aclnnReduceNansum
Applicable Products
| Product | Supported |
|---|---|
| × | |
| √ | |
| √ | |
| × | |
| × | |
| × |
Function
Returns the sum of the input tensor along the given dimensions after treating NaN values as 0.
Function Prototype
Each operator is divided into a two-phase API. The "aclnnReduceNansumGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnReduceNansum" API is called to perform the computation.
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)aclnnReduceNansumGetWorkspaceSize
Parameters:
Return Value:
aclnnStatus: status code. For details, see aclnn Return Codes.The first-phase API performs input parameter validation and returns an error in the following scenarios:
Return Value Error Code Description ACLNN_ERR_PARAM_NULLPTR 161001 The self, dim, or out passed in is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of self or out is not within the supported range. A dimension in the dim array exceeds the dimension range of the input tensor. The axis specified by dim is duplicated. The shape of self or out exceeds 8 dimensions. The data type of dtype is inconsistent with that of out. The shape of out does not match the actual shape.
aclnnReduceNansum
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address applied for on the Device side. workspaceSize Input Size of the workspace applied for on the Device side, obtained from the first-phase API aclnnReduceNansumGetWorkspaceSize. executor Input Operator executor, which contains the operator computation flow. stream Input Specifies the stream for task execution. Return value
aclnnStatus: return code. For details, see aclnn Return Codes.
Constraints
Deterministic computation:
- aclnnReduceNansum defaults to a deterministic implementation.
Example
The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.
#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) {
// Boilerplate: resource initialization.
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);
// Call aclrtMalloc to apply for device-side memory.
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);
// Call aclrtMemcpy to copy host-side data to the device-side memory.
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);
// Calculate strides of a contiguous tensor.
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];
}
// Call the aclCreateTensor API to create an 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. (Boilerplate) Initialize the device/stream. See the ACL API manual.
// Fill in the deviceId based on your actual device.
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. Construct the input and output. Custom construction is required based on the API.
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;
// Create self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create out aclTensor.
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create dim aclIntArray.
dim = aclCreateIntArray(dimData.data(), 1);
CHECK_RET(dim != nullptr, return ret);
// 3. Call the CANN operator library API. Replace with the specific API name.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnReduceNansum.
ret = aclnnReduceNansumGetWorkspaceSize(self, dim, keepDim, dtype, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReduceNansumGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
// Apply for device memory based on the workspaceSize calculated by the first-phase API.
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);
}
// Call the second-phase API of aclnnReduceNansum.
ret = aclnnReduceNansum(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnReduceNansum failed. ERROR: %d\n", ret); return ret);
// 4. (Boilerplate) Synchronize and wait for task execution to complete.
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
// 5. Obtain the output value and copy the result from the device memory to the host memory. Modify based on the specific API definition.
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. Release aclTensor and aclIntArray. Modify based on the specific API definition.
aclDestroyTensor(self);
aclDestroyIntArray(dim);
aclDestroyTensor(out);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}