Add FP16 depthwise kernels for SME2
Resolves: COMPMID-5988
Change-Id: I93e78edf31c9eec8242ccbb8c3c768f46a7c7c38
Signed-off-by: David Mansell <David.Mansell@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9456
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt
index 336d2cd..28028e8 100644
--- a/src/CMakeLists.txt
+++ b/src/CMakeLists.txt
@@ -108,6 +108,16 @@
core/NEON/kernels/arm_conv/depthwise/interleaves/sve_8b_mla.cpp
core/NEON/kernels/arm_conv/depthwise/interleaves/sve_s8q_3x3_dot.cpp
core/NEON/kernels/arm_conv/depthwise/interleaves/sve_u8q_3x3_dot.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_3x3_s1_output2x2_mla_depthfirst/generic_direct.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_3x3_s1_output2x2_mla_depthfirst/generic_indirect.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_3x3_s1_output3x3_mla_depthfirst/generic_direct.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_3x3_s1_output3x3_mla_depthfirst/generic_indirect.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_3x3_s1_output4x4_mla_depthfirst/generic_direct.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_3x3_s1_output4x4_mla_depthfirst/generic_indirect.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_3x3_s2_output2x2_mla_depthfirst/generic_direct.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_3x3_s2_output2x2_mla_depthfirst/generic_indirect.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_5x5_s1_output2x2_mla_depthfirst/generic_direct.cpp
+ core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp16_nhwc_5x5_s1_output2x2_mla_depthfirst/generic_indirect.cpp
core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp32_nhwc_3x3_s1_output2x2_mla_depthfirst/generic_direct.cpp
core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp32_nhwc_3x3_s1_output2x2_mla_depthfirst/generic_indirect.cpp
core/NEON/kernels/arm_conv/depthwise/kernels/sme2_fp32_nhwc_3x3_s1_output3x3_mla_depthfirst/generic_direct.cpp
@@ -733,6 +743,8 @@
cpu/kernels/elementwise_unary/generic/neon/impl.cpp
cpu/kernels/elementwise_unary/generic/neon/integer.cpp
cpu/kernels/elementwise_unary/generic/neon/q8.cpp
+ cpu/kernels/elementwise_unary/generic/neon/qasymm8.cpp
+ cpu/kernels/elementwise_unary/generic/neon/qasymm8_signed.cpp
cpu/kernels/floor/neon/fp16.cpp
cpu/kernels/floor/neon/fp32.cpp
cpu/kernels/fuse_batch_normalization/generic/fp16.cpp
@@ -962,4 +974,5 @@
runtime/Tensor.cpp
runtime/TensorAllocator.cpp
runtime/Utils.cpp
-)
\ No newline at end of file
+)
+
\ No newline at end of file