aclnnHardswish&aclnnInplaceHardswish

Applicable Products

Product	Supported
Ascend 950PR/Ascend 950DT	×
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	×
Atlas inference products	×
Atlas training products	√

Function

Description: An activation function that returns an output tensor with the same shape as the input tensor. When the input value is less than -3, it returns 0; when greater than 3, it returns the value; otherwise, it returns the value plus 3, multiplied by the value, and then divided by 6.
Formula:
$Hardswish(x)=\begin{cases} x, & x\gt3 \\ 0, & x\le -3 \\ \frac{x · (x + 3)}{6}, & otherwise \end{cases}$

Function Prototype

aclnnHardswish and aclnnInplaceHardswish implement the same functionality. The differences are as follows. Select the appropriate operator based on your actual scenario.
- aclnnHardswish: Requires creating a new output tensor object to store the computation result.
- aclnnInplaceHardswish: Does not require creating a new output tensor object. The computation result is stored directly in the memory of the input tensor.
Each operator uses a two-phase API. You must first call the "aclnnHardswishGetWorkspaceSize" or "aclnnInplaceHardswishGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnHardswish" or "aclnnInplaceHardswish" API to perform the computation.

aclnnStatus aclnnHardswishGetWorkspaceSize(
  const aclTensor* self,
  const aclTensor* out,
  uint64_t*        workspaceSize,
  aclOpExecutor**  executor)

aclnnStatus aclnnHardswish(
  void*             workspace,
  uint64_t          workspaceSize,
  aclOpExecutor*    executor,
  const aclrtStream stream)

aclnnStatus aclnnInplaceHardswishGetWorkspaceSize(
  const aclTensor* self,
  uint64_t*        workspaceSize,
  aclOpExecutor**  executor)

aclnnStatus aclnnInplaceHardswish(
  void*             workspace,
  uint64_t          workspaceSize,
  aclOpExecutor*    executor,
  const aclrtStream stream)

aclnnHardswishGetWorkspaceSize

Parameters:

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
self (aclTensor*)	Input	Represents the input tensor of the activation function, i.e., the input x in the formula.	Supports empty tensors. The data type of self must be convertible to the data type of out (see Conversion Relationship).	BFLOAT16, FLOAT16, FLOAT32	ND	0-8	√
out (aclTensor*)	Output	Represents the output tensor of the activation function, i.e., the output Hardswish in the formula.	The data type of out must be convertible to the data type of self (see Conversion Relationship).	BFLOAT16, FLOAT16, FLOAT32	ND	0-8	√
workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Returns the operator executor, which contains the operator computation flow.	-	-	-	-	-

Atlas training products: The supported data types are FLOAT16 and FLOAT32.

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 self or out is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data type or data format of self or out is not within the supported range.
		The shape of self is inconsistent with the shape of the output out.
		The data types of self and out do not satisfy the conversion relationship.

aclnnHardswish

Parameters:

Parameter	Input/Output	Description
workspace	Input	The workspace memory address applied for on the Device side.
workspaceSize	Input	The workspace size applied for on the Device side, obtained by the first-phase API aclnnHardswishGetWorkspaceSize.
executor	Input	Operator executor, which contains the operator computation flow.
stream	Input	Specifies the stream for executing the task.

Return value

aclnnStatus: return code. For details, see aclnn Return Code.

aclnnInplaceHardswishGetWorkspaceSize

Parameters:

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
self (aclTensor*)	Input	Represents the input/output tensor of the activation function, i.e., x and the output result in the formula.	Supports empty tensors.	BFLOAT16, FLOAT16, FLOAT32	ND	0-8	√
workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation process.	-	-	-	-	-

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 self is a null pointer.
ACLNN_ERR_PARAM_INVALID	161002	The data type or data format of self is not within the supported range.

aclnnInplaceHardswish

Parameters:

Parameter	Input/Output	Description
workspace	Input	Specifies the workspace memory address applied for on the device.
workspaceSize	Input	Specifies the workspace size applied for on the device, which is obtained by the first-phase API aclnnInplaceHardswishGetWorkspaceSize.
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 Code.

Constraints

Deterministic computation:
- aclnnHardswish&aclnnInplaceHardswish default 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_hardswish.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-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 host-side data to 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 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];
  }

  // Create an aclTensor by calling aclCreateTensor.
  *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);
  // 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.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> outShape = {4, 2};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {-4, -3, -2, 0, 1, 2, 4, 5};
  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 out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // Example of aclnnHardswish API call.
  // 3. Call the CANN operator library API.
  // Call the first-phase API of aclnnHardswish.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  ret = aclnnHardswishGetWorkspaceSize(self, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnHardswishGetWorkspaceSize 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 aclnnHardswish.
  ret = aclnnHardswish(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnHardswish 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. 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]);
  }

  // Example of calling the aclnnInplaceHardswish API
  // 3. Call the CANN operator library API.
  LOG_PRINT("\ntest aclnnInplaceHardswish\n");
  // Call the first-phase API of aclnnInplaceHardswish.
  uint64_t inplaceWorkspaceSize = 0;
  aclOpExecutor* inplaceExecutor;
  ret = aclnnInplaceHardswishGetWorkspaceSize(self, &inplaceWorkspaceSize, &inplaceExecutor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceHardswishGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Apply for device memory based on the workspaceSize calculated by the first-phase API.
  void* inplaceWorkspaceAddr = nullptr;
  if (inplaceWorkspaceSize > 0) {
    ret = aclrtMalloc(&inplaceWorkspaceAddr, inplaceWorkspaceSize, 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 aclnnInplaceHardswish.
  ret = aclnnInplaceHardswish(inplaceWorkspaceAddr, inplaceWorkspaceSize, inplaceExecutor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceHardswish 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 side. Modify based on the specific API definition.
  size = GetShapeSize(outShape);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfDeviceAddr, 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(self);
  aclDestroyTensor(out);

  // 7. Release device resources. Modify based on the specific API definition.
  aclrtFree(selfDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  if (inplaceWorkspaceSize > 0) {
    aclrtFree(inplaceWorkspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}