvF3XOiPdEnpzR6uylz2QMfYF1Dl3HPg/3kukif8Ln4TH3jm5uEbXpg0zy3qRzOX4udZJ93v+jJtbILBxwXqNj4gOluXzg3oHnfNaVPlvq/BH74xoY5Dm6MXz9RObwCM9jzjqjnwjiTqMjrckjx19ZH6C/KWI0fH660M2oebxDL62Y878D9pemiejl2NRkdHycK4mk70EqteMVndydBJwXMedp7ZizPuYaaYw39D/6sUylvrxbrCMzH7j/Oa+jbtyOipim6LnLgOsxh3J2zOphX3LBHOuHHg4l/pVgToUmnsa9ytDHv3y9yFPbvZqspVEqvdIxZn30xvPMmAW2/wXNI3Ouo+dF3AePZHx5QD9FjmEhX57r8aLfhB+xnp9KLy9Zq62BPfvadX9v799vSQyf/dKWrOXecVDYvAP3SCJ9cME2BnWlkW9yyuhjGUrvNtb3pl/CBOeJkUMMTV8GkkFHeixJ34/20J7FG/M8MbYdPVi4Nw/kT+NGOlHWUwv5Kxpf2k+OSvYYvTIG2KdxnENyhIPKdV7/OFdj+wKLraQxGoW29sbEb3E2h88ODllnYv3CtvSwnwpMjwpzHXNy2pYaPdR95H3XPJZLJj0EMc8Re6v5EWLzAz5LLr4u+S99lhHOg9Cz2VhNyPbs8kMXvQ7R0xuxFeQVeXxxbiKLE8wN7iPBcZwl/zzo8nmLLMp77ESmV1feEw4+pI+YLXoHiB4yuUHY42wpPTHG+NwE++uW5Hxi6dlGc3rAPfhxHi+2+VSsI/g4vpzDEf8B/aXgnw85hzJJTb/ZhuvG5nCd2jR/TsgBZ/alvz18ZORBIrb3EeKkHHPAHBrBP4PvAPtKMuqYHNzU43xJtxOYuPqO7BlyodAFyRC5MO4f1fdL+oVjIezzm71TfOQYKeIsqMOTmrkW5x/JN+ZcKu0LcEbD9KJBnOQoNdkxzk77F/YcDfa8C47hQ9em4l9NOG6XswBwRpXrCdBnjNbsQjgxB2a/fE5AscH/fRVIdnD6zrL8LM6pARzrt99ZkNZ3Qcee1dGxivFRjI9ifBTjoxgfxfgoxkcxPorxUYyPYnwU46MYH8X4KMZHMT6K8VGMj2J8FOOjGB/F+CjGRzE+ivFRjI9ifBTjoxgfxfjk+kUxPorxUYyPYnwU46MYn0gxPorxUYyPYnwU46MYH8X4KMZHMT6K8VGMj2J8FOOjGB/F+CjGRzE+ivFRjI9ifBTjoxgfxfjkz60YH8X4KMZHMT6uLVKMj2J8FOOjGB/F+CjGRzE+ivEpYniK8VGMj2J8FOOjGB/F+CjGRzE+ivFRjI9ifBTjoxifSDE+ivFRjI9ifBTjoxgfxfgoxkcxPorxUYzPTjE+ivFRjI9ifBTjoxgfxfi8DuPjn9UwPqftnwDjE9YwPpt1slmsk1/aJ7P7B/ry66vdA8vgZEVP8+FqS68SvGJqT9u7XyTb2X6xWdf4P/T5i4cdyD+H28V+fvkwi/Gbw3aGG97u7+lRuy16udtvN8v5+Wa12fI7/Y8fffon/80fRkDtrzMWQeiVBiJ8Xx+IlufVhyH4ZsNw0kBTOvmfxw3kvKUP2RQ/1gditUkW6/rlxS/hh9N37979EnZrQ7PdPK6vwWDqei8Pz2y1SNb0ejW/wX1vFquVM1Y3NzftOG4axeuTq5Pw5CthsFrlMTv162N22jBk4TcbstNnhmy2eridvXHI3v/XDlkDtuz7DtlZbcged/Ptji7Fq/ls/evjQ31I6JOu5vPkZvePUW/hSUW9nfxo9dby6ovlZn6gC+vN9XzHj8Z3uZrTfx4fyLLQRKcHWeO/i/V+DhODS9XR2W9wE77VbBtjGOL943b+9rH6GuYleFlVtdoN8j/7dvKvz3wR2sdLWHDSLCLw7Xx2/ethSxLCYDzuIcTV5jAneXv/z+Dj5f9bEyzJZP/cbF9v1vOKAjKXrIqKSdL0Af4HSHgRz1Yd84v7xfX16qkhK2vD7WYvLojfPfO+kvbyK6N