master

Nnihuiniapple a11 and a12 do not support armv8.2 dotprod, restore the fp16-only optimized path

11794675创建于 2021年8月2日历史提交

文件	最后提交记录	最后更新时间
ncnnConfig.cmake.in	find threads in cmake config	5 年前
ncnn_add_layer.cmake	apple a11 and a12 do not support armv8.2 dotprod, restore the fp16-only optimized path	4 年前
ncnn_add_shader.cmake	bring up vulkan 1.1 (#2191) * query subgroup features * compile spirv 1.3 * drop offline spirv build * do not build tests for android and ios, as they are never tested anyway * code style	5 年前
ncnn_generate_arm82_source.cmake	armv8.2 infrastructure (#1856) * runtime cpu dispatch * force thread one * disable openmp for coverage * simplify test layer * print NCNN_TARGET_ARCH * less ci build variants * weight fp16 storage option * test convdw int8 * apple a12 a13 * ncnn_add_layer ncnn_add_shader cmake macro	5 年前
ncnn_generate_arm82dot_source.cmake	runtime detect armv8.2 dotprod	5 年前
ncnn_generate_avx2_source.cmake	avx2 infrastructure (#1943)	5 年前
ncnn_generate_avx_source.cmake	Added ability to switch AVX/AVX2 during runtime (#3076)	4 年前
ncnn_generate_mmi_source.cmake	runtime cpu dispatch for mips msa and loongson mmi	4 年前
ncnn_generate_msa_source.cmake	runtime cpu dispatch for mips msa and loongson mmi	4 年前
ncnn_generate_rvv_source.cmake	runtime riscv v and zfh dispatch, riscv v optimization for cast	5 年前
ncnn_generate_shader_comp_header.cmake	fix ci build	6 年前
ncnn_generate_shader_spv_header.cmake	fix image1d_xx8 macro, normalize image shader	6 年前
run_test.cmake	Ci rv64gcv and rv64gc (#1936)	5 年前