Eigen::internal::ExpressionHasTensorBroadcastingOp< Expression > Struct Template Reference

#include <TensorExecutor.h>

Public Types

enum  { value = false }
 

Detailed Description

template<typename Expression>
struct Eigen::internal::ExpressionHasTensorBroadcastingOp< Expression >

Evaluating TensorBroadcastingOp via coefficient of packet path is extremely expensive. If expression has at least one broadcast op in it, and it supports block based evaluation, we always prefer it, even for the small tensors. For all other tileable ops, block evaluation overhead for small tensors (fits into L1) is too large, and we fallback on vectorized evaluation.

Member Enumeration Documentation

◆ anonymous enum

template<typename Expression >
anonymous enum
Enumerator
value 
46 { value = false };
@ value
Definition: TensorExecutor.h:46

The documentation for this struct was generated from the following file: