aclnnAminmaxAll
Applicable Products
| Product | Supported |
|---|---|
| โ | |
| โ | |
| โ | |
| ร | |
| ร | |
| โ |
Function
Returns the minimum value and maximum value of the input tensor across all dimensions.
Function Prototype
Each operator is divided into a two-phase API. You must first call the "aclnnAminmaxAllGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the process, and then call the "aclnnAminmaxAll" API to perform the computation.
aclnnStatus aclnnAminmaxAllGetWorkspaceSize(
const aclTensor *self,
aclTensor *minOut,
aclTensor *maxOut,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnAminmaxAll(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnAminmaxAllGetWorkspaceSize
Parameters:
Parameter Input/Output Description Instruction Data Type Data Format Dimensions (shape) Non-Contiguous Tensor self Input Input tensor. - FLOAT, BFLOAT16, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, BOOL ND - โ minOut Output Output tensor for the minimum value. Same data type as self. FLOAT, BFLOAT16, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, BOOL ND - โ maxOut Output Outputs the maximum value tensor. The data type is the same as that of self. FLOAT, BFLOAT16, FLOAT16, DOUBLE, INT8, INT16, INT32, INT64, UINT8, BOOL ND - โ workspaceSize Output Returns the workspace size to be applied for on the Device. - - - - - executor Output Returns the operator executor, which contains the operator computation flow. - - - - - Atlas training products : The BFLOAT16 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 Code Error Code Description ACLNN_ERR_PARAM_NULLPTR 161001 Passes a null pointer for self, minOut, or maxOut. ACLNN_ERR_PARAM_INVALID 161002 The data type of self is not within the supported range. The data type of minOut or maxOut is inconsistent with that of self. The shape of self, minOut, or maxOut has more than eight dimensions.
aclnnAminmaxAll
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address allocated on the Device side. workspaceSize Input Workspace size allocated on the Device side, obtained from the first-phase API aclnnAminmaxAllGetWorkspaceSize. executor Input Operator executor, which contains the operator computation process. stream Input Specifies the stream that executes the task. Return value
aclnnStatus: return code. For details, see aclnn Return Codes.
Constraints
Deterministic computation:
- aclnnAminmaxAll 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_aminmax_all.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 for 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 allocate 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 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 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);
// Handle the check based on your requirements.
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
// 2. Construct the input and output. Customize the construction based on the API interface.
std::vector<int64_t> selfShape = {2, 3, 2};
std::vector<int64_t> outShape = {1};
void* selfDeviceAddr = nullptr;
void* minOutDeviceAddr = nullptr;
void* maxOutDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* minOut = nullptr;
aclTensor* maxOut = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11};
std::vector<float> minOutHostData = {0};
std::vector<float> maxOutHostData = {0};
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the out aclTensor.
ret = CreateAclTensor(minOutHostData, outShape, &minOutDeviceAddr, aclDataType::ACL_FLOAT, &minOut);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(maxOutHostData, outShape, &maxOutDeviceAddr, aclDataType::ACL_FLOAT, &maxOut);
CHECK_RET(ret == ACL_SUCCESS, 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 aclnnAminmaxAll.
ret = aclnnAminmaxAllGetWorkspaceSize(self, minOut, maxOut, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAminmaxAllGetWorkspaceSize 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 aclnnAminmaxAll.
ret = aclnnAminmaxAll(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAminmaxAll 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 this based on the specific API definition.
auto size = GetShapeSize(outShape);
std::vector<float> minResultData(size, 0);
ret = aclrtMemcpy(minResultData.data(), minResultData.size() * sizeof(minResultData[0]), minOutDeviceAddr,
size * sizeof(minResultData[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, minResultData[i]);
}
std::vector<float> maxResultData(size, 0);
ret = aclrtMemcpy(maxResultData.data(), maxResultData.size() * sizeof(maxResultData[0]), maxOutDeviceAddr,
size * sizeof(maxResultData[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, maxResultData[i]);
}
// 6. Release aclTensor. Modify this based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(minOut);
aclDestroyTensor(maxOut);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(minOutDeviceAddr);
aclrtFree(maxOutDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}