Add partial vectorization for matrices and tensors of bool. This speeds up boolean operations on Tensors by up to 25x.

Benchmark numbers for the logical and of two NxN tensors:

name                                               old time/op             new time/op             delta
BM_booleanAnd_1T/3   [using 1 threads]             14.6ns ± 0%             14.4ns ± 0%   -0.96%
BM_booleanAnd_1T/4   [using 1 threads]             20.5ns ±12%              9.0ns ± 0%  -56.07%
BM_booleanAnd_1T/7   [using 1 threads]             41.7ns ± 0%             10.5ns ± 0%  -74.87%
BM_booleanAnd_1T/8   [using 1 threads]             52.1ns ± 0%             10.1ns ± 0%  -80.59%
BM_booleanAnd_1T/10  [using 1 threads]             76.3ns ± 0%             13.8ns ± 0%  -81.87%
BM_booleanAnd_1T/15  [using 1 threads]              167ns ± 0%               16ns ± 0%  -90.45%
BM_booleanAnd_1T/16  [using 1 threads]              188ns ± 0%               16ns ± 0%  -91.57%
BM_booleanAnd_1T/31  [using 1 threads]              667ns ± 0%               34ns ± 0%  -94.83%
BM_booleanAnd_1T/32  [using 1 threads]              710ns ± 0%               35ns ± 0%  -95.01%
BM_booleanAnd_1T/64  [using 1 threads]             2.80µs ± 0%             0.11µs ± 0%  -95.93%
BM_booleanAnd_1T/128 [using 1 threads]             11.2µs ± 0%              0.4µs ± 0%  -96.11%
BM_booleanAnd_1T/256 [using 1 threads]             44.6µs ± 0%              2.5µs ± 0%  -94.31%
BM_booleanAnd_1T/512 [using 1 threads]              178µs ± 0%               10µs ± 0%  -94.35%
BM_booleanAnd_1T/1k  [using 1 threads]              717µs ± 0%               78µs ± 1%  -89.07%
BM_booleanAnd_1T/2k  [using 1 threads]             2.87ms ± 0%             0.31ms ± 1%  -89.08%
BM_booleanAnd_1T/4k  [using 1 threads]             11.7ms ± 0%              1.9ms ± 4%  -83.55%
BM_booleanAnd_1T/10k [using 1 threads]             70.3ms ± 0%             17.2ms ± 4%  -75.48%

1 files changed, 12 insertions, 3 deletions

diff --git a/Eigen/src/Core/functors/BinaryFunctors.h b/Eigen/src/Core/functors/BinaryFunctors.h
index 0ea40bab0..a2bc58c76 100644
--- a/Eigen/src/Core/functors/BinaryFunctors.h
+++ b/Eigen/src/Core/functors/BinaryFunctors.h
@@ -382,11 +382,14 @@ struct functor_traits<scalar_quotient_op<LhsScalar,RhsScalar> > {
 struct scalar_boolean_and_op {
   EIGEN_EMPTY_STRUCT_CTOR(scalar_boolean_and_op)
   EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE bool operator() (const bool& a, const bool& b) const { return a && b; }
+  template<typename Packet>
+  EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE const Packet packetOp(const Packet& a, const Packet& b) const
+  { return internal::pand(a,b); }
 };
 template<> struct functor_traits<scalar_boolean_and_op> {
   enum {
     Cost = NumTraits<bool>::AddCost,
-    PacketAccess = false
+    PacketAccess = true
   };
 };
 
@@ -398,11 +401,14 @@ template<> struct functor_traits<scalar_boolean_and_op> {
 struct scalar_boolean_or_op {
   EIGEN_EMPTY_STRUCT_CTOR(scalar_boolean_or_op)
   EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE bool operator() (const bool& a, const bool& b) const { return a || b; }
+  template<typename Packet>
+  EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE const Packet packetOp(const Packet& a, const Packet& b) const
+  { return internal::por(a,b); }
 };
 template<> struct functor_traits<scalar_boolean_or_op> {
   enum {
     Cost = NumTraits<bool>::AddCost,
-    PacketAccess = false
+    PacketAccess = true
   };
 };
 
@@ -414,11 +420,14 @@ template<> struct functor_traits<scalar_boolean_or_op> {
 struct scalar_boolean_xor_op {
   EIGEN_EMPTY_STRUCT_CTOR(scalar_boolean_xor_op)
   EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE bool operator() (const bool& a, const bool& b) const { return a ^ b; }
+  template<typename Packet>
+  EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE const Packet packetOp(const Packet& a, const Packet& b) const
+  { return internal::pxor(a,b); }
 };
 template<> struct functor_traits<scalar_boolean_xor_op> {
   enum {
     Cost = NumTraits<bool>::AddCost,
-    PacketAccess = false
+    PacketAccess = true
   };
 };