From e972b55ec45fd4bf07205d8c41c1a623380db0a3 Mon Sep 17 00:00:00 2001
From: Benoit Jacob <benoitjacob@google.com>
Date: Fri, 13 Feb 2015 14:52:36 -0500
Subject: [PATCH] bug #953 - Fix prefetches in 3px4 product kernel

This gives a 10% speedup on nexus 4 and on nexus 5.
---
 Eigen/src/Core/products/GeneralBlockPanelKernel.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Eigen/src/Core/products/GeneralBlockPanelKernel.h b/Eigen/src/Core/products/GeneralBlockPanelKernel.h
index 11e5f591d..15bf04d1f 100644
--- a/Eigen/src/Core/products/GeneralBlockPanelKernel.h
+++ b/Eigen/src/Core/products/GeneralBlockPanelKernel.h
@@ -810,6 +810,7 @@ void gebp_kernel<LhsScalar,RhsScalar,Index,DataMapper,mr,nr,ConjugateLhs,Conjuga
               EIGEN_ASM_COMMENT("begin step of gebp micro kernel 3pX4"); \
               EIGEN_ASM_COMMENT("Note: these asm comments work around bug 935!"); \
               internal::prefetch(blA+(3*K+16)*LhsProgress); \
+              internal::prefetch(blB+(4*K+16)*RhsProgress); /* Bug 953 */ \
               traits.loadLhs(&blA[(0+3*K)*LhsProgress], A0);  \
               traits.loadLhs(&blA[(1+3*K)*LhsProgress], A1);  \
               traits.loadLhs(&blA[(2+3*K)*LhsProgress], A2);  \
@@ -832,12 +833,11 @@ void gebp_kernel<LhsScalar,RhsScalar,Index,DataMapper,mr,nr,ConjugateLhs,Conjuga
               EIGEN_ASM_COMMENT("end step of gebp micro kernel 3pX4"); \
             } while(false)
         
-            internal::prefetch(blB+(48+0));
+            internal::prefetch(blB + 4 * pk * sizeof(RhsScalar)); /* Bug 953 */
             EIGEN_GEBGP_ONESTEP(0);
             EIGEN_GEBGP_ONESTEP(1);
             EIGEN_GEBGP_ONESTEP(2);
             EIGEN_GEBGP_ONESTEP(3);
-            internal::prefetch(blB+(48+16));
             EIGEN_GEBGP_ONESTEP(4);
             EIGEN_GEBGP_ONESTEP(5);
             EIGEN_GEBGP_ONESTEP(6);