Sign inSign up

tudinfse/elzar

By tudinfse

•Updated over 10 years ago

LLVM extension for Triple Modular Redundancy using Intel Advanced Vector Extensions.

Image
0

1.1K

tudinfse/elzar repository overview

⁠Elzar

ELZAR is a compiler framework that transforms unmodified multithreaded applications to support triple modular redundancy using Intel AVX extensions for vectorization. See Elzar paper⁠ for details.

⁠Dependencies
⁠Get image
[sudo] docker pull tudinfse/elzar
⁠Run Parsec 3.0 and Phoenix Pthread benchmarks

Start container:

[sudo] docker run -it --privileged=true -v $(pwd)/data:/data  --name=elzar_container tudinfse/elzar

Inside container:

  • Install benchmarks
./entrypoint.py install
  • Run benchmarks (caution! - may take a couple of days to perform all tests). Argument --num_runs sets the number of times each benchmark is executed.
./entrypoint.py performance_tests --num_runs n

When finished, results will be located in data/parsec_raw.txt and data/phoenix_raw.txt.

Tag summary

Content type

Image

Digest

Size

1.5 GB

Last updated

over 10 years ago

docker pull tudinfse/elzar