% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@MISC{Hoppe:1034769,
author = {Hoppe, Fabian and Osterfeld, Fynn and Gutiérrez Hermosillo
Muriedas, Juan Pedro and Vaithinathan Aravindan, Ashwath and
Comito, Claudia and Krajsek, Kai and Nguyen Xuan, Tu and
Tarnawa, Michael and Coquelin, Daniel and Debus, Charlotte
and Götz, Markus and Hagemeier, Björn and Knechtges,
Philipp and Rüttgers, Alexander},
title = {{H}eat (v1.5.0); 1.5.0},
reportid = {FZJ-2024-07524},
year = {2024},
abstract = {Heat 1.5 Release Notes Overview Highlights Performance
Improvements Sparse Signal Processing RNG Statistics
Manipulations I/O Machine Learning Deep Learning Other
Updates Contributors Overview With Heat 1.5 we release the
first set of features developed within the ESAPCA project
co-funded by the European Space Agency (ESA). The main focus
of this release is on distributed linear algebra operations,
such as tall-skinny SVD, batch matrix multiplication, and
triangular solver. We also introduce vectorization via vmap
across MPI processes, and batch-parallel random number
generation as default for distributed operations. This
release also includes a new class for distributed Compressed
Sparse Column matrices, paving the way for future
implementation of distributed sparse matrix multiplication.
On the performance side, our new array redistribution via
MPI Custom Datatypes provides significant speed-up in
operations that require it, such as FFTs. We are grateful to
our community of users, students, open-source contributors,
the European Space Agency and the Helmholtz Association for
their support and feedback. Highlights [ESAPCA] Distributed
tall-skinny SVD: ht.linalg.svd (by @mrfh92) Distributed
batch matrix multiplication: ht.linalg.matmul (by
@FOsterfeld) Distributed solver for triangular systems:
$ht.linalg.solve_triangular$ (by @FOsterfeld) Vectorization
across MPI processes: ht.vmap (by @mrfh92) Other Changes
Performance Improvements #1493 Redistribution speed-up via
MPI Custom Datatypes available by default in ht.resplit (by
@JuanPedroGHM) Sparse #1377 New class: Distributed
Compressed Sparse Column Matrix $ht.sparse.DCSC_matrix()$
(by @Mystic-Slice) Signal Processing #1515 Support batch 1-d
convolution in ht.signal.convolve (by @ClaudiaComito) RNG
#1508 Introduce batch-parallel RNG as default for
distributed operations (by @mrfh92) Statistics #1420 Support
sketched percentile/median for large datasets with
ht.percentile(sketched=True) (and ht.median) (by @mrhf92)
#1510 Support multiple axes for distributed ht.percentile
and ht.median (by @ClaudiaComito) Manipulations #1419
Implement distributed unfold operation (by @FOsterfeld) I/O
#1602 Improve load balancing when loading .npy files from
path (by @Reisii) #1551 Improve load balancing when loading
.csv files from path (by @Reisii) Machine Learning #1593
Improved batch-parallel clustering
ht.cluster.BatchParallelKMeans and
ht.cluster.BatchParallelKMedians (by @mrfh92) Deep Learning
#1529 Make dataset.ishuffle optional. (by @krajsek) Other
Updates #1618 Support mpi4py 4.x.x (by @JuanPedroGHM)
Contributors @mrfh92, @FOsterfeld, @JuanPedroGHM,
@Mystic-Slice, @ClaudiaComito, @Reisii, @mtar and @krajsek},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
and Research Groups (POF4-511) / 5111 - Domain-Specific
Simulation $\&$ Data Life Cycle Labs (SDLs) and Research
Groups (POF4-511)},
pid = {G:(DE-HGF)POF4-5112 / G:(DE-HGF)POF4-5111},
typ = {PUB:(DE-HGF)33},
doi = {10.5281/ZENODO.14001852},
url = {https://juser.fz-juelich.de/record/1034769},
}