aclnnSimThreadExponential

Applicable Products

Function

• Description: Generates random numbers following an exponential distribution with parameter lambda and fills them into the selfRef tensor.

• Formula:

  $$f(x) = -\frac{1}{\lambda} \ln(1 - u), u \sim \text{Uniform}(0, 1]$$

Function Prototype

The operator execution API is a two-phase API. You must first call the "aclnnSimThreadExponentialGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the computation process, and then call the "aclnnSimThreadExponential" API to perform the computation.

aclnnStatus aclnnSimThreadExponentialGetWorkspaceSize(
  aclTensor       *selfRef,
  int64_t          count,
  double           lambda,
  int64_t          seed,
  int64_t          offset,
  uint64_t        *workspaceSize,
  aclOpExecutor   **executor)

aclnnStatus aclnnSimThreadExponential(
  void              *workspace,
  uint64_t           workspace_size,
  aclOpExecutor     *executor,
  aclrtStream  stream)

aclnnSimThreadExponentialGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  selfRef	Input/Output	f(x) in the formula.	-	FLOAT16, BFLOAT16, FLOAT32	ND	Less than or equal to 8 dimensions.	√
  count	Attribute	Number of generated random numbers.	-	INT64	-	-	-
  lambda	Attribute	Lambda in the formula.	-	DOUBLE	-	-	-
  seed	Attribute	Random seed.	-	INT64	-	-	-
  offset	Attribute.	Random number offset.	-	INT64	-	-	-
  workspaceSize	Output	Returns the workspace size that the user needs to apply for on the Device side.	-	-	-	1	-
  executor	Output	Returns the operator executor, which contains the operator computation flow.	-	-	-	1	-

• 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	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	Indicates that the passed selfRef is a null pointer.
  ACLN_ERR_PARAM_INVALID	161002	The data type of selfRef is not within the supported range.
  		The shape of selfRef exceeds 8 dimensions.
  		lambd is less than or equal to 0.

aclnnSimThreadExponential

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	The workspace memory address applied for on the Device side.
  workspaceSize	Input	Size of the workspace applied for on the Device side, obtained by the first-phase API aclnnSimThreadExponential.
  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 Codes.

Constraints

• Deterministic computation:

  • aclnnSimThreadExponential 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 "acl/acl.h"
#include "aclnnop/aclnn_sim_thread_exponential.h"
#include <iostream>
#include <vector>

#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 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 data to 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.
    // Fill in the deviceId based on your actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    // Handle the check based on your needs.
    CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    // 2. Construct the input and output based on the API definition.
    std::vector<int64_t> selfRefShape = {2, 5};
    void* selfRefDeviceAddr = nullptr;
    aclTensor* selfRef = nullptr;
    std::vector<float> selfRefHostData = {0, 1, 2, 3, 4, 5, 6, 7};
    // Create the selfRef aclTensor.
    ret = CreateAclTensor(selfRefHostData, selfRefShape, &selfRefDeviceAddr, aclDataType::ACL_FLOAT, &selfRef);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    uint64_t count = 10;
    double lambd = 1.0;
    uint64_t seed = 5;
    uint64_t offset = 0;
    // 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 aclnnSimThreadExponential.
    ret = aclnnSimThreadExponentialGetWorkspaceSize(selfRef, count, lambd, seed, offset, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSimThreadExponentialGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
    // Apply for 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 aclnnSimThreadExponential.
    ret = aclnnSimThreadExponential(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSimRandomUniform 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. Modify based on the specific API definition.
    auto size = GetShapeSize(selfRefShape);
    std::vector<float> resultData(size, 0);
    ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfRefDeviceAddr, 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(selfRef);

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