aclnnLeakyReluBackward
Applicable Products
| Product | Supported |
|---|---|
| √ | |
| √ | |
| √ | |
| × | |
| √ | |
| √ |
Function
Description: Backward propagation of the aclnnLeakyRelu activation function. Formula:
Function Prototype
Each operator is divided into a two-phase API. First call the "aclnnLeakyReluBackwardGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnLeakyReluBackward" API to perform the computation.
aclnnStatus aclnnLeakyReluBackwardGetWorkspaceSize(
const aclTensor *gradOutput,
const aclTensor *self,
const aclScalar *negativeSlope,
bool selfIsResult,
aclTensor *out,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnLeakyReluBackward(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnLeakyReluBackwardGetWorkspaceSize
Parameters:
Atlas inference products ,Atlas training products : The data types of gradOutput, self, and out support FLOAT, FLOAT16, and DOUBLE. The data type of negativeSlope supports FLOAT, FLOAT16, DOUBLE, INT32, INT64, INT8, BOOL, INT16, and UINT8.
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 The passed gradOutput, self, negativeSlope, or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of gradOutput, self, or negativeSlope is not within the supported range. The shape of gradOutput, self, or out exceeds 8 dimensions. The shapes of gradOutput and self do not satisfy the broadcast relationship, or the shape of out is inconsistent with the broadcast result. selfIsResult is true and negativeSlope is negative.
aclnnLeakyReluBackward
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address applied for on the Device side. workspaceSize Input Workspace size applied for on the Device side, obtained from the first-phase API aclnnLeakyReluBackwardGetWorkspaceSize. executor Input Operator executor, which contains the operator computation flow. stream Input Specifies the stream on which the task is executed. Return value
aclnnStatus: return code. For details, see aclnn Return Code.
Constraints
Deterministic computation:
- aclnnLeakyReluBackward 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_leaky_relu_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 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 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 data from the host to the device 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);
// 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];
}
// 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.
// 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 interface.
std::vector<int64_t> gradShape = {4};
std::vector<int64_t> selfShape = {4};
std::vector<int64_t> outShape = {4};
void* gradDeviceAddr = nullptr;
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* grad = nullptr;
aclTensor* self = nullptr;
aclScalar* negativeSlope = nullptr;
aclTensor* out = nullptr;
std::vector<float> gradHostData = {2, 3, 4, 5};
std::vector<float> selfHostData = {1, 2, 3, 4};
std::vector<float> outHostData = {0, 0, 0, 0};
float negativeSlopeValue = 0.01f;
bool selfIsResultValue = true;
// Create the grad aclTensor.
ret = CreateAclTensor(gradHostData, gradShape, &gradDeviceAddr, aclDataType::ACL_FLOAT, &grad);
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 negativeSlope aclScalar.
negativeSlope = aclCreateScalar(&negativeSlopeValue, aclDataType::ACL_FLOAT);
CHECK_RET(negativeSlope != nullptr, 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 actual API name.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnLeakyReluBackward.
ret = aclnnLeakyReluBackwardGetWorkspaceSize(
grad, self, negativeSlope, selfIsResultValue, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnLeakyReluBackwardGetWorkspaceSize 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 aclnnLeakyReluBackward.
ret = aclnnLeakyReluBackward(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnLeakyReluBackward 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(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(grad);
aclDestroyTensor(self);
aclDestroyScalar(negativeSlope);
aclDestroyTensor(out);
// 7. Release device resources.
aclrtFree(gradDeviceAddr);
aclrtFree(selfDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}