CANN/ops-math正态分布随机数生成

aclnnNormalTensorFloat

【免费下载链接】ops-math本项目是CANN提供的数学类基础计算算子库，实现网络在NPU上加速计算。项目地址: https://gitcode.com/cann/ops-math

📄 查看源码

产品支持情况

功能说明

算子功能：返回一个随机数张量，该随机数是从给定的均值(tensor)和标准差(float)的独立正态分布中获取。

函数原型

每个算子分为两段式接口，必须先调用“aclnnNormalTensorFloatGetWorkspaceSize”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“aclnnNormalTensorFloat”接口执行计算。

aclnnStatus aclnnNormalTensorFloatGetWorkspaceSize( const aclTensor *mean, float std, int64_t seed, int64_t offset, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)

aclnnStatus aclnnNormalTensorFloat( void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)

aclnnNormalTensorFloatGetWorkspaceSize

• 参数说明：

• 返回值：

  aclnnStatus：返回状态码，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：

  返回码	错误码	描述
  ACLNN_ERR_PARAM_NULLPTR	161001	传入的mean或者out为空指针。
  ACLNN_ERR_PARAM_INVALID	161002	传入的mean和out的数据类型不在支持的范围之内。
  		mean和out的shape无法做broadcast。
  		传入的mean或者out的shape维度超过8维。

aclnnNormalTensorFloat

• 参数说明：

• 返回值：

  aclnnStatus：返回状态码，具体参见aclnn返回码。

约束说明

• 确定性计算：
  • aclnnNormalTensorFloat默认确定性实现。

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_normal_out.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, 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_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> meanShape = {1, 4}; std::vector<int64_t> outShape = {1, 4}; void* meanDeviceAddr = nullptr; void* outDeviceAddr = nullptr; aclTensor* mean = nullptr; aclTensor* out = nullptr; std::vector<float> meanHostData = {1.1, 1.2, 1.3, 1.4}; std::vector<float> outHostData = {0.0, 0.0, 0.0, 0.0}; float stdValue = 1.2f; int64_t seed = 1; int64_t offset = 1; // 创建self aclTensor ret = CreateAclTensor(meanHostData, meanShape, &meanDeviceAddr, aclDataType::ACL_FLOAT, &mean); 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aclnnNormalTensorFloat第一段接口 ret = aclnnNormalTensorFloatGetWorkspaceSize(mean, stdValue, seed, offset, out, &workspaceSize, &executor); CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnNormalTensorFloatGetWorkspaceSize 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aclnnNormalTensorFloat第二段接口 ret = aclnnNormalTensorFloat(workspaceAddr, workspaceSize, executor, stream); CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnNormalTensorFloat 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(mean); aclDestroyTensor(out); // 7. 释放device 资源 aclrtFree(meanDeviceAddr); aclrtFree(outDeviceAddr); if (workspaceSize > 0) { aclrtFree(workspaceAddr); } aclrtDestroyStream(stream); aclrtResetDevice(deviceId); aclFinalize(); return 0; }

【免费下载链接】ops-math本项目是CANN提供的数学类基础计算算子库，实现网络在NPU上加速计算。项目地址: https://gitcode.com/cann/ops-math