42jCKT7hr324htVq1gbQqbHY9e9g3rBB6MAzfLt4uHvb/HC0WnIYl+b8P6vK33ut3kn37Sdnv5zuslbr0ZZXtNjf7w+zvqKXvLHw/LCa2lX/rlfL3v5n8m5xkRY4qclSRo4ocVeSoIkcVOarIUUWOKnJUkaOKHFXkqCJHFTmqyFFFjipyVJGjihxV5KgiRxU5qshRRY5KaaIiR5/wKRU5WrKxihxV5KgiRxU5qsjRnSJHFTmqyFFFjtaPfStyVJGjihxV5KgiR8ttsBU5qshRRY4qclSRo4ocVeSoIkcVOarIUUWOKnJUkaOKHFXkqCJHLQJEkaOKHFXkqCJHFTmqyFFFjipyVJGjihxV5KgiR208Q5GjkSJHFTmqyFHr1ypyVJGjO0WOKnJUkaOKHFXkqCJHLxQ5qshRRY4qclSRo4ocVeSoIkcVOVqMqyJHFTmqyNGdIkcVOarIUUWOKnJUkaOKHFXk6MV/OXL0JKgjR8MfjxxttZrIicrxUY6PcnyU46McH+X4KMdHOT7K8VGOj3J8lOOjHB/l+CjHRzk+yvFRjo9yfJTjoxwf5fgox0c5PsrxkXyfcnye8CmV41OyscrxUY6PcnyU46Mcn51yfJTjoxwf5fjUz1Iox0c5PsrxUY6PcnzKveWU46McH+X4KMdHOT7K8VGOj3J8lOOjHB/l+CjHRzk+yvFRjo9yfGxfXeX4KMdHOT7K8VGOj3J8lOOjHB/l+CjHRzk+yvGx8Qzl+ETK8VGOj3J8rF+rHB/l+OyU46McH+X4KMdHOT7K8blQjo9yfJTjoxwf5fgox0c5PsrxUY5PMa7K8VGOj3J8dsrxUY6PcnyU46McH+X4KMdHOT4X//s4Pu9bPwPH532N43OzWM/wxl26jul/6L6rx91+y2SeeDvbx7d11A991OJhB8jP4Xaxn18+zGL85rCdPdC12/09PVW39XVE2T71SnJseSd1QbY8ry7G4JuJse29jEOar6872+3mQD+tN2vI6nq2uwUIiSXjCAnXP8/2+/l2zVfank9XaQw2y/kf5juSgD5sN4/ra76B95xo59fJ/FnBOnILG8Rmr23nq9l+8WVeunmTLM0nfN4s6EmKcTsJK+MWVsZjt3ncxnPztmJIanc6eV+dAdU77WfbZL6v3YkHN//if2e8Ww3jffI/jxsS2YeHzWG+PSt+plcr/O/Vll4leLXaJIt1/TJNgPDDu3fvfgm7tdlTHusXVtlstUgwdVbzG9z3ZrFanW9Wmy3fyr+5uWnHcT6jnN9cn1ydhCdfSeO1yoP0vgFbdvrMbPsGi7StzDJllimzTJllyixTZpkyy5RZpswyZZZ1lFmmzDJllimzTJllyixTZpkyy5RZpswyZZYps0yZZcosU2aZ8yzKLFNmmTLLlFmmzDJllimzTJllyixTZpkyy5RZpswyZZYps0yZZcosU2ZZpMwyZZYps0yZZcosU2aZMsuUWabMMmWWKbMssb0OlVmmzDJllimzTJllyixTZpkyy5RZpswyZZY17sF2yixTZpkyy5RZpswyt6ZFmWXKLFNmmTLLlFmmzDJllimzTJllyixTZpkyy5RZpswyZZb1lVmmzDJllimzTJllyixTZpkyy5RZpswyZZbJmldmmTLLlFm2U2aZMsuUWfY2ZtnpT8Asa4c1js9uP3/49Sr9Ff9Lv3l8uJ7t5wwv+4DbrffzZDvbLzbrH0ou80+rBKwGcba8sAGK9Axt628K86QmzPHscfu4M4wqb76P331TGlWIf3F9s9471+WfJkrVCf/zbWByZw2UqkaWXPvbTe/T2ojsb+e7OSP5aILf7/jx+E5XfPX2EXC0682BpNypjRVJYl8ekLJEDYzOHRZzqTJwkOoinq065vL94vp69dTKeSWb7i+M1Mn7dyft8mC164PVPmsYrG+oi+r8xD0vn8Uv4YfQ81oW5+b9yurIMuFkjbmMuP8tKyx837DCTr7vCjurDdr1Ync/W+9Xi3VCv9jcfINVFJMM59ufYB1VxqOBnnn2vU2638TPtGtjS5+yeQNOEUvw9L8Gp+i9wnf4vjxF/zkI5mz1cDt746C9/68dtHyi/7hBq0Mw1/MDXfh4Sf+5JwnvScJsqiojc1jQE9Nj0lNiWB7m+LufUktuN3tx9v3u2VfSmiee9+7krLICgwZLdtZ655/VB/TboYd9v2EVKtVUqaZKNVWqqVJNlWqqVFOlmirVVKmmSjVVqqlSTZVqqlRTpZoq1VSppko1VaqpUk2VaqpUU6WaKtVUqh+VavqET6lU05KNVaqpUk2VaqpUU6Wa7pRqqlRTpZoq1bR+slyppko1VaqpUk2ValrutK1UU6WaKtVUqaZKNVWqqVJNlWqqVFOlmirVVKmmSjVVqqlSTZVqaikjSjVVqqlSTZVqqlRTpZoq1VSppko1VaqpUk2VamrjGUo1jZRqqlRTpZpav1appko13SnVVKmmSjVVqqlSTZVqeqFUU6WaKtVUqaZKNVWqqVJNlWqqVNNiXJVqqlRTpZrulGqqVFOlmirVVKmmSjVVqqlSTS/+66mm7SrVtOWd/QRYUz9QkI+CfBTkoyAfBfkoyEdBPgryUZCPgnw6CvJRkI+CfBTkoyAfBfkoyEdBPgryUZCPgnwU5KMgHwX5KMjHeRYF+SjIR0E+CvJRkI+CfBTkoyAfBfkoyEdBPgryUZCPgnwU5KMgHwX5KMgnUpCPgnwU5KMgHwX5KMhHQT4K8lGQj4J8FOST2AZgCvJRkI+CfBTkoyAfBfkoyEdBPgryUZCPgnwa92A7BfkoyEdBPgryUZCPW9OiIB8F+SjIR0E+CvJRkI+CfBTkoyAfBfkoyEdBPgryUZCPgnz6CvJRkI+CfBTkoyAfBfkoyEdBPgryUZCPgnxkzSvIR0E+CvLZKchHQT4K8nkbyKcV/gwgn7AB5HPyP48b+uQPD5vDfHtW/EyvVvjfqy29SvBqtUkW6/rl+9Uv4Yd37979EnZrWKDt5nF9Df5P16O/PNwu9vPLh1mM3x62swe6drun9/vdFphBq0Wypter+Q3ue7NYrc43q82Wb+Xf3Ny045iu7/bbzXLu/Ob65OokPPk6Yxe2g3enVQjTaX3s7CV34MJvN3AnSmBSApMSmJTApAQmJTApgUkJTEpgUgJTRwlMSmBSApMSmJTApAQmJTApgUkJTEpgUgKTEpiUwKQEJiUwOc+iBCYlMCmBSQlMSmBSApMSmJTApAQmJTApgUkJTEpgUgKTEpiUwKQEJiUwRUpgUgKTEpiUwKQEJiUwKYFJCUxKYFICkxKYEtu5TQlMSmBSApMSmJTApAQmJTApgUkJTEpgUgJT4x5spwQmJTApgUkJTEpgcmtalMCkBCYlMCmBSQlMSmBSApMSmJTApAQmJTApgUkJTEpgUgJTXwlMSmBSApMSmJTApAQmJTApgUkJTEpgUgKTrHklMCmBSQlMOyUwKYFJCUyvoPiE79+dtCsUn7OfgcB0+gyB6e5xtZg9B2Da3T+8/+9ELLX8H45Yeq+IJUUsKWJJEUuKWFLEkiKWFLGkiCVFLHUUsaSIJUUsKWJJEUuKWFLEkiKWFLGkiCVFLCliSRFLilhSxJLzLIpYUsSSIpYUsaSIJUUsKWJJEUuKWFLEkiKWFLGkiCVFLCliSRFLilhSxFKkiCVFLCliSRFLilhSxJIilhSxpIglRSwpYimxrdkUsaSIJUUsKWJJEUuKWFLEkiKWFLGkiCVFLDXuwXaKWFLEkiKWFLGkiCW3pkURS4pYUsSSIpYUsaSIJUUsKWJJEUuKWFLEkiKWFLGkiCVFLPUVsaSIJUUsKWJJEUuKWFLEkiKWFLGkiCVFLMmaV8SSIpYUsbRTxJIilhSx9DbEUiv8roil//nj9nZ9fd6fp7+t/fX78Xzypf9ruwHj83H1uNtvmcSzu/6lTTemT/94NZ8nNzt68e7du2eoSq2XqUpVjFKIf3F9s9471+WfJrzSCf/zdQbGPw1Ko3LWMCit9kl9SNrfakiC2pDcLNaz1SJbrJM65IrZSW3vfpFsZ/vFZl0bGvrExcNu/vKw1MT88WNpAP4wAml/JcG3wirUKqxL3mugWgXfSvJhTfLb+a/x7GrFkvc2N3Xxx5v7h8c9rRUvxqqZb3dvH4CvoWZOvPJsbjfN5m9ECvv39rfbztnmc9e/f8geD5u7QRT92qrJ9PPtbAeBtZ4Eht2s5sfOdrs5kFDm62vzshuvZrvdIi4Lrcxzc1XL9fxm9sjDRUvjejEvlEvxG3mE+XUyLwm8NgZ1gTsCDZ+R53a+omX5pXz7JiGbT/i8WdAH5+NJC6CySCrjtNs8buO5eVcxVC/eKKxalP1sm8z3tRvxmOdf++3ToG5n7DR4mhun0+DJ0Tv9StPg/dn3nQb+k9PAZy+jhnC83Wzx+Nebw3q/uKc/PJndQ22ur3YP+cC9Fe+43ezFZvrdMy+/W03bvmoi2DcEFQV8cvKu3WDXrK0rOXntd+E30sJ1juZ2l67jusCv8F3+7P9Wt2K0OC7NjzQmt5tkQ05Jr7haWYLF31xsNg9G4Hfz/T69XGS4yexxvykPx/y42P/HeT3Frd6F5qfu0dyZf0gbVjq5LK2rWWvebnJmPO+k1/n4F9Y6fXteVM9I1Xhqsmae+buwecq8Win8raGvu5N0m4ft5m4e7+vOyg915P/WyssBqDnB1mvwfU4alPTX8OSfHvfvI/rXomj/lojD9k8n4jqGdr3Z3s/wvs3D/KktUeFMrDfrOe+idre56B0x4/rn2Z78+jVfgZ1q2g+Vdd9P705Udgmt9lvdypPT8IU7fWOH4uxJhyKoDbv6lbWJ4J29qwyg92bXsn6vrzcZ6MftBpjv4s9JJd5Gm+s5/uL/Bw==</diagram></mxfile>
\ No newline at end of file
doc.zih.tu-dresden.de/docs/misc/migration2023.png 0 → 100644
+ 0
− 0
View file @ ddf9cbf4
doc.zih.tu-dresden.de/docs/misc/migration2023.png

205 KiB

doc.zih.tu-dresden.de/docs/software/performance_engineering_overview.md
+ 0
− 14
View file @ ddf9cbf4
......@@ -44,7 +44,6 @@ software performance engineering or application performance engineering within s
| [Perf](#perf-tools) | Produce and visualize [profile](#profile) | easy | medium | low | (no)[^2] |
| [PIKA](#pika) | Show performance [profile](#profile) and [trace](#trace) | very easy | low | very low | no |
| [Score-P](#score-p) | Create performance [trace](#trace) | complex | high | variable | yes |
| [Slurm](#slurm-profiler) | Produce and visualize simple [trace](#trace)| easy | low | low | no |
| [Vampir](#vampir) | Visualize performance [trace](#trace) | complex | high | n.a. | n.a. |
[^2]: Re-compilation is not required. Yet, to obtain more details it is recommended to re-compile with the `-g` compiler option, which adds debugging information to the executable of an application.
