Bot releases are visible (Hide)
Published by vpirogov over 1 year ago
This is a patch release containing the following changes to v3.0:
bfloat16
convolution weight gradient on Intel CPUs (a17a64c330d1153fdea3d81f1420fb38c50248bd)fp16
and bfloat16
convolution backward propagation on systems with Intel AMX support (293561b6a2644ef05d8d664cd81c1bcde876b481)int8
RNN primitive Vanilla GRU flavor on Intel CPUs (f4a149c16faff0fb51fb292d12a7b51f6fac53bf, fbf8dca1ba9b565ddedd1cb291d3b466d0a5a45b)int8
convolution with zero-points on Intel Data Center GPU Max Series (96e868c473bb0e2a9b1a42b51e8f91997b52b471)fp16
and bfloat16
convolution backward propagation on future Intel Xeon processors (code name Sierra Forest) (399b7c5af4c5238f9956d71270adbd44f3cb25a3)OHWI
and OIHW
weight formats on Intel Data Center GPU Max Series (2d0b31ee82dc681b829f67100c05ae4e689633e6, 5bd5d52e7ee832fb0d5ece6d42a6b230023c9dd0)tbb::finalize
to tests and examples to address intermittent test crashes with TBB runtime (891a41560382cc0f991c428392078d13ccb76129, c79e54322f251aa70783ca1b837ce0d558bf3396, 8312c3addc597e6565cf1233801234c2ffafd092, 1a32b95a2c61d094206ed49d69843fdcdeb2ffcd, bd0389d81509baf6696d3927d0da4cce4c06d2d4, f05013d0e419df22ec2755dc5d74f5974871cf9e, ab7938f1b889aa43f155216f774297e8c765cd97, 31c9e7b3c1a7e262cecafe98bed128843f1c2969, f3261e4556935424946697be4b336020653b41a5, d58ac41a12179f8cca48962c4b5a44940bea97d7, f8c67b9026dc2945ed66a8f1c276611c063dae4d, 258849b71c24a89b08ac12972ec1fcaa72a9da39, b20a8c786c5a2cb676a2a8b599edf5cfd7ee0c3a)fp16
convolution primitive on future Intel Xeon processors (code name Granite Rapids) (a574ffff870318cc104d8af4a2368d47b433b27f)fp16
convolution primitive on future Intel Xeon processors (code name Sierra Forest) (f165ed8a8872e72a7d9651c3dd38bd6c2909fdce)int8
convolution primitive on Intel CPUs (ca1592237b87cae5e4a55fb464ad90fb9f91957d, 27845b8e66d354549ac6c6fceeb92c267a9e910f)int8
convolution primitive on Intel Data Center GPU Max Series (8bb651cb99e2875aea44b907bdc54418b2d4932a)sum
and relu
post-ops on Intel CPUs (63ad769939dd8307935caac67c0fc7c9bc9206de, 1b1303748b80360e5f93740d6ea03063132fd8f8, 0a8116b3de98243a234680d8cda869d2f20dd178, 9972cb80a29da9f14efbe8518bc10a21f7ae6e36)Published by vpirogov over 1 year ago
This is a patch release containing the following changes to graph-v0.8:
query_dynamic_outputs()
interface implementation in graph compiler backend (8dbca04)Published by tprimak almost 2 years ago
This is a patch release containing the following changes to v2.7.2:
Published by vpirogov almost 2 years ago
This is the Beta Update 2 release of oneDNN Graph API based on oneDNN v2.7.2.
HardSigmoid
operation.IOX
and XOI
weight formats for ConvTranspose
operation.query_dynamic_outputs
API to support dynamic shapes in the graph. This functionality allows Graph API to infer output tensors shapes based on input tensors.This release contains contributions from the project core teams as well as Jiong Gong, Chunyuan Wu, Sanchit Jain, Yiqiang Li, Yunfei Mao, Kiefer Kuah and others.
