Developer Guide

Contents

Concat Backward Layer

The forward concat layer generates a tensor from input arguments
X
. For more details, see Forward Concat Layer. The backward concat layer deconcatenates a tensor from the input argument
G
into multiple output tensors
Z
(
j
)
.

Problem Statement

Given the dimension
k
along which the concatenation to be implemented, a collection
N
= (
n
k
1
,...,
n
k
t
) of
t
integer elements, and a
p
-dimensional tensor
G
=(
g
i
1
...
i
p
) of size
n
1
x
n
2
x ... x
n
p
, the problem is to generate
t
p
-dimensional tensors
Z
(
j
)
,
j
=1, ...,
t
, of size
n
1
x...
n
k
j
x ... x
n
p
such that:

Product and Performance Information

1

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804