From 780e98022609cb0b1e90a388549b1185671f089a Mon Sep 17 00:00:00 2001 From: Martin Perdacher Date: Fri, 12 Apr 2019 17:02:00 +0200 Subject: [PATCH] Update README.md --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index ad6fdb7..1db22a1 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,8 @@ For our BLAS variant of the similarity-join, we use the matrix multiplication provided by BLAS and the Euclidean distance by scalar product (see paper). -![matrix multiplication](https://gitlab.cs.univie.ac.at/Google-TPU/BLAS-join/blob/master/description.jpg "BLAS-similarity join") +![LLC](measure/cache/figures/processorTileBlock.jpg "Processor Tile Block") +![matrix_multiplication](description.jpg "BLAS-similarity join") The individual blocksize needs to be experimental evaluated for each individual hardware. Our selfjoin variant, only iterates over the lower triangle of the similarity matrix. -- GitLab