COMPMID-3348: Fix issue in gemmlowp_matrix_b_reduction OpenCL kernel

Change-Id: I67be39a9f60d20694dda970356c94cb6d90445ea
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3016
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>

diff --git a/src/core/CL/cl_kernels/gemmlowp.cl b/src/core/CL/cl_kernels/gemmlowp.cl
index d6f415b715c518c86280bba9bcf904a406104c8d..127df063f64234134ce15c341db988b3221f097f 100644 (file)
--- a/src/core/CL/cl_kernels/gemmlowp.cl
+++ b/src/core/CL/cl_kernels/gemmlowp.cl
@@ -1496,7 +1496,7 @@ __kernel void gemmlowp_matrix_b_reduction(TENSOR3D_DECLARATION(src),
     sum_col_32 *= (VEC_DATA_TYPE(ACC_DATA_TYPE, 16))SCALAR;
 #endif // defined(SCALAR)
     VSTORE(16)
-    (sum_col_32, 0, (__global int *)dst.ptr);
+    (convert_int16(sum_col_32), 0, (__global int *)dst.ptr);
 }
 #endif // defined(COLS_B) && defined(ROWS_B)