p60975123
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!23653 [MSLITE][Develop] clean code check warnings 

Merge pull request !23653 from yangruoqi713/codex
This commit is contained in:
i-robot 2021-09-18 01:26:21 +00:00 committed by Gitee
parent 9a257bd487 2b60b2cf39
commit 6fd0e67a7f
12 changed files with 72 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/fp32/layer_norm_fp32.c
View File

@ -68,7 +68,7 @@ void LayerNormGammaAndBeta(float *dst, const float *src, const float *gamma_data
}
int LayerNorm(const float *src_data, const float *gamma_data, const float *beta_data, float *dst_data, float *out_mean,
float *out_deno, LayerNormParameter *param, size_t task_id) {
float *out_deno, const LayerNormParameter *param, size_t task_id) {
if (src_data == NULL || dst_data == NULL || gamma_data == NULL || beta_data == NULL) {
return NNACL_NULL_PTR;
}

2
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/fp32/layer_norm_fp32.h
View File

@ -24,7 +24,7 @@ extern "C" {
#endif
int LayerNorm(const float *src_data, const float *gamma_data, const float *beta_data, float *dst_data, float *out_mean,
float *out_deno, LayerNormParameter *param, size_t task_id);
float *out_deno, const LayerNormParameter *param, size_t task_id);
#ifdef __cplusplus
}
#endif

21
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/fp32/lstm_fp32.c
View File

@ -154,20 +154,23 @@ void UpdataOutput(const float *cell_state, const float *output_gate, float *hidd
void UpdateLstmGate(float *gate_buffer, const float *input, const float *weight, const float *bias, int row, int deep,
int col, int col_align, bool is_vec, float *packed_ptr) {
const float *weight_i = weight;
const float *bias_i = bias;
float *gate_i = gate_buffer;
for (int i = 0; i < 4; i++) {
const float *weight_i;
LstmMatMul(gate_i, input, weight_i, bias_i, row, deep, col, col_align, is_vec, packed_ptr);
#ifdef ENABLE_AVX
if (is_vec) {
weight_i = weight + deep * col_align * i;
weight_i += deep * col_align;
} else {
weight_i = weight + deep * col * i;
weight_i += deep * col;
}
#else
weight_i = weight + deep * col * i;
weight_i += deep * col;
#endif
const float *bias_i = bias + col_align * i;
float *gate = gate_buffer + row * col * i;
LstmMatMul(gate, input, weight_i, bias_i, row, deep, col, col_align, is_vec, packed_ptr);
bias_i += col_align;
gate_i += row * col;
}
}
@ -228,7 +231,7 @@ void LstmStepUnit(float *output, float *input_gate, float *forget_gate, float *c
void LstmUnidirectional(float *output, const float *packed_input, const float *weight_i, const float *weight_h,
const float *input_bias, const float *state_bias, float *hidden_state, float *cell_state,
float *buffer[6], const LstmParameter *lstm_param, bool is_backward) {
float *buffer[7], const LstmParameter *lstm_param, bool is_backward) {
float *gate = buffer[1];
for (int i = 0; i < 4; i++) {
const float *weight_loop = weight_i + lstm_param->input_size_ * lstm_param->input_col_align_ * i;
@ -256,7 +259,7 @@ void LstmUnidirectional(float *output, const float *packed_input, const float *w
}
void Lstm(float *output, const float *input, const float *weight_i, const float *weight_h, const float *input_bias,
const float *state_bias, float *hidden_state, float *cell_state, float *buffer[6],
const float *state_bias, float *hidden_state, float *cell_state, float *buffer[7],
const LstmParameter *lstm_param) {
// forward
float *packed_input = buffer[0];

4
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/fp32/lstm_fp32.h
View File

@ -36,10 +36,10 @@ int ElementOptMulAcc(const float *input0, const float input1, float *output, con
void LstmStepUnit(float *output, float *input_gate, float *forget_gate, float *cell_gate, float *output_gate,
const float *state_weight, const float *state_bias, float *hidden_state, float *cell_state,
float *buffer[6], const LstmParameter *lstm_param);
float *buffer[7], const LstmParameter *lstm_param);
void Lstm(float *output, const float *input, const float *weight_i, const float *weight_h, const float *input_bias,
const float *state_bias, float *hidden_state, float *cell_state, float *buffer[6],
const float *state_bias, float *hidden_state, float *cell_state, float *buffer[7],
const LstmParameter *lstm_param);
#ifdef __cplusplus
}

