aclnnLogAddExp
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 logarithm (base e) of the sum of exponentials of the input tensors.
-
Formula:
out=log(ex+ey)=log[em(1+e−∣x−y∣)]=m+log(1+e−∣x−y∣)wherem=max(x,y)out = \log(e^x+e^y)=\log[e^m(1+e^{-|x-y|})]=m+\log(1+e^{-|x-y|}) \quad where m=\max(x,y)
where xx represents self and yy represents other.
Function Prototype
Each operator uses a two-phase API. You must first call the "aclnnLogAddExpGetWorkspaceSize" API to obtain the workspace size required for the computation and the executor containing the operator computation process. Then call the "aclnnLogAddExp" API to perform the computation.
aclnnStatus aclnnLogAddExpGetWorkspaceSize(
const aclTensor* self,
const aclTensor* other,
aclTensor* out,
uint64_t* workspaceSize,
aclOpExecutor** executor)
aclnnStatus aclnnLogAddExp(
void* workspace,
uint64_t workspaceSize,
aclOpExecutor* executor,
aclrtStream stream)
aclnnLogAddExpGetWorkspaceSize
-
Parameters:
Parameter Input/Output Description Instruction Data Type Data Format Dimensions (shape) Non-contiguous Tensor self (aclTensor*) Input x in the formula. - The data type must be convertible to the data type of out (see conversion relationship).
- The shapes of self and other satisfy the broadcast relationship.
FLOAT16, FLOAT, DOUBLE, UINT8, INT8, UINT16, INT16, UINT32, INT32, UINT64, INT64, BOOL, BFLOAT16 ND 0-8 √ other (aclTensor*) Input y in the formula. - The data type must be convertible to the data type of out (see conversion relationship).
- The shape of other and self must satisfy the broadcast relationship.
FLOAT16, FLOAT, DOUBLE, UINT8, INT8, UINT16, INT16, UINT32, INT32, UINT64, INT64, BOOL, BFLOAT16 ND 0-8 √ out (aclTensor*) Output out in the formula. The shape must be the broadcast shape of self and other. FLOAT, FLOAT16, BFLOAT16 ND 0-8 √ workspaceSize (uint64_t*) Output Returns the size of the workspace to be requested 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 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 self, other, or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of self, other, or out is not supported. The data type of self and other cannot be converted to the data type of out. The dimension of self, other, or out is greater than 8. The shapes of self and other cannot be broadcast. The shape of out is inconsistent with the shape of self and other after broadcasting.
aclnnLogAddExp
-
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address allocated on the device. workspaceSize Input Workspace size allocated on the device, obtained by calling the first-phase API aclnnLogAddExpGetWorkspaceSize. executor Input op executor, which contains the computation flow of the operator. stream Input Specifies the stream for executing tasks. -
Return value
aclnnStatus: return status code. For details, see aclnn Return Codes.
Constraints
- Deterministic computation:
- aclnnLogAddExp 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_logaddexp.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 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.
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 aclCreateTensor 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 inputs and outputs. Customize the construction based on the API.
std::vector<int64_t> selfShape = {4, 2};
std::vector<int64_t> otherShape = {4, 2};
std::vector<int64_t> outShape = {4, 2};
void* selfDeviceAddr = nullptr;
void* otherDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* other = nullptr;
aclTensor* out = nullptr;
std::vector<float> selfHostData = {1, 2, 3, 4, 5, 6, 7, 8};
std::vector<float> otherHostData = {1, 2, 3, 4, 5, 6, 7, 8};
std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the other aclTensor.
ret = CreateAclTensor(otherHostData, otherShape, &otherDeviceAddr, aclDataType::ACL_FLOAT, &other);
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 it with the specific API name.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnLogAddExp.
ret = aclnnLogAddExpGetWorkspaceSize(self, other, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnLogAddExpGetWorkspaceSize 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 aclnnLogAddExp.
ret = aclnnLogAddExp(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnLogAddExp failed. ERROR: %d\n", ret); return ret);
// 4. (Boilerplate) Wait synchronously for the task to complete.
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
// 5. Obtain the output values. Copy the result from the device memory to the host. Modify it 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 the aclTensor. Modify it based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(other);
aclDestroyTensor(out);
// 7. Release device resources. Modify it based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(otherDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}