aclnnGeScalar&aclnnInplaceGeScalar

Supported Products

Product	Supported
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: Determines whether each element in the input tensor is greater than or equal to the corresponding one of the other scalar and returns a Boolean tensor that indicates whether the behavior of the greater-than-or-equal-to is true.
Formula: For the input parameter self and the comparison scalar other, ge can be expressed by the following formula:
$out_{i}= (self_i >= other) ? True : False$

Prototype

aclnnGeScalar and aclnnInplaceGeScalar implement the same function in different ways. Select a proper operator based on your requirements.
- aclnnGeScalar: An output tensor object needs to be created to store the computation result.
- aclnnInplaceGeScalar: No output tensor object needs to be created, and the computation result is stored in the memory of the input tensor.
Each operator has two-phase API calls. First, aclnnGeScalarGetWorkspaceSize or aclnnInplaceGeScalarGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnGeScalar or aclnnInplaceGeScalar is called to perform computation.
- aclnnStatus aclnnGeScalarGetWorkspaceSize(const aclTensor *self, const aclScalar *other, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
- aclnnStatus aclnnGeScalar(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, const aclrtStream stream)
- aclnnStatus aclnnInplaceGeScalarGetWorkspaceSize(aclTensor *selfRef, const aclScalar *other, uint64_t *workspaceSize, aclOpExecutor **executor)
- aclnnStatus aclnnInplaceGeScalar(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)

aclnnGeScalarGetWorkspaceSize

Parameters:
- self (aclTensor*, computation input): aclTensor on the device. The shape dimension cannot exceed 8. Non-contiguous tensors are supported. The data format can be ND.
  - Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: DOUBLE, BFLOAT16, FLOAT16, FLOAT32, INT32, UINT32, INT64, UINT64, INT16, UINT16, INT8, UINT8, or BOOL is supported. The deduction relationship with other must be met (see Deduction Relationship).
  - Atlas training products and Atlas inference products: DOUBLE, FLOAT16, FLOAT32, INT32, UINT32, INT64, UINT64, INT16, UINT16, INT8, UINT8, or BOOL is supported. The deduction relationship with other must be met (see Deduction Relationship).
- other (aclScalar*, computation input): aclScalar on the host.
  - Atlas A2 training products/Atlas A2 inference products, and Atlas A3 training products/Atlas A3 inference products: DOUBLE, BFLOAT16, FLOAT16, FLOAT32, INT32, UINT32, INT64, UINT64, INT16, UINT16, INT8, UINT8, or BOOL is supported. The deduction relationship with self must be met (see Deduction Relationship).
  - Atlas training products and Atlas inference products: DOUBLE, FLOAT16, FLOAT32, INT32, UINT32, INT64, UINT64, INT16, UINT16, INT8, UINT8, or BOOL is supported. The deduction relationship with self must be met (see Deduction Relationship).
- out (aclTensor *, computation output): aclTensor on the device. The data type must be convertible to BOOL (see Conversion Relationship). Non-contiguous tensors are supported. The data format can be ND.
  - Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: DOUBLE, BFLOAT16, FLOAT16, FLOAT32, INT32, UINT32, INT64, UINT64, INT16, UINT16, INT8, UINT8, BOOL, COMPLEX64, or COMPLEX128 is supported.
  - Atlas training products and Atlas inference products: DOUBLE, FLOAT16, FLOAT32, INT32, UINT32, INT64, UINT64, INT16, UINT16, INT8, UINT8, BOOL, COMPLEX64, or COMPLEX128 is supported.
- workspaceSize (uint64_t*, output): size of the workspace to be allocated on the device.
- executor (aclOpExecutor**, output): operator executor, covering the operator computation process.

Returns:

aclnnStatus: status code. For details, see aclnn Return Codes.

The first-phase API performs input parameter validation. The following error codes may be returned:
161001 (ACLNN_ERR_PARAM_NULLPTR): 1. The passed self, other, or out is a null pointer.
161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type of self, other, or out is not supported.
                                  2. The data types of self and other do not meet the type deduction rules.
                                  3. The shape of self is different from that of out.
                                  4. The dimensions of self and out are greater than 8.

aclnnGeScalar

Parameters:
- workspace (void*, input): address of the workspace to be allocated on the device.
- workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by the first-phase API aclnnGeScalarGetWorkspaceSize.
- executor (aclOpExecutor*, input): operator executor, covering the operator computation process.
- stream (aclrtStream, input): stream for executing the task.
Outputs:

aclnnStatus: status code. For details, see aclnn Return Codes.

