sfqcyy
/
mindspore
forked from OSSInnovation/mindspore
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

optimize arithmetic

This commit is contained in:
zhangxuetong 2020-08-14 09:12:19 +08:00
parent 1002ee4887
commit 9f51871c66
9 changed files with 116 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
build.sh
View File

@ -706,6 +706,7 @@ build_lite()
mkdir -p ${OUTPUT_DIR}/include/schema/
cp ${BASEPATH}/mindspore/lite/schema/*.h ${OUTPUT_DIR}/include/schema/
cp ${BASEPATH}/mindspore/lite/build/src/libmindspore-lite.so ${OUTPUT_DIR}/lib/
cp ${BASEPATH}/mindspore/lite/build/src/runtime/kernel/arm/nnacl/liboptimize.so ${OUTPUT_DIR}/lib/
mkdir -p ${OUTPUT_DIR}/third_party/flatbuffers
cp -r ${BASEPATH}/third_party/flatbuffers/include/ ${OUTPUT_DIR}/third_party/flatbuffers/
cd ..

7
mindspore/lite/src/runtime/kernel/arm/fp16/convolution_3x3_fp16.cc
View File

@ -266,7 +266,8 @@ int Convolution3x3FP16CPUKernel::Run() {
}
auto input_tensor = in_tensors_.at(kInputIndex);
auto ori_input_data = reinterpret_cast<float *>(input_tensor->Data());
for (int i = 0; i < input_tensor->ElementsNum(); ++i) {
auto input_element_num = input_tensor->ElementsNum();
for (int i = 0; i < input_element_num; ++i) {
fp16_input_[i] = (float16_t)ori_input_data[i];
}
@ -285,7 +286,9 @@ int Convolution3x3FP16CPUKernel::Run() {
// cast fp16 out to fp32 data
auto out_tensor = out_tensors_.at(kOutputIndex);
auto output_addr = reinterpret_cast<float *>(out_tensor->Data());
for (int j = 0; j < out_tensor->ElementsNum(); ++j) {
auto output_element_num = out_tensor->ElementsNum();
for (int j = 0; j < output_element_num; ++j) {
output_addr[j] = static_cast<float>(fp16_out_[j]);
}
return RET_OK;

6
mindspore/lite/src/runtime/kernel/arm/fp16/convolution_fp16.cc
View File

@ -231,7 +231,8 @@ int ConvolutionFP16CPUKernel::Run() {
}
auto input_tensor = in_tensors_.at(kInputIndex);
auto ori_input_data = reinterpret_cast<float *>(input_tensor->Data());
for (int i = 0; i < input_tensor->ElementsNum(); ++i) {
auto input_element_num = input_tensor->ElementsNum();
for (int i = 0; i < input_element_num; ++i) {
fp16_input_[i] = (float16_t)ori_input_data[i];
}
@ -250,7 +251,8 @@ int ConvolutionFP16CPUKernel::Run() {
// cast fp16 out to fp32 data
auto out_tensor = out_tensors_.at(kOutputIndex);
auto output_addr = reinterpret_cast<float *>(out_tensor->Data());
for (int j = 0; j < out_tensor->ElementsNum(); ++j) {
auto output_element_num = out_tensor->ElementsNum();
for (int j = 0; j < output_element_num; ++j) {
output_addr[j] = static_cast<float>(fp16_out_[j]);
}
return RET_OK;

45
mindspore/lite/src/runtime/kernel/arm/fp32/arithmetic.cc
View File

@ -51,10 +51,36 @@ int ArithmeticCPUKernel::Init() {
int ArithmeticCPUKernel::ReSize() {
FreeTileData();
auto element_num = out_tensors_[0]->ElementsNum();
arithmeticParameter_->in_elements_num0_ = in_tensors_[0]->ElementsNum();
arithmeticParameter_->in_elements_num1_ = in_tensors_[1]->ElementsNum();
arithmeticParameter_->out_elements_num_ = out_tensors_[0]->ElementsNum();
if (arithmeticParameter_->in_elements_num0_ == 1 || arithmeticParameter_->in_elements_num1_ == 1) {
if (arithmeticParameter_->activation_type_ == schema::ActivationType_NO_ACTIVATION) {
switch (arithmeticParameter_->op_parameter_.type_) {
case PrimitiveType_Mul:
arithmeticParameter_->broadcasting_ = false;
arithmetic_opt_run_ = ElementOptMul;
break;
case PrimitiveType_Add:
arithmeticParameter_->broadcasting_ = false;
arithmetic_opt_run_ = ElementOptAdd;
break;
case PrimitiveType_Sub:
arithmeticParameter_->broadcasting_ = false;
arithmetic_opt_run_ = ElementOptSub;
break;
default:
break;
}
}
}
if (arithmeticParameter_->broadcasting_) {
tile_data0_ = new float[arithmeticParameter_->out_elements_num_];
tile_data1_ = new float[arithmeticParameter_->out_elements_num_];
}
tile_data0_ = new float[element_num];
tile_data1_ = new float[element_num];
return RET_OK;
}
@ -77,7 +103,17 @@ int ArithmeticCPUKernel::DoArithmetic(int task_id) {
if (arithmeticParameter_->broadcasting_) {
error_code = arithmetic_run_(tile_data0_ + stride * task_id, tile_data1_ + stride * task_id,
output_data + stride * task_id, count);
} else if (arithmetic_opt_run_ != nullptr) {
if (arithmeticParameter_->in_elements_num0_ == 1) {
error_code = arithmetic_opt_run_(input0_data, input1_data1 + stride * task_id, output_data + stride * task_id,
count, arithmeticParameter_);
} else if (arithmeticParameter_->in_elements_num1_ == 1) {
error_code = arithmetic_opt_run_(input0_data + stride * task_id, input1_data1, output_data + stride * task_id,
count, arithmeticParameter_);
} else {
error_code = arithmetic_opt_run_(input0_data + stride * task_id, input1_data1 + stride * task_id,
output_data + stride * task_id, count, arithmeticParameter_);
}
} else {
error_code = arithmetic_run_(input0_data + stride * task_id, input1_data1 + stride * task_id,
output_data + stride * task_id, count);
@ -104,6 +140,7 @@ int ArithmeticCPUKernel::Run() {
MS_LOG(ERROR) << "Prepare fail!ret: " << ret;
return ret;
}
if (arithmeticParameter_->broadcasting_) {
auto input_data0 = reinterpret_cast<float *>(in_tensors_[0]->Data());
auto input_data1 = reinterpret_cast<float *>(in_tensors_[1]->Data());

7
mindspore/lite/src/runtime/kernel/arm/fp32/arithmetic.h
View File

@ -43,6 +43,8 @@ using mindspore::schema::PrimitiveType_Sub;
namespace mindspore::kernel {
class ArithmeticCPUKernel : public LiteKernel {
typedef int (*ArithmeticRun)(float *input0, float *input1, float *output, int element_size);
typedef int (*ArithmeticOptRun)(float *input0, float *input1, float *output, int element_size,
ArithmeticParameter *param);
typedef int (*ArithmeticBroadcastRun)(float *input0, float *input1, float *tile_input0, float *tile_input1,
float *output, int element_size, ArithmeticParameter *param);
@ -177,8 +179,9 @@ class ArithmeticCPUKernel : public LiteKernel {
float *tile_data0_ = nullptr;
float *tile_data1_ = nullptr;
ArithmeticParameter *arithmeticParameter_;
ArithmeticRun arithmetic_run_;
ArithmeticBroadcastRun arithmetic_broadcast_run_;
ArithmeticRun arithmetic_run_ = nullptr;
ArithmeticBroadcastRun arithmetic_broadcast_run_ = nullptr;
ArithmeticOptRun arithmetic_opt_run_ = nullptr;
};
} // namespace mindspore::kernel
#endif // MINDSPORE_LITE_SRC_RUNTIME_KERNEL_ARM_FP32_ARITHMETIC_H_

3
mindspore/lite/src/runtime/kernel/arm/fp32/convolution.cc
View File

@ -277,7 +277,8 @@ kernel::LiteKernel *CpuConvFp32KernelCreator(const std::vector<lite::tensor::Ten
kernel =
new (std::nothrow) kernel::ConvolutionWinogradCPUKernel(opParameter, inputs, outputs, ctx, primitive, out_unit);
} else if (use_sw) {
kernel = new (std::nothrow) kernel::ConvolutionSWCPUKernel(opParameter, inputs, outputs, ctx, primitive);
// kernel = new (std::nothrow) kernel::ConvolutionSWCPUKernel(opParameter, inputs, outputs, ctx, primitive);
kernel = new (std::nothrow) kernel::ConvolutionCPUKernel(opParameter, inputs, outputs, ctx, primitive);
} else {
kernel = new (std::nothrow) kernel::ConvolutionCPUKernel(opParameter, inputs, outputs, ctx, primitive);
}

4
mindspore/lite/src/runtime/kernel/arm/nnacl/arithmetic_common.h
View File

@ -29,8 +29,12 @@ typedef struct ArithmeticParameter {
size_t ndim_;
int activation_type_;
int in_shape0_[5];
int in_elements_num0_;
int in_shape1_[5];
int in_elements_num1_;
int out_shape_[5];
int out_elements_num_;
int in_strides0_[5];
int in_strides1_[5];

51
mindspore/lite/src/runtime/kernel/arm/nnacl/fp32/arithmetic.c
View File

@ -19,6 +19,57 @@
#define ACCURACY_DATA 0.00000001
int ElementOptMul(float *input0, float *input1, float *output, int element_size, ArithmeticParameter *param) {
if (param->in_elements_num0_ == 1) {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[0] * input1[i];
}
} else if (param->in_elements_num1_ == 1) {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[i] * input1[0];
}
} else {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[i] * input1[i];
}
}
return NNACL_OK;
}
int ElementOptSub(float *input0, float *input1, float *output, int element_size, ArithmeticParameter *param) {
if (param->in_elements_num0_ == 1) {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[0] - input1[i];
}
} else if (param->in_elements_num1_ == 1) {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[i] - input1[0];
}
} else {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[i] - input1[i];
}
}
return NNACL_OK;
}
int ElementOptAdd(float *input0, float *input1, float *output, int element_size, ArithmeticParameter *param) {
if (param->in_elements_num0_ == 1) {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[0] + input1[i];
}
} else if (param->in_elements_num1_ == 1) {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[i] + input1[0];
}
} else {
for (int i = 0; i < element_size; ++i) {
output[i] = input0[i] + input1[i];
}
}
return NNACL_OK;
}
int ElementMul(float *input0, float *input1, float *output, int element_size) {
int block_mod = element_size % C4NUM;
int block_c4 = element_size - block_mod;

3
mindspore/lite/src/runtime/kernel/arm/nnacl/fp32/arithmetic.h
View File

@ -26,6 +26,9 @@
#ifdef __cplusplus
extern "C" {
#endif
int ElementOptAdd(float *input0, float *input1, float *output, int element_size, ArithmeticParameter *param);
int ElementOptSub(float *input0, float *input1, float *output, int element_size, ArithmeticParameter *param);
int ElementOptMul(float *input0, float *input1, float *output, int element_size, ArithmeticParameter *param);
int ElementMul(float *input0, float *input1, float *output, int element_size);
int ElementMulRelu(float *input0, float *input1, float *output, int element_size);
int ElementMulRelu6(float *input0, float *input1, float *output, int element_size);