commit 4a1c91767142f76e92bf4575564d7e54fcd0ebf4
author Pablo Marquez Tello <pablo.tello@arm.com> Tue Jul 18 14:51:24 2023 +0100
committer Pablo Marquez Tello <pablo.tello@arm.com> Wed Jul 19 15:21:03 2023 +0000
tree 9ff60356ad77b07c3704826c14eb316a9eb9ac27
parent 314d3e2c691734ff942c9a1aca1120b826a267d9

Add support for input S64/U64 in CpuCastKernel

* The kernel now supports the following conversions:
    S64 -> F32
    U64 -> F32

* Resolves MLCE-1089

Change-Id: I277cf58b78d919fde25947520d2056e1412c7f82
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9935
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

src/core/Utils.cpp

diff --git a/src/core/Utils.cpp b/src/core/Utils.cpp
index ef7186a..89f373f 100644
--- a/src/core/Utils.cpp
+++ b/src/core/Utils.cpp
@@ -414,7 +414,7 @@
     return QuantizationInfo(1.f / 256, 0);
 }
 
-std::pair<int32_t, int32_t> get_quantized_activation_min_max(const ActivationLayerInfo& act_info, DataType data_type, UniformQuantizationInfo oq_info)
+std::pair<int32_t, int32_t> get_quantized_activation_min_max(const ActivationLayerInfo &act_info, DataType data_type, UniformQuantizationInfo oq_info)
 {
     const bool is_qasymm8_signed = is_data_type_quantized_asymmetric_signed(data_type);
     const auto a                 = act_info.a();
@@ -497,6 +497,12 @@
         case DataType::S32:
             print_consecutive_elements_impl<int32_t>(s, reinterpret_cast<const int32_t *>(ptr), n, stream_width, element_delim);
             break;
+        case DataType::U64:
+            print_consecutive_elements_impl<uint64_t>(s, reinterpret_cast<const uint64_t *>(ptr), n, stream_width, element_delim);
+            break;
+        case DataType::S64:
+            print_consecutive_elements_impl<int64_t>(s, reinterpret_cast<const int64_t *>(ptr), n, stream_width, element_delim);
+            break;
         case DataType::BFLOAT16:
             print_consecutive_elements_impl<bfloat16>(s, reinterpret_cast<const bfloat16 *>(ptr), n, stream_width, element_delim);
             break;
@@ -533,6 +539,10 @@
             return max_consecutive_elements_display_width_impl<uint32_t>(s, reinterpret_cast<const uint32_t *>(ptr), n);
         case DataType::S32:
             return max_consecutive_elements_display_width_impl<int32_t>(s, reinterpret_cast<const int32_t *>(ptr), n);
+        case DataType::U64:
+            return max_consecutive_elements_display_width_impl<uint64_t>(s, reinterpret_cast<const uint64_t *>(ptr), n);
+        case DataType::S64:
+            return max_consecutive_elements_display_width_impl<int64_t>(s, reinterpret_cast<const int64_t *>(ptr), n);
         case DataType::BFLOAT16:
             return max_consecutive_elements_display_width_impl<bfloat16>(s, reinterpret_cast<const bfloat16 *>(ptr), n);
         case DataType::F16: