forked from mindspore-Ecosystem/mindspore
!5044 Clean building warnings for arm64.
Merge pull request !5044 from wangshaocong/lite_clean
This commit is contained in:
commit
72d8f871c0
|
@ -147,7 +147,7 @@ class LogWriter {
|
|||
|
||||
LogWriter(const LocationInfo &location, MsLogLevel log_level, SubModuleId submodule,
|
||||
ExceptionType excp_type = NoExceptionType)
|
||||
: location_(location), log_level_(log_level), submodule_(submodule), exception_type_(excp_type) {}
|
||||
: location_(location), log_level_(log_level), exception_type_(excp_type) {}
|
||||
~LogWriter() = default;
|
||||
|
||||
void operator<(const LogStream &stream) const noexcept __attribute__((visibility("default")));
|
||||
|
@ -161,7 +161,6 @@ class LogWriter {
|
|||
|
||||
LocationInfo location_;
|
||||
MsLogLevel log_level_;
|
||||
SubModuleId submodule_;
|
||||
ExceptionType exception_type_;
|
||||
|
||||
inline static ExceptionHandler exception_handler_ = nullptr;
|
||||
|
|
|
@ -65,22 +65,21 @@ set(CMAKE_VERBOSE_MAKEFILE on)
|
|||
add_compile_definitions(USE_ANDROID_LOG)
|
||||
add_compile_definitions(NO_DLIB)
|
||||
add_compile_options(-fPIC)
|
||||
if (NOT PLATFORM_ARM64 AND NOT PLATFORM_ARM32)
|
||||
if ("${CMAKE_BUILD_TYPE}" STREQUAL "Debug")
|
||||
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DDebug -g")
|
||||
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DDebug -g")
|
||||
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fvisibility=default")
|
||||
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fvisibility=default")
|
||||
else ()
|
||||
## enable for binscope for release
|
||||
set(CMAKE_C_FLAGS "-fPIC -fPIE -D_FORTIFY_SOURCE=2 -O2 -Wall -Werror -fstack-protector-strong -Wno-attributes -Wno-deprecated-declarations ${CMAKE_C_FLAGS}")
|
||||
set(CMAKE_CXX_FLAGS "-fPIC -fPIE -D_FORTIFY_SOURCE=2 -O2 -Wall -Werror -fstack-protector-strong -Wno-attributes -Wno-deprecated-declarations ${CMAKE_CXX_FLAGS}")
|
||||
if (NOT WIN32)
|
||||
set(CMAKE_SHARED_LINKER_FLAGS "-Wl,-z,relro,-z,now -Wl,-z,noexecstack ${CMAKE_SHARED_LINKER_FLAGS}")
|
||||
set(CMAKE_EXE_LINKER_FLAGS "-Wl,-z,relro,-z,now -Wl,-z,noexecstack ${CMAKE_EXE_LINKER_FLAGS}")
|
||||
endif()
|
||||
string(REPLACE " -g " " " CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
|
||||
endif ()
|
||||
|
||||
if ("${CMAKE_BUILD_TYPE}" STREQUAL "Debug")
|
||||
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -DDebug -g")
|
||||
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -DDebug -g")
|
||||
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fvisibility=default")
|
||||
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fvisibility=default")
|
||||
else ()
|
||||
## enable for binscope for release
|
||||
set(CMAKE_C_FLAGS "-fPIC -fPIE -D_FORTIFY_SOURCE=2 -O2 -Wall -Werror -fstack-protector-strong -Wno-attributes -Wno-deprecated-declarations -Wno-missing-braces -Wno-overloaded-virtual ${CMAKE_C_FLAGS}")
|
||||
set(CMAKE_CXX_FLAGS "-fPIC -fPIE -D_FORTIFY_SOURCE=2 -O2 -Wall -Werror -fstack-protector-strong -Wno-attributes -Wno-deprecated-declarations -Wno-missing-braces -Wno-overloaded-virtual ${CMAKE_CXX_FLAGS}")
|
||||
if (NOT WIN32)
|
||||
