aclnnMinN
Applicable Products
- Ascend 950PR&950DT products: Supported
- Atlas A3 products: Supported
- Atlas A2 products: Supported
- Atlas 200I/500 A2 inference products: Not supported
- Atlas inference products: Supported
- Atlas training products: Supported
Function
-
Description: Computes the minimum of the corresponding elements in each input tensor of the input tensor list.
-
Formula:
outi=min(input0i,input1i,...)out_i = min(input0_i, input1_i,...)
Function Prototype
Each operator uses a two-phase API. Call "aclnnMinNGetWorkspaceSize" first to obtain the workspace size required for the computation and the executor that contains the computation process, and then call "aclnnMinN" to execute 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:
Parameter Input/Output Description Instruction Data Type Data Format Shape Non-contiguous Tensor tensors (aclTensorList*) Input List of input tensors to compute. Must be the same as the data type of out. The shape of each tensor in tensors must satisfy the broadcast relationship with out. FLOAT16, FLOAT, INT8, UINT8, INT32, INT64, BFLOAT16 ND Not greater than 8 √ out (aclTensor*) Output Output tensor. Must be the same as the data type of tensors. The shape must satisfy the broadcast relationship with the shapes of the tensors in tensors. FLOAT16, FLOAT, INT8, UINT8, INT32, INT64, BFLOAT16 ND - √ workspaceSize (uint64_t*) Output Returns the size of the workspace to be allocated on the device. - - - - - executor (aclOpExecutor**) Output Returns the op executor, which contains the operator computation process. - - - - - - Atlas inference products and Atlas training products: The BFLOAT16 and UINT8 data types are not supported.
- Atlas A2 products, Atlas A3 products: The UINT8 data type is not supported.
-
Return value
aclnnStatus: return 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 Returned when 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 does not meet the broadcast rules with out, or the shape after broadcasting is inconsistent with out. The maximum number of dimensions of a tensor in the tensors list exceeds 8.
aclnnMinN
-
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address requested on the device. workspaceSize Input Size of the workspace requested on the device, obtained by the first-phase API aclnnMinNGetWorkspaceSize. executor Input op executor, which contains the computation flow of the operator. stream Input Stream for executing tasks. -
Return value
aclnnStatus: return status code. For details, see aclnn Return Codes.
Constraints
- Deterministic computation:
- aclnnMinN defaults to a deterministic implementation.
Example
The following sample code is for reference only. For details about compilation and execution, 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, 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); aclFinalize(); return ret);
ret = aclrtCreateStream(stream);
CHECK_RET(ret == ACL_SUCCESS,
LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret);
aclrtResetDevice(deviceId); aclFinalize(); 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 memory on the device.
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 the host to the 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);
// Calculate the strides of the 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. For details, see the acl API manual.
// Set deviceId based on the 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> 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 the input1 aclTensor.
ret = CreateAclTensor(input1HostData, selfShape1, &input1DeviceAddr, aclDataType::ACL_FLOAT, &input1);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the input2 aclTensor.
ret = CreateAclTensor(input2HostData, selfShape2, &input2DeviceAddr, aclDataType::ACL_FLOAT, &input2);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the 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 specific 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);
// Allocate device memory based on the workspaceSize computed 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) Wait for the task execution to complete synchronously.
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 on device memory to host memory. Modify the code 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 the code based on the specific API definition.
aclDestroyTensorList(tensorList);
aclDestroyTensor(out);
// 7. Release Device resources. Modify the code based on the specific API definition.
aclrtFree(input1DeviceAddr);
aclrtFree(input2DeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}