35
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/int8/common_func_int8.h
View File

@ -34,17 +34,17 @@ void PostFuncInt8C4(const int32_t *in, const int32_t *bias, int8_t *out, size_t
void ConvDwInt8Row(int32_t *output_ptr, const int8_t *input_ptr, const int16_t *weight_ptr, int num_pixels,
int output_channel, int input_step, int8_t input_zp);
void ConvDwInt8PostAlign4PerChannel(int8_t *dst, int32_t *buffer, int channel4, int32_t output_zp,
int32_t *out_multiplier, int32_t *left_shift, int32_t *right_shift, int32_t acc_min,
int32_t acc_max);
const int32_t *out_multiplier, const int32_t *left_shift,
const int32_t *right_shift, int32_t acc_min, int32_t acc_max);
void ConvDwInt8PostAlign4(int8_t *dst, int32_t *buffer, int num_pixels, int32_t output_zp, int32_t out_multiplier,
int32_t left_shift, int32_t right_shift, int32_t acc_min, int32_t acc_max);
void IndirectGemmInt16to32_8x4(int32_t *dst, const int16_t *src, const int16_t *weight, size_t ksize, size_t ic8,
size_t oc4, size_t offset);
void ConvDwInt8Center(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, size_t height,
size_t width, size_t kernel_h, size_t kernel_w, size_t out_h_step, size_t block_channel,
size_t in_sh_step, size_t in_sw_step, size_t in_kh_step, size_t in_kw_step, int8_t *in_zp,
int32_t *out_zp, int32_t *out_multiplier, int32_t *left_shift, int32_t *right_shift,
int32_t *acc_min, int32_t *acc_max);
size_t in_sh_step, size_t in_sw_step, size_t in_kh_step, size_t in_kw_step, const int8_t *in_zp,
const int32_t *out_zp, const int32_t *out_multiplier, const int32_t *left_shift,
const int32_t *right_shift, const int32_t *acc_min, const int32_t *acc_max);
void DeconvDwInt8Center(int32_t *dst, const int16_t *src, const int16_t *weight, size_t height, size_t width,
size_t kernel_h, size_t kernel_w, size_t out_h_step, size_t block_channel, size_t in_sh_step,
size_t in_sw_step, size_t in_kh_step, size_t in_kw_step);
@ -59,8 +59,8 @@ int32x4_t ClacScaledInput(int32x4_t input, int32x4_t left_shift_result_vec, int3
#ifdef ENABLE_ARM32
void ConvDw3x3Int8BorderPixel(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, int height,
int width, int in_kh_step, int in_kw_step, int channel, int8_t in_zp, int32_t out_zp,
int32_t *out_multiplier, int32_t *left_shift, int32_t *right_shift, int32_t acc_min,
int32_t acc_max, size_t per_channel);
const int32_t *out_multiplier, const int32_t *left_shift, const int32_t *right_shift,
int32_t acc_min, int32_t acc_max, size_t per_channel);
#endif
#ifdef ENABLE_ARM64
@ -69,23 +69,24 @@ void PostFuncInt8C4Neon64(const int32_t *in, const int32_t *bias, int8_t *out, s
int32_t zp, int32_t mini, int32_t maxi);
void ConvDw3x3Int8Neon64(int8_t *output, const int8_t *input, const int16_t *weight, const int32_t *bias,
int input_col_size, int input_row_size, int channel, int output_h, int output_w, int8_t in_zp,
int32_t out_zp, int32_t *out_multiplier, int32_t *left_shift, int32_t *right_shift,
int32_t acc_min, int32_t acc_max, size_t per_channel);
int32_t out_zp, const int32_t *out_multiplier, const int32_t *left_shift,
const int32_t *right_shift, int32_t acc_min, int32_t acc_max, size_t per_channel);
void ConvDw3x3Int8Stride2(int8_t *output, const int8_t *input, const int16_t *weight, const int32_t *bias,
int input_col_size, int input_row_size, int channel, int output_h, int output_w, int8_t in_zp,
int32_t out_zp, int32_t *out_multiplier, int32_t *left_shift, int32_t *right_shift,
int32_t acc_min, int32_t acc_max, size_t per_channel);
int32_t out_zp, const int32_t *out_multiplier, const int32_t *left_shift,
const int32_t *right_shift, int32_t acc_min, int32_t acc_max, size_t per_channel);
void ConvDw3x3Int8Corner(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, size_t in_kh_step,
size_t in_kw_step, size_t channel, size_t in_zp, size_t out_zp, int32_t *out_multiplier,
int32_t *left_shift, int32_t *right_shift, size_t acc_min, size_t acc_max, size_t per_channel);
size_t in_kw_step, size_t channel, size_t in_zp, size_t out_zp, const int32_t *out_multiplier,
const int32_t *left_shift, const int32_t *right_shift, size_t acc_min, size_t acc_max,
size_t per_channel);
void ConvDw3x3Int8Vertical(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias,
size_t in_kh_step, size_t in_kw_step, size_t channel, size_t in_zp, size_t out_zp,
int32_t *out_multiplier, int32_t *left_shift, int32_t *right_shift, size_t acc_min,
size_t acc_max, size_t per_channel);
const int32_t *out_multiplier, const int32_t *left_shift, const int32_t *right_shift,
size_t acc_min, size_t acc_max, size_t per_channel);
void ConvDw3x3Int8Horizontal(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias,
size_t in_kh_step, size_t in_kw_step, size_t channel, size_t in_zp, size_t out_zp,
int32_t *out_multiplier, int32_t *left_shift, int32_t *right_shift, size_t acc_min,
size_t acc_max, size_t per_channel);
const int32_t *out_multiplier, const int32_t *left_shift, const int32_t *right_shift,
size_t acc_min, size_t acc_max, size_t per_channel);
#endif
#ifdef __cplusplus
}

