diff options
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/std_transforms_fixed.hpp')
-rw-r--r-- | src/core/NEON/kernels/arm_gemm/std_transforms_fixed.hpp | 20 |
1 files changed, 17 insertions, 3 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/std_transforms_fixed.hpp b/src/core/NEON/kernels/arm_gemm/std_transforms_fixed.hpp index 1d3aee7911..4669be9993 100644 --- a/src/core/NEON/kernels/arm_gemm/std_transforms_fixed.hpp +++ b/src/core/NEON/kernels/arm_gemm/std_transforms_fixed.hpp @@ -23,8 +23,10 @@ */ #pragma once +#include "convolver.hpp" #include "mergeresults.hpp" #include "transform.hpp" +#include "interleave_indirect.hpp" namespace arm_gemm { @@ -39,14 +41,26 @@ namespace arm_gemm { * The optional 'block' parameter is for kernels using dot-product type * instructions like UDOT and SDOT. */ -template<typename TOperand, typename TResult, unsigned int height, unsigned int width, unsigned int block=1> +template<typename TOperand, typename TResult, unsigned int height, unsigned int width, unsigned int block=1, bool integrate_sums=false> class StdTransformsFixed { public: template<typename TIn> void PrepareA(TOperand *out, const TIn *in, const int stride, const int y0, - const int ymax, const int k0, const int kmax) const { - Transform<height, block, false>(out, in, stride, y0, ymax, k0, kmax); + const int ymax, const int k0, const int kmax, int32_t row_sum_multiplier) const { + Interleave<height, block, VLType::None>(out, in, stride, y0, ymax, k0, kmax, integrate_sums, row_sum_multiplier); + } + + template<typename TIn> + void PrepareA_indirect(TOperand *out, const TIn * const * const *ptr, size_t stringlen, size_t rounded_stringlen, const int y0, + const int ymax, const int k0, const int kmax, int32_t row_sum_multiplier) { + IndirectInterleave<height, block, VLType::None>(out, ptr, stringlen, rounded_stringlen, y0, ymax, k0, kmax, integrate_sums, row_sum_multiplier); + } + + template<typename TIn> + void PrepareA_convolution(TOperand *out, const TIn *ptr, size_t stride, const convolver<TIn> &conv, size_t rounded_stringlen, + const int y0, const int ymax, const int k0, const int kmax, int32_t row_sum_multiplier) { + ConvolutionInterleave<height, block, VLType::None>(out, ptr, stride, conv, rounded_stringlen, y0, ymax, k0, kmax, integrate_sums, row_sum_multiplier); } template<typename TIn> |