set(CMAKE_SHARED_LINKER_FLAGS "-Wl,-z,relro,-z,now -Wl,-z,noexecstack ${CMAKE_SHARED_LINKER_FLAGS}")
|
||||
set(CMAKE_EXE_LINKER_FLAGS "-Wl,-z,relro,-z,now -Wl,-z,noexecstack ${CMAKE_EXE_LINKER_FLAGS}")
|
||||
endif()
|
||||
string(REPLACE " -g " " " CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
|
||||
endif ()
|
||||
|
||||
if (BUILD_DEVICE)
|
||||
|
|
|
@ -51,6 +51,8 @@ void TileOneDimension(float *inData, float *outData, int dim, size_t ndim, int *
|
|||
int *outStrides, int *multiple);
|
||||
void ComputeStrides(int *shape, int *strides, int ndim);
|
||||
|
||||
void CalcMultiplesAndStrides(ArithmeticParameter *param);
|
||||
|
||||
void TileDimensions(float *data0, float *data1, float *tile_data0, float *tile_data1, ArithmeticParameter *param);
|
||||
void TileDimensionsUint8(uint8_t *data0, uint8_t *data1, uint8_t *tile_data0, uint8_t *tile_data1,
|
||||
ArithmeticParameter *param);
|
||||
|
|
|
@ -395,7 +395,6 @@ void Conv3x3Fp16(float16_t *input_data, float16_t *transed_weight, const float16
|
|||
|
||||
int input_batch = conv_param->input_batch_;
|
||||
for (int batch = 0; batch < input_batch; batch++) {
|
||||
int in_batch_offset = batch * ic4 * C4NUM * conv_param->input_h_ * conv_param->input_w_;
|
||||
int tmp_out_batch_offset = batch * oc8 * C8NUM * out_w_block * out_h_block * output_unit * output_unit;
|
||||
for (int thread_id = task_id; thread_id < output_tile_count; thread_id += thread_count) {
|
||||
int start_index = thread_id * tile_num;
|
||||
|
|
|
@ -55,7 +55,6 @@ void Im2ColPackUnitFp16(float16_t *input_data, ConvParameter *conv_param, float1
|
|||
int in_w = conv_param->input_w_;
|
||||
int out_w = conv_param->output_w_;
|
||||
int channel_block = UP_DIV(in_channel, 4);
|
||||
int kernel_plane = kernel_h * kernel_w;
|
||||
|
||||
for (int i = 0; i < real_cal_num; i++) {
|
||||
int block_start = block_index + i;
|
||||
|
|
|
@ -607,7 +607,7 @@ void WinogradInputTransformFp16(const float16_t *input_data, float16_t *trans_in
|
|||
for (int j = 0; j < (interval_x_e - interval_x_s); j++) {
|
||||
int src_x_offset = src_y_offset + j * ic8 * C8NUM;
|
||||
int dst_x_offset = dst_y_offset + j * C8NUM;
|
||||
float16_t *src_addr = input_data + src_x_offset;
|
||||
const float16_t *src_addr = input_data + src_x_offset;
|
||||
float16_t *dst_addr = tmp_data + dst_x_offset;
|
||||
#ifdef ENABLE_NEON
|
||||
vst1q_f16(dst_addr, vld1q_f16(src_addr));
|
||||
|
|
|
@ -28,7 +28,7 @@ void IndirectGemmInt8(int8_t *dst, int32_t *tmp_dst, const int8_t *src, const in
|
|||
int32_t out_zp = conv_param->conv_quant_arg_.output_quant_args_[0].zp_;
|
||||
int32_t act_min = conv_param->conv_quant_arg_.out_act_min_[0];
|
||||
int32_t act_max = conv_param->conv_quant_arg_.out_act_max_[0];
|
||||
int oc4 = UP_DIV(output_channel, C4NUM);
|
||||
|
||||
#ifdef ENABLE_ARM64
|
||||
size_t asymmetric = conv_param->conv_quant_arg_.asymmetric_ & FILTER_ASYMMETRIC;
|
||||
size_t per_channel = conv_param->conv_quant_arg_.per_channel_ & FILTER_PER_CHANNEL;
|
||||
|
@ -36,6 +36,7 @@ void IndirectGemmInt8(int8_t *dst, int32_t *tmp_dst, const int8_t *src, const in
|
|||
output_channel * sizeof(int8_t), input_sum, act_min, act_max, out_zp, out_multiplier,
|
||||