42
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/int8/conv_depthwise_int8.c
View File

@ -33,8 +33,9 @@ void ConvDwInt8Row(int32_t *output_ptr, const int8_t *input_ptr, const int16_t *
}
#endif
void ConvDwInt8Post(int8_t *dst, int32_t *buffer, int output_w, int channel, int32_t output_zp, int32_t *out_multiplier,
int32_t *left_shift, int32_t *right_shift, int32_t acc_min, int32_t acc_max, bool per_channel) {
void ConvDwInt8Post(int8_t *dst, int32_t *buffer, int output_w, int channel, int32_t output_zp,
const int32_t *out_multiplier, const int32_t *left_shift, const int32_t *right_shift,
int32_t acc_min, int32_t acc_max, bool per_channel) {
if (per_channel) {
// support perchannel
for (int w = 0; w < output_w; w++) {
@ -207,8 +208,8 @@ void ConvDw3x3Int8Window(int8_t *output, const int8_t *buffer, const int16_t *we
void ConvDw3x3Int8Block(int8_t *output, const int8_t *buffer, const int16_t *weight, const int32_t *bias, int start_c,
int end_c, int col_size, int row_size, int channel, int output_h, int output_w, int8_t in_zp,
int32_t out_zp, int32_t *out_multiplier, int32_t *left_shift, int32_t *right_shift,
int32_t acc_min, int32_t acc_max, int stride, bool per_channel) {
int32_t out_zp, const int32_t *out_multiplier, const int32_t *left_shift,
const int32_t *right_shift, int32_t acc_min, int32_t acc_max, int stride, bool per_channel) {
for (; start_c <= end_c - 8; start_c += 8) {
#ifdef ENABLE_ARM64
if (stride == 1) {
@ -330,8 +331,8 @@ void ConvDw3x3Int8(int8_t *output_data, int8_t *buffer, const int8_t *input_data
#ifndef ENABLE_ARM32
void ConvDw3x3Int8BorderPixel(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, int height,
int width, int in_kh_step, int in_kw_step, int channel, int8_t in_zp, int32_t out_zp,
const int *out_multiplier, const int *left_shift, const int *right_shift, int32_t acc_min,
int32_t acc_max, bool per_channel) {
const int *out_multiplier, const int *left_shift, const int *right_shift,
const int32_t acc_min, const int32_t acc_max, bool per_channel) {
for (int c = 0; c < channel; c += 8) {
int tmp_buffer[8];
for (int i = 0; i < 8; i++) {
@ -385,22 +386,25 @@ void ConvDw3x3Int8BorderPixel(int8_t *dst, const int8_t *src, const int16_t *wei
#ifndef ENABLE_ARM64
void ConvDw3x3Int8Corner(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, int in_kh_step,
int in_kw_step, int channel, int8_t in_zp, int32_t out_zp, int *out_multiplier,
int *left_shift, int *right_shift, int32_t acc_min, int32_t acc_max, bool per_channel) {
int in_kw_step, int channel, int8_t in_zp, int32_t out_zp, const int *out_multiplier,
const int *left_shift, const int *right_shift, int32_t acc_min, int32_t acc_max,
bool per_channel) {
ConvDw3x3Int8BorderPixel(dst, src, weight, bias, 2, 2, in_kh_step, in_kw_step, channel, in_zp, out_zp, out_multiplier,
left_shift, right_shift, acc_min, acc_max, per_channel);
}
void ConvDw3x3Int8Vertical(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, int in_kh_step,
int in_kw_step, int channel, int8_t in_zp, int32_t out_zp, int *out_multiplier,
int *left_shift, int *right_shift, int32_t acc_min, int32_t acc_max, bool per_channel) {
int in_kw_step, int channel, int8_t in_zp, int32_t out_zp, const int *out_multiplier,
const int *left_shift, const int *right_shift, int32_t acc_min, int32_t acc_max,
bool per_channel) {
ConvDw3x3Int8BorderPixel(dst, src, weight, bias, 2, 3, in_kh_step, in_kw_step, channel, in_zp, out_zp, out_multiplier,
left_shift, right_shift, acc_min, acc_max, per_channel);
}
void ConvDw3x3Int8Horizontal(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, int in_kh_step,
int in_kw_step, int channel, int8_t in_zp, int32_t out_zp, int *out_multiplier,
int *left_shift, int *right_shift, int32_t acc_min, int32_t acc_max, bool per_channel) {
int in_kw_step, int channel, int8_t in_zp, int32_t out_zp, const int *out_multiplier,
const int *left_shift, const int *right_shift, int32_t acc_min, int32_t acc_max,
bool per_channel) {
ConvDw3x3Int8BorderPixel(dst, src, weight, bias, 3, 2, in_kh_step, in_kw_step, channel, in_zp, out_zp, out_multiplier,
left_shift, right_shift, acc_min, acc_max, per_channel);
}
@ -494,9 +498,9 @@ void ConvDw3x3Int8Pad(int8_t *output_data, const int8_t *input_data, const int16
/*conv depthwise sliding window perchannel int8 begin*/
void ConvDwInt8BorderPixel(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, int height,
int width, int in_kh_step, int in_kw_step, int kernel_w, int8_t *input_zp, int32_t *out_zp,
const int *out_multiplier, const int *left_shift, const int *right_shift, int32_t *acc_min,
int32_t *acc_max) {
int width, int in_kh_step, int in_kw_step, int kernel_w, const int8_t *input_zp,
const int32_t *out_zp, const int *out_multiplier, const int *left_shift,
const int *right_shift, int32_t *acc_min, int32_t *acc_max) {
int tmp_buffer[C8NUM];
for (int i = 0; i < C8NUM; i++) {
tmp_buffer[i] = 0;
@ -531,7 +535,7 @@ void ConvDwInt8BorderPixel(int8_t *dst, const int8_t *src, const int16_t *weight
void ConvDwInt8Border(int8_t *dst, const int8_t *src, const int16_t *weight, const int32_t *bias, int top, int bottom,
int left, int right, const ConvParameter *conv_param, const SlidingWindowParam *sliding,
int8_t *in_zp, int32_t *out_zp, const int *out_multiplier, const int *left_shift,
const int8_t *in_zp, const int32_t *out_zp, const int *out_multiplier, const int *left_shift,
const int *right_shift, int32_t *acc_min, int32_t *acc_max) {
int8_t *dst_h = dst + top * sliding->out_h_step_;
for (int oh = top; oh < bottom; oh++) {
@ -613,7 +617,7 @@ void ConvDwInt8Center(int8_t *dst, const int8_t *src, const int16_t *weight, con
#endif
void ConvDwInt8SW(int8_t *output_data, const int8_t *input_data, const int16_t *weight_data, const int32_t *bias_data,
int8_t *input_zp, int32_t *output_zp, const ConvParameter *conv_param,
const int8_t *input_zp, const int32_t *output_zp, const ConvParameter *conv_param,
const SlidingWindowParam *sliding, int task_id) {
NNACL_CHECK_ZERO_RETURN(conv_param->dilation_h_);
NNACL_CHECK_ZERO_RETURN(conv_param->dilation_w_);
@ -631,8 +635,8 @@ void ConvDwInt8SW(int8_t *output_data, const int8_t *input_data, const int16_t *
int *right_shift = conv_param->conv_quant_arg_.right_shift_ + oc * C8NUM;
int *acc_min = conv_param->conv_quant_arg_.out_act_min_ + oc * C8NUM;
int *acc_max = conv_param->conv_quant_arg_.out_act_max_ + oc * C8NUM;
int8_t *in_zp = input_zp + oc * C8NUM;
int32_t *out_zp = output_zp + oc * C8NUM;
const int8_t *in_zp = input_zp + oc * C8NUM;
const int32_t *out_zp = output_zp + oc * C8NUM;
ConvDwInt8Border(dst_data, src_data, weight, bias, 0, sliding->top_, 0, conv_param->output_w_, conv_param,
sliding, in_zp, out_zp, out_multiplier, left_shift, right_shift, acc_min, acc_max);

