diff options
author | Gian Marco <gianmarco.iodice@arm.com> | 2017-11-28 09:10:03 +0000 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:41:58 +0000 |
commit | 58c5794b917dae10ff115dd85ec69e2ca41136c1 (patch) | |
tree | f2cea2d94e6566be720256dc6105056798723699 /arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h | |
parent | 754e9526a7caf50876c2db9563dc72f096093b34 (diff) | |
download | ComputeLibrary-58c5794b917dae10ff115dd85ec69e2ca41136c1.tar.gz |
COMPMID-706 - Add GEMMLowp output stage for scaling by a fixed point number
DoD:
- Implement NEON kernel for quantizing down the gemmlowp result. The
result should be scaled by a fixedpoint number
- Implement OpenCL kernel for quantizing down the gemmlowp result. The
result should be scaled by a fixedpoint number
- Add test for validating the result
Required for:
- Integration of GEMMLowp in Android NN
- Convolution quantized
- Fully connected quantized
Change-Id: Ia963d25d695471e963961fb49a5600e78374ac4f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110981
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h')
-rw-r--r-- | arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h | 19 |
1 files changed, 16 insertions, 3 deletions
diff --git a/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h b/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h index 75f3750714..08554983d6 100644 --- a/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h +++ b/arm_compute/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel.h @@ -21,8 +21,8 @@ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ -#ifndef __ARM_COMPUTE_CLGEMMLOWPQUANTIZEDOWNINT32TOUINT8SCALE_H__ -#define __ARM_COMPUTE_CLGEMMLOWPQUANTIZEDOWNINT32TOUINT8SCALE_H__ +#ifndef __ARM_COMPUTE_CLGEMMLOWPQUANTIZEDOWNINT32TOUINT8SCALEKERNEL_H__ +#define __ARM_COMPUTE_CLGEMMLOWPQUANTIZEDOWNINT32TOUINT8SCALEKERNEL_H__ #include "arm_compute/core/CL/ICLKernel.h" @@ -70,6 +70,19 @@ public: * Along with @p min, this value can be used to implement "rectified linear unit" activation functions */ void configure(const ICLTensor *input, const ICLTensor *bias, ICLTensor *output, int result_offset, int result_mult_int, int result_shift, int min = 0, int max = 0); + /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMLowpQuantizeDownInt32ToUint8ScaleKernel + * + * @param[in] input Input tensor. Data type supported: S32 + * @param[in] bias Biases tensor. Only shared biases supported and it can be a nullptr if the biases addition is not required. + * Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p input. + * @param[in] output Output tensor. Data type supported: Data type supported: QASYMM8 + * @param[in] min (Optional) Min value used to saturate down the output result before converting back to QASYMM8 + * @param[in] max (Optional) Max value used to saturate up the output result before converting back to QASYMM8, + * Along with @p min, this value can be used to implement "rectified linear unit" activation functions + * + * @return an error status + */ + static Error validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, int min = 0, int max = 0); // Inherited methods overridden: void run(const Window &window, cl::CommandQueue &queue) override; @@ -81,4 +94,4 @@ private: }; } // namespace arm_compute -#endif /* __ARM_COMPUTE_CLGEMMLOWPQUANTIZEDOWNINT32TOUINT8SCALE_H__ */
\ No newline at end of file +#endif /* __ARM_COMPUTE_CLGEMMLOWPQUANTIZEDOWNINT32TOUINT8SCALEKERNEL_H__ */
\ No newline at end of file |