aclnnMultinomial

📄 View Source Code

Applicable Products

Function

Extracts numsamples samples from the input tensor based on the probability distribution of each object, and stores the indices of these samples in the output tensor.

Function Prototype

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

aclnnStatus aclnnMultinomialGetWorkspaceSize(
  const aclTensor*      self,
  int64_t               numsamples,
  bool                  replacement,
  int64_t               seed,
  int64_t               offset,
  aclTensor*            out,
  uint64_t*             workspaceSize,
  aclOpExecutor**       executor)

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

aclnnMultinomialGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-Contiguous Tensor
  self (aclTensor*)	Input	Input tensor.	The value range of self must be greater than or equal to 0.	BFLOAT16, FLOAT16, FLOAT, DOUBLE	ND	The shape is (N, C) or (C), and self has the same dimension as out.	√
  numsamples (int64_t)	Input	Number of samples to draw from each multinomial distribution.	numsamples is a positive number. When replacement is false, numsamples is not greater than C.	INT64	-	-	-
  replacement (bool)	Input	Determines whether elements are sampled with replacement.	-	BOOL	-	-	-
  seed (int64_t)	Input	Seed of the random number generator, which affects the generated random number sequence.	-	INT64	-	-	-
  offset (int64_t)	Input	Specifies the offset of the random number generator, which affects the position of the generated random number sequence. After the offset is set, the generated random number sequence starts from the specified position.	-	INT64	-	-	-
  out (aclTensor*)	Output	Output tensor.	-	INT64	ND	(N, numsamples) or (numsamples), where self and out have the same dimensions.	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied on the device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which includes 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	Indicates that self or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of self is not within the supported range.
  		The data type of out is not INT64.
  		The dimension of self is not 1D or 2D.
  		The dimensions of self and out are inconsistent.
  		The value of numsamples is less than or equal to 0.
  		replacement is false and numsamples is greater than the size of the last dimension of self.
  		The size of the last dimension of self cannot exceed 2^24.
  		The last dimension of out must be consistent with the size of numsamples.
  		When self is a 2D tensor, the first dimension of out must be equal to the size of the first dimension of self.

aclnnMultinomial

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	The workspace memory address applied on the device side.
  workspaceSize	Input	Size of the side-applied workspace on the device, obtained by the first-phase API aclnnMultinomialGetWorkspaceSize.
  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:

  • aclnnMultinomial 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_multinomial.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 shapeSize = 1;
  for (auto i : shape) {
    shapeSize *= i;
  }
  return shapeSize;
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // Boilerplate: initialize resources.
  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 data from the host to the device using 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 strides for 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 aclCreateTensor 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.
  // Specify the device ID based on your actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. Construct the input and output based on the API interface.
  std::vector<int64_t> selfShape = {4};
  std::vector<int64_t> outShape = {2};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {0, 10, 3, 0};
  std::vector<float> outHostData = {2, 0};
  int64_t numsamples = 2;
  bool replacement = false;
  int64_t seed = 1234;
  int64_t offset = 0;
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_INT64, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API. Replace it with the specific API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnMultinomial.
  ret = aclnnMultinomialGetWorkspaceSize(self, numsamples, replacement, seed, offset, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMultinomialGetWorkspaceSize 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 aclnnMultinomial.
  ret = aclnnMultinomial(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMultinomial failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Wait for the task execution to complete synchronously.
  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(selfShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfDeviceAddr,
                    size * sizeof(resultData[0]), 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);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}