aclnnClampMin

📄 View Source Code

Applicable Products

Function

• Description: Clamps all elements of the input to the range [min, inf].

• Formula:

  $${y}_{i} = max({{x}_{i}},{min\_value}_{i})$$

Function Prototype

Each operator is divided into a two-phase API. The "aclnnClampMinGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnClampMin" API is called to perform the computation.

aclnnStatus aclnnClampMinGetWorkspaceSize(
    const aclTensor *self,
    const aclScalar *clipValueMin,
    aclTensor       *out,
    uint64_t        *workspaceSize,
    aclOpExecutor  **executor)

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

aclnnClampMinGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (shape)	Non-contiguous Tensor
  self (aclTensor*)	Input	Input tensor, the tensor to be clamped, i.e., xi in the formula.	The data type of self and max must satisfy the data type deduction rules (see conversion relationship).	FLOAT16, FLOAT, DOUBLE, INT8, UINT8, INT16, INT32, INT64, BFLOAT16	ND	1-8	√
  clipValueMin (aclScalar*)	Input	Input scalar that specifies the lower bound for self, i.e., mini in the formula.	The data type of min must satisfy the data type deduction rules with the data type of self (see Conversion Relationship).	FLOAT16, FLOAT, DOUBLE, INT8, UINT8, INT16, INT32, INT64, BFLOAT16, BOOL	ND	1-8	-
  out (aclTensor*)	Output	Output tensor, i.e., outi in the formula.	The data type must be a data type that is convertible after deduction from self and clipValueMin.	FLOAT16, FLOAT, DOUBLE, INT8, UINT8, INT16, INT32, INT64, BFLOAT16	ND	Consistent with self.	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be allocated on the device side.	-	-	-	-	-
  （aclOpExecutor**）	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

  • Atlas training products, Atlas inference products:

    • The data types of self and out do not support BOOL or BFLOAT16.

    • The data type of clipValueMin does not support BFLOAT16.

  • Atlas A2 training products/Atlas A2 inference products, Atlas A3 training products/Atlas A3 inference products

    • The data type of self and out cannot be BOOL.

• 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 Value	Return Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	Indicates that either self or out is a null pointer, or clipValueMin 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.

aclnnClampMin

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	The workspace memory address allocated on the Device side.
  workspaceSize	Input	Size of the workspace requested on the device side, obtained through the first-phase API aclnnClampMinGetWorkspaceSize.
  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 Codes.

Constraints

• Deterministic computation:

  • aclnnClampMin 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_clamp.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 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);

    // 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 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 PrepareInputAndOutput(
    std::vector<int64_t>& shape, void** selfDeviceAddr, aclTensor** self, aclScalar** min, void** outDeviceAddr, aclTensor** out)
{
    double min_v = 2;

    std::vector<double> selfHostData = {0, 1, 0, 3, 0, 5, 0, 7};
    std::vector<double> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};

    // Create the self aclTensor.
    auto ret = CreateAclTensor(selfHostData, shape, selfDeviceAddr, aclDataType::ACL_DOUBLE, self);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create min.
    *min = aclCreateScalar(&min_v, aclDataType::ACL_DOUBLE);
    CHECK_RET(*min != nullptr, return ret);
    // Create the out aclTensor.
    ret = CreateAclTensor(outHostData, shape, outDeviceAddr, aclDataType::ACL_DOUBLE, out);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    return ACL_SUCCESS;
}

void ReleaseTensorAndScalar(aclTensor* self, aclScalar* min, aclTensor* out)
{
  aclDestroyTensor(self);
  aclDestroyScalar(min);
  aclDestroyTensor(out);
}

void ReleaseDevice(
    void* selfDeviceAddr, void* outDeviceAddr, uint64_t workspaceSize, void* workspaceAddr, aclrtStream stream,
    int32_t deviceId)
{
  aclrtFree(selfDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
}

int main() {
    // 1. Boilerplate: device/stream initialization. See the ACL external API list.
    // Set 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 inputs and outputs based on the API definition.
    std::vector<int64_t> shape = {4, 2};

    void* selfDeviceAddr = nullptr;
    void* outDeviceAddr = nullptr;
    aclTensor* self = nullptr;
    aclScalar* min = nullptr;
    aclTensor* out = nullptr;

    ret = PrepareInputAndOutput(shape, &selfDeviceAddr, &self, &min, &outDeviceAddr, &out);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 3. Call the CANN operator library API. Replace with the specific API.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // Call the first-phase API of aclnnClampMin.
    ret = aclnnClampMinGetWorkspaceSize(self, min, out, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnClampMinGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
    // Allocate device memory based on the workspaceSize computed 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 aclnnClampMin.
    ret = aclnnClampMin(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnClampMin failed. ERROR: %d\n", ret); return ret);
    // 4. Boilerplate: synchronize and wait for the task 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 this step based on the specific API definition.
    auto size = GetShapeSize(shape);
    std::vector<double> resultData(size, 0);
    ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr, size * sizeof(double),
                      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 this step based on the specific API definition.
  ReleaseTensorAndScalar(self, min, out);

    // 7. Release device resources.
  ReleaseDevice(selfDeviceAddr, outDeviceAddr, workspaceSize, workspaceAddr, stream, deviceId);

    return 0;
}