aclnnMinN
Applicable Products
| Product | Supported |
|---|---|
| โ | |
| โ | |
| โ | |
| ร | |
| โ | |
| โ |
Function
Description: Computes the minimum of the corresponding elements in each input tensor of the input tensor list.
Formula:
Function Prototype
Each operator is divided into a two-phase API. The "aclnnMinNGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnMinN" API is called to perform the computation.
aclnnStatus aclnnMinNGetWorkspaceSize(
const aclTensorList *tensors,
aclTensor *out,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnMinN(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnMinNGetWorkspaceSize
Parameters:
Atlas inference products andAtlas training products : The BFLOAT16 and UINT8 data types are not supported.Atlas A2 training products/Atlas A2 inference products ,Atlas A3 training products/Atlas A3 inference products : The UINT8 data type is not supported.
Return value
aclnnStatus: return 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 input tensors or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of a tensor in the tensors list or out is not within the supported range. The data types of the tensors list and out are inconsistent. The shape of a tensor in the tensors list and out does not comply with broadcast rules, or the broadcast shape is inconsistent with out. The maximum dimension of a tensor in the tensors list exceeds 8.
aclnnMinN
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address applied on the Device side. workspaceSize Input Workspace size applied on the Device side, obtained from the first-phase API aclnnMinNGetWorkspaceSize. executor Input Operator executor that 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:
- aclnnMinN 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_minn.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: initialize resources.
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 allocate device 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 data from host memory to device 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);
// Compute the 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 inputs and outputs. Custom construction is required based on the API.
std::vector<int64_t> selfShape1 = {2, 3};
std::vector<int64_t> selfShape2 = {1, 3};
std::vector<int64_t> outShape = {2, 3};
void* input1DeviceAddr = nullptr;
void* input2DeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* input1 = nullptr;
aclTensor* input2 = nullptr;
aclTensor* out = nullptr;
std::vector<float> input1HostData = {11, 12, 13, 4, 5, 6};
std::vector<float> input2HostData = {7, 8, 9};
std::vector<float> outHostData(6, 0);
// Create input1 aclTensor.
ret = CreateAclTensor(input1HostData, selfShape1, &input1DeviceAddr, aclDataType::ACL_FLOAT, &input1);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create input2 aclTensor.
ret = CreateAclTensor(input2HostData, selfShape2, &input2DeviceAddr, aclDataType::ACL_FLOAT, &input2);
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);
std::vector<aclTensor*> tmp{input1, input2};
aclTensorList* tensorList = aclCreateTensorList(tmp.data(), tmp.size());
// 3. Call the CANN operator library API. Replace with the actual API name.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnMinN.
ret = aclnnMinNGetWorkspaceSize(tensorList, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMinNGetWorkspaceSize 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 aclnnMinN.
ret = aclnnMinN(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMinN failed. ERROR: %d\n", ret); return ret);
// 4. (Boilerplate) Synchronously 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 side. 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 aclScalar. Modify based on the specific API definition.
aclDestroyTensorList(tensorList);
aclDestroyTensor(out);
// 7. Release Device resources. Modify based on the specific API definition.
aclrtFree(input1DeviceAddr);
aclrtFree(input2DeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}