aclnnInplaceRandomTensor【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产品是否支持Ascend 950PR/Ascend 950DT√Atlas A3 训练系列产品/Atlas A3 推理系列产品√Atlas A2 训练系列产品/Atlas A2 推理系列产品√Atlas 200I/500 A2 推理产品×Atlas 推理系列产品×Atlas 训练系列产品×功能说明从[from, to-1]的离散均匀分布中采样的数填充selfRef张量。函数原型每个算子分为两段式接口必须先调用“aclnnInplaceRandomTensorGetWorkspaceSize”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“aclnnInplaceRandomTensor”接口执行计算。aclnnStatus aclnnInplaceRandomTensorGetWorkspaceSize( const aclTensor* selfRef, int64_t from, int64_t to, const aclTensor* seedTensor, const aclTensor* offsetTensor, int64_t offset, uint64_t* workspaceSize, aclOpExecutor** executor)aclnnStatus aclnnInplaceRandomTensor( void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)aclnnInplaceRandomTensorGetWorkspaceSize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tensorselfRef输入/输出输入输出tensor。支持空tensor场景。BFLOAT16、FLOAT16、FLOAT32、DOUBLE、INT32、INT64、INT16、INT8、UINT8、BOOL、COMPLEX64、COMPLEX128ND0-8×from输入进行离散均匀分布取值的左边界。from的值需要在selfRef的数据类型取值范围内from的取值需要小于to。INT64---to输入进行离散均匀分布取值的右边界。to的值需要在selfRef的数据类型取值范围内。INT64---seedTensor输入设置随机数生成器的种子值它影响生成的随机数序列。-INT64ND1×offsetTensor输入表示随机数的偏移量它影响生成的随机数序列的位置。设置偏移量后生成的随机数序列会从指定位置开始。与标量offset的累加结果作为随机数算子的偏移量。INT64ND1×offset输入作为offsetTensor的累加量。-INT64---workspaceSize输出返回用户需要在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。第一段接口完成入参校验出现以下场景时报错返回值错误码描述ACLNN_ERR_PARAM_NULLPTR161001传入的selfRef是空指针。ACLNN_ERR_PARAM_INVALID161002selfRef的数据类型不在支持的范围之内。from大于等于to。to超过selfRef数据类型的取值范围。aclnnInplaceRandomTensor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aclnnInplaceRandomTensorGetWorkspaceSize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。#include iostream #include vector #include acl/acl.h #include aclnnop/aclnn_random.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::vectorint64_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::vectorT hostData, const std::vectorint64_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::vectorint64_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::vectorint64_t selfShape {4, 2}; std::vectorint64_t seedShape {1}; std::vectorint64_t offsetShape {1}; void* selfDeviceAddr nullptr; aclTensor* self nullptr; void* seedDeviceAddr nullptr; aclTensor* seed nullptr; void* offsetDeviceAddr nullptr; aclTensor* offset nullptr; int64_t offset2 102; std::vectorfloat selfHostData {1, 2, 3, 4, 5, 6, 7, 8}; std::vectorint64_t seedHostData {0}; std::vectorint64_t offsetHostData {392}; int64_t from 0; int64_t to 10; // 创建self aclTensor ret CreateAclTensor(selfHostData, selfShape, selfDeviceAddr, aclDataType::ACL_FLOAT, self); CHECK_RET(ret ACL_SUCCESS, return ret); // 创建seed aclTensor ret CreateAclTensor(seedHostData, seedShape, seedDeviceAddr, aclDataType::ACL_INT64, seed); CHECK_RET(ret ACL_SUCCESS, return ret); // 创建offset aclTensor ret CreateAclTensor(offsetHostData, offsetShape, offsetDeviceAddr, aclDataType::ACL_INT64, offset); 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aclnnInplaceRandomTensor第一段接口 ret aclnnInplaceRandomTensorGetWorkspaceSize(self, from, to, seed, offset, offset2, workspaceSize, executor); CHECK_RET(ret ACL_SUCCESS, LOG_PRINT(aclnnInplaceRandomTensorGetWorkspaceSize 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aclnnInplaceRandomTensor第二段接口 ret aclnnInplaceRandomTensor(workspaceAddr, workspaceSize, executor, stream); CHECK_RET(ret ACL_SUCCESS, LOG_PRINT(aclnnInplaceRandomTensor 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(selfShape); std::vectorfloat resultData(size, 0); ret aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfDeviceAddr, 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(self); aclDestroyTensor(seed); aclDestroyTensor(offset); // 7. 释放Device资源需要根据具体API的接口定义修改 aclrtFree(selfDeviceAddr); aclrtFree(seedDeviceAddr); aclrtFree(offsetDeviceAddr); 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创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考