Update CPU kernel implementations and guard directives
Resolves COMPMID-6023
Change-Id: I868975d14c4f98af6716726feda22405a6a4c891
Signed-off-by: Michael Tyler <michael.tyler@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9686
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>
diff --git a/src/core/NEON/kernels/arm_conv/depthwise/depthwise_fp16.cpp b/src/core/NEON/kernels/arm_conv/depthwise/depthwise_fp16.cpp
index 350e93b..134dbd1 100644
--- a/src/core/NEON/kernels/arm_conv/depthwise/depthwise_fp16.cpp
+++ b/src/core/NEON/kernels/arm_conv/depthwise/depthwise_fp16.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2021-2022 Arm Limited.
+ * Copyright (c) 2021-2023 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -77,6 +77,18 @@
);
}
+ template <class Strategy>
+ unsigned int planar_cycle_estimate(const DepthwiseArgs &args, const Nothing &)
+ {
+ // First-pass: compute the number of output pixels which will be computed.
+ return arm_gemm::roundup(args.output_rows, Strategy::output_rows) *
+ args.output_cols *
+ arm_gemm::iceildiv(
+ (long unsigned) args.input_channels * args.channel_multiplier,
+ arm_gemm::utils::get_vector_length<typename Strategy::return_type>(Strategy::vl_type)
+ );
+ }
+
#if defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC)
unsigned int not_preferred(const DepthwiseArgs &, const Nothing &) __attribute__ ((unused));
unsigned int not_preferred(const DepthwiseArgs &, const Nothing &)