Optimize away weights_T during training.

Mnist-1000: 18s -> 15s.

1 files changed, 6 insertions, 0 deletions

diff --git a/src/lib/include/neuralnet/matrix.h b/src/lib/include/neuralnet/matrix.h
index 9816b81..0cb40cf 100644
--- a/src/lib/include/neuralnet/matrix.h
+++ b/src/lib/include/neuralnet/matrix.h
@@ -52,6 +52,12 @@ void nnMatrixInitConstant(nnMatrix*, R value);
 /// Multiply two matrices.
 void nnMatrixMul(const nnMatrix* left, const nnMatrix* right, nnMatrix* out);
 
+/// Multiply two matrices, row variant.
+///
+/// This function multiples two matrices row-by-row instead of row-by-column.
+/// nnMatrixMul(A, B, O) == nnMatrixMulRows(A, B^T, O).
+void nnMatrixMulRows(const nnMatrix* left, const nnMatrix* right, nnMatrix* out);
+
 /// Matrix multiply-add.
 ///
 /// out = left + (right * scale)