aclnnFlatten
支持的产品型号
- Atlas 训练系列产品。
- Atlas A2训练系列产品/Atlas 800I A2推理产品。
接口原型
每个算子分为两段式接口，必须先调用“aclnnFlattenGetWorkspaceSize”接口获取计算所需workspace大小以及包含了算子计算流程的执行器，再调用“aclnnFlatten”接口执行计算。
aclnnStatus aclnnFlattenGetWorkspaceSize(const aclTensor *self, int64_t axis, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)aclnnStatus aclnnFlatten(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, const aclrtStream stream)
功能描述
算子功能：将输入Tensor，基于给定的axis，扁平化为一个2D的Tensor。
- 若self的shape为(d_0,d_1,...,d_n)，那么输出out的shape为(d_0 X d_1 ... X d_(axis-1), d_axis X d_(axis+1)... X d_n)。
- 若axis取值为0，则输出out的shape为(1, d_0 X d_1 ... X d_n)。
aclnnFlattenGetWorkspaceSize
参数说明：
self(aclTensor*,计算输入)：输入
self,数据类型支持INT8、INT16、INT32、INT64、UINT8、UINT16、UINT32、UINT64、BOOL、BFLOAT16（仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持）、FLOAT、FLOAT16。支持非连续的Tensor，数据格式支持ND。axis(int64_t, 计算输入)：输入
axis，int64_t类型整数。表示flatten计算的基准轴。取值范围为[-self.dim(),self.dim()-1]。out(aclTensor*,计算输出)：输出
out,数据类型支持INT8、INT16、INT32、INT64、UINT8、UINT16、UINT32、UINT64、BOOL、BFLOAT16（仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持）、FLOAT、FLOAT16。shape为2D。支持非连续的Tensor，数据格式支持ND。workspaceSize(uint64_t*,出参)：返回需要在Device侧申请的workspace大小。
executor(aclOpExecutor**,出参)：返回op执行器，包含了算子计算流程。
返回值：
aclnnStatus：返回状态码，具体参见aclnn返回码。
161001(ACLNN_ERR_PARAM_NULLPTR): 1. 传入的self、out是空指针。 161002(ACLNN_ERR_PARAM_INVALID): 1. self和out的数据类型不在支持的范围之内。 2. self和out的数据类型不一致。 3. axis不在输入self的合理维度范围之内。 4. self的维度大于8。
aclnnFlatten
参数说明：
workspace(void*, 入参)：在Device侧申请的workspace内存地址。
workspaceSize(uint64_t, 入参)：在Device侧申请的workspace大小，由第一段接口aclnnFlattenGetWorkspaceSize获取。
executor(aclOpExecutor*, 入参)：op执行器，包含了算子计算流程。
stream(aclrtStream, 入参)：指定执行任务的AscendCL Stream流。
返回值：
aclnnStatus：返回状态码，具体参见aclnn返回码。
约束与限制
无。
调用示例
示例代码如下，仅供参考，具体编译和执行过程请参考编译与运行样例。
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_flatten.h"
#define CHECK_RET(cond, return_expr) \
do { \
if (!(cond)) { \
return_expr; \
} \
} while(0)
#define LOG_PRINT(message, ...) \
do { \
printf(message, ##__VA_ARGS__); \
} while(0)
int64_t GetShapeSize(const std::vector<int64_t>& shape) {
int64_t shape_size = 1;
for (auto i : shape) {
shape_size *= i;
}
return shape_size;
}
int Init(int32_t deviceId, aclrtStream* stream) {
// 固定写法,AscendCL初始化
auto ret = aclInit(nullptr);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
ret = aclrtSetDevice(deviceId);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
ret = aclrtCreateStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
return 0;
}
template<typename T>
int CreateAclTensor(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
aclDataType dataType, aclTensor** tensor) {
auto size = GetShapeSize(shape) * sizeof(T);
// 调用aclrtMalloc申请device侧引擎
auto ret = aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);
// 调用aclrtMemcpy将host侧数据拷贝到device侧内存上
ret = aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);
// 计算连续tensor的strides
std::vector<int64_t> strides(shape.size(), 1);
for (int64_t i = shape.size() - 2; i >= 0; i--) {
strides[i] = shape[i + 1] * strides[i + 1];
}
// 调用aclCreateTensor接口创建aclTensor
*tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
shape.data(), shape.size(), *deviceAddr);
return 0;
}
int main() {
int32_t deviceId = 0;
aclrtStream stream;
auto ret = Init(deviceId, &stream);
CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
std::vector<int64_t> selfShape = {4, 2};
std::vector<int64_t> outShape = {1, 8};
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* out = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
std::vector<float> outHostData = {1, 1, 1, 1, 0, 0, 0, 0};
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建attr
int64_t axis = 0;
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
ret = aclnnFlattenGetWorkspaceSize(self, axis, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFlattenGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
void* workspaceAddr = nullptr;
if (workspaceSize > 0) {
ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
}
ret = aclnnFlatten(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFlatten failed. ERROR: %d\n", ret); return ret);
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
auto size = GetShapeSize(outShape);
std::vector<float> resultData(size, 0);
ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr, size * sizeof(float), ACL_MEMCPY_DEVICE_TO_HOST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
for (int64_t i = 0; i < size; i++) {
LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
}
aclDestroyTensor(self);
aclDestroyTensor(out);
// 释放device资源
aclrtFree(selfDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}