Skip to content

Instantly share code, notes, and snippets.

🐕
Such programming

Hadrien G. HadrienG2

Block or report user

Report or block HadrienG2

Hide content and notifications from this user.

Learn more about blocking users

Contact Support about this user’s behavior.

Learn more about reporting abuse

Report abuse
View GitHub Profile
@HadrienG2
HadrienG2 / dd.exclude
Created Jun 14, 2018
Debug dump from a failed verrou_dd run
View dd.exclude
This file has been truncated, but you can view the full file.
_ZN5boost9unit_test9framework8shutdownEv /root/acts-core/build/IntegrationTests/PropagationTests
_ZNK5boost9unit_test12test_results11result_codeEv /root/acts-core/build/IntegrationTests/PropagationTests
_ZN5boost9unit_test6output22plain_report_formatter21results_report_finishERSo /root/acts-core/build/IntegrationTests/PropagationTests
_ZN5boost9unit_test5utils14scope_setcolorD1Ev /root/acts-core/build/IntegrationTests/PropagationTests
_ZN5boost9unit_test9ut_detail30ignore_unused_variable_warningINS0_5utils14scope_setcolorEEEvRKT_ /root/acts-core/build/IntegrationTests/PropagationTests
_ZN5boost9unit_test5utils14scope_setcolorC1Ev /root/acts-core/build/IntegrationTests/PropagationTests
_ZN5boost9unit_test6output22plain_report_formatter22do_confirmation_reportERKNS0_9test_unitERSo /root/acts-core/build/IntegrationTests/PropagationTests
_ZN5boost9unit_test9framework3getINS0_9test_unitEEERT_m /root/acts-core/build/IntegrationTests/PropagationTests
__tls_get_addr /lib64/ld-2.27.so
@HadrienG2
HadrienG2 / High_Performance_Rust.md
Last active Jan 9, 2019
Making Rust a perfect fit for high-performance computations
View High_Performance_Rust.md

Hello, Rust community!

My name is Hadrien and I am a software performance engineer in a particle physics lab. My daily job is to figure out ways to make scientific software use hardware more efficiently without sacrificing its correctness, primarily by adapting old-ish codebases to the changes that occured in the software and computing landscape since the days where they were designed:

  • CPU clock rates and instruction-level parallelism stopped going up, so optimizing code is now more important.
  • Multi-core CPUs went from an exotic niche to a cheap commodity, so parallelism is not optional anymore.
  • Core counts grow faster than RAM prices go down, so multi-processing is not enough anymore.
  • SIMD vectors become wider and wider, so vectorization is not a gimmick anymore.
You can’t perform that action at this time.