aclnnExpandv
产品支持情况
| 产品 | 是否支持 |
|---|---|
<term>Atlas A2 训练系列产品/Atlas 800I A2 推理产品/A200I A2 Box 异构组件 </term> |
√ |
功能说明
- 算子功能：将张量在长度为1的维度广播到目标 shape，理想情况下为视图。
- 计算公式：
yi=xoffset y_i = x_{offset}
函数原型
每个算子分为两段式接口，必须先调用“aclnnExpandvGetWorkspaceSize”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“aclnnExpandv”接口执行计算。
aclnnStatus aclnnExpandvGetWorkspaceSize(
const aclTensor *self,
const aclIntArray* shape,
aclTensor *out,
uint64_t *workspaceSize,
aclOpExecutor **executor)
aclnnStatus aclnnExpandv(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
const aclrtStream stream)
aclnnExpandvGetWorkspaceSize
-
参数说明：
参数名 输入/输出 描述 使用说明 数据类型 数据格式 维度(shape) 非连续Tensor x 输入 待进行expand计算的入参，公式中的x。 无 FLOAT、FLOAT16、DOUBLE、BFLOAT16、INT8、INT16、INT32、INT64、UINT8、BOOL ND 1 √ shape 输入 待进行expand计算的入参,广播后的形状。 无 INT64 ND 2-8 √ y 输出 待进行expand计算的入参，公式中的y。 shape与self相同。 FLOAT、FLOAT16、DOUBLE、BFLOAT16、INT8、INT16、INT32、INT64、UINT8、BOOL ND 2-8 √ workspaceSize 输出 返回需要在Device侧申请的workspace大小。 - - - - - executor 输出 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。
第一段接口会完成入参校验，出现以下场景时报错：
返回码 错误码 描述 ACLNN_ERR_PARAM_NULLPTR 161001 传入的tensor是空指针。 ACLNN_ERR_PARAM_INVALID 161002 condition, self, 和other的数据类型和数据格式不在支持的范围之内。 condition, self, 和other的数据维度超过了8维。 condition, self, other和out的数据形状不一致。
aclnnExpandv
-
参数说明：
参数名 输入/输出 描述 workspace 输入 在Device侧申请的workspace内存地址。 workspaceSize 输入 在Device侧申请的workspace大小，由第一段接口aclnnExpandvGetWorkspaceSize获取。 executor 输入 op执行器，包含了算子计算流程。 stream 输入 指定执行任务的Stream。 -
返回值：
aclnnStatus：返回状态码，具体参见aclnn返回码。
约束说明
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。
/**
* This file is part of the OpenBOAT project at Harbin Institute of Technology (HIT)
* and is contributed to the CANN Open Software.
*
* Copyright (c) 2025 AISS Group, Harbin Institute of Technology (HIT).
* All Rights Reserved.
*
* Authors (accounts):
* - Shi Xiangyang <@shi-xiangyang225>
* - Su Tonghua <@sutonghua>
*
* This program is free software: you can redistribute it and/or modify it.
* Licensed under the CANN Open Software License Agreement Version 2.0 (the "License").
* You may not use this file except in compliance with the License.
* See the LICENSE file at the root of the repository for the full text of the License.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTIES OF ANY KIND, EXPRESS OR IMPLIED,
* INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
*/
/**
* This program is free software, you can redistribute it and/or modify it.
* Copyright (c) 2025 Huawei Technologies Co., Ltd.
* This file is a part of the CANN Open Software.
* Licensed under CANN Open Software License Agreement Version 2.0 (the "License").
* Please refer to the License for details. You may not use this file except in compliance with the License.
* THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING
* BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
* See LICENSE in the root of the software repository for the full text of the License.
*/
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_expand.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，资源初始化
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/stream初始化, 参考acl API手册
// 根据自己的实际device填写deviceId
int32_t deviceId = 0;
aclrtStream stream;
auto ret = Init(deviceId, &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, 1, 3};
std::vector<int64_t> outShape = {4,5,3};
const std::vector<int64_t> expandSections = {4,5,3};
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* out = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11};
std::vector<float> outHostData(60, 0);
// 创建self aclTensor
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
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);
// 创建参数的ACL IntArray
aclIntArray *aclExpandSections = aclCreateIntArray(expandSections.data(), expandSections.size());
if(aclExpandSections == nullptr){LOG_PRINT("aclCreateIntArray for expand sections failed \n");}
// 3. 调用CANN算子库API
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// 调用aclnnExpand第一段接口
ret = aclnnExpandGetWorkspaceSize(self, aclExpandSections, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnExpandGetWorkspaceSize 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aclnnExpand第二段接口
ret = aclnnExpand(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnExpand 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(out);
// 7.释放device资源，需要根据具体API的接口定义修改
aclrtFree(selfDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}