aclnnReplicationPad1d
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 aclnnReplicationPad1dGetWorkspaceSize(const aclTensor *self, const aclIntArray *padding, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
- 第二段接口:aclnnStatus aclnnReplicationPad1d(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, const aclrtStream stream)
功能描述
- 算子功能:使用输入的边界值填充张量(1D)。
- 示例:
输入self=([[0,1,2]]) 输入padding=([2,2]) 输出out=([[0,0,0,1,2,2,2]])
aclnnReplicationPad1dGetWorkspaceSize
- 接口定义:
aclnnStatus aclnnReplicationPad1dGetWorkspaceSize(const aclTensor *self, const aclIntArray *padding, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
- 参数说明:
- self:Device侧的aclTensor,输入张量,数据类型支持FLOAT16、FLOAT32、DOUBLE、INT8、INT16、INT32、INT64、UINT8、COMPLEX64、COMPLEX128,支持非连续的Tensor,数据格式支持ND。维度支持二维或三维,在最后一维做padding。
- padding:Host侧的aclIntArray,数据类型为INT64,长度为2,数值依次代表左、右需要填充的值。
- out:Device侧的aclTensor,输出张量,数据类型、数据格式、维度与self一致,out最后一维度的数值等于self最后一维度的数值加padding的两个值。支持非连续的Tensor。
- 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self或out是空指针。
- 返回161002(ACLNN_ERR_PARAM_INVALID):
- self、padding和out的数据类型或数据格式不在支持的范围之内。
- self、padding和out的输入shape不在支持的范围之内。
- self为空tensor且存在非batch size维度的值为0。
- out最后一维的值不等于self最后一维的值加padding的两个值。
aclnnReplicationPad1d
- 接口定义:
aclnnStatus aclnnReplicationPad1d(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aclnnReplicationPad1dGetWorkspaceSize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_replication_pad1d.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 = {1, 3}; std::vector<int64_t> outShape = {1, 7}; void* selfDeviceAddr = nullptr; void* outDeviceAddr = nullptr; aclTensor* self = nullptr; aclIntArray* padding = nullptr; aclTensor* out = nullptr; std::vector<float> selfHostData = {1, 2, 3}; std::vector<int64_t> paddingData = {2, 2}; std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0}; // 创建self aclTensor ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self); CHECK_RET(ret == ACL_SUCCESS, return ret); // 创建padding aclIntArray padding = aclCreateIntArray(paddingData.data(), 2); CHECK_RET(padding != nullptr, 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aclnnReplicationPad1d第一段接口 ret = aclnnReplicationPad1dGetWorkspaceSize(self, padding, out, &workspaceSize, &executor); CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReplicationPad1dGetWorkspaceSize 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aclnnReplicationPad1d第二段接口 ret = aclnnReplicationPad1d(workspaceAddr, workspaceSize, executor, stream); CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReplicationPad1d 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,需要根据具体API的接口定义修改 aclDestroyTensor(self); aclDestroyIntArray(padding); aclDestroyTensor(out); return 0; }
父主题: NN类算子接口