......@@ -248,19 +247,6 @@ Many raw data sources are supported by Score-P.
It requires some time, training, and practice to fully benefit from the tool's features.
See [Score-P](scorep.md) for further details.
### Slurm Profiler
!!! hint "Easy to use performance visualization of entire batch jobs"
The [Slurm Profiler](../jobs_and_resources/slurm_profiling.md) gathers performance data from every
task/node of a given [batch job](../jobs_and_resources/slurm.md).
It records a coarse-grained [trace](#trace) for subsequent analysis.
[Instrumentation](#instrumentation) of the applications under test is not needed.
The data analysis of the given set of system metrics needs to be initiated by the user with a
command line interface.
The resulting performance metrics are accessible in a simple graphical front-end that provides
time/performance graphs.
### Vampir
!!! hint "Complex and powerful performance data visualization of parallel applications"
......
doc.zih.tu-dresden.de/mkdocs.yml
+ 6
− 2
View file @ ddf9cbf4
......@@ -93,7 +93,6 @@ nav:
- Produce Performance Overview with Perf: software/perf_tools.md
- Track Slurm Jobs with PIKA: software/pika.md
- Record Course of Events with Score-P: software/scorep.md
- Profile Jobs with Slurm: jobs_and_resources/slurm_profiling.md
- Study Course of Events with Vampir: software/vampir.md
- Measure Energy Consumption: software/energy_measurement.md
- Compare System Performance with SPEChpc: software/spec.md
......@@ -102,6 +101,10 @@ nav:
- Overview: jobs_and_resources/overview.md
- HPC Resources:
- Overview: jobs_and_resources/hardware_overview.md
- New Systems 2023:
- Architectural Re-Design 2023: jobs_and_resources/architecture_2023.md
- Overview 2023: jobs_and_resources/hardware_overview_2023.md
- Migration 2023: jobs_and_resources/migration_2023.md
- AMD Rome Nodes: jobs_and_resources/rome_nodes.md
- NVMe Storage: jobs_and_resources/nvme_storage.md
- Alpha Centauri: jobs_and_resources/alpha_centauri.md
......@@ -113,7 +116,6 @@ nav:
- Partitions and Limits: jobs_and_resources/partitions_and_limits.md
- Slurm Job File Generator: jobs_and_resources/slurm_generator.md
- Checkpoint/Restart: jobs_and_resources/checkpoint_restart.md
- Job Profiling: jobs_and_resources/slurm_profiling.md
- Binding and Distribution of Tasks: jobs_and_resources/binding_and_distribution_of_tasks.md
- User Support: support/support.md
- Archive:
......@@ -126,7 +128,9 @@ nav:
- Platform LSF: archive/platform_lsf.md
- BeeGFS Filesystem on Demand: archive/beegfs_on_demand.md
- Jupyter Installation: archive/install_jupyter.md
- Profile Jobs with Slurm: archive/slurm_profiling.md
- Switched-Off Systems:
- Overview 2022: archive/hardware_overview_2022.md
- Overview: archive/systems_switched_off.md
- Migration From Deimos to Atlas: archive/migrate_to_atlas.md
- System Altix: archive/system_altix.md
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
Nutzungsbedingungen | Datenschutzerklärung | Barrierefreiheitserklärung