commit c4f2743951473f8d97f5a43767fdbb31a4df967c
author Gunes Bayir <gunes.bayir@arm.com> Sun Sep 11 15:59:19 2022 +0100
committer Gunes Bayir <gunes.bayir@arm.com> Fri Sep 16 12:38:59 2022 +0000
tree 26c49b1af8113bb169931f3af5e502904d455a25
parent 0d05b6690fe69c57f63ca43d59b551f074613062

Optimize Quantized/Integer Bilinear Scale for Neon™

This patch introduces several performance optimizations regarding the Bilinear Scale operator with REPLICATE Border mode. Changes apply only to NHWC.

This patch
   - Reduces the memory footprint by disabling precomputation of indices and weights when they're not used
   - Rewrites the kernels for QASYMM8/QASYMM8_SIGNED/U8(Uint8)
   - Adds S8(Int8) Bilinear Scale for Border mode REPLICATE
   - Removes Bilinear Scale SVE kernels for Quantized and Integer types and adjust the heuristics to choose the Neon™ implementation
   - Adds new test cases where the input and output of the Bilinear Scale operator have different quantization scale and offset

Resolves: COMPMID-5453, COMPMID-5454

Change-Id: I3d251e76e0c6978fd5a0a1795ec62ab536bec93c
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8250
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

src/core/utils/ScaleUtils.cpp

diff --git a/src/core/utils/ScaleUtils.cpp b/src/core/utils/ScaleUtils.cpp
index 82c6405..ee57a8e 100644
--- a/src/core/utils/ScaleUtils.cpp
+++ b/src/core/utils/ScaleUtils.cpp
@@ -40,12 +40,26 @@
     return static_cast<float>(in) / static_cast<float>(out);
 }
 
-bool arm_compute::scale_utils::is_precomputation_required(DataLayout data_layout, DataType data_type, InterpolationPolicy policy)
+bool arm_compute::scale_utils::is_precomputation_required(DataLayout data_layout, DataType data_type,
+                                                          InterpolationPolicy policy, BorderMode border_mode)
 {
-    // whether to precompute indices & weights
-    // The Neon™ kernels (which are preferred over SVE when policy is BILINEAR) do not use
-    // precomputed index and weights when data type is FP32/16.
-    // If policy is nearest_neighbor for SVE, then precompute because it's being used
-    // To be revised in COMPMID-5453/5454
-    return data_layout != DataLayout::NHWC || (data_type != DataType::F32 && data_type != DataType::F16) || (CPUInfo::get().get_isa().sve == true && policy == InterpolationPolicy::NEAREST_NEIGHBOR);
+    // Do not calculate precomputed weights and indices if kernel code doesn't use them
+    if(data_layout == DataLayout::NHWC)
+    {
+        switch(data_type)
+        {
+            case DataType::F32:
+            case DataType::F16:
+                return (CPUInfo::get().get_isa().sve == true && policy == InterpolationPolicy::NEAREST_NEIGHBOR);
+            case DataType::U8:
+            case DataType::S8:
+            case DataType::QASYMM8:
+            case DataType::QASYMM8_SIGNED:
+                return (border_mode != BorderMode::REPLICATE) || (policy == InterpolationPolicy::NEAREST_NEIGHBOR);
+            default:
+                return true;
+        }
+    }
+
+    return true;
 }
\ No newline at end of file