forked from FT_DSP/FT_DSP.gitlink.net
105 lines
4.4 KiB
ReStructuredText
105 lines
4.4 KiB
ReStructuredText
ReverseSequence
|
||
=================
|
||
|
||
对输入序列进行部分反转。
|
||
|
||
输入：
|
||
- **src** - 需反转数据的地址
|
||
- **seq_lengths** - 指定反转长度，为一维向量。
|
||
- **param** - 算子计算所需参数的结构体。其各成员见下述。
|
||
- **core_mask** - 核掩码。
|
||
|
||
**ReverseSequenceParameter定义：**
|
||
|
||
.. code-block:: c
|
||
:linenos:
|
||
|
||
typedef struct ReverseSequenceParameter {
|
||
int* shape_; // 输入和输出张量的形状
|
||
int* strides_; // 一个记录张量每一维步长的数组
|
||
int seq_dim_; // 指定反转的维度
|
||
int batch_dim_; // 指定切片维度
|
||
int ndim_; // 输入和输出张量的维度
|
||
int type_size_; // 输入和输出张量数据类型的长度
|
||
int copy_elem_num_; // 在inner_count循环中一次应被拷贝的元素数目
|
||
int outer_stride_; // 外层元素间的步长
|
||
int outer_count_; // 外层元素数
|
||
int inner_stride_; // 内层元素间的步长
|
||
int inner_count_; // 内层元素数
|
||
} ReverseSequenceParameter;
|
||
|
||
输出：
|
||
- **dst** - 输出地址。
|
||
|
||
支持平台：
|
||
``FT78NE``
|
||
``MT7004``
|
||
|
||
.. note::
|
||
- FT78NE 支持int8, int16, int32, fp32, fp64, cplx64, cplx128
|
||
- MT7004 支持fp16, fp32, int16, int32, cplx64
|
||
|
||
**共享/私有存储版本:**
|
||
|
||
.. c:function:: void anytype_reverse_sequence_anycore(void* src, void* dst, int* seq_lengths, ReverseSequenceParameter* param, int core_mask)
|
||
|
||
各种数据类型、私有及共享空间版本均使用该函数。对于不同数据类型，改变param中的type_size_参数即可。
|
||
|
||
**C调用示例：**
|
||
|
||
.. code-block:: c
|
||
:linenos:
|
||
:emphasize-lines: 41
|
||
|
||
void Resize(ReverseSequenceParameter* param) {
|
||
param->strides_ = (int*)0xA8020000;
|
||
ComputeStrides(param->shape_, param->strides_, param->ndim_);
|
||
int less_dim = param->batch_dim_ > param->seq_dim_ ? param->seq_dim_ : param->batch_dim_;
|
||
int greater_dim = param->batch_dim_ < param->seq_dim_ ? param->seq_dim_ : param->batch_dim_;
|
||
// calculate the size of elements should be copied at one time
|
||
param->copy_elem_num_ = CountElementAfterDim(param->shape_, greater_dim, param->ndim_);
|
||
// calculate the number of elements before the less axis and the stride
|
||
param->outer_count_ = CountElementBeforeDim(param->shape_, less_dim);
|
||
param->outer_stride_ = param->shape_[less_dim] * CountElementAfterDim(param->shape_, less_dim, param->ndim_);
|
||
// calculate the number of elements between the less axis and the greater axis and the stride
|
||
param->inner_count_ = 1;
|
||
int i;
|
||
for (i = less_dim + 1; i < greater_dim; i++) {
|
||
param->inner_count_ *= param->shape_[i];
|
||
}
|
||
param->inner_stride_ = param->shape_[greater_dim] * CountElementAfterDim(param->shape_, greater_dim, param->ndim_);
|
||
}
|
||
|
||
void TestReverseSequenceFp32(int* shape, int* orig_seq_lengths, int seq_dim, int batch_dim, int ndim, int core_mask) {
|
||
int core_id = get_core_id();
|
||
int core_num = GetCoreNum(core_mask);
|
||
int logic_core_id = GetLogicCoreId(core_mask, core_id);
|
||
float* input_data = (float*)0x88000000; // 测试私有空间时地址设置在私有空间内即可
|
||
float* output_data = (float*)0x98000000;
|
||
float* check = (float*)0xB8000000;
|
||
int* seq_lengths = (int*)0xC8000000;
|
||
ReverseSequenceParameter* param = (ReverseSequenceParameter*)0xA8000000;
|
||
int i;
|
||
if (logic_core_id == 0) {
|
||
param->shape_ = (int*)0xA8010000;
|
||
memcpy(param->shape_, shape, sizeof(int) * ndim);
|
||
memcpy(seq_lengths, orig_seq_lengths, sizeof(int) * shape[batch_dim]);
|
||
param->batch_dim_ = batch_dim;
|
||
param->seq_dim_ = seq_dim;
|
||
param->ndim_ = ndim;
|
||
param->type_size_ = sizeof(float);
|
||
Resize(param);
|
||
}
|
||
sys_bar(0, core_num); // 初始化参数完成后进行同步
|
||
anytype_reverse_sequence_anycore(input_data, output_data, seq_lengths, param, core_mask);
|
||
}
|
||
|
||
void main(){
|
||
int shape[3] = {3, 4, 10};
|
||
int seq_lengths[3] = {1, 2, 3};
|
||
int ndim = 3;
|
||
int seq_dim = 1;
|
||
int batch_dim = 0;
|
||
int core_mask = 0b1111; // 测试单核时核掩码设置为0b0001即可
|
||
TestReverseSequenceFp32(shape, seq_lengths, seq_dim, batch_dim, ndim, core_mask);
|
||
} |