https://github.com/lquenti/blackheap
An blackbox approach to I/O modelling. (Migrated to Codeberg)
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.7%) to scientific vocabulary
Keywords
benchmark
fuse
hpc
kernel-density-estimation
linear-regression
performance-analysis
statistics
Last synced: 4 months ago
·
JSON representation
Repository
An blackbox approach to I/O modelling. (Migrated to Codeberg)
Statistics
- Stars: 5
- Watchers: 2
- Forks: 0
- Open Issues: 0
- Releases: 0
Archived
Topics
benchmark
fuse
hpc
kernel-density-estimation
linear-regression
performance-analysis
statistics
Created almost 4 years ago
· Last pushed 10 months ago
Metadata Files
Readme
README.md
Blackheap
BIG RECODE, old-v0 is the old branch
This tool creates a performance model of your I/O speed and further allows to predict future preformance.
Note
There is a big recode right now. But how does one eat an elephant...
How to get it running
Locally, normal device
Normally
cargo build --release
should suffice
SCC cluster
- Use
rustup, not modules Get a up to date rust compiler via
rustup updatecc, which is mapped to the defaultgcc, is too old.- Load a newer gcc via
module load gcc/11.4.0 - Tell rust to use that one via
CC=$(which gcc) cargo build --release
- Load a newer gcc via
Emmy HLRN cluster
- Use
rustup, not modules Get a up to date rust compiler via
rustup updateget the newest
gccas module as well- Tell rust to use that one via
CC=$(which gcc) cargo build --release
- Tell rust to use that one via