aclnnTanhBackward
Applicable Products
| Product | Supported |
|---|---|
| โ | |
| โ | |
| โ | |
| ร | |
| โ | |
| โ |
Function
Description: backward propagation of aclnnTanh.
Formula:
Function Prototype
Each operator is divided into a two-phase API. You must first call the "aclnnTanhBackwardGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the process, and then call the "aclnnTanhBackward" API to perform the computation.
aclnnStatus aclnnTanhBackwardGetWorkspaceSize(
const aclTensor *gradOutput,
const aclTensor *output,
aclTensor *gradInput,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnTanhBackward(
void* workspace,
uint64_t workspaceSize,
aclOpExecutor* executor,
const aclrtStream stream)aclnnTanhBackwardGetWorkspaceSize
Parameters
Parameter Input/Output Description Instruction Data Type Data Format Dimension (shape) Non-contiguous Tensor gradOutput (aclTensor*) Input The input gradOutputin the formula.FLOAT, FLOAT16, DOUBLE, BFLOAT16 ND - โ output (aclTensor*) Input The input outputin the formula.FLOAT, FLOAT16, DOUBLE, BFLOAT16 ND - โ gradInput (aclTensor*) Output gradInputin the formula.- Has the same data format as gradOutput and output.
- Has the same shape as gradOutput and output, or the shape after broadcasting gradOutput and output.
- Has the same data type as gradOutput and output.
FLOAT, FLOAT16, DOUBLE, BFLOAT16 ND - โ 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 BFLOAT16 data type is not supported.
Return value
aclnnStatus: return code. For details, see aclnn Return Codes.
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, output, and gradInput are null pointers. ACLNN_ERR_PARAM_INVALID 161002 The data types and dimensions of gradOutput, output, and gradInput are not within the supported range. The data types of gradOutput, output, and gradInput are different. The shapes of gradOutput, output, and gradInput are different.
aclnnTanhBackward
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 through the first-phase API aclnnTanhBackwardGetWorkspaceSize. 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 Codes.
Constraints
Deterministic computation:
- aclnnTanhBackward 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_tanh_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: 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 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);
// Call aclrtMemcpy to copy host-side data to the device-side 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 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.
// Fill in the deviceId based on your actual device.
int32_t deviceId = 0;
aclrtStream stream;
auto ret = Init(deviceId, &stream);
// Handle the check as needed.
CHECK_RET(ret == 0, 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 = {4, 2};
std::vector<int64_t> outputShape = {4, 2};
std::vector<int64_t> gradInputShape = {4, 2};
void* gradOutputDeviceAddr = nullptr;
void* outputDeviceAddr = nullptr;
void* gradInputDeviceAddr = nullptr;
aclTensor* gradOutput = nullptr;
aclTensor* output = nullptr;
aclTensor* gradInput = nullptr;
std::vector<float> gradOutputHostData = {0, 1, 2, 3, 4, 5, 6, 7.0};
std::vector<float> outputHostData = {1, 1, 1, 2, 2, 2, 3, 3.0};
std::vector<float> gradInputHostData = {0, 0, 0, 0, 0, 0, 0, 0.0};
// Create gradOutput aclTensor.
ret = CreateAclTensor(gradOutputHostData, gradOutputShape, &gradOutputDeviceAddr, aclDataType::ACL_FLOAT,
&gradOutput);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create output aclTensor.
ret = CreateAclTensor(outputHostData, outputShape, &outputDeviceAddr, aclDataType::ACL_FLOAT, &output);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create gradInput aclTensor.
ret = CreateAclTensor(gradInputHostData, gradInputShape, &gradInputDeviceAddr, aclDataType::ACL_FLOAT, &gradInput);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. Call the CANN operator library API. Replace with the specific API as needed.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnTanhBackward.
ret = aclnnTanhBackwardGetWorkspaceSize(gradOutput, output, gradInput, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTanhBackwardGetWorkspaceSize 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 aclnnTanhBackward.
ret = aclnnTanhBackward(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTanhBackward failed. ERROR: %d\n", ret); return ret);
// 4. (Boilerplate) Synchronously 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. Modify based on the specific API definition.
auto size = GetShapeSize(gradInputShape);
std::vector<float> resultData(size, 0);
ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), gradInputDeviceAddr,
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 and aclScalar. Modify based on the specific API definition.
aclDestroyTensor(gradOutput);
aclDestroyTensor(output);
aclDestroyTensor(gradInput);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(gradOutputDeviceAddr);
aclrtFree(outputDeviceAddr);
aclrtFree(gradInputDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}