Published by harrymao2022 almost 2 years ago
ONEDNN_BUILD_GRAPH=ON
flag.This release contains contributions from the project core team as well as @akshatasangelkar, Aryan Karumuri @AryanKarumuri, Crefeda Rodrigues @cfRod, Divakar Mariyanna @bmdivakar, Gordon Fossum @austinpagan, Jonathan Deakin @jondea, Kentaro Kawakami @kawakami-k, lilianhuang @lilh9598, Milos Puzovic @milpuz01, Mona Minakshi @monaminakshi, Nathan John Sircombe @nSircombe, Peter Caday @petercad, and Sreekanth Yalachigere @sreekanth-yalachigere. We would also like to thank everyone who asked questions and reported issues.
Published by harrymao2022 almost 2 years ago
This is a release candidate for oneDNN v3.0. Please provide feedback and submit defect reports via Github issues.
ONEDNN_BUILD_GRAPH=ON
flag.This release contains contributions from the project core team as well as @akshatasangelkar, Aryan Karumuri @AryanKarumuri, Crefeda Rodrigues @cfRod, Divakar Mariyanna @bmdivakar, Gordon Fossum @austinpagan, Jonathan Deakin @jondea, Kentaro Kawakami @kawakami-k, lilianhuang @lilh9598, Milos Puzovic @milpuz01, Mona Minakshi @monaminakshi, Nathan John Sircombe @nSircombe, Peter Caday @petercad, and Sreekanth Yalachigere @sreekanth-yalachigere. We would also like to thank everyone who asked questions and reported issues.
Published by vpirogov almost 2 years ago
This is a patch release containing the following changes to graph-v0.7.1:
Published by vpirogov almost 2 years ago
This is a patch release containing the following changes to v2.7.1:
Published by vpirogov almost 2 years ago
This is a patch release containing the following changes to graph-v0.7:
Published by vpirogov almost 2 years ago
This is a patch release containing the following changes to v2.7:
matmul_perf
example (b5faa77a4a651f1e44fa77348eded54ea3ec3eef)tanh
post-op on Xe Architecture GPUs (88b4e57718014bd50f78461a5c80dc680074f9b6, 83ce6d27a8699d7ab0d1ee450e2e7e9ec87a6e13, 6224dc6b3e2073c98f4b8278bf7e87769dd85a55, 10f0d0ade797a90c93b7450c1e0b151dc415dab3)Published by tprimak almost 2 years ago
This is a patch release containing the following changes to v2.6.2:
Published by vpirogov about 2 years ago
This is the Beta Update release for oneDNN Graph API based on oneDNN v2.7 release.
Select
, LogicalAnd
, LogicalOr
, LogicalXor
, LogicalNot
, Greater
, GreaterEqual
, Equal
, NoeEqual
, Less
, and LessEqual
.boolean
data type to support logical operations.This release contains contributions from the project core teams as well as Jiong Gong, Chunyuan Wu, Sanchit Jain, Yiqiang Li, Yunfei Mao, Kiefer Kuah and others.
Published by vpirogov about 2 years ago
This is the Beta release for oneDNN Graph based on oneDNN v2.7 release.
graph::finalize()
function to indicate that the user has finished adding operations into the graph and the graph is ready for partitioning.AbsBackprop
, Mish
, MishBackprop
, and LeakyReLU
.include/oneapi/dnnl
.src/graph
.dnnl::engine
and dnnl::stream
. The original dnnl::graph::engine
and dnnl::graph::stream
API were removed.make_engine_with_allocator()
API to create dnnl::engine
with dnnl::graph::allocator
.dnnl_status_t
, dnnl_data_type_t
, and dnnl_dims_t
, etc.ONEDNN_BUILD_GRAPH
build option to manage Graph component build.ONEDNN_GRAPH_DUMP
environment variable that serialized library graph and subgraph into JSON files.HardTanh
, Index
, Pow
, etc. Please check the operation kind list for details.ONEDNN_BUILD_GRAPH
is not compatible with some of the build options supported by the build system including ONEDNN_GPU_RUNTIME=OCL
, ONEDNN_ENABLE_WORKLOAD=INFERENCE
, ONEDNN_ENABLE_PRIMITIVE
, and others.This release contains contributions from the project core teams as well as Jiong Gong, Chunyuan Wu, Sanchit Jain, Yiqiang Li, Yunfei Mao, Kiefer Kuah and others.
Published by harrymao2022 about 2 years ago
hardsigmoid
algorithm.dnnl_fuse_norm_add_relu
flag that allows to fuse sum and relu operations. The implementation is available for Intel GPUs.matmul_perf
example that benchmarks matmul primitive for all supported data types.dnnl_*gemm*
calls.mode=po
).This release contains contributions from the project core team as well as Aidan Belton @AidanBeltonS, @akshatasangelkar, Alex Bojan @lb991, Crefeda Rodrigues @cfRod, Damian Szwichtenberg @dszwicht, Diana Bite @diaena, Divakar Mariyanna @bmdivakar, Emilio Cota @cota, Gordon Fossum @austinpagan, Hugh Delaney @hdelan, Jacek Czaja @jczaja, @jakpiase, Jonathan Deakin @jondea, Kentaro Kawakami @kawakami-k, Kotha Sowmya @Sowmyakotha1999, Louie Tsai @louie-tsai, Mark Ryan @markdryan, MITSUNARI Shigeo @herumi, Mona Minakshi @monaminakshi, @NaNAGISaSA, Nathan John Sircombe @nSircombe, Peter Caday @petercad, @pgorlani, Sreekanth Yalachigere @sreekanth-yalachigere, Tadej Ciglarič @t4c1, and Thiago Macieira @thiagomacieira. We would also like to thank everyone who asked questions and reported issues.
Published by harrymao2022 about 2 years ago
This is a release candidate for oneDNN v2.7. Please provide feedback and submit defect reports via Github issues.
hardsigmoid
algorithm.dnnl_fuse_norm_add_relu
flag that allows to fuse sum and relu operations. The implementation is available for Intel GPUs.dnnl_*gemm*
calls.mode=po
).This release contains contributions from the project core team as well as Aidan Belton @AidanBeltonS, @akshatasangelkar, Alex Bojan @lb991, Crefeda Rodrigues @cfRod, Damian Szwichtenberg @dszwicht, Diana Bite @diaena, Divakar Mariyanna @bmdivakar, Emilio Cota @cota, Gordon Fossum @austinpagan, Hugh Delaney @hdelan, Jacek Czaja @jczaja, @jakpiase, Jonathan Deakin @jondea, Kentaro Kawakami @kawakami-k, Kotha Sowmya @Sowmyakotha1999, Louie Tsai @louie-tsai, Mark Ryan @markdryan, MITSUNARI Shigeo @herumi, Mona Minakshi @monaminakshi, @NaNAGISaSA, Nathan John Sircombe @nSircombe, Peter Caday @petercad, @pgorlani, Sreekanth Yalachigere @sreekanth-yalachigere, Tadej Ciglarič @t4c1, and Thiago Macieira @thiagomacieira. We would also like to thank everyone who asked questions and reported issues.
Published by vpirogov about 2 years ago
This is a patch release containing the following changes to v2.6.1:
Published by tprimak about 2 years ago
This is a patch release containing the following changes to graph-v0.5.1:
Published by vpirogov over 2 years ago
This is a patch release containing the following changes to v2.6:
inf
and -inf
values in eltwise log algorithm (732cbdd2651bc8ea4c7ae125c29e542fecd79b8e, 3fd0f2e44c84869181aa2506e8924c37e9267b64)test_isa_hints
gtest on GPUs (78c1c68305f81cb087f3e4dc2cebb07cace1ef4d)-Werror=odr
option (27668dd728a3a3460315e44275490daab317fa8d)Published by vpirogov over 2 years ago
This is a patch release containing the following changes to graph-v0.5:
Published by vpirogov over 2 years ago
This is a patch release containing the following changes to graph-v0.4.2: