Functions — github.com/Tencent/FeatherCNN

CodeHub MCPcopy Create free account

hub / github.com/Tencent/FeatherCNN / functions

Functions513 in github.com/Tencent/FeatherCNN

⨍ Functions 513◇ Types & classes 59

↓ 128 callersFunctionvfmaq_laneq_f32

src/booster/include/booster/helper.h:53

↓ 52 callersMethoddata

↓ 40 callersMethodget

src/ncnn/paramdict.cpp:33

↓ 36 callersMethodempty

src/ncnn/mat.h:813

↓ 31 callersMethodchannel

src/ncnn/mat.h:823

↓ 27 callersMethodset

src/ncnn/paramdict.cpp:48

↓ 20 callersMethodchannels

↓ 19 callersMethodReshapeWithRealloc

src/blob.cpp:38

↓ 19 callersMethodheight

↓ 19 callersMethodwidth

↓ 18 callersFunctionalignSize

Aligns a buffer size to the specified number of bytes The function returns the minimum number that is greater or equal to sz and is divisible by n sz

src/ncnn/allocator.h:52

↓ 16 callersFunctionmin

src/utils.cpp:45

↓ 12 callersMethoddata_size

↓ 11 callersMethodcreate

src/ncnn/mat.h:592

↓ 11 callersMethodload_param

src/ncnn/paramdict.cpp:92

↓ 10 callersFunctionclock_gettime

src/booster/avx/helper.cpp:83

↓ 10 callersMethodload

src/ncnn/modelbin.cpp:24

↓ 9 callersFunction_mm_malloc

src/utils.cpp:52

↓ 9 callersMethodnum

↓ 9 callersMethodunlock

src/ncnn/allocator.h:129

↓ 8 callersFunctionfastMalloc

src/ncnn/allocator.h:57

↓ 8 callersFunctioninput_transform

src/booster/avx/winograd_kernels_F63.cpp:272

↓ 8 callersFunctionneon_transpose4x4_inplace_f32_cpp

src/booster/arm/winograd_kernels_F63.cpp:65

↓ 8 callersFunctionneon_transpose4x4_inplace_f32_cpp

src/booster/avx/winograd_kernels_F63.cpp:67

↓ 8 callersFunctionwinograd_f6k3_output_transform_inplace

src/booster/avx/winograd_kernels_F63.cpp:1029

↓ 7 callersMethodAssignPaddedDim

src/booster/include/booster/booster.h:126

↓ 7 callersMethodCopyDataFromMat

src/blob.cpp:79

↓ 7 callersMethodlock

src/ncnn/allocator.h:128

↓ 6 callersFunction_mm_free

src/utils.cpp:67

↓ 6 callersMethodendBench

src/booster/arm/helper.cpp:112

↓ 6 callersMethodfastMalloc

src/ncnn/allocator.cpp:75

↓ 6 callersMethodstartBench

src/booster/arm/helper.cpp:107

↓ 5 callersFunctionfastFree

src/ncnn/allocator.h:78

↓ 4 callersFunctionNCNN_XADD

thread-unsafe branch

src/ncnn/allocator.h:119

↓ 4 callersFunctioninput_transform

src/booster/arm/winograd_kernels_F63.cpp:291

↓ 4 callersFunctioninternalPackB8

src/booster/arm/sgemm_legacy.cpp:833

↓ 4 callersFunctionnaive_gemm_temp

src/booster/arm/winograd_kernels_F63.cpp:41

↓ 4 callersFunctionnaive_gemm_temp

src/booster/avx/winograd_kernels_F63_fused.cpp:222

↓ 4 callersFunctionnaive_gemm_temp

src/booster/avx/winograd_kernels_F63.cpp:42

↓ 4 callersFunctionvstr_is_float

src/ncnn/paramdict.cpp:77

↓ 4 callersFunctionwinograd_f6k3_output_transform_inplace

src/booster/arm/winograd_kernels_F63.cpp:971

↓ 3 callersFunctionalign_ceil

src/booster/arm/sgemm.cpp:17

↓ 3 callersFunctionalign_ceil

src/booster/arm/sgeconv.cpp:13

↓ 3 callersFunctionalign_ceil

src/booster/avx/sgemm.cpp:6

↓ 3 callersFunctionalign_ceil

src/booster/avx/sgeconv.cpp:6

↓ 3 callersFunctionblock_sgemm_pack

src/booster/arm/sgemm_legacy.cpp:295

↓ 3 callersFunctionblock_sgemm_pack_8x8

double check here

src/booster/arm/sgemm_legacy.cpp:329

↓ 3 callersMethodendBench

src/booster/avx/helper.cpp:94

↓ 3 callersFunctionget_innerkernel_8

src/booster/arm/sgemm_legacy.cpp:122

↓ 3 callersFunctioninternalPackA4

src/booster/arm/sgemm_legacy.cpp:756

↓ 3 callersMethodnum_threads

src/rt_param.h:47

↓ 3 callersFunctionpad_input

src/booster/arm/generic_kernels.cpp:31

↓ 3 callersFunctionresize_bilinear_c1

src/ncnn/mat_pixel_resize.cpp:27

↓ 3 callersFunctionsgemm_8x8_pack

src/booster/arm/sgemm_legacy.cpp:508

↓ 3 callersMethodstartBench

src/booster/avx/helper.cpp:89

↓ 2 callersMethodFree

src/mempool.cpp:69

