aclnnForeachLog1p
Applicable Products
| Product | Supported |
|---|---|
| × | |
| √ | |
| √ | |
| × | |
| × | |
| × |
Function
Description: Performs the operation of adding one to each element in a tensor list and then computing the natural logarithm (base e).
Formula:
Function Prototype
Each operator is divided into a two-phase API. You must first call the "aclnnForeachLog1pGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the computation process, and then call the "aclnnForeachLog1p" API to perform the computation.
aclnnStatus aclnnForeachLog1pGetWorkspaceSize(
const aclTensorList *x,
const aclTensorList *out,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnForeachLog1p(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnForeachLog1pGetWorkspaceSize
Parameters
Parameter Input/Output Description Instruction Data Type Data Format Dimension (Shape) Non-contiguous Tensor x (aclTensorList*) Input Indicates the list of input tensors for the natural logarithm function after adding one, corresponding to `x` in the formula. - Supports empty tensors.
- All tensors in this parameter must have the same data type.
BFLOAT16, FLOAT16, FLOAT32 ND 0-8 √ out (aclTensorList*) Output Indicates the output tensor list after adding one and then performing the base-e logarithmic operation, corresponding to `y` in the formula. - Supports empty tensors.
- All tensors in this parameter must have the same data type.
- The data type and data format are consistent with those of the input parameter `x`, and the shape size is greater than or equal to the shape size of the input parameter `x`.
BFLOAT16, FLOAT16, FLOAT32 ND 0-8 √ workspaceSize (uint64_t*) Output Returns the workspace size to be requested on the Device side. - - - - - executor（aclOpExecutor**） Output Returns the operator executor, which contains the operator computation flow. - - - - - Return Value
aclnnStatus: return code. For details, see aclnn Return Code.
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 Indicates that x or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 Indicates that the data type of x or out is not within the supported range. The data types of x and out are inconsistent. ACLNN_ERR_INNER_TILING_ERROR 561002 The shapes of x and out do not meet the constraints. The data types of tensors in x or out are inconsistent. The dimension of a tensor in x or out exceeds 8.
aclnnForeachLog1p
Parameters
Parameter Input/Output Description workspace Input Specifies the workspace memory address requested on the device. workspaceSize Input Specifies the workspace size requested on the device, which is obtained by the first-phase API aclnnForeachLog1pGetWorkspaceSize. 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 Code.
Constraints
Deterministic computation:
- aclnnForeachLog1p 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_foreach_log1p.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);
// Copy host-side data to the device memory using 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);
// 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];
}
// Create an aclTensor by calling the aclCreateTensor API.
*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.
// 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 inputs and outputs. Customize the construction based on the API interface.
std::vector<int64_t> selfShape1 = {2, 3};
std::vector<int64_t> selfShape2 = {1, 3};
std::vector<int64_t> outShape1 = {2, 3};
std::vector<int64_t> outShape2 = {1, 3};
void* input1DeviceAddr = nullptr;
void* input2DeviceAddr = nullptr;
void* out1DeviceAddr = nullptr;
void* out2DeviceAddr = nullptr;
aclTensor* input1 = nullptr;
aclTensor* input2 = nullptr;
aclTensor* out1 = nullptr;
aclTensor* out2 = nullptr;
std::vector<float> input1HostData = {1, 2, 3, 4, 5, 6};
std::vector<float> input2HostData = {7, 8, 9};
std::vector<float> out1HostData(6, 0);
std::vector<float> out2HostData(3, 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 out1 aclTensor.
ret = CreateAclTensor(out1HostData, outShape1, &out1DeviceAddr, aclDataType::ACL_FLOAT, &out1);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the out2 aclTensor.
ret = CreateAclTensor(out2HostData, outShape2, &out2DeviceAddr, aclDataType::ACL_FLOAT, &out2);
CHECK_RET(ret == ACL_SUCCESS, return ret);
std::vector<aclTensor*> tempInput{input1, input2};
aclTensorList* tensorListInput = aclCreateTensorList(tempInput.data(), tempInput.size());
std::vector<aclTensor*> tempOutput{out1, out2};
aclTensorList* tensorListOutput = aclCreateTensorList(tempOutput.data(), tempOutput.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 aclnnForeachLog1p.
ret = aclnnForeachLog1pGetWorkspaceSize(tensorListInput, tensorListOutput, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachLog1pGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
// Apply for 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 aclnnForeachLog1p.
ret = aclnnForeachLog1p(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachLog1p 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(outShape1);
std::vector<float> out1Data(size, 0);
ret = aclrtMemcpy(out1Data.data(), out1Data.size() * sizeof(out1Data[0]), out1DeviceAddr,
size * sizeof(out1Data[0]), ACL_MEMCPY_DEVICE_TO_HOST);
for (int64_t i = 0; i < size; i++) {
LOG_PRINT("out1 result[%ld] is: %f\n", i, out1Data[i]);
}
size = GetShapeSize(outShape2);
std::vector<float> out2Data(size, 0);
ret = aclrtMemcpy(out2Data.data(), out2Data.size() * sizeof(out2Data[0]), out2DeviceAddr,
size * sizeof(out2Data[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("out2 result[%ld] is: %f\n", i, out2Data[i]);
}
// 6. Release aclTensor. Modify based on the specific API definition.
aclDestroyTensorList(tensorListInput);
aclDestroyTensorList(tensorListOutput);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(input1DeviceAddr);
aclrtFree(input2DeviceAddr);
aclrtFree(out1DeviceAddr);
aclrtFree(out2DeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}