From 6cf195b6d5e15ac0abeb2be1aa5d34361b475c7e Mon Sep 17 00:00:00 2001 From: Roman Gareev Date: Thu, 14 Jul 2016 10:40:15 +0000 Subject: [PATCH] [NFC] Add full title/author information to "Apply the BLIS matmul optimization pattern" llvm-svn: 275392 --- polly/include/polly/ScheduleOptimizer.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/polly/include/polly/ScheduleOptimizer.h b/polly/include/polly/ScheduleOptimizer.h index 138f4b3..d8bcbb2 100644 --- a/polly/include/polly/ScheduleOptimizer.h +++ b/polly/include/polly/ScheduleOptimizer.h @@ -107,12 +107,17 @@ private: /// @brief Apply the BLIS matmul optimization pattern /// - /// Apply the BLIS matmul optimization pattern - /// (http://www.cs.utexas.edu/users/flame/pubs/TOMS-BLIS-Analytical.pdf). - /// BLIS implements gemm as three nested loops around a macro-kernel, - /// plus two packing routines. The macro-kernel is implemented in terms - /// of two additional loops around a micro-kernel. The micro-kernel - /// is a loop around a rank-1 (i.e., outer product) update. + /// Apply the BLIS matmul optimization pattern. BLIS implements gemm + /// as three nested loops around a macro-kernel, plus two packing routines. + /// The macro-kernel is implemented in terms of two additional loops around + /// a micro-kernel. The micro-kernel is a loop around a rank-1 + /// (i.e., outer product) update. + /// + /// For a detailed description please see: + /// Analytical Modeling is Enough for High Performance BLIS + /// Tze Meng Low, Francisco D Igual, Tyler M Smith, Enrique S Quintana-Orti + /// Technical Report, 2014 + /// http://www.cs.utexas.edu/users/flame/pubs/TOMS-BLIS-Analytical.pdf /// /// We create the BLIS micro-kernel by applying a combination of tiling /// and unrolling. In subsequent changes we will add the extraction -- 2.7.4