Skip to content

Bfloat16 #1709

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.

Sign up for GitHub

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

Jump to bottom
Closed
wants to merge 48 commits into from
Closed

Bfloat16 #1709

wants to merge 48 commits into from

Conversation

yhmtsai
Copy link
Member

@yhmtsai yhmtsai commented Oct 24, 2024

Just to make it more visible, ginkgo can also support bfloat16 like half in the future.

Please do not review this pr, it will follow half structure after merging half

yhmtsai and others added 30 commits September 29, 2023 15:58
@yhmtsai
only can compile cuda/omp
c0f2d9a
@yhmtsai
next_precision to itself when complex only float, double add empty co…
ac1dbb2 
…nditional
@yhmtsai
can compile with cuda/omp/ref (without test)
7bffc78
@yhmtsai
compile for cuda/sycl/test/mpi (hip needs trick)
c517644
@yhmtsai
hip finally
6b5a4ec
@yhmtsai
fix the narrow issue and atomic support
add37ab
@yhmtsai
fixed more error
2f53fce
@yhmtsai @MarcelKoch
fix the op order and gdb
cdc4d6b 
Co-authored-by: Marcel Koch <marcel.koch@kit.edu>
@yhmtsai
add the rand template not_implemented
c1c1551
@yhmtsai
this version can compile/run complex<half> on cuda114
3f11657 
stack size can not be determined statically issue
some tests are failed
@yhmtsai
does not work for the other executor
6b9546b
@yhmtsai
fix complex issue and sqrt issue
384371b 
sqrt need to be global namespace to live with hip sqrt
@yhmtsai
try fix the compilation issue from MSVC and MacOS
c04d7d0 
It seems to use complex version even using half only
@yhmtsai
move the half to public and use sycl::half for dpcpp
efb9aea
@yhmtsai
limit the next precision in test and benchmark
9480b50 
next_precision<double> = float not half
@yhmtsai
allow disable half operation
9625e11
@yhmtsai
fix macro
620aef5
@yhmtsai
clean and refine the code
06a6f46
@yhmtsai
move half.hpp out of type.hpp
814dca4
@yhmtsai
enable half for testing
54755b4
@yhmtsai
__habs is added in cuda10.2
cc3a7d5 
create_empty for its own type
@yhmtsai
fix nullptr and missing instantiation.
7af58c9 
sycl::half has different rule in conv and full operator after 5.7
@yhmtsai
fix missing device_type and ptr_param
35a47fa
@yhmtsai
update rounding
faea48d
@yhmtsai
do not use distribution with half
f1c1181
@yhmtsai
WIP fix half of failed test
d450dc5
@yhmtsai
fix/skip half test and fix numeric_limit on device
e83d53d
@yhmtsai
mkl csr does not support half
2d7f4cb
@yhmtsai
add half to batch_vector
b04c993
@yhmtsai
fix hip thrust complex op, avoid const in nvhpc, reduce job in windows
10bb4ae
@yhmtsai yhmtsai added the 1:ST:do-not-merge Please do not merge PR this yet. label Oct 24, 2024
@ginkgo-bot ginkgo-bot added reg:build This is related to the build system. reg:testing This is related to testing. reg:ci-cd This is related to the continuous integration system. reg:benchmarking This is related to benchmarking. type:solver This is related to the solvers type:preconditioner This is related to the preconditioners type:matrix-format This is related to the Matrix formats type:factorization This is related to the Factorizations type:reordering This is related to the matrix(LinOp) reordering reg:helper-scripts This issue/PR is related to the helper scripts mainly concerned with development of Ginkgo. type:multigrid This is related to multigrid type:stopping-criteria This is related to the stopping criteria mod:all This touches all Ginkgo modules. labels Oct 24, 2024
@MarcelKoch MarcelKoch added this to the Ginkgo 1.10.0 milestone Mar 13, 2025
@MarcelKoch
Copy link
Member

This should be closed in favor of #1827 and #1825l, right?

@yhmtsai
Copy link
Member Author

yhmtsai commented May 6, 2025

Yes, I hold it until the other two are merged.

@MarcelKoch
Copy link
Member

This can be closed, right?

@yhmtsai
Copy link
Member Author

yhmtsai commented May 21, 2025

Yes. it can be closed now.

@yhmtsai yhmtsai closed this May 21, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees

@yhmtsai yhmtsai

Labels
1:ST:do-not-merge Please do not merge PR this yet. mod:all This touches all Ginkgo modules. reg:benchmarking This is related to benchmarking. reg:build This is related to the build system. reg:ci-cd This is related to the continuous integration system. reg:helper-scripts This issue/PR is related to the helper scripts mainly concerned with development of Ginkgo. reg:testing This is related to testing. type:factorization This is related to the Factorizations type:matrix-format This is related to the Matrix formats type:multigrid This is related to multigrid type:preconditioner This is related to the preconditioners type:reordering This is related to the matrix(LinOp) reordering type:solver This is related to the solvers type:stopping-criteria This is related to the stopping criteria
Projects
None yet
Milestone
Ginkgo 1.10.0
Development

Successfully merging this pull request may close these issues.
3 participants
@yhmtsai @MarcelKoch @ginkgo-bot