shift_before, shift_after, asymmetric, per_channel);
|
||||
#else
|
||||
int oc4 = UP_DIV(output_channel, C4NUM);
|
||||
int tile_num = conv_param->tile_num_;
|
||||
int plane_c4 = UP_DIV(kernel_plane, C4NUM);
|
||||
for (int oc = 0; oc < output_channel; oc++) {
|
||||
|
|
|
@ -63,16 +63,17 @@ void RowMajor2Row16x4MajorInt8(void *src_ptr, void *dst_ptr, int row, int col) {
|
|||
for (int ri = 0; ri < row_4div; ri += C4NUM) {
|
||||
for (int ci = 0; ci < col_16div; ci += C16NUM) {
|
||||
#ifdef ENABLE_ARM64
|
||||
size_t col_offset = col;
|
||||
int8_t *src_c = src_r + ci;
|
||||
int8_t *dst_c = dst_r + ci * C4NUM;
|
||||
asm volatile(
|
||||
"mov x10, %[src_c] \n"
|
||||
"mov x11, %[dst_c] \n"
|
||||
|
||||
"ld1 {v0.16b}, [x10], %[col]\n"
|
||||
"ld1 {v1.16b}, [x10], %[col]\n"
|
||||
"ld1 {v2.16b}, [x10], %[col]\n"
|
||||
"ld1 {v3.16b}, [x10], %[col]\n"
|
||||
"ld1 {v0.16b}, [x10], %[col_offset]\n"
|
||||
"ld1 {v1.16b}, [x10], %[col_offset]\n"
|
||||
"ld1 {v2.16b}, [x10], %[col_offset]\n"
|
||||
"ld1 {v3.16b}, [x10], %[col_offset]\n"
|
||||
|
||||
"st1 {v0.16b}, [x11], #16\n"
|
||||
"st1 {v1.16b}, [x11], #16\n"
|
||||
|
@ -80,7 +81,7 @@ void RowMajor2Row16x4MajorInt8(void *src_ptr, void *dst_ptr, int row, int col) {
|
|||
"st1 {v3.16b}, [x11], #16\n"
|
||||
|
||||
:
|
||||
: [ dst_c ] "r"(dst_c), [ src_c ] "r"(src_c), [ col ] "r"(col)
|
||||
: [ dst_c ] "r"(dst_c), [ src_c ] "r"(src_c), [ col_offset ] "r"(col_offset)
|
||||
: "x10", "x11", "v0", "v1", "v2", "v3");
|
||||
#else
|
||||
MatrixPack4x16UnitInt8(src_r + ci, dst_r + ci * C4NUM, C4NUM, C16NUM, col);
|
||||
|
|
|
@ -1225,9 +1225,9 @@ void Conv3x3Uint8OutputUnit(const int32_t *gemm_out, const int32_t *bias_data, i
|
|||
ls = vld1q_s32(left_shift);
|
||||
rs = vld1q_s32(right_shift);
|
||||
} else {
|
||||
out_multiplier = vdupq_n_s32(quant_multiplier);
|
||||
ls = vdupq_n_s32(left_shift);
|
||||
rs = vdupq_n_s32(right_shift);
|
||||
out_multiplier = vdupq_n_s32(quant_multiplier[0]);
|
||||
ls = vdupq_n_s32(left_shift[0]);
|
||||
rs = vdupq_n_s32(right_shift[0]);
|
||||
}
|
||||
int32x4_t out_zp = vdupq_n_s32(output_zp);
|
||||
int32x4_t output_min = vdupq_n_s32(out_min);
|
||||
|
|
|
@ -43,7 +43,7 @@ std::vector<size_t> GetGraphInputNodes(const schema::MetaGraph *meta_graph) {
|
|||
}
|
||||
}
|
||||
}
|
||||
return std::move(ret);
|
||||
return ret;
|
||||
}
|
||||
|
||||
std::vector<size_t> GetGraphOutputNodes(const schema::MetaGraph *meta_graph) {
|
||||
|
@ -64,7 +64,7 @@ std::vector<size_t> GetGraphOutputNodes(const schema::MetaGraph *meta_graph) {
|
|||
}
|
||||
}
|
||||
}
|
||||
return std::move(ret);
|
||||
return ret;
|
||||
}
|
||||
|
||||
// NODE_ID OpNode::ID() { return id; }
|
||||
|
|
|
@ -54,7 +54,10 @@ int Resize::InferShape(std::vector<lite::tensor::Tensor *> inputs_, std::vector<
|
|||
if (input == nullptr) {
|
||||
return 1;
|
||||
}
|
||||
MS_ASSERT(input->shape().size() == kInputRank);
|
||||
if (input->shape().size() != kInputRank) {
|
||||
MS_LOG(ERROR) << "Size of input shape is wrong.";
|
||||
return RET_ERROR;
|
||||
}
|
||||
|
||||
auto output = outputs_.front();
|
||||
if (output == nullptr) {
|
||||
|
|
|
@ -40,8 +40,14 @@ int PriorBoxCPUKernel::Init() {
|
|||
return RET_NULL_PTR;
|
||||
}
|
||||
|
||||
MS_ASSERT(in_tensors_.size() == kInputNum);
|
||||
MS_ASSERT(out_tensors_.size() == kOutputNum);
|
||||
if (in_tensors_.size() != kInputNum) {
|
||||
MS_LOG(ERROR) << "Size of input tensors is wrong.";
|
||||
return RET_ERROR;
|
||||
}
|
||||
if (in_tensors_.size() != kOutputNum) {
|
||||
MS_LOG(ERROR) << "Size of input tensors is wrong.";
|
||||
return RET_ERROR;
|
||||
}
|
||||
|
||||
if (!InferShapeDone()) {
|
||||
return RET_OK;
|
||||
|
|
|
@ -46,7 +46,6 @@ class ArithmeticFP16CPUKernel : public LiteKernel {
|
|||
private:
|
||||
void FreeTmpBuffer();
|
||||
int break_pos_;
|
||||
int outside_;
|
||||
int out_thread_stride_;
|
||||
int out_count_;
|
||||
float16_t *tile_data0_ = nullptr;
|
||||
|
|
|
@ -44,7 +44,6 @@ class ReduceFp16CPUKernel : public ReduceBaseCPUKernel {
|
|||
private:
|
||||
Reducer reducer_ = nullptr;
|
||||
std::vector<float16_t *> data_buffers_;
|
||||
const float *src_data_ = nullptr;
|
||||
float *dst_data_ = nullptr;
|
||||
float16_t *fp16_input_ = nullptr;
|
||||
const float16_t *fp16_src_data_ = nullptr;
|
||||
|
|
|
@ -111,8 +111,8 @@ int SplitFp16CPUKernel::Run() {
|
|||
context_->allocator->Free(output_ptr_[i]);
|
||||
output_ptr_[i] = nullptr;
|
||||
}
|
||||
return RET_OK;
|
||||
}
|
||||
return RET_OK;
|
||||
}
|
||||
|
||||
kernel::LiteKernel *CpuSplitFp16KernelCreator(const std::vector<lite::tensor::Tensor *> &inputs,
|
||||
|
|
|
@ -30,10 +30,6 @@ using mindspore::lite::RET_OP_EXECUTE_FAILURE;
|
|||
using mindspore::schema::PrimitiveType_Transpose;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
namespace {
|
||||
constexpr int kTransposeInputNum = 1;
|
||||
constexpr int kTransposeOutputNum = 1;
|
||||
} // namespace
|
||||
int TransposeFp16CPUKernel::Init() {
|
||||
TransposeParameter *param = reinterpret_cast<TransposeParameter *>(this->op_parameter_);
|
||||
num_unit_ = static_cast<int>(in_tensors_[kInputIndex]->shape().at(param->perm_[kNHWC_H]));
|
||||
|
|
|
@ -46,7 +46,7 @@ class ArithmeticSelfCPUKernel : public LiteKernel {
|
|||
explicit ArithmeticSelfCPUKernel(OpParameter *parameter, const std::vector<lite::tensor::Tensor *> &inputs,
|
||||
const std::vector<lite::tensor::Tensor *> &outputs, const lite::Context *ctx,
|
||||
const mindspore::lite::PrimitiveC *primitive)
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), ctx_(ctx), thread_count_(ctx->thread_num_) {
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), thread_count_(ctx->thread_num_) {
|
||||
switch (parameter->type_) {
|
||||
case PrimitiveType_Abs:
|
||||
arithmeticSelf_run_ = ElementAbs;
|
||||
|
@ -102,7 +102,6 @@ class ArithmeticSelfCPUKernel : public LiteKernel {
|
|||
size_t data_size_;
|
||||
ArithmeticSelfParameter *arithmeticSelfParameter_;
|
||||
ArithmeticSelfRun arithmeticSelf_run_;
|
||||
const Context *ctx_;
|
||||
int thread_count_;
|
||||
float *in_ptr_;
|
||||
float *out_ptr_;
|
||||
|
|
|
@ -28,12 +28,6 @@ using mindspore::lite::RET_OK;
|
|||
using mindspore::schema::PrimitiveType_ConstantOfShape;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
|
||||
namespace {
|
||||
constexpr int kInputNum = 1;
|
||||
constexpr int kOutputNum = 1;
|
||||
} // namespace
|
||||
|
||||
int ConstantOfShapeCPUKernel::Init() { return RET_OK; }
|
||||
|
||||
int ConstantOfShapeCPUKernel::ReSize() { return RET_OK; }
|
||||
|
|
|
@ -32,7 +32,7 @@ class ExpandDimsCPUKernel : public LiteKernel {
|
|||
ExpandDimsCPUKernel(OpParameter *parameter, const std::vector<lite::tensor::Tensor *> &inputs,
|
||||
const std::vector<lite::tensor::Tensor *> &outputs, const lite::Context *ctx,
|
||||
const mindspore::lite::PrimitiveC *primitive)
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), ctx_(ctx), thread_count_(ctx->thread_num_) {}
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), thread_count_(ctx->thread_num_) {}
|
||||
~ExpandDimsCPUKernel() override = default;
|
||||
|
||||
int Init() override;
|
||||
|
@ -46,7 +46,6 @@ class ExpandDimsCPUKernel : public LiteKernel {
|
|||
size_t data_size_;
|
||||
float *in_ptr_;
|
||||
float *out_ptr_;
|
||||
const Context *ctx_;
|
||||
int thread_count_;
|
||||
};
|
||||
} // namespace mindspore::kernel
|
||||
|
|
|
@ -28,12 +28,6 @@ using mindspore::lite::RET_OK;
|
|||
using mindspore::schema::PrimitiveType_Fill;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
|
||||
namespace {
|
||||
constexpr int kInputNum = 1;
|
||||
constexpr int kOutputNum = 1;
|
||||
} // namespace
|
||||
|
||||
int FillCPUKernel::Init() {
|
||||
if (!InferShapeDone()) {
|
||||
return RET_OK;
|
||||
|
|
|
@ -30,7 +30,7 @@ class FillCPUKernel : public LiteKernel {
|
|||
FillCPUKernel(OpParameter *parameter, const std::vector<lite::tensor::Tensor *> &inputs,
|
||||
const std::vector<lite::tensor::Tensor *> &outputs, const lite::Context *ctx,
|
||||
const mindspore::lite::PrimitiveC *primitive)
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), ctx_(ctx), thread_count_(ctx->thread_num_) {}
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), thread_count_(ctx->thread_num_) {}
|
||||
~FillCPUKernel() override = default;
|
||||
|
||||
int Init() override;
|
||||
|
@ -44,7 +44,6 @@ class FillCPUKernel : public LiteKernel {
|
|||
int data_size_;
|
||||
float src_data_;
|
||||
float *out_ptr_;
|
||||
const Context *ctx_;
|
||||
int thread_count_;
|
||||
};
|
||||
} // namespace mindspore::kernel
|
||||
|
|
|
@ -32,7 +32,7 @@ class GatherNdCPUKernel : public LiteKernel {
|
|||
GatherNdCPUKernel(OpParameter *parameter, const std::vector<lite::tensor::Tensor *> &inputs,
|
||||
const std::vector<lite::tensor::Tensor *> &outputs, const Context *ctx,
|
||||
const mindspore::lite::PrimitiveC *primitive)
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), ctx_(ctx), thread_count_(ctx->thread_num_) {}
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), thread_count_(ctx->thread_num_) {}
|
||||
~GatherNdCPUKernel() override;
|
||||
|
||||
int Init() override;
|
||||
|
@ -48,7 +48,6 @@ class GatherNdCPUKernel : public LiteKernel {
|
|||
int *in_offset_ = nullptr;
|
||||
float *in_ptr_;
|
||||
float *out_ptr_;
|
||||
const Context *ctx_;
|
||||
int thread_count_;
|
||||
};
|
||||
} // namespace mindspore::kernel
|
||||
|
|
|
@ -30,7 +30,6 @@ class PowerCPUKernel : public PowerBaseCPUKernel {
|
|||
const std::vector<lite::tensor::Tensor *> &outputs, const lite::Context *ctx,
|
||||
const mindspore::lite::PrimitiveC *primitive)
|
||||
: PowerBaseCPUKernel(param, inputs, outputs, ctx, primitive),
|
||||
ctx_(ctx),
|
||||
thread_count_(ctx->thread_num_),
|
||||
power_(reinterpret_cast<PowerParameter *>(op_parameter_)->power_),
|
||||
scale_(reinterpret_cast<PowerParameter *>(op_parameter_)->scale_),
|
||||
|
@ -43,7 +42,6 @@ class PowerCPUKernel : public PowerBaseCPUKernel {
|
|||
int RunImpl(int task_id);
|
||||
|
||||
private:
|
||||
const lite::Context *ctx_;
|
||||
int thread_count_;
|
||||
float power_;
|
||||
float scale_;
|
||||
|
|
|
@ -27,12 +27,6 @@ using mindspore::lite::RET_OK;
|
|||
using mindspore::schema::PrimitiveType_Range;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
|
||||
namespace {
|
||||
constexpr int kInputNum = 0;
|
||||
constexpr int kOutputNum = 1;
|
||||
} // namespace
|
||||
|
||||
int RangeCPUKernel::Init() { return RET_OK; }
|
||||
|
||||
int RangeCPUKernel::ReSize() { return RET_OK; }
|
||||
|
|
|
@ -27,12 +27,6 @@ using mindspore::lite::RET_OK;
|
|||
using mindspore::schema::PrimitiveType_Rank;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
|
||||
namespace {
|
||||
constexpr int kInputNum = 1;
|
||||
constexpr int kOutputNum = 1;
|
||||
} // namespace
|
||||
|
||||
int RankCPUKernel::Init() { return RET_OK; }
|
||||
|
||||
int RankCPUKernel::ReSize() { return RET_OK; }
|
||||
|
|
|
@ -31,7 +31,7 @@ class ReverseCPUKernel : public LiteKernel {
|
|||
ReverseCPUKernel(OpParameter *parameter, const std::vector<lite::tensor::Tensor *> &inputs,
|
||||
const std::vector<lite::tensor::Tensor *> &outputs, const lite::Context *ctx,
|
||||
const mindspore::lite::PrimitiveC *primitive)
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), ctx_(ctx), thread_count_(ctx->thread_num_) {}
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), thread_count_(ctx->thread_num_) {}
|
||||
~ReverseCPUKernel() {
|
||||
if (tmp_ != nullptr) {
|
||||
free(tmp_);
|
||||
|
@ -52,7 +52,6 @@ class ReverseCPUKernel : public LiteKernel {
|
|||
int strides_[REVERSE_STRIDE_MAX_SIZE];
|
||||
int inCount_[REVERSE_STRIDE_MAX_SIZE];
|
||||
int outCount_[REVERSE_STRIDE_MAX_SIZE];
|
||||
const Context *ctx_;
|
||||
int thread_count_;
|
||||
int *tmp_ = nullptr;
|
||||
float *in_ptr_;
|
||||
|
|
|
@ -30,8 +30,6 @@ using mindspore::schema::PrimitiveType_ScatterND;
|
|||
|
||||
namespace mindspore::kernel {
|
||||
namespace {
|
||||
constexpr int kScatterNDInputNum = 3;
|
||||
constexpr int kScatterNDOutputNum = 1;
|
||||
constexpr int kScatterShapeIndex = 0;
|
||||
constexpr int kScatterIndicesIndex = 1;
|
||||
constexpr int kScatterUpdateIndex = 2;
|
||||
|
|
|
@ -26,10 +26,6 @@ using mindspore::lite::RET_OK;
|
|||
using mindspore::schema::PrimitiveType_Shape;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
namespace {
|
||||
constexpr int kShapeInputNum = 1;
|
||||
constexpr int kShapeOutputNum = 1;
|
||||
} // namespace
|
||||
int ShapeCPUKernel::Init() { return RET_OK; }
|
||||
|
||||
int ShapeCPUKernel::ReSize() { return RET_OK; }
|
||||
|
|
|
@ -27,11 +27,6 @@ using mindspore::lite::RET_OK;
|
|||
using mindspore::schema::PrimitiveType_Squeeze;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
namespace {
|
||||
constexpr int kSqueezeInputNum = 1;
|
||||
constexpr int kSqueezeOutputNum = 1;
|
||||
} // namespace
|
||||
|
||||
int SqueezeCPUKernel::Init() { return RET_OK; }
|
||||
|
||||
int SqueezeCPUKernel::ReSize() { return RET_OK; }
|
||||
|
|
|
@ -29,10 +29,6 @@ using mindspore::lite::RET_OP_EXECUTE_FAILURE;
|
|||
using mindspore::schema::PrimitiveType_Transpose;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
namespace {
|
||||
constexpr int kTransposeInputNum = 1;
|
||||
constexpr int kTransposeOutputNum = 1;
|
||||
} // namespace
|
||||
int TransposeCPUKernel::Init() {
|
||||
TransposeParameter *param = reinterpret_cast<TransposeParameter *>(this->op_parameter_);
|
||||
num_unit_ = static_cast<int>(in_tensors_[kInputIndex]->shape().at(param->perm_[kNHWC_H]));
|
||||
|
|
|
@ -27,9 +27,6 @@ using mindspore::lite::RET_OK;
|
|||
using mindspore::schema::PrimitiveType_ZerosLike;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
constexpr int kInputNum = 1;
|
||||
constexpr int kOutputNum = 1;
|
||||
|
||||
int ZerosLikeCPUKernel::Init() { return RET_OK; }
|
||||
|
||||
int ZerosLikeCPUKernel::Run() {
|
||||
|
|
|
@ -92,7 +92,7 @@ int QuantizedAddCPUKernel::Run() {
|
|||
input0_data_ = static_cast<int8_t *>(ctx_->allocator->Malloc(out_tensors_.at(0)->Size()));
|
||||
input1_data_ = static_cast<int8_t *>(ctx_->allocator->Malloc(out_tensors_.at(0)->Size()));
|
||||
|
||||
ArithmeticParameter tile_para = {0};
|
||||
ArithmeticParameter tile_para;
|
||||
tile_para.ndim_ = out_tensors_.at(0)->shape().size();
|
||||
for (size_t i = 0; i < tile_para.ndim_; i++) {
|
||||
tile_para.in_shape0_[i] = in_tensors_.at(0)->DimensionSize(i);
|
||||
|
|
|
@ -45,7 +45,7 @@ class ArithmeticSelfInt8CPUKernel : public LiteKernel {
|
|||
explicit ArithmeticSelfInt8CPUKernel(OpParameter *parameter, const std::vector<lite::tensor::Tensor *> &inputs,
|
||||
const std::vector<lite::tensor::Tensor *> &outputs, const Context *ctx,
|
||||
const mindspore::lite::PrimitiveC *primitive)
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), ctx_(ctx), thread_count_(ctx->thread_num_) {
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), thread_count_(ctx->thread_num_) {
|
||||
switch (parameter->type_) {
|
||||
case PrimitiveType_Round:
|
||||
arithmeticSelf_run_ = Int8ElementRound;
|
||||
|
@ -98,7 +98,6 @@ class ArithmeticSelfInt8CPUKernel : public LiteKernel {
|
|||
size_t data_size_;
|
||||
ArithmeticSelfParameter *para_;
|
||||
ArithmeticSelfInt8Run arithmeticSelf_run_;
|
||||
const Context *ctx_;
|
||||
int thread_count_;
|
||||
int8_t *in_ptr_;
|
||||
int8_t *out_ptr_;
|
||||
|
|
|
@ -104,7 +104,7 @@ int DivInt8CPUKernel::Run() {
|
|||
}
|
||||
|
||||
if (broadcast_) {
|
||||
ArithmeticParameter tile_para = {0};
|
||||
ArithmeticParameter tile_para;
|
||||
tile_para.ndim_ = out_tensors_.at(0)->shape().size();
|
||||
for (size_t i = 0; i < tile_para.ndim_; i++) {
|
||||
tile_para.in_shape0_[i] = in_tensors_.at(0)->DimensionSize(i);
|
||||
|
|
|
@ -77,7 +77,7 @@ int MulInt8CPUKernel::Run() {
|
|||
input0_data_ = static_cast<int8_t *>(ctx_->allocator->Malloc(out_tensors_.at(0)->Size()));
|
||||
input1_data_ = static_cast<int8_t *>(ctx_->allocator->Malloc(out_tensors_.at(0)->Size()));
|
||||
|
||||
ArithmeticParameter tile_para = {0};
|
||||
ArithmeticParameter tile_para;
|
||||
tile_para.ndim_ = out_tensors_.at(0)->shape().size();
|
||||
for (size_t i = 0; i < tile_para.ndim_; i++) {
|
||||
tile_para.in_shape0_[i] = in_tensors_.at(0)->DimensionSize(i);
|
||||
|
|
|
@ -30,12 +30,6 @@ using mindspore::lite::RET_NULL_PTR;
|
|||
using mindspore::lite::RET_OK;
|
||||
|
||||
namespace mindspore::kernel {
|
||||
namespace {
|
||||
constexpr int kInputNum = 1;
|
||||
constexpr int kOutputNum = 1;
|
||||
constexpr size_t kRank = 4;
|
||||
} // namespace
|
||||
|
||||
int ResizeInt8CPUKernel::Init() {
|
||||
auto ret = ResizeBaseCPUKernel::Init();
|
||||
if (ret != RET_OK) {
|
||||
|
|
|
@ -128,7 +128,7 @@ int SubInt8CPUKernel::Run() {
|
|||
}
|
||||
|
||||
if (broadcast_) {
|
||||
ArithmeticParameter tile_para = {0};
|
||||
ArithmeticParameter tile_para;
|
||||
tile_para.ndim_ = out_tensors_.at(0)->shape().size();
|
||||
for (size_t i = 0; i < tile_para.ndim_; i++) {
|
||||
tile_para.in_shape0_[i] = in_tensors_.at(0)->DimensionSize(i);
|
||||
|
|
|
@ -30,7 +30,7 @@ class Unsqueezeint8CPUKernel : public LiteKernel {
|
|||
Unsqueezeint8CPUKernel(OpParameter *parameter, const std::vector<lite::tensor::Tensor *> &inputs,
|
||||
const std::vector<lite::tensor::Tensor *> &outputs, const Context *ctx,
|
||||
const mindspore::lite::PrimitiveC *primitive)
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), ctx_(ctx), thread_count_(ctx->thread_num_) {
|
||||
: LiteKernel(parameter, inputs, outputs, ctx, primitive), thread_count_(ctx->thread_num_) {
|
||||
Unsq_para_ = reinterpret_cast<UnSqueezeParameter *>(op_parameter_);
|
||||
Unsq_para_->thread_count_ = op_parameter_->thread_num_;
|
||||
}
|
||||
|
@ -42,14 +42,12 @@ class Unsqueezeint8CPUKernel : public LiteKernel {
|
|||
int DoUnsqueeze(int task_id);
|
||||
|
||||
private:
|
||||
UnSqueezeQuantArg *quant_Unsqueeze_parm_;
|
||||
UnSqueezeParameter *Unsq_para_;
|
||||
int thread_sz_count_;
|
||||
int thread_sz_stride_;
|
||||
int data_size_;
|
||||
float *in_ptr_;
|
||||
float *out_ptr_;
|
||||
const Context *ctx_;
|
||||
int thread_count_;
|
||||
};
|
||||
} // namespace mindspore::kernel
|
||||
|
|
|
@ -57,7 +57,6 @@ class SubGraphOpenCLKernel : public SubGraphKernel {
|
|||
std::vector<std::vector<kernel::LiteKernel *>> *out_kernels, bool is_from);
|
||||
|
||||
private:
|
||||
SubGraphOpenCLParameter *subgraph_ocl_parameter_;
|
||||
lite::opencl::OpenCLAllocator *allocator_;
|
||||
std::vector<lite::tensor::Tensor *> in_convert_tensors_;
|
||||
std::vector<lite::tensor::Tensor *> out_convert_tensors_;
|
||||
|
|
|
@ -17,5 +17,10 @@ else()
|
|||
target_link_libraries(timeprofile mindspore-lite pthread)
|
||||
endif()
|
||||
|
||||
install(TARGETS timeprofile
|
||||
RUNTIME DESTINATION ${MAIN_DIR}/time_profile COMPONENT ${COMPONENT_NAME})
|
||||
if (PLATFORM_ARM32 OR PLATFORM_ARM64)
|
||||
install(TARGETS timeprofile
|
||||
RUNTIME DESTINATION ${MAIN_DIR}/time_profile COMPONENT ${COMPONENT_NAME})
|
||||
else()
|
||||
install(TARGETS timeprofile
|
||||
RUNTIME DESTINATION ${MAIN_DIR}/time_profile COMPONENT ${RUN_X86_COMPONENT_NAME})
|
||||
endif()
|
||||
|
|
Loading…
Reference in New Issue