Developer Guide and Reference

  • 2022.1
  • 04/11/2022
  • Public Content
Contents

Reduction

General

The reduction primitive performs reduction operation on arbitrary data. Each element in the destination is the result of reduction operation with specified algorithm along one or multiple source tensor dimensions:
LaTex Math image.
where LaTex Math image. can be max, min, sum, mul, mean, Lp-norm and Lp-norm-power-p, LaTex Math image. is an index in an idle dimension and LaTex Math image. is an index in a reduction dimension.
Mean:
LaTex Math image.
where LaTex Math image. is the size of a reduction dimension.
Lp-norm:
LaTex Math image.
where LaTex Math image. can be max and sum.
Lp-norm-power-p:
LaTex Math image.
where LaTex Math image. can be max and sum.
Notes
  • The reduction primitive requires the source and destination tensors to have the same number of dimensions.
  • Reduction dimensions are of size 1 in a destination tensor.
  • The reduction primitive does not have a notion of forward or backward propagations.

Execution Arguments

When executed, the inputs and outputs should be mapped to an execution argument index as specified by the following table.
Primitive input/output
Execution argument index
LaTex Math image.
DNNL_ARG_SRC
LaTex Math image.
DNNL_ARG_DST
LaTex Math image.

Implementation Details

General Notes
  • The LaTex Math image. memory format can be either specified explicitly or by dnnl::memory::format_tag::any (recommended), in which case the primitive will derive the most appropriate memory format based on the format of the source tensor.
Post-Ops and Attributes
The following attributes are supported:
Type
Operation
Description
Restrictions
Post-op
Adds the operation result to the destination tensor instead of overwriting it.
Post-op
Applies an Eltwise operation to the result.
Post-op
Applies a Binary operation to the result
General binary post-op restrictions
Data Types Support
The source and destination tensors may have
f32
,
bf16
, or
int8
data types. See Data Types page for more details.
Data Representation
Sources, Destination
The reduction primitive works with arbitrary data tensors. There is no special meaning associated with any of the dimensions of a tensor.

Implementation Limitations

  1. Refer to Data Types for limitations related to data types support.

Performance Tips

  1. Whenever possible, avoid specifying different memory formats for source and destination tensors.

Example

This C++ API example demonstrates how to create and execute a Reduction primitive.

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.