Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TridiagSolver (distributed): "bulkerify" rank1 problem solution #904

Merged
merged 29 commits into from
Jul 7, 2023
Merged
Changes from all commits
Commits
Show all changes
29 commits
Select commit Hold shift + click to select a range
2fa0228
minor changes
albestro May 31, 2023
588d766
first step: step1 laed4 + basic structure
albestro May 31, 2023
8f43990
fix nthreads
albestro May 31, 2023
df4739a
embed assembleDistEvalsVec in bulk
albestro May 31, 2023
e5e463e
embed step2 in bulk
albestro Jun 6, 2023
399b3b5
add basic version of step3 in bulk
albestro Jun 6, 2023
1679134
remove superfluous copies
albestro Jun 6, 2023
a3120c8
use blas::dot
albestro Jun 6, 2023
ddeaefa
apply fix for k<=2 as done in last PR merged on master
albestro Jun 6, 2023
55fc508
last step (normalization) reduce number of communications
albestro Jun 9, 2023
9ff7944
remove blocking mpi calls allowing yielding
albestro Jun 12, 2023
8b56f26
add missing barrier between multi to single threaded transition
albestro Jun 12, 2023
17ef1b1
rename according to new guidelines + minor changes
albestro Jun 12, 2023
9efd932
revert temporary change
albestro Jun 12, 2023
cb9974c
minor fixes
albestro Jun 12, 2023
9401feb
start factoring out bcast and remove superfluous barriers
albestro Jun 12, 2023
9646224
remove sync_wait for bcast (it just wait at the end of bulk) + other …
albestro Jun 13, 2023
4574565
minor changes
albestro Jun 14, 2023
7c9023f
Update include/dlaf/eigensolver/tridiag_solver/merge.h
albestro Jun 14, 2023
49c63fe
add barrier busy wait + remove todo
albestro Jun 14, 2023
e033844
bug fix: race-condition over LAED4 workspace in case of multiple workers
albestro Jun 21, 2023
664eb10
use make_unique instead of make_shared as suggested in #911
albestro Jun 22, 2023
74f47e1
minor change: reorder communicators (row first, col second)
albestro Jun 22, 2023
2ee1fda
minor comment
albestro Jun 22, 2023
a9453fd
use "sub"-pipeline to force communications order on row communicator
albestro Jun 22, 2023
1c08795
remove unused capture
albestro Jun 22, 2023
9a7c871
clang-format
albestro Jun 22, 2023
ebe9bee
rename all_reduce lambda as suggested
albestro Jul 4, 2023
d8fcc7a
Update include/dlaf/eigensolver/tridiag_solver/merge.h
albestro Jul 6, 2023
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading