commit 9d0c4deb760efc2ca07e5e0b8218995201ad8a1f
author Gunes Bayir <gunes.bayir@arm.com> Thu Apr 13 18:22:58 2023 +0100
committer Gunes Bayir <gunes.bayir@arm.com> Mon Apr 17 15:54:44 2023 +0000
tree 8f64b754d05768e2f69cfae387137140a6bb22b5
parent 99145f787e9e99b45522f16d861c8527583f2b4e

Add quantized CL MatMul kernels for Lhs NT/T, Rhs NT

Implement OpenCL kernels for batched Matrix Multiplication for the quantized data types QASYMM8 and QASYMM8_SIGNED.

Quantized MatMul is supported with the following MatMul attributes:
* adj_x = false, adj_y = false
* adj_x = true, adj_y = false

We consider native format kernels only. In other words, no reshaping of the operand matrices is done.

Resolves: COMPMID-5921, COMPMID-5922

Change-Id: I99e0f68054a2bd635c60ec2641acc2e7ff398473
Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com>
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9435
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

SConscript

diff --git a/SConscript b/SConscript
index 03b94b6..e6ef73c 100644
--- a/SConscript
+++ b/SConscript
@@ -390,6 +390,7 @@
                        'src/core/CL/cl_kernels/common/instance_normalization.cl',
                        'src/core/CL/cl_kernels/common/l2_normalize.cl',
                        'src/core/CL/cl_kernels/common/mat_mul.cl',
+                       'src/core/CL/cl_kernels/common/mat_mul_quantized.cl',
                        'src/core/CL/cl_kernels/common/mean_stddev_normalization.cl',
                        'src/core/CL/cl_kernels/common/memset.cl',
                        'src/core/CL/cl_kernels/common/minmax_layer.cl',