aclnnBinaryCrossEntropyWithLogitsBackward
Applicable Products
| Product | Supported |
|---|---|
| x | |
| √ | |
| √ | |
| × | |
| √ | |
| √ |
Function
Performs logits computation on the input self, and then performs backward propagation of BCELoss using the resulting values together with the label values target.
Function Prototype
Each operator consists of a two-phase API. You must first call the "aclnnBinaryCrossEntropyWithLogitsBackwardGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the process, and then call the "aclnnBinaryCrossEntropyWithLogitsBackward" API to perform the computation.
aclnnStatus aclnnBinaryCrossEntropyWithLogitsBackwardGetWorkspaceSize(
const aclTensor *gradOutput,
const aclTensor *self,
const aclTensor *target,
const aclTensor *weightOptional,
const aclTensor *posWeightOptional,
int64_t reduction,
aclTensor *out,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnBinaryCrossEntropyWithLogitsBackward(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
const aclrtStream stream)aclnnBinaryCrossEntropyWithLogitsBackwardGetWorkspaceSize
Parameters:
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:
aclnnBinaryCrossEntropyWithLogitsBackward
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 aclnnBinaryCrossEntropyWithLogitsBackwardGetWorkspaceSize. executor Input Operator executor, which 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:
- aclnnBinaryCrossEntropyWithLogitsBackward 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_binary_cross_entropy_with_logits_backward.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 the host-side data to the 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 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.
// Fill in the deviceId based on the actual device.
int32_t deviceId = 0;
aclrtStream stream;
auto ret = Init(deviceId, &stream);
// Handle the check based on your needs.
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> gradOutputShape = {2, 2};
std::vector<int64_t> selfShape = {2, 2};
std::vector<int64_t> targetShape = {2, 2};
std::vector<int64_t> weightShape = {2, 2};
std::vector<int64_t> posWeightShape = {2, 2};
std::vector<int64_t> outShape = {2, 2};
void* gradOutputDeviceAddr = nullptr;
void* selfDeviceAddr = nullptr;
void* targetDeviceAddr = nullptr;
void* weightDeviceAddr = nullptr;
void* posWeightDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* gradOutput = nullptr;
aclTensor* self = nullptr;
aclTensor* target = nullptr;
aclTensor* out = nullptr;
aclTensor* weight = nullptr;
aclTensor* posWeight = nullptr;
std::vector<float> gradOutputHostData = {0, 1, 2, 3};
std::vector<float> selfHostData = {0, 1, 2, 3};
std::vector<float> targetHostData = {0.1, 0.1, 0.1, 0.1};
std::vector<float> weightHostData = {0, 1, 2, 3};
std::vector<float> posWeightHostData = {0, 1, 2, 3};
std::vector<float> outHostData = {0, 0, 0, 0};
int64_t reduction = 0;
// Create the gradOutput aclTensor.
ret = CreateAclTensor(gradOutputHostData, gradOutputShape, &gradOutputDeviceAddr, aclDataType::ACL_FLOAT, &gradOutput);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the target aclTensor.
ret = CreateAclTensor(targetHostData, targetShape, &targetDeviceAddr, aclDataType::ACL_FLOAT, &target);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the weight aclTensor.
ret = CreateAclTensor(weightHostData, weightShape, &weightDeviceAddr, aclDataType::ACL_FLOAT, &weight);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the posWeight aclTensor.
ret = CreateAclTensor(posWeightHostData, posWeightShape, &posWeightDeviceAddr, aclDataType::ACL_FLOAT, &posWeight);
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);
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Example of aclnnBinaryCrossEntropyWithLogitsBackward API call.
// 3. Call the CANN operator library API. Replace it with the specific API name.
// Call the first-phase API of aclnnBinaryCrossEntropyWithLogitsBackward.
ret = aclnnBinaryCrossEntropyWithLogitsBackwardGetWorkspaceSize(gradOutput, self, target, weight, posWeight,
reduction, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBinaryCrossEntropyWithLogitsBackwardGetWorkspaceSize 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 aclnnBinaryCrossEntropyWithLogitsBackward.
ret = aclnnBinaryCrossEntropyWithLogitsBackward(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBinaryCrossEntropyWithLogitsBackward 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 API definition of the specific API.
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.
aclDestroyTensor(gradOutput);
aclDestroyTensor(self);
aclDestroyTensor(target);
aclDestroyTensor(weight);
aclDestroyTensor(posWeight);
aclDestroyTensor(out);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(gradOutputDeviceAddr);
aclrtFree(selfDeviceAddr);
aclrtFree(targetDeviceAddr);
aclrtFree(weightDeviceAddr);
aclrtFree(posWeightDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}