diff options
| author |  Rasmus Munk Larsen <rmlarsen@google.com> | 2020-04-24 17:29:25 -0700 |
|---|---|---|
| committer | Rasmus Munk Larsen <rmlarsen@google.com> | 2020-04-28 16:12:47 +0000 |
| commit | ab773c7e914633ec4a3ee1f7cdea8b168d3bce1a (patch) | |
| tree | 5a82a3071e3c5de39e934ce144023c20f62b2de4 /unsupported/test/cxx11_tensor_block_io.cpp | |
| parent | b47c7779937c1984b7cd2f1d2f8df33d67c396f7 (diff) | |
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)
Diffstat (limited to 'unsupported/test/cxx11_tensor_block_io.cpp')
| -rw-r--r-- | unsupported/test/cxx11_tensor_block_io.cpp | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/unsupported/test/cxx11_tensor_block_io.cpp b/unsupported/test/cxx11_tensor_block_io.cpp index a6f7a44cd..52f7dde9b 100644 --- a/unsupported/test/cxx11_tensor_block_io.cpp +++ b/unsupported/test/cxx11_tensor_block_io.cpp @@ -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 |