|
|
|
[[_TOC_]]
|
|
|
|
|
|
# ELPA Library
|
|
# ELPA Library
|
|
For static calculations, it is recommended to use [ELPA](https://elpa.mpcdf.mpg.de/) Library, which has better performance than ScaLapack. In particular, ELPA allows for the utilization of GPUs which provide a significant boost for calculations. In order to activate ELPA lib in [predefines.h](https://gitlab.fizyka.pw.edu.pl/gabrielw/wslda/-/tree/public/st-myproject-template/predefines.h) set:
|
|
For static calculations, it is recommended to use [ELPA](https://elpa.mpcdf.mpg.de/) Library, which has better performance than ScaLapack. In particular, ELPA allows for the utilization of GPUs which provide a significant boost for calculations. In order to activate ELPA lib in [predefines.h](https://gitlab.fizyka.pw.edu.pl/gabrielw/wslda/-/tree/public/st-myproject-template/predefines.h) set:
|
|
```c
|
|
```c
|
... | @@ -45,6 +47,7 @@ It is recommended to use `PZHEEVR`. This engine takes advantage from the fact th |
... | @@ -45,6 +47,7 @@ It is recommended to use `PZHEEVR`. This engine takes advantage from the fact th |
|
|
|
|
|
# Benchmarks & Scalings
|
|
# Benchmarks & Scalings
|
|
All tests correspond to the extraction of **all** eigenvectors.
|
|
All tests correspond to the extraction of **all** eigenvectors.
|
|
|
|
## Table
|
|
|
|
|
|
| matrix size | p | q | mb | nb | prec. | routine | system | time [sec] | cost |
|
|
| matrix size | p | q | mb | nb | prec. | routine | system | time [sec] | cost |
|
|
| ------------|---|---|----|----|--------|---------|--------|------------|------|
|
|
| ------------|---|---|----|----|--------|---------|--------|------------|------|
|
... | @@ -69,6 +72,6 @@ All tests correspond to the extraction of **all** eigenvectors. |
... | @@ -69,6 +72,6 @@ All tests correspond to the extraction of **all** eigenvectors. |
|
|
|
|
|
## Plots
|
|
## Plots
|
|
These scalings are derived empirically: points correspond to **real** measurement on target system, while line shows a fit of ideal scaling for level-3 rutines ($`\sim N^3`$)
|
|
These scalings are derived empirically: points correspond to **real** measurement on target system, while line shows a fit of ideal scaling for level-3 rutines ($`\sim N^3`$)
|
|
### Summit
|
|
### [Summit](https://docs.olcf.ornl.gov/systems/summit_user_guide.html)
|
|
The scaling was derived within ALCC grant [Quantum Turbulence in Fermi Superfluids](https://www.olcf.ornl.gov/web-project/quantum-turbulence-in-fermi-superfluids/).
|
|
The scaling was derived within ALCC grant [Quantum Turbulence in Fermi Superfluids](https://www.olcf.ornl.gov/web-project/quantum-turbulence-in-fermi-superfluids/).
|
|
![summit-scaling](uploads/e27884d7a5cb4ed751635a06d3f25ca7/summit-scaling.png) |
|
![summit-scaling](uploads/e27884d7a5cb4ed751635a06d3f25ca7/summit-scaling.png) |
|
|
|
\ No newline at end of file |