2
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/int8/conv_depthwise_int8.h
View File

@ -35,7 +35,7 @@ void ConvDw3x3Int8(int8_t *output_data, int8_t *buffer, const int8_t *input_data
int task_id);
void ConvDwInt8SW(int8_t *output_data, const int8_t *input_data, const int16_t *weight_data, const int32_t *bias_data,
int8_t *input_zp, int32_t *output_zp, const ConvParameter *conv_param,
const int8_t *input_zp, const int32_t *output_zp, const ConvParameter *conv_param,
const SlidingWindowParam *sliding, int task_id);
void DeconvDwInt8(int8_t *output_data, int32_t *output_buffer, const int16_t *input_data, const int16_t *weight_data,

18
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/int8/mul_int8.c
View File

@ -115,7 +115,7 @@ void FastMul(const int8_t *input0_data, const int8_t *input1_data, int8_t *outpu
}
#ifdef ENABLE_ARM
int32x4_t output_multiplier_vec = vdupq_n_s32(quant_arg->output_multiplier_);
int32x4_t left_shift_out_vec = vdupq_n_s32(1 << quant_arg->shift_left_);
int32x4_t left_shift_out_vec = vdupq_n_s32(1 << (size_t)quant_arg->shift_left_);
int32x4_t right_shift_out_vec = vdupq_n_s32(-quant_arg->shift_right_);
int16x8_t out_zp_vec = vdupq_n_s16(quant_arg->out_quant_arg_.zp_);
int8x16_t out_min_vec = vdupq_n_s8(quant_arg->output_activation_min_);
@ -199,10 +199,10 @@ void FastMul(const int8_t *input0_data, const int8_t *input1_data, int8_t *outpu
for (; j < depth; ++j) {
const int32_t input0_val = zp1 + input0_data[j];
const int32_t input1_val = zp2 + input1_data[0];
int32_t mul_result =
RoundingDivideByPOT(SaturatingRoundingDoublingHighMul(input0_val * input1_val * (1 << quant_arg->shift_left_),
quant_arg->output_multiplier_),
quant_arg->shift_right_);
int32_t mul_result = RoundingDivideByPOT(
SaturatingRoundingDoublingHighMul(input0_val * input1_val * (1 << (size_t)quant_arg->shift_left_),
quant_arg->output_multiplier_),
quant_arg->shift_right_);
mul_result += quant_arg->out_quant_arg_.zp_;
mul_result = mul_result < quant_arg->output_activation_max_ ? mul_result : quant_arg->output_activation_max_;
@ -224,10 +224,10 @@ void Mul(const int8_t *input0_data, const int8_t *input1_data, int8_t *output_da
for (; index < real_dst_count; ++index) {
const int32_t input0_val = quant_arg->in_quant_args_[0].zp_ + input0_data[index];
const int32_t input1_val = quant_arg->in_quant_args_[1].zp_ + input1_data[index];
int32_t mul_result =
RoundingDivideByPOT(SaturatingRoundingDoublingHighMul(input0_val * input1_val * (1 << quant_arg->shift_left_),
