aclnnReduceNansum
支持的产品型号
- Atlas A2训练系列产品/Atlas 800I A2推理产品。
接口原型
每个算子分为两段式接口,必须先调用“aclnnReduceNansumGetWorkspaceSize”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“aclnnReduceNansum”接口执行计算。
- aclnnStatus aclnnReduceNansumGetWorkspaceSize(const aclTensor* self, const aclIntArray* dim, bool keepDim, aclDataType dtype, aclTensor* out, uint64_t* workspaceSize, aclOpExecutor** executor)
- aclnnStatus aclnnReduceNansum(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)
功能描述
算子功能:将tensor中NaN处理为0后,返回输入tensor给定维度上的和。
aclnnReduceNansumGetWorkspaceSize
参数说明:
self(aclTensor*, 计算输入):输入tensor,数据类型支持FLOAT16, FLOAT32, INT8, INT16, INT32, INT64, UINT8, BOOL, BFLOAT16(仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持)。数据类型和out的dtype满足可转换关系(参见互转换关系),支持非连续的Tensor,数据格式支持ND。
dim(aclIntArray*, 计算输入):参与计算的维度,取值范围为[-self.dim(), self.dim()],dim数组长度为0时,对所有轴做ReduceNansum计算,数据类型支持INT32, INT64。
keepDim(bool, 计算输入):是否在输出张量中保留要缩减的维度。
dtype(aclDataType, 计算输入):返回张量的所需数据类型,支持FLOAT16, FLOAT32, INT8, INT16, INT32, INT64, UINT8, BOOL, BFLOAT16(仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持)。
out(aclTensor*, 计算输出):输出tensor,数据类型支持FLOAT16, FLOAT32, INT8, INT16, INT32, INT64, UINT8, BOOL, BFLOAT16(仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持)。数据类型和self的dtype满足可转换关系(参见互转换关系),支持非连续的Tensor,数据格式支持ND。
workspaceSize(uint64_t*, 出参):返回需要在Device侧申请的workspace大小。
executor(aclOpExecutor**, 出参):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。
161001 (ACLNN_ERR_PARAM_NULLPTR): 1. 传入的self、dim或out是空指针。 161002 (ACLNN_ERR_PARAM_INVALID): 1. self或out的数据类型不在支持范围内。 2. dim数组中的维度超出输入tensor的维度范围。 3. dim指定的轴重复。 4. self或out的shape超过8维。 5. dtype和out的数据类型不一致时。 6. out shape与实际不匹配。
aclnnReduceNansum
参数说明:
workspace(void*, 入参):在Device侧申请的workspace内存地址。
workspaceSize(uint64_t, 入参):在Device侧申请的workspace大小,由第一段接口aclnnReduceNansumGetWorkspaceSize获取。
executor(aclOpExecutor*, 入参):op执行器,包含了算子计算流程。
stream(aclrtStream, 入参):指定执行任务的 AscendCL Stream流。
返回值:
aclnnStatus:返回状态码,具体参见aclnn返回码。
约束与限制
仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持。
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。
aclnnLeTensor示例代码:
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_reduce_nansum.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,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 = 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AscendCL对外接口列表
// 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> selfShape = {4, 2};
std::vector<int64_t> outShape = {2};
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclIntArray* dim = nullptr;
aclTensor* out = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
std::vector<float> outHostData = {0, 0};
std::vector<int64_t> dimData = {0};
bool keepDim = false;
auto dtype = aclDataType::ACL_FLOAT;
// 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dim aclIntArray
dim = aclCreateIntArray(dimData.data(), 1);
CHECK_RET(dim != nullptr, 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aclnnReduceNansum第一段接口
ret = aclnnReduceNansumGetWorkspaceSize(self, dim, keepDim, dtype, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReduceNansumGetWorkspaceSize 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aclnnReduceNansum第二段接口
ret = aclnnReduceNansum(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReduceNansum 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aclIntArray,需要根据具体API的接口定义修改
aclDestroyTensor(self);
aclDestroyIntArray(dim);
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;
}