Revert "Update CPU kernels and add mixed sign GEMM support"

This reverts commit fc94f4d23abd4bc427b701f54ad85282e9ec7872 and 5d6fff041ade7eb44af0945867212f3979be3d3e (because the latter fixes a build failure caused by the former)

Change-Id: I7d07fea8307e9a7033b30874bbb14ba9202b23d8
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11815
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Adnan AlSinan <adnan.alsinan@arm.com>

5 files changed, 26 insertions, 26 deletions

diff --git a/src/core/NEON/kernels/convolution/winograd/output_transforms/a64_fp16_4x4_3x3.cpp b/src/core/NEON/kernels/convolution/winograd/output_transforms/a64_fp16_4x4_3x3.cpp
index 4218b754b4..295005a2ee 100644
--- a/src/core/NEON/kernels/convolution/winograd/output_transforms/a64_fp16_4x4_3x3.cpp
+++ b/src/core/NEON/kernels/convolution/winograd/output_transforms/a64_fp16_4x4_3x3.cpp
@@ -34,13 +34,13 @@ namespace output_transform {
 void a64_fp16_4x4_3x3(
     unsigned int n_channels,
     const __fp16* inptr,
-    const size_t matrix_stride,
+    size_t matrix_stride,
     const __fp16* bptr,
     __fp16* const output,
-    const size_t output_row_stride,
-    const size_t output_col_stride,
-    const __fp16 output_min,
-    const __fp16 output_max
+    size_t output_row_stride,
+    size_t output_col_stride,
+    __fp16 output_min,
+    __fp16 output_max
 )
 {
     constexpr int output_tile_rows = 4, output_tile_cols = 4;
diff --git a/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_2x2_3x3.cpp b/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_2x2_3x3.cpp
index 4c7376bef8..28f042bcbf 100644
--- a/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_2x2_3x3.cpp
+++ b/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_2x2_3x3.cpp
@@ -33,13 +33,13 @@ namespace output_transform {
 void arm_fp32_2x2_3x3(
   unsigned int n_channels,
   const float* inptr,
-  const size_t matrix_stride,
+  size_t matrix_stride,
   const float* bptr,
   float *outptr,
-  const size_t output_row_stride,
-  const size_t output_col_stride,
-  const float output_min,
-  const float output_max
+  size_t output_row_stride,
+  size_t output_col_stride,
+  float output_min,
+  float output_max
 )
 {
   constexpr auto output_tile_rows = 2u, output_tile_cols = 2u;
diff --git a/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_2x2_5x5.cpp b/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_2x2_5x5.cpp
index d5649b8a18..8e5ba74ac3 100644
--- a/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_2x2_5x5.cpp
+++ b/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_2x2_5x5.cpp
@@ -33,13 +33,13 @@ namespace output_transform {
 void arm_fp32_2x2_5x5(
   unsigned int n_channels,
   const float* inptr,
-  const size_t matrix_stride,
+  size_t matrix_stride,
   const float* bptr,
   float *outptr,
-  const size_t output_row_stride,
-  const size_t output_col_stride,
-  const float output_min,
-  const float output_max
+  size_t output_row_stride,
+  size_t output_col_stride,
+  float output_min,
+  float output_max
 )
 {
   constexpr auto output_tile_rows = 2u, output_tile_cols = 2u;
diff --git a/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_4x4_3x3.cpp b/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_4x4_3x3.cpp
index 6a32f67b5d..72c43019fa 100644
--- a/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_4x4_3x3.cpp
+++ b/src/core/NEON/kernels/convolution/winograd/output_transforms/arm_fp32_4x4_3x3.cpp
@@ -33,13 +33,13 @@ namespace output_transform {
 void arm_fp32_4x4_3x3(
   unsigned int n_channels,
   const float* inptr,
-  const size_t matrix_stride,
+  size_t matrix_stride,
   const float* bptr,
   float *outptr,
-  const size_t output_row_stride,
-  const size_t output_col_stride,
-  const float output_min,
-  const float output_max
+  size_t output_row_stride,
+  size_t output_col_stride,
+  float output_min,
+  float output_max
 )
 {
   constexpr auto output_tile_rows = 4u, output_tile_cols = 4u;
diff --git a/src/core/NEON/kernels/convolution/winograd/output_transforms/sme_fp32_mopa_4x4_3x3.cpp b/src/core/NEON/kernels/convolution/winograd/output_transforms/sme_fp32_mopa_4x4_3x3.cpp
index 8d2b00c1fb..043914d590 100644
--- a/src/core/NEON/kernels/convolution/winograd/output_transforms/sme_fp32_mopa_4x4_3x3.cpp
+++ b/src/core/NEON/kernels/convolution/winograd/output_transforms/sme_fp32_mopa_4x4_3x3.cpp
@@ -31,15 +31,15 @@ namespace winograd {
 namespace output_transform {
 
 void sme_fp32_mopa_4x4_3x3(
-  const unsigned int n_channels,
+  unsigned int n_channels,
   const float* inptr,
-  const size_t matrix_stride,
+  size_t matrix_stride,
   const float* bptr,
   float* const output,
-  const size_t output_row_stride,
-  const size_t output_col_stride,
-  const float output_min,
-  const float output_max
+  size_t output_row_stride,
+  size_t output_col_stride,
+  float output_min,
+  float output_max
 )
 {
   // The below assembler uses the Kronecker product and the "vec trick" to