ONCPUML-1072: Remove double definition of get_mws for Mul kernel

Signed-off-by: fadara01 <fadi.arafeh@arm.com>
Change-Id: Ieaa2fa4a6a69e7e0a48633967dabe91c786b42b7
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8682
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

2 files changed, 15 insertions, 17 deletions

diff --git a/src/cpu/kernels/CpuMulKernel.cpp b/src/cpu/kernels/CpuMulKernel.cpp
index 81bb85c3dd..cc7efe0a1d 100644
--- a/src/cpu/kernels/CpuMulKernel.cpp
+++ b/src/cpu/kernels/CpuMulKernel.cpp
@@ -38,6 +38,7 @@ namespace
 {
     static constexpr size_t default_mws_N1_fp32_neon = 22447;
     static constexpr size_t default_mws_V1_fp32_neon = 38982;
+    static constexpr size_t default_mws_other_platforms_1d_tensor = 10240;
 }
 namespace arm_compute
 {
@@ -1932,7 +1933,13 @@ size_t CpuMulKernel::get_mws(const CPUInfo &platform, size_t thread_count) const
         }
         else
         {
-            return ICPPKernel::default_mws;
+            if(_split_dimension == Window::DimX)
+            {
+                // Don't split the work load too small if the tensor has been reinterpreted as 1D.
+                // This number is loosely chosen as threading overhead in each platform varies wildly.
+                return default_mws_other_platforms_1d_tensor;
+            }
+            return default_mws;
         }
 
         // tensor is 1D or was re-interpreted as 1D
@@ -1952,7 +1959,13 @@ size_t CpuMulKernel::get_mws(const CPUInfo &platform, size_t thread_count) const
 #else /* ENABLE_FP32_KERNELS */
     ARM_COMPUTE_UNUSED(platform);
 #endif /* ENABLE_FP32_KERNELS */
-    return ICPPKernel::default_mws;
+    if(_split_dimension == Window::DimX)
+    {
+        // Don't split the work load too small if the tensor has been reinterpreted as 1D.
+        // This number is loosely chosen as threading overhead in each platform varies wildly.
+        return default_mws_other_platforms_1d_tensor;
+    }
+    return default_mws;
 }
 
 Status CpuMulKernel::validate(const ITensorInfo *src1, const ITensorInfo *src2, const ITensorInfo *dst, float scale, ConvertPolicy overflow_policy,
@@ -1994,20 +2007,6 @@ const char *CpuMulKernel::name() const
     return "CpuMulKernel";
 }
 
-size_t CpuMulKernel::get_mws(const CPUInfo &platform, size_t thread_count) const
-{
-    ARM_COMPUTE_UNUSED(platform, thread_count);
-
-    if(_split_dimension == Window::DimX)
-    {
-        // Don't split the work load too small if the tensor has been reinterpreted as 1D.
-        // This number is loosely chosen as threading overhead in each platform varies wildly.
-        return 10240;
-    }
-
-    return default_mws;
-}
-
 namespace
 {
 Status validate_arguments_complex(const ITensorInfo *src1, const ITensorInfo *src2, const ITensorInfo *dst)
diff --git a/src/cpu/kernels/CpuMulKernel.h b/src/cpu/kernels/CpuMulKernel.h
index 73ffc0dd2b..0d6f586117 100644
--- a/src/cpu/kernels/CpuMulKernel.h
+++ b/src/cpu/kernels/CpuMulKernel.h
@@ -79,7 +79,6 @@ public:
     // Inherited methods overridden
     void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override;
     const char *name() const override;
-    size_t get_mws(const CPUInfo &platform, size_t thread_count) const override;
 
     /** Return minimum workload size of the relevant kernel
      *