quant_arg->output_multiplier_),
quant_arg->shift_right_);
int32_t mul_result = RoundingDivideByPOT(
SaturatingRoundingDoublingHighMul(input0_val * input1_val * (1 << (size_t)quant_arg->shift_left_),
quant_arg->output_multiplier_),
quant_arg->shift_right_);
mul_result += quant_arg->out_quant_arg_.zp_;
mul_result = mul_result < quant_arg->output_activation_max_ ? mul_result : quant_arg->output_activation_max_;

1
mindspore/lite/micro/coder/opcoders/nnacl/fp32/lstm_fp32_coder.cc
View File

@ -145,6 +145,7 @@ int LstmFP32Coder::MallocRunBuffer(CoderContext *const context) {
kNumberTypeFloat32, lstm_param_->batch_ * lstm_param_->hidden_size_ * sizeof(float), kWorkspace));
MS_CHECK_PTR(buffer_[5]);
}
buffer_[6] = nullptr;
return RET_OK;
}

2
mindspore/lite/micro/coder/opcoders/nnacl/fp32/lstm_fp32_coder.h
View File

@ -44,7 +44,7 @@ class LstmFP32Coder final : public OperatorCoder {
float *weight_h_ptr_{nullptr};
float *input_bias_{nullptr};
float *state_bias_{nullptr};
float *buffer_[6];
float *buffer_[7];
int row_tile_{0};
int col_tile_{0};
int weight_batch_{0};

2
mindspore/lite/src/delegate/npu/npu_subgraph.cc
View File

@ -160,7 +160,7 @@ int NPUSubGraph::BuildNPUInputOp() {
auto in_tensor = op->inputs()[i];
if (IsSubGraphInputTensor(in_tensor)) {
auto tensor_name = "Input_" + std::to_string(count++) + '_' + op->name();
hiai::op::Data *data;
hiai::op::Data *data = nullptr;
data = ConverterToNPUData(in_tensor, tensor_name);
subgraph_input_ops_.push_back(*data);
input_ops.push_back(data);

6
mindspore/lite/src/delegate/npu/transpose_kernel.cc
View File

@ -98,13 +98,11 @@ inline void Transpose8X8Fp32Arm64(const float *src_ptr, float *dst_ptr, int src_
void PackNHWCToNCHWFp32(const void *src, void *dst, int batches, int plane, int channel) {
int hw8 = plane / C8NUM * C8NUM;
int task_start = 0;
int task_end = plane;
int batch = plane * channel;
for (int n = 0; n < batches; n++) {
const float *src_batch = (const float *)src + n * batch;
float *dst_batch = reinterpret_cast<float *>(dst) + n * batch;
int hw = task_start;
int hw = 0;
for (; hw < hw8; hw += C8NUM) {
int c = 0;
#ifdef ENABLE_ARM64
@ -122,7 +120,7 @@ void PackNHWCToNCHWFp32(const void *src, void *dst, int batches, int plane, int
}
}
}
for (; hw < task_end; hw++) {
for (; hw < plane; hw++) {
const float *src_ptr = src_batch + hw * channel;
float *dst_ptr = dst_batch + hw;
for (size_t i = 0; i < channel; i++) {