aclnnPowScalarTensor
Applicable Products
| Product | Supported |
|---|---|
| โ | |
| โ | |
| โ | |
| โ | |
| โ | |
| โ |
Function
Description: Each element of exponent is used as the exponent for the corresponding element of input to compute the power.
Formula:
Operator constraint: INT32 integer computation times out in scenarios outside the following ranges.
Shape Exponent_value <=100000 (one hundred thousand) -200000000~200000000 (two hundred million) <=1000000 (one million) -20000000~20000000 (twenty million) <=10000000 (ten million) -2000000~2000000 (two million) <=100000000 (one hundred million) -200000~200000 (two hundred thousand) <=1000000000 (one billion) -20000~20000 (twenty thousand)
Function Prototype
Each operator is divided into a two-phase API. The "aclnnPowScalarTensorGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnPowScalarTensor" API is called to perform the computation.
aclnnStatus aclnnPowScalarTensorGetWorkspaceSize(
const aclScalar* self,
const aclTensor* exponent,
const aclTensor* out,
uint64_t* workspaceSize,
aclOpExecutor** executor)aclnnStatus aclnnPowScalarTensor(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnPowScalarTensorGetWorkspaceSize
Parameters
Atlas 200I/500 A2 inference products ,Atlas inference products ,Atlas training products : The data type BFLOAT16 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 Passed self, exponent, or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of exponent is not within the supported range. self and exponent do not satisfy the data type deduction rules. The deduced data type cannot be converted to the type of out. The shapes of exponent and out are inconsistent.
aclnnPowScalarTensor
Parameters
Parameter Input/Output Description workspace Input Address of the workspace memory applied for on the Device side. workspaceSize Input Size of the workspace applied for on the Device side, obtained from the first-phase API aclnnPowScalarTensorGetWorkspaceSize. executor Input Operator executor that contains the operator computation flow. stream Input Specifies the stream for executing the task. Return Value
aclnnStatus: return code. For details, see aclnn Return Codes.
Constraints
Deterministic computation:
- aclnnPowScalarTensor defaults to a deterministic implementation.
Atlas training products andAtlas inference products : In this scenario, if the computed result exceeds the value range of the specified data type, the boundary value of that data type is returned as the result.
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_pow.h"
#define CHECK_RET(cond, return_exponentr) \
do { \
if (!(cond)) { \
return_exponentr; \
} \
} 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 request 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);
// Copy host-side data to device memory by calling aclrtMemcpy.
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];
}
// Create an aclTensor by calling aclCreateTensor.
*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 documentation.
// 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. Customize the construction based on the API.
std::vector<int64_t> exponentShape = {4, 2};
std::vector<int64_t> outShape = {4, 2};
void* exponentDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclScalar* self = nullptr;
aclTensor* exponent = nullptr;
aclTensor* out = nullptr;
std::vector<float> exponentHostData = {1, 1, 1, 2, 2, 2, 3, 3};
std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
float selfValue = 1.2f;
// Create the self aclScalar.
self = aclCreateScalar(&selfValue, aclDataType::ACL_FLOAT);
CHECK_RET(self != nullptr, return ret);
// Create the exponent aclTensor.
ret = CreateAclTensor(exponentHostData, exponentShape, &exponentDeviceAddr, aclDataType::ACL_FLOAT, &exponent);
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);
// 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 aclnnPowScalarTensor.
ret = aclnnPowScalarTensorGetWorkspaceSize(self, exponent, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnPowScalarTensorGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
// Allocate 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 aclnnPowScalarTensor.
ret = aclnnPowScalarTensor(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnPowScalarTensor failed. ERROR: %d\n", ret); return ret);
// 4. (Boilerplate) Synchronously wait for the 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 this 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.
aclDestroyScalar(self);
aclDestroyTensor(exponent);
aclDestroyTensor(out);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(exponentDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}