aclnnInplaceGeScalarGetWorkspaceSize

Parameters:
- selfRef (aclTensor*, computation input | computation output): input and output tensor, self and out in the formula, aclTensor on the device. The shape dimension cannot exceed 8. Non-contiguous tensors are supported. The data format can be ND.
  - Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: FLOAT32, FLOAT16, INT32, INT64, INT16, INT8, UINT8, DOUBLE, UINT16, UINT64, UINT32, BOOL, or BFLOAT16 is supported. The deduction relationship with other must be met (see Deduction Relationship).
  - Atlas training products and Atlas inference products: FLOAT32, FLOAT16, INT32, INT64, INT16, INT8, UINT8, DOUBLE, UINT16, UINT64, UINT32, or BOOL is supported. The deduction relationship with other must be met (see Deduction Relationship).
- other (aclScalar*, computation input): aclScalar on the host.
  - Atlas A2 training products/Atlas A2 inference products and Atlas A3 training products/Atlas A3 inference products: FLOAT32, FLOAT16, INT32, INT64, INT16, INT8, UINT8, DOUBLE, UINT16, UINT64, UINT32, BOOL, or BFLOAT16 is supported. The deduction relationship with selfRef must be met (see Deduction Relationship).
  - Atlas training products and Atlas inference products: FLOAT32, FLOAT16, INT32, INT64, INT16, INT8, UINT8, DOUBLE, UINT16, UINT64, UINT32, or BOOL is supported. The deduction relationship with selfRef must be met (see Deduction Relationship).
- workspaceSize (uint64_t*, output): size of the workspace to be allocated on the device.
- executor (aclOpExecutor**, output): operator executor, containing the operator computation process.

Returns:

aclnnStatus: status code. For details, see aclnn Return Codes.

The first-phase API performs input parameter validation. The following error codes may be returned:
161001 (ACLNN_ERR_PARAM_NULLPTR): 1. The passed selfRef or other is a null pointer.
161002 (ACLNN_ERR_PARAM_INVALID): 1. The data type of selfRef or other is not supported.
                                  2. The data types of selfRef and other do not meet the data type deduction rules.
                                  3. The dimensions of selfRef are greater than 8.

aclnnInplaceGeScalar

Parameters:
- workspace (void*, input): address of the workspace to be allocated on the device.
- workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by the first-phase API aclnnInplaceGeScalarGetWorkspaceSize.
- executor (aclOpExecutor*, input): operator executor, covering the operator computation process.
- stream (aclrtStream, input): stream for executing the task.
Returns:

aclnnStatus: status code. For details, see aclnn Return Codes.

Constraints

Deterministic computing:
- aclnnGeScalar and aclnnInplaceGeScalar default to deterministic implementation.

Example

The following example is for reference only. For details, see Compilation and Running Sample.

Sample code of aclnnGeScalar:

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_ge_scalar.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 allocate memory on the device.
  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 the data on the host to the memory on the device.
  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 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];
  }

  // 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 and stream. For details, see the ACL API manual.
  // Set the device ID in use.
  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 inputs and outputs based on the API definition.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> outShape = {4, 2};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclScalar* other = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<char> outHostData(8, 0);
  float otherValue = 3.5f;
  // Create a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create an other aclScalar.
  other = aclCreateScalar(&otherValue, aclDataType::ACL_FLOAT);
  CHECK_RET(other != nullptr, return ret);
  // Create an out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_BOOL, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API, which needs to be replaced with the actual API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnGeScalar.
  ret = aclnnGeScalarGetWorkspaceSize(self, other, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGeScalarGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on 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 aclnnGeScalar.
  ret = aclnnGeScalar(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGeScalar failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Wait until the task execution is 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 the code based on the API definition.
  auto size = GetShapeSize(outShape);
  std::vector<char> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr,
                    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: %d\n", i, resultData[i]);
  }

  // 6. Release aclTensor and aclScalar. Modify the configuration based on the API definition.
  aclDestroyTensor(self);
  aclDestroyScalar(other);
  aclDestroyTensor(out);

  // 7. Release device resources.
  aclrtFree(selfDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}

Sample code of aclnnInplaceGeScalar:

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_ge_scalar.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 allocate memory on the device.
  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 the data on the host to the memory on the device.
  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 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];
  }

  // 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 and stream. For details, see the ACL API manual.
  // Set the device ID in use.
  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 inputs and outputs based on the API definition.
  std::vector<int64_t> selfShape = {4, 2};
  void* selfDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclScalar* other = nullptr;
  std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  float otherValue = 3.5f;
  // Create a self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create an other aclScalar.
  other = aclCreateScalar(&otherValue, aclDataType::ACL_FLOAT);
  CHECK_RET(other != nullptr, return ret);

  // 3. Call the CANN operator library API, which needs to be replaced with the actual API.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnInplaceGeScalar.
  ret = aclnnInplaceGeScalarGetWorkspaceSize(self, other, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceGeScalarGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on 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 aclnnInplaceGeScalar.
  ret = aclnnInplaceGeScalar(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceGeScalar failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Wait until the task execution is 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 the code based on the 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 the configuration based on the API definition.
  aclDestroyTensor(self);
  aclDestroyScalar(other);

  // 7. Release device resources.
  aclrtFree(selfDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}