diff options
author | Anthony Barbier <anthony.barbier@arm.com> | 2018-07-06 17:05:59 +0100 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:54:54 +0000 |
commit | 71d9b57aac146ae3ad5648c1308a872cea90070d (patch) | |
tree | b4f36f7c6a45782ef9e40fe4c6a9e9a68d716948 /arm_compute/runtime/NEON/functions/NEGEMM.h | |
parent | d1794ebfa10d05af7d2458c5d506152fd38068d3 (diff) | |
download | ComputeLibrary-71d9b57aac146ae3ad5648c1308a872cea90070d.tar.gz |
COMPMID-1381: Cleaned up the AssemblyHelper interface
Introduced a new IFunction for when we'll fork the arm_gemm functions
Increased encapsulation and abstraction of which method is used
Change-Id: I5fd8b14b5c77e7f8ecb09029b5e2eccd10dbdcf4
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/139108
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEGEMM.h')
-rw-r--r-- | arm_compute/runtime/NEON/functions/NEGEMM.h | 7 |
1 files changed, 2 insertions, 5 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEGEMM.h b/arm_compute/runtime/NEON/functions/NEGEMM.h index cf059e5c4d..523f1d33a1 100644 --- a/arm_compute/runtime/NEON/functions/NEGEMM.h +++ b/arm_compute/runtime/NEON/functions/NEGEMM.h @@ -32,10 +32,9 @@ #include "arm_compute/runtime/IFunction.h" #include "arm_compute/runtime/IMemoryManager.h" #include "arm_compute/runtime/MemoryGroup.h" +#include "arm_compute/runtime/NEON/functions/NEGEMMAssemblyDispatch.h" #include "arm_compute/runtime/Tensor.h" -#include "arm_compute/runtime/NEON/AssemblyHelper.h" - #include <memory> namespace arm_compute @@ -86,12 +85,10 @@ private: NEGEMMInterleave4x4Kernel _interleave_kernel; NEGEMMTranspose1xWKernel _transpose_kernel; NEGEMMMatrixMultiplyKernel _mm_kernel; - AssemblyKernelGlueF32 _asm_glue; + NEGEMMAssemblyDispatchF32 _asm_glue; NEGEMMMatrixAdditionKernel _ma_kernel; Tensor _tmp_a; Tensor _tmp_b; - Tensor _workspace; - Tensor _B_pretransposed; const ITensor *_original_b; bool _run_vector_matrix_multiplication; bool _run_addition; |