diff options
author | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-06-27 17:00:52 +0100 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-07-26 11:55:15 +0000 |
commit | cfa2bba98169cb5ab1945462514be1b6badf7d98 (patch) | |
tree | 1635e6e9463e9798c7195f0aa71b5df3f2650df1 /arm_compute/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.h | |
parent | f59b16f42ef68bde877b70816ffb953d64c8baa3 (diff) | |
download | ComputeLibrary-cfa2bba98169cb5ab1945462514be1b6badf7d98.tar.gz |
COMPMID-2178: Update GEMM assembly code.
Perform offset reduction and requantization within the assembly wrapper.
Change-Id: I5d5b3e1f6f9ef4c71805362c57f88ff199c027a3
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1541
Comments-Addressed: Pablo Marquez <pablo.tello@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.h')
-rw-r--r-- | arm_compute/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.h | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.h b/arm_compute/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.h index 38682843b7..dd23f1ce22 100644 --- a/arm_compute/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.h +++ b/arm_compute/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.h @@ -35,11 +35,10 @@ namespace arm_compute { +// Forward declarations class ITensor; -/** Basic function to execute matrix multiply assembly kernels. - * -*/ +/** Basic function to execute matrix multiply assembly kernels. */ class NEGEMMLowpAssemblyMatrixMultiplyCore : public IFunction { public: @@ -49,9 +48,10 @@ public: * * @param[in] a First input tensor (Matrix A). Data type supported: U8, S8. * @param[in] b Second input tensor (Matrix B). Data type supported: same as @p a + * @param[in] c Third input tensor (Matrix C). Data type supported: same as @p a * @param[out] output Output tensor. Data type supported: Data type supported: U32, S32 */ - void configure(const ITensor *a, const ITensor *b, ITensor *output); + void configure(const ITensor *a, const ITensor *b, const ITensor *c, ITensor *output); // Inherited methods overridden: void run() override; @@ -65,5 +65,5 @@ private: Tensor _tmp_a; Tensor _tmp_b; }; -} +} // namespace arm_compute #endif /*__ARM_COMPUTE_NEGEMMLOWPASSEMBLYMATRIXMULTIPLYCORE_H__ */ |