From 8a8a109e56751730caf2a4da830fb3e63e069cda Mon Sep 17 00:00:00 2001
From: Benoit Jacob <benoitjacob@google.com>
Date: Thu, 9 May 2019 21:40:54 -0700
Subject: [PATCH] Fix the kernel layout description for the float NEON kernels.
 <Rowmajor,4,8> is the correct layout, is essentially the same layout as
 <Rowmajor,1,8> as we were declaring since they're both row-major and differ
 only in the number of block rows, but it still makes a difference on padding:
 the kernel expects input packed matrix data to be padded to the next multiple
 of 4 rows, and by incorrectly describing the kernel layout as <rowmajor,1,8>,
 we did not honor that. As we reflected the same incorrect layout description
 in pack.h, we were also using packing code that wrote padded data, but we
 were not allocating a suitably enlarged buffer, so my guess is that we were
 overrunning buffers, explaining the non-deterministic failures. Asan didn't
 see anything because this is assembly code, we would need valgrind for that.

PiperOrigin-RevId: 247550630
---
 tensorflow/lite/experimental/ruy/kernel.h | 4 ++--
 tensorflow/lite/experimental/ruy/pack.h   | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tensorflow/lite/experimental/ruy/kernel.h b/tensorflow/lite/experimental/ruy/kernel.h
index fae8515790e..80402b046a2 100644
--- a/tensorflow/lite/experimental/ruy/kernel.h
+++ b/tensorflow/lite/experimental/ruy/kernel.h
@@ -453,8 +453,8 @@ void KernelFloatNeonDotprodInOrder(const KernelParamsFloat<8, 8>& params);
 template <>
 struct Kernel<Path::kNeon, float, float, float, BasicSpec<float, float>> {
   Tuning tuning = Tuning::kAuto;
-  using LhsLayout = FixedKernelLayout<Order::kRowMajor, 1, 8>;
-  using RhsLayout = FixedKernelLayout<Order::kRowMajor, 1, 8>;
+  using LhsLayout = FixedKernelLayout<Order::kRowMajor, 4, 8>;
+  using RhsLayout = FixedKernelLayout<Order::kRowMajor, 4, 8>;
   explicit Kernel(Tuning tuning_) : tuning(tuning_) {}
   void Run(const PackedMatrix<float>& lhs, const PackedMatrix<float>& rhs,
            const BasicSpec<float, float>& spec, int start_row, int start_col,
diff --git a/tensorflow/lite/experimental/ruy/pack.h b/tensorflow/lite/experimental/ruy/pack.h
index 520099cabfc..556821087d7 100644
--- a/tensorflow/lite/experimental/ruy/pack.h
+++ b/tensorflow/lite/experimental/ruy/pack.h
@@ -262,7 +262,7 @@ void PackFloatNeonInOrder(const float* src_ptr0, const float* src_ptr1,
                           float* packed_ptr, int start_col, int end_col);
 
 template <>
-struct PackImpl<Path::kNeon, FixedKernelLayout<Order::kRowMajor, 1, 8>, float,
+struct PackImpl<Path::kNeon, FixedKernelLayout<Order::kRowMajor, 4, 8>, float,
                 float, float> {
   static void Run(Tuning tuning, const Matrix<float>& src_matrix,
                   PackedMatrix<float>* packed_matrix, int start_col,