Issues: oneapi-src/oneDNN
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
BenchDNN failures for inner product with int8 datatypes an sum postop, when ref. impl. is used.
sighting
Suspicious library behavior. Should be promoted to a bug when confirmed
#1649
opened May 17, 2023 by
nSircombe
Typos in the Memory Format Diagram of Blocked Layout
documentation
A request to change/fix/improve the documentation
#1643
opened May 6, 2023 by
topsy404
performance differences of ip between v2.7.3 and v3.1
question
#1640
opened Apr 28, 2023 by
zhenwei-intel
Allow arrays larger than 4GB on GPUs
enhancement
A feature or an optimization request
#1638
opened Apr 25, 2023 by
BA8F0D39
oneDNN 3.0.1 uses non public headers from ACL
bug
A confirmed library bug
#1599
opened Mar 21, 2023 by
ggardet
How to use eltwise post op as part of binary primitive
question
#1487
opened Nov 2, 2022 by
ItayLasch
sgemm accuracy drops with AVX2
sighting
Suspicious library behavior. Should be promoted to a bug when confirmed
#1486
opened Nov 2, 2022 by
penpornk
Does brgemm support transA/transB?
enhancement
A feature or an optimization request
#1450
opened Sep 8, 2022 by
gengoks
compiling
help wanted
sighting
Suspicious library behavior. Should be promoted to a bug when confirmed
#1447
opened Aug 26, 2022 by
magicse
LSTM kernel performs 1.5x slower for v2.6 compared with v1.4
performance
sighting
Suspicious library behavior. Should be promoted to a bug when confirmed
#1415
opened Jul 11, 2022 by
Hari-MathWorks
onednn-2.6 compiler error with Intel compiler 1.190 in Windows
bug
A confirmed library bug
#1397
opened Jun 14, 2022 by
rfg-gh
test_concurrency intermittent segfault inside docker
sighting
Suspicious library behavior. Should be promoted to a bug when confirmed
#1372
opened May 11, 2022 by
jondea
convolution forward results are different in AVX512 VNNI and AVX2
enhancement
A feature or an optimization request
#1354
opened Apr 24, 2022 by
dagdoron
Ability to generate JIT code with frame pointers to enable Linux perf stack unwinding
enhancement
A feature or an optimization request
#1232
opened Jan 15, 2022 by
aalexand
MKLDNN library size increase from v1.0 to v1.4
enhancement
A feature or an optimization request
#855
opened Oct 21, 2020 by
uu-praveeng
BenchDNN error handling issue
enhancement
A feature or an optimization request
#771
opened Jul 2, 2020 by
huangzhiyuan
DNNL MatMul with SGEMM
enhancement
A feature or an optimization request
performance
#724
opened May 1, 2020 by
affranchi
DNNL vs FBGEMM u8s8s32 with small m
enhancement
A feature or an optimization request
performance
#673
opened Mar 18, 2020 by
ppetrushkov
bit mask support for dropout
enhancement
A feature or an optimization request
#656
opened Feb 27, 2020 by
eric-haibin-lin
gemm_s8s8s32: latest version is 1.4x slower than v0.21 with Intel MKL on AVX2
performance
#619
opened Dec 18, 2019 by
guillaumekln
ProTip!
Follow long discussions with comments:>50.

