Extend support for Packet16b:

* Add ptranspose<*,4> to support matmul and add unit test for Matrix<bool> * Matrix<bool>
* work around a bug in slicing of Tensor<bool>.
* Add tensor tests

This speeds up matmul for boolean matrices by about 10x

name                            old time/op             new time/op             delta
BM_MatMul<bool>/8                267ns ± 0%              479ns ± 0%  +79.25%          (p=0.008 n=5+5)
BM_MatMul<bool>/32              6.42µs ± 0%             0.87µs ± 0%  -86.50%          (p=0.008 n=5+5)
BM_MatMul<bool>/64              43.3µs ± 0%              5.9µs ± 0%  -86.42%          (p=0.008 n=5+5)
BM_MatMul<bool>/128              315µs ± 0%               44µs ± 0%  -85.98%          (p=0.008 n=5+5)
BM_MatMul<bool>/256             2.41ms ± 0%             0.34ms ± 0%  -85.68%          (p=0.008 n=5+5)
BM_MatMul<bool>/512             18.8ms ± 0%              2.7ms ± 0%  -85.53%          (p=0.008 n=5+5)
BM_MatMul<bool>/1k               149ms ± 0%               22ms ± 0%  -85.40%          (p=0.008 n=5+5)
This commit is contained in:
Rasmus Munk Larsen
2020-04-24 17:29:25 -07:00
parent b47c777993
commit ab773c7e91
10 changed files with 267 additions and 162 deletions

View File

@@ -415,7 +415,15 @@ static void test_block_io_squeeze_ones() {
CALL_SUBTEST((NAME<float, 1, ColMajor>())); \
CALL_SUBTEST((NAME<float, 2, ColMajor>())); \
CALL_SUBTEST((NAME<float, 4, ColMajor>())); \
CALL_SUBTEST((NAME<float, 5, ColMajor>()))
CALL_SUBTEST((NAME<float, 5, ColMajor>())); \
CALL_SUBTEST((NAME<bool, 1, RowMajor>())); \
CALL_SUBTEST((NAME<bool, 2, RowMajor>())); \
CALL_SUBTEST((NAME<bool, 4, RowMajor>())); \
CALL_SUBTEST((NAME<bool, 5, RowMajor>())); \
CALL_SUBTEST((NAME<bool, 1, ColMajor>())); \
CALL_SUBTEST((NAME<bool, 2, ColMajor>())); \
CALL_SUBTEST((NAME<bool, 4, ColMajor>())); \
CALL_SUBTEST((NAME<bool, 5, ColMajor>()))
EIGEN_DECLARE_TEST(cxx11_tensor_block_io) {
// clang-format off