---
title: aclnnSoftMarginLossBackward
description: "每个算子有两段接口，必须先调用“aclnnXxxGetWorkspaceSize”接口获取入参并根据计算流程计算所需workspace大小，再调用“aclnnXxx”接口执行计算。两段式接口如下："
url: https://www.hiascend.com/document/detail/zh/Atlas200IDKA2DeveloperKit/latest/Application%20Development%20Guide/aadgc/aclcppdevg_03_0541.html
sourcePath: /source/zh/Atlas200IDKA2DeveloperKit/23.0.RC2/Application Development Guide/aadgc/aclcppdevg_03_0541.html
indexId: 69a79ba8fd2573b3b7b8fb3d95acfd480d5cc5b16c81f1f91a1144006e9f5ff8105
---
# aclnnSoftMarginLossBackward

#### 接口原型

每个算子有两段接口，必须先调用“aclnnXxxGetWorkspaceSize”接口获取入参并根据计算流程计算所需workspace大小，再调用“aclnnXxx”接口执行计算。两段式接口如下：

- 第一段接口：aclnnStatus aclnnSoftMarginLossBackwardGetWorkspaceSize(const aclTensor *gradOutput, const aclTensor *self, const aclTensor *target, int64_t reduction, aclTensor *gradInput, uint64_t *workspaceSize, aclOpExecutor **executor)
- 第二段接口：aclnnStatus aclnnSoftMarginLossBackward(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)


#### 功能描述

算子功能：计算二分类逻辑损失函数（aclnnSoftMarginLoss）的反向传播。


#### aclnnSoftMarginLossBackwardGetWorkspaceSize

- 接口定义：
  aclnnStatus aclnnSoftMarginLossBackwardGetWorkspaceSize(const aclTensor *gradOutput, const aclTensor *self, const aclTensor *target, int64_t reduction, aclTensor *gradInput, uint64_t *workspaceSize, aclOpExecutor **executor)

- 参数说明：

  - gradOutput(aclTensor*, 计算输入)：数据类型支持FLOAT、FLOAT16，shape需要与self、target满足broadcast关系。支持非连续的Tensor，数据格式支持ND。
  - self(aclTensor*, 计算输入)：数据类型支持FLOAT、FLOAT16，shape需要与gradOutput、target满足broadcast关系。支持非连续的Tensor，数据格式支持ND。
  - target(aclTensor*, 计算输入)：数据类型支持FLOAT、FLOAT16，shape需要与gradOutput、self满足broadcast关系。支持非连续的Tensor，数据格式支持ND。
  - reduction(int64_t，计算输入)：指定要应用到输出的缩减.。支持3种枚举值，取0时为'none' ，表示不应用减少；取1时为'mean' ，表示输出的总和除以输出中的元素数。取2时为'sum' ，表示输出将被求和。
  - gradInput(aclTensor*, 计算输出)：数据类型支持FLOAT、FLOAT16，shape需要与self、target、gradOutput满足broadcast关系。支持非连续的Tensor，数据格式支持ND。
  - workspaceSize(uint64_t*, 出参)：返回用户需要在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：
  返回aclnnStatus状态码，具体参见aclnn返回码。

  第一段接口完成入参校验，出现以下场景时报错： 返回161001（ACLNN_ERR_PARAM_NULLPTR）：传入的gradOutput、self、target或gradInput是空指针。 返回161002（ACLNN_ERR_PARAM_INVALID）： gradOutput、self、target的数据类型不在支持的范围之内。 gradOutput、self和target、gradInput的shape不满足broadcast规则。 gradOutput、self和target、gradInput做broadcast后的shape与gradInput不一致。


#### aclnnSoftMarginLossBackward

- 接口定义：
  aclnnStatus aclnnSoftMarginLossBackward(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)

- 参数说明：

  - workspace：在Device侧申请的workspace内存起址。
  - workspaceSize：在Device侧申请的workspace大小，由第一段接口aclnnSoftMarginLossBackwardGetWorkspaceSize获取。
  - executor：op执行器，包含了算子计算流程。
  - stream：指定执行任务的AscendCL stream流。
- 返回值：
  返回aclnnStatus状态码，具体参见aclnn返回码。


#### 调用示例

```
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_soft_margin_loss_backward.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 shapeSize = 1;
for (auto i : shape) {
shapeSize *= i;
}
return shapeSize;
}
int Init(int32_t deviceId, aclrtContext* context, 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 = aclrtCreateContext(context, deviceId);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateContext failed. ERROR: %d\n", ret); return ret);
ret = aclrtSetCurrentContext(*context);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetCurrentContext 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侧内存
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() {
// 1. （固定写法）device/context/stream初始化，参考AscendCL对外接口列表
// 根据自己的实际device填写deviceId
int32_t deviceId = 0;
aclrtContext context;
aclrtStream stream;
auto ret = Init(deviceId, &context, &stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
// 2. 构造输入与输出，需要根据API的接口自定义构造gradOutput
std::vector<int64_t> gradOutputShape = {2, 2};
std::vector<int64_t> selfShape = {2, 2};
std::vector<int64_t> targetShape = {2, 2};
std::vector<int64_t> outShape = {2, 2};
void* gradOutputDeviceAddr = nullptr;
void* selfDeviceAddr = nullptr;
void* targetDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* gradOutput = nullptr;
aclTensor* self = nullptr;
aclTensor* target = nullptr;
aclTensor* out = nullptr;
std::vector<float> gradOutputHostData = {0, 1, 2, 3};
std::vector<float> selfHostData = {0, 1, 2, 3};
std::vector<float> targetHostData = {1, 1, 1, 1};
std::vector<float> outHostData(4, 0);
// 创建gradOutput aclTensor
ret = CreateAclTensor(gradOutputHostData, gradOutputShape, &gradOutputDeviceAddr,
aclDataType::ACL_FLOAT, &gradOutput);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建self aclTensor
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建target aclTensor
ret = CreateAclTensor(targetHostData, targetShape, &targetDeviceAddr, aclDataType::ACL_FLOAT, &target);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建out aclTensor
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建reduction
int64_t reduction = 1;
// 3. 调用CANN算子库API，需要修改为具体的API名称
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// 调用aclnnSoftMarginLossBackward第一段接口
ret =
aclnnSoftMarginLossBackwardGetWorkspaceSize(gradOutput, self, target, reduction, out, &workspaceSize, &executor)
;
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSoftMarginLossBackwardGetWorkspaceSize failed. ERROR: %d\n", ret);
return ret);
// 根据第一段接口计算出的workspaceSize申请device内存
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);
}
// 调用aclnnSoftMarginLossBackward第二段接口
ret =
aclnnSoftMarginLossBackward(workspaceAddr, workspaceSize, executor, stream
);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSoftMarginLossBackward failed. ERROR: %d\n", ret); return ret);
// 4. （固定写法）同步等待任务执行结束
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
// 5. 获取输出的值，将device侧内存上的结果拷贝至host侧，需要根据具体API的接口定义修改
auto size = GetShapeSize(outShape);
std::vector<float> resultData(size, 0);
ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr,
size * sizeof(resultData[0]), 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]);
}
// 6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改
aclDestroyTensor(gradOutput);
aclDestroyTensor(self);
aclDestroyTensor(target);
aclDestroyTensor(out);
// 7. 释放device资源，需要根据具体API的接口定义修改
aclrtFree(gradOutputDeviceAddr);
aclrtFree(selfDeviceAddr);
aclrtFree(targetDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtDestroyContext(context);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}
```