Skip to content
Snippets Groups Projects
Commit 25c5abf4 authored by Jan Siwiec's avatar Jan Siwiec
Browse files

Update 4 files

- /content/docs/general/tools/cli-client-tools.mdx
- /content/docs/software/compilers/karolina-compilation.mdx
- /content/docs/software/debuggers/score-p.mdx
- /content/docs/software/intel/intel-mkl.mdx
parent 164a411a
No related branches found
Tags
No related merge requests found
Pipeline #44201 passed with warnings
......@@ -26,7 +26,7 @@ Options:
### Example Output of 'it4ifree'
```code
```console
╭─────────────┬──────────────┬───────────────┬──────────────────────────┬────────────┬───────┬──────────────╮
│ Project PID ┆ Resource ┆ Resource Type ┆ Validity Period ┆ Allocation ┆ Usage ┆ Time left │
╞═════════════╪══════════════╪═══════════════╪══════════════════════════╪════════════╪═══════╪══════════════╡
......@@ -38,7 +38,7 @@ Options:
### Example Output of 'it4ifree -u -s all'
```code
```console
╭───────────────────┬──────────────┬───────────────┬──────────────────────────┬────────────┬───────────────┬────────────┬──────────────╮
│ Project PID ┆ Resource ┆ Resource Type ┆ Validity Period ┆ Allocation ┆ User / Total ┆ Usage ┆ Time left │
╞═══════════════════╪══════════════╪═══════════════╪══════════════════════════╪════════════╪═══════════════╪════════════╪══════════════╡
......@@ -64,7 +64,7 @@ The command shows IT4I messages of the day.
Usage: `it4imotd [OPTIONS]`
```code
```console
Options:
-w, --width <WIDTH> [default: 78]
-c, --category <CATEGORY> [possible values: public-service-announcement, service-recovered-up, critical-service-down, service-hard-down, auxiliry-service-down, planned-outage, service-degraded, important, notice]
......@@ -72,7 +72,7 @@ Options:
-V, --version Print version
```
```code
```console
Critical service down: Unplanned Power Outage
Posted: 2024-09-13 12:35:18
Outage: 2024-12-17 14:27:43 to 2025-12-17 18:27:43
......@@ -92,7 +92,7 @@ Project quotas are active during the lifetime of a project.
Usage: `it4ifsusage [OPTIONS]`
```code
```console
Options:
-s, --status <STATUS> [default: active] [possible values: active, expired, all]
-j, --json Output to json instead of a table
......@@ -100,7 +100,7 @@ Options:
-V, --version Print version
```
```code
```console
╭────────────┬───────────────┬─────────────┬────────────┬─────────────┬──────────────┬───────────────┬────────────┬────────────────────────────╮
│ Quota Type ┆ Cluster / PID ┆ File System ┆ Space Used ┆ Space Limit ┆ Entries Used ┆ Entries Limit ┆ Expiration ┆ Last Update │
╞════════════╪═══════════════╪═════════════╪════════════╪═════════════╪══════════════╪═══════════════╪════════════╪════════════════════════════╡
......@@ -118,7 +118,7 @@ Retrieves dedicated time entries, optionally filtered by cluster name/status.
Usage: `it4idedicatedtime [OPTIONS]`
```code
```console
Options:
-s, --status <STATUS> [default: active] [possible values: active, planned]
-c, --cluster <CLUSTER> [default: all] [possible values: all, barbora, karolina, comp-sys, dgx]
......@@ -127,7 +127,7 @@ Options:
-V, --version Print version
```
```code
```console
╭─────────┬─────────────────────┬─────────────────────┬─────────────────────╮
│ Cluster ┆ Start ┆ End ┆ Last Update │
╞═════════╪═════════════════════╪═════════════════════╪═════════════════════╡
......
......@@ -30,7 +30,7 @@ To combine the optimizations for the general CPU code and have the most efficien
For the compilation as well for the runtime of compiled code use:
```code
```console
ml PrgEnv-intel
ml cray-pmi/6.1.14
......@@ -43,13 +43,13 @@ There are usually two standard situation how to compile and run the code
To compile the code against the LibSci, without MPI, but still enabling OpenMP run over multiple cores use:
```code
```console
icx -qopenmp -L$CRAY_LIBSCI_PREFIX_DIR/lib -I$CRAY_LIBSCI_PREFIX_DIR/include -o BINARY.x SOURCE_CODE.c -lsci_intel_mp
```
To run the resulting binary use:
```code
```console
OMP_NUM_THREADS=128 OMP_PROC_BIND=true BINARY.x
```
......@@ -59,13 +59,13 @@ This enables effective run over all 128 cores available on a single Karlina comp
To compile the code against the LibSci, with MPI, use:
```code
```console
mpiicx -qopenmp -L$CRAY_LIBSCI_PREFIX_DIR/lib -I$CRAY_LIBSCI_PREFIX_DIR/include -o BINARY.x SOURCE_CODE.c -lsci_intel_mp -lsci_intel_mpi_mp
```
To run the resulting binary use:
```code
```console
OMP_NUM_THREADS=64 OMP_PROC_BIND=true mpirun -n 2 ${HOME}/BINARY.x
```
......@@ -73,13 +73,13 @@ This example runs the BINARY.x, placed in `${HOME}` as 2 MPI processes, each usi
Another example would be to run a job on 2 full nodes, utilizing 128 cores on each (so 256 cores in total) and letting the LibSci efficiently placing the BLAS routines across the allocated CPU sockets:
```code
```console
OMP_NUM_THREADS=128 OMP_PROC_BIND=true mpirun -n 2 ${HOME}/BINARY.x
```
This assumes you have allocated 2 full nodes on Karolina using SLURM's directives, e. g. in a submission script:
```code
```console
#SBATCH --nodes 2
#SBATCH --ntasks-per-node 128
```
......
......@@ -65,7 +65,7 @@ void foo()
and Fortran:
```fortran
```cpp
#include "scorep/SCOREP_User.inc"
subroutine foo
SCOREP_USER_REGION_DEFINE( my_region_handle )
......@@ -102,7 +102,7 @@ void foo(...)
and in Fortran:
```fortran
```cpp
subroutine foo(...)
!declarations
!POMP$ INST BEGIN(foo)
......
......@@ -101,20 +101,20 @@ Threading on Karolina AMD processors requires [TBB][2].
Example 1
```code
```console
icpc -O2 -qopenmp -DMKL_ILP64 -I"${MKLROOT}/include" source.cpp -o program.x -L${MKLROOT}/lib/intel64 -lmkl_intel_ilp64 -lmkl_tbb_thread -lmkl_core -ltbb -lstdc++ -lp
thread -lm -ldl
```
Example 2
```code
```console
icpc -qopenmp mkltest.cpp -o mkltest.x -lmkl_tbb_thread -ltbb -mkl
```
**Intel/GNU compilator**
```code
```console
[Monday 10:23 AM] Krupcik Lukas
g++ -fopenmp mkl_test.cpp -o test -lmkl_tbb_thread -lmkl_core -lmkl_intel_ilp64 -ltbb
```
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment