mozga-intel commented on a change in pull request #20533:
URL: https://github.com/apache/incubator-mxnet/pull/20533#discussion_r693914049
##########
File path: docs/static_site/src/pages/api/faq/env_var.md
##########
@@ -298,9 +298,9 @@ If ctypes is used, it must be
`mxnet._ctypes.ndarray.NDArrayBase`.
- Values: Int ```(default=-1)```
- Flag to set num of elements that MKLDNN cache can hold. Default is -1
which means cache size is unbounded. Should only be set if your model has
variable input shapes, as cache size may grow unbounded. The number represents
the number of items in the cache and is proportional to the number of layers
that use MKLDNN and different input shape.
-* MXNET_MKLDNN_DISABLE_BRGEMM_FC
- - Values: 0, 1 ```(default=1)```
- - Flag which disables BRGEMM kernels in FullyConnected executed with MKLDNN
support - Should only be set to 0 if your model has constant input shapes or
FullyConnected is calculated with large tensors. Supported on machines with
AVX512-VNNI.
+* MXNET_MKLDNN_FORCE_FC_AB_FORMAT
+ - Values: 0, 1 ```(default=0)```
+ - If set to true, FullyConnected will use only AB format for weights, thus
MXNet won't use BRGEMM implementation of FC on machines with AVX512-VNNI
support.
Review comment:
thus -> Otherwise [?]
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
