aclnnEmbedding
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 aclnnEmbeddingGetWorkspaceSize(const aclTensor *weight, const aclTensor *indices, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
- 第二段接口：aclnnStatus aclnnEmbedding(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, const aclrtStream stream)
功能描述
算子功能：Embedding计算是将数据集合映射到向量空间，进而将数据进行量化。
假设Embedding的二维权重矩阵为weight（m+1行、n列），对于任意输入索引张量indices（假设1行3列），输出out是一个3行n列张量。如下所示：
aclnnEmbeddingGetWorkspaceSize
- 接口定义：
aclnnStatus aclnnEmbeddingGetWorkspaceSize(const aclTensor *weight, const aclTensor *indices, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
- 参数说明：
- weight：Device侧的aclTensor，数据类型支持FLOAT、FLOAT16、INT64、INT32、INT16、INT8、UINT8、BOOL、DOUBLE、COMPLEX64、COMPLEX128、BFLOAT16（仅Atlas A2训练系列产品支持），支持非连续的Tensor，数据格式支持ND。
- indices：Device侧的aclTensor，当indices值越界时，对应行的输出值为随机值。数据类型支持INT64、INT32，支持非连续的Tensor，数据格式支持ND。
- out：Device侧的aclTensor，数据类型同weight，数据格式支持ND，比indices的维度多一。
- workspaceSize：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weight、indices、out是空指针。
- 返回161002（ACLNN_ERR_PARAM_INVALID）：
- weight、indices、out的数据类型和数据格式不在支持的范围内。
- indices和out的shape不满足匹配关系。
- 入参的最大维度超过8。
aclnnEmbedding
- 接口定义：
aclnnStatus aclnnEmbedding(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aclnnEmbeddingGetWorkspaceSize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_embedding.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
std::vector<int64_t> weightShape = {10, 3};
std::vector<int64_t> indicesShape = {4};
std::vector<int64_t> outShape = {4, 3};
void* weightDeviceAddr = nullptr;
void* indicesDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* weight = nullptr;
aclTensor* indices = nullptr;
aclTensor* out = nullptr;
std::vector<float> weightHostData = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23,24, 25, 26, 27, 28, 29, 30};
std::vector<int64_t> indicesHostData = {1, 2, 3, 4};
std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
// 创建weight aclTensor
ret = CreateAclTensor(weightHostData, weightShape, &weightDeviceAddr, aclDataType::ACL_FLOAT, &weight);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建indices aclTensor
ret = CreateAclTensor(indicesHostData, indicesShape, &indicesDeviceAddr, aclDataType::ACL_INT64, &indices);
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API名称
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// 调用aclnnEmbedding第一段接口
ret = aclnnEmbeddingGetWorkspaceSize(weight, indices, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnEmbeddingGetWorkspaceSize 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aclnnEmbedding第二段接口
ret = aclnnEmbedding(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnEmbedding 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 resultData from device to host failed. ERROR: %d\n", ret);
return ret);
for (int64_t i = 0; i < size; i++) {
LOG_PRINT("resultData[%ld] is: %f\n", i, resultData[i]);
}
// 6. 释放aclTensor，需要根据具体API的接口定义修改
aclDestroyTensor(weight);
aclDestroyTensor(indices);
aclDestroyTensor(out);
return 0;
}
父主题： NN类算子接口