↓ 2 callersFunctionGEBPInnerKernel4x1x4

src/booster/arm/winograd_kernels.cpp:705

↓ 2 callersFunctionGEBPInnerKernel4x2x4

src/booster/arm/winograd_kernels.cpp:629

↓ 2 callersFunctionGEBPInnerKernel4x3x4

src/booster/arm/winograd_kernels.cpp:537

↓ 2 callersFunctionGEBPInnerKernel4x4x4

src/booster/arm/winograd_kernels.cpp:431

↓ 2 callersFunctionSGEBP_externalPackA_tiny_scale_8x8

src/booster/arm/sgemm_legacy.cpp:240

↓ 2 callersMethodSetFuncs

src/booster/arm/booster.cpp:304

↓ 2 callersMethodSetFuncs

src/booster/avx/booster.cpp:319

↓ 2 callersFunctionTensorGEMM

static inline void TensorGEMMInnerKernel4x1x4(float* &WTp, const int &wstride, const float* &UTp, const float* &vp, const int &inChannels)

src/booster/avx/winograd_kernels_F63.cpp:518

↓ 2 callersFunctionTensorGEMMInnerKernel4x1x4

src/booster/avx/winograd_kernels_F63.cpp:981

↓ 2 callersFunctionTensorGEMMInnerKernel4x2x4

src/booster/avx/winograd_kernels_F63.cpp:923

↓ 2 callersFunctionTensorGEMMInnerKernel4x3x4

src/booster/avx/winograd_kernels_F63.cpp:849

↓ 2 callersMethodcommon_mempool

src/rt_param.h:43

↓ 2 callersFunctionfeather_mm256_get_mask

src/booster/avx/winograd_kernels_F63_fused.cpp:416

↓ 2 callersFunctionim2col

src/booster/arm/generic_kernels.cpp:50

↓ 2 callersFunctionim2col

src/booster/avx/generic_kernels.cpp:50

↓ 2 callersFunctioninner_kernel_4x12

src/booster/arm/sgeconv.cpp:110

↓ 2 callersFunctioninputTransform

src/booster/arm/winograd_kernels.cpp:349

↓ 2 callersFunctioninput_transform_avx

src/booster/avx/winograd_kernels_F63_fused.cpp:356

↓ 2 callersFunctionmemset_floats_neon

src/booster/arm/sgeconv.cpp:68

↓ 2 callersFunctionneon_transpose4x4_inplace_f32

src/booster/arm/winograd_kernels.cpp:30

↓ 2 callersFunctionpack_B_avx

src/booster/avx/sgemm.cpp:350

↓ 2 callersFunctionpack_B_neon

src/booster/arm/sgemm.cpp:1058

↓ 2 callersFunctionpad_input

src/booster/avx/generic_kernels.cpp:31

↓ 2 callersMethodreshape

src/ncnn/mat.h:484

↓ 2 callersFunctionresize_bilinear_c3

src/ncnn/mat_pixel_resize.cpp:575

↓ 2 callersFunctionresize_bilinear_c4

src/ncnn/mat_pixel_resize.cpp:873

↓ 2 callersFunctionsgemm_4x8_pack

src/booster/arm/sgemm_legacy.cpp:619

↓ 2 callersFunctionsincos_ps

evaluation of 4 sines & cosines at once. * * The code is the exact rewriting of the cephes sinf function. * Precision is excellent as long as x

src/booster/include/booster/power.h:221

↓ 2 callersFunctiontransformKernel_F6x6_3x3

src/booster/avx/winograd_kernels_F63.cpp:256

↓ 2 callersFunctiontranspose8_avx_ps

src/booster/avx/winograd_kernels_F63_fused.cpp:125

↓ 2 callersFunctiontranspose_temp

src/booster/arm/winograd_kernels_F63.cpp:58

↓ 2 callersFunctiontranspose_temp

src/booster/avx/winograd_kernels_F63_fused.cpp:239

↓ 2 callersFunctiontranspose_temp

src/booster/avx/winograd_kernels_F63.cpp:59

↓ 2 callersFunctionwinogradInputFrameTransformSeq

src/booster/avx/winograd_kernels_F63.cpp:327

↓ 2 callersFunctionwinogradInputFrameTransformStride

src/booster/arm/winograd_kernels.cpp:363

↓ 2 callersFunctionwinogradKernelTransformPacked

src/booster/avx/winograd_kernels_F63_fused.cpp:278

↓ 2 callersFunctionwinogradOutputTransform

src/booster/arm/winograd_kernels.cpp:806

↓ 2 callersFunctionwinogradOutputTransformBias

src/booster/arm/winograd_kernels.cpp:861

↓ 2 callersFunctionwinogradOutputTransformBiasReLU

src/booster/arm/winograd_kernels.cpp:914

↓ 2 callersFunctionwinogradOutputTransformReLU

src/booster/arm/winograd_kernels.cpp:971

↓ 2 callersFunctionwinograd_f6k3_output_transform_inplace_avx

src/booster/avx/winograd_kernels_F63_fused.cpp:164

↓ 1 callersMethodAlloc

src/mempool.cpp:32

↓ 1 callersMethodAlloc

src/blob.cpp:22

↓ 1 callersMethodAssignOutputDim

src/booster/include/booster/booster.h:113

next →1–100 of 513, ranked by callers