---
title: aclnnSWhere
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_0557.html
sourcePath: /source/zh/Atlas200IDKA2DeveloperKit/23.0.RC2/Application Development Guide/aadgc/aclcppdevg_03_0557.html
indexId: da00301ef8e846de242e5fa4ebd7fe7e78556c548ee4a851a5c9238d8c2f639d105
---
# aclnnSWhere

#### 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 aclnnSWhereGetWorkspaceSize(const aclTensor *condition, const aclTensor *self, const aclTensor *other, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
- 第二段接口：aclnnStatus aclnnSWhere(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, const aclrtStream stream)


#### 功能描述

- 算子功能：根据张量condition选取张量self或other中元素，或者按照维度返回非零元素的位置。
- 计算公式：


#### aclnnSWhereGetWorkspaceSize

- 接口定义：
  aclnnStatus aclnnSWhereGetWorkspaceSize(const aclTensor *condition, const aclTensor *self, const aclTensor *other, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)

- 参数说明：

  - condition：Device侧的aclTensor，数据类型支持UINT8、BOOL，shape需要与self和other满足broadcast关系。支持非连续的Tensor，数据格式支持ND。
  - self：Device侧的aclTensor，数据类型支持FLOAT、FLOAT16、 INT8、 INT32、UINT8、INT16、INT64、DOUBLE、BOOL、COMPLEX64、BFLOAT16（仅Atlas A2训练系列产品支持）。shape需要与other和condition满足broadcast关系，支持非连续的Tensor，数据格式支持ND。
  - other：Device侧的aclTensor，数据类型支持FLOAT、FLOAT16、 INT8、 INT32、UINT8、INT16、INT64、DOUBLE、BOOL、COMPLEX64、BFLOAT16（仅Atlas A2训练系列产品支持）。shape需要与self和condition满足broadcast关系，支持非连续的Tensor，数据格式支持ND。
  - out：Device侧的aclTensor，数据类型需与self相同，shape需要是selfother和condition broadcast之后的shape。支持非连续的Tensor，数据格式支持ND。
  - workspace_size：返回用户需要在Device侧申请的workspace大小。
  - executor：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self、other、condition、out是空指针。 返回161002（ACLNN_ERR_PARAM_INVALID）： self、other、condition的数据类型不在支持的范围内。 self和other、out数据类型不相同。 self、other、condition broadcast推导失败或broadcast结果与out的shape不相同。


#### aclnnSWhere

- 接口定义：
  aclnnStatus aclnnSWhere(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, const 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aclnnSWhereGetWorkspaceSize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_s_where.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, 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根据自己的需要处理
CHECK_RET(ret == 0, 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
std::vector<int64_t> selfShape = {4, 2};
std::vector<int64_t> otherShape = {4, 2};
std::vector<int64_t> conditionShape = {4, 2};
std::vector<int64_t> outShape = {4, 2};
void* selfDeviceAddr = nullptr;
void* otherDeviceAddr = nullptr;
void* conditionDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* other = nullptr;
aclTensor* condition = nullptr;
aclTensor* out = nullptr;
std::vector<float> selfHostData = {0, 0, 0, 0, 0, 0, 0, 7};
std::vector<float> otherHostData = {0, 1, 2, 3, 4, 5, 6, 7};
std::vector<int8_t> conditionHostData = {false,false,false,false,true,true,true,true};
std::vector<float> outHostData = {10, 10, 10, 10, 10, 10, 10, 10};
// 创建self aclTensor
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建self aclTensor
ret = CreateAclTensor(otherHostData, otherShape, &otherDeviceAddr, aclDataType::ACL_FLOAT, &other);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建condition aclTensor
ret = CreateAclTensor(conditionHostData, conditionShape, &conditionDeviceAddr, aclDataType::ACL_BOOL, &condition);
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);
//
3.调用CANN算子库API，需要修改为具体的算子接口
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// 调用aclnnSWhere第一段接口
ret =
aclnnSWhereGetWorkspaceSize(condition, self, other, out, &workspaceSize, &executor)
;
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSWhereGetWorkspaceSize 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aclnnSWhere第二段接口
ret =
aclnnSWhere(workspaceAddr, workspaceSize, executor, stream)
;
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSWhere 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(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]);
}
//
6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改
aclDestroyTensor(self);
aclDestroyTensor(other);
aclDestroyTensor(condition);
aclDestroyTensor(out);
return 0;
}
```