aclnnHardsigmoidBackward
Applicable Products
| Product | Supported |
|---|---|
| × | |
| √ | |
| √ | |
| × | |
| √ | |
| √ |
Function
Description: backward propagation of aclnnHardsigmoid.
Function Prototype
Each operator is divided into a two-phase API. First call the "aclnnHardsigmoidBackwardGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnHardsigmoidBackward" API to perform the computation.
aclnnStatus aclnnHardsigmoidBackwardGetWorkspaceSize(
const aclTensor* gradOutput,
const aclTensor* self,
aclTensor* out,
uint64_t* workspaceSize,
aclOpExecutor** executor)aclnnStatus aclnnHardsigmoidBackward(
void* workspace,
uint64_t workspaceSize,
aclOpExecutor* executor,
aclrtStream stream)aclnnHardsigmoidBackwardGetWorkspaceSize
Parameters:
Parameter Input/Output Description Instruction Data Type Data Format Dimension (Shape) Non-contiguous Tensor gradOutput (aclTensor*) Input Input tensor for computation. - Supports empty tensors.
- The shape of gradOutput must be the same as that of self and out.
BFLOAT16, FLOAT16, FLOAT ND 0-8 √ self (aclTensor*) Input Specifies the input parameter for computation. - Empty tensors are supported.
- gradOutput, self, and out have the same shape.
BFLOAT16, FLOAT16, FLOAT ND 0-8 √ out (aclTensor*) Output Gradient value of self, i.e., grad_input in the formula. BFLOAT16, FLOAT16, FLOAT ND 0-8 √ workspaceSize (uint64_t*) Output Returns the workspace size to be requested on the device side. - - - - - executor (aclOpExecutor**) Output Returns the op executor, which contains the operator computation flow. - - - - - Atlas inference products ,Atlas training products : The supported data types are FLOAT16 and FLOAT.
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, or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of gradOutput or self is not within the supported range. The shapes of gradOutput, self, and out are different. The data type deduced from gradOutput and self cannot be converted to the data type of out.
aclnnHardsigmoidBackward
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 by the first-phase API aclnnHardsigmoidBackwardGetWorkspaceSize. executor Input Operator executor, which contains the operator computation flow. stream Input Specifies the stream that executes the task. Return value
aclnnStatus: return code. For details, see aclnn Return Code.
Constraints
Deterministic computation:
- aclnnHardsigmoidBackward 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_hardsigmoid_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 shape_size = 1;
for (auto i : shape) {
shape_size *= i;
}
return shape_size;
}
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 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);
// Call aclrtMemcpy to 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);
// 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 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. 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);
// Handle the check based on your requirements.
CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
// 2. Construct the input and output. Custom construction is required based on the API.
std::vector<int64_t> gradOutShape = {4, 2};
std::vector<int64_t> selfShape = {4, 2};
std::vector<int64_t> outShape = {4, 2};
void* selfDeviceAddr = nullptr;
void* gradOutDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* gradOut = nullptr;
aclTensor* out = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
std::vector<float> gradOutHostData = {0, 1, 2, 3, 4, 5, 6, 7};
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 gradOut aclTensor.
ret = CreateAclTensor(gradOutHostData, gradOutShape, &gradOutDeviceAddr, aclDataType::ACL_FLOAT, &gradOut);
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.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnHardsigmoidBackward.
ret = aclnnHardsigmoidBackwardGetWorkspaceSize(gradOut, self, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnHardsigmoidBackwardGetWorkspaceSize 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 aclnnHardsigmoidBackward.
ret = aclnnHardsigmoidBackward(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnHardsigmoidBackward 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 side memory to the host side. 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(float),
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. Modify based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(gradOut);
aclDestroyTensor(out);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(gradOutDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}