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/NEON/wrapper/intrinsics/cvt.h

diff --git a/src/core/NEON/wrapper/intrinsics/cvt.h b/src/core/NEON/wrapper/intrinsics/cvt.h
index e52e3dd..baad131 100644
--- a/src/core/NEON/wrapper/intrinsics/cvt.h
+++ b/src/core/NEON/wrapper/intrinsics/cvt.h
@@ -59,19 +59,35 @@
 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
 
 template <typename T>
-inline typename std::enable_if<std::is_same<T, uint8_t>::value, uint32x4_t>::type
+inline typename std::enable_if < std::is_same<T, uint8_t>::value || std::is_same<T, uint32_t>::value, uint32x4_t >::type
 vcvt(const float32x4_t &a)
 {
     return vcvtq_u32_f32(a);
 }
 
 template <typename T>
-inline typename std::enable_if<std::is_same<T, int8_t>::value, int32x4_t>::type
+inline typename std::enable_if < std::is_same<T, int8_t>::value || std::is_same<T, int32_t>::value, int32x4_t >::type
 vcvt(const float32x4_t &a)
 {
     return vcvtq_s32_f32(a);
 }
 
+#ifdef __aarch64__
+template <typename T>
+inline typename std::enable_if<std::is_same<T, uint32_t>::value, uint32x4_t>::type
+vcvta(const float32x4_t &a)
+{
+    return vcvtaq_u32_f32(a);
+}
+
+template <typename T>
+inline typename std::enable_if<std::is_same<T, int32_t>::value, int32x4_t>::type
+vcvta(const float32x4_t &a)
+{
+    return vcvtaq_s32_f32(a);
+}
+#endif //__aarch64__
+
 #if defined(ARM_COMPUTE_ENABLE_BF16)
 /** Convert 2x128-bit floating point vectors into 1x128-bit bfloat16 vector
  *