Documentation
Download
文档中心
aclnnForeachSubList

aclnnForeachSubList

📄 View Source Code

Applicable Products

ProductSupported
Ascend 950PR/Ascend 950DTNo
Atlas A3 training products/Atlas A3 inference productsYes
Atlas A2 training products/Atlas A2 inference productsYes
Atlas 200I/500 A2 inference productsNo
Atlas inference productsNo
Atlas training productsNo

Function

  • Description: Performs element-wise subtraction operation on two input tensor lists, with the subtraction coefficient adjustable via the alpha parameter.

  • Formula:

    x1=[x10,x11,...x1n−1]x2=[x20,x21,...x2n−1]y=[y0,y1,...yn−1]x1 = [{x1_0}, {x1_1}, ... {x1_{n-1}}]\\ x2 = [{x2_0}, {x2_1}, ... {x2_{n-1}}]\\ y = [{y_0}, {y_1}, ... {y_{n-1}}]\\ yi=x1i−x2i∗alpha(i=0,1,...n−1)y_i = x1_i-{x2_i}*alpha (i=0,1,...n-1)

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnForeachSubListGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the computation process, and then call the "aclnnForeachSubList" API to perform the computation.

aclnnStatus aclnnForeachSubListGetWorkspaceSize(
  const aclTensorList     *x1,
  const aclTensorList     *x2,
  const aclTensor         *alpha,
  const aclTensorList     *out,
  uint64_t                *workspaceSize,
  aclOpExecutor          **executor)
aclnnStatus aclnnForeachSubList(
  void               *workspace,
  uint64_t           workspaceSize,
  aclOpExecutor      *executor,
  aclrtStream         stream)

aclnnForeachSubListGetWorkspaceSize

  • Parameters

    Parameter Input/Output Description Instruction Data Type Data Format Shape Non-contiguous Tensor
    x1 (aclTensorList*) Input Represents the tensor list of minuends in the subtraction operation, corresponding to `x1` in the formula.
    • Empty tensors are supported.
    • All tensors in this parameter must have the same data type.
    		 FLOAT32, FLOAT16, BFLOAT16, INT32 ND 0-8 √
    x2 (aclTensorList*) Input Represents the tensor list of subtrahends in the subtraction operation, corresponding to `x2` in the formula.
    • Empty tensors are supported.
    • The data type, data format, and shape are consistent with those of the input parameter x1.
    		 FLOAT32, FLOAT16, BFLOAT16, INT32 ND 0-8 √
    alpha (aclTensor*) Input Represents the coefficient of the subtrahend in the subtraction operation, corresponding to `alpha` in the formula.
    • Empty tensor is not supported.
    • The number of elements is 1.
    • The data type has a specific correspondence with the data type of the input parameter `x1`:
      • When the data type of `x1` is FLOAT32, FLOAT16, or INT32, the data type remains consistent with that of `x1`.
      • When the data type of `x1` is BFLOAT16, the data type supports FLOAT32.
    		 FLOAT32, FLOAT16, INT32 ND 0-8 √
    out (aclTensorList*) Output Output tensor list of the subtraction operation, corresponding to `y` in the formula.
    • Empty tensors are supported.
    • All tensors in this parameter must have the same data type.
    • The data type and data format are the same as those of the input parameter `x1`, and the shape size is greater than or equal to that of `x1`.
    		 FLOAT32, FLOAT16, BFLOAT16, INT32 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. - - - - -

  • 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 x1, x2, alpha, or out is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data types of x1, x2, alpha, and out are not within the supported range.
    The data types of x1, x2, and out are inconsistent.
    ACLNN_ERR_PARAM_INVALID 561002 The shapes of x1, x2, and out do not meet the constraints.
    The data types of tensors in x1, x2, or out are inconsistent.
    The dimensions of tensors in x1, x2, or out exceed 8.
    The number of elements in alpha is not 1.

aclnnForeachSubList

  • Parameters

    Parameter Input/Output Description
    workspace Input Memory address of the workspace applied for on the Device side.
    workspaceSize Input Size of the workspace applied for on the Device side, obtained through the first-phase API aclnnForeachSubListGetWorkspaceSize.
    executor Input Operator executor, which 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:

    • aclnnForeachSubList 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_foreach_sub_list.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 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-side memory 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 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. Refer to the ACL API manual.
  // Set deviceId based on the 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 inputs and outputs. Customize the construction based on the API.
  std::vector<int64_t> selfShape1 = {2, 3};
  std::vector<int64_t> selfShape2 = {1, 3};
  std::vector<int64_t> otherShape1 = {2, 3};
  std::vector<int64_t> otherShape2 = {1, 3};
  std::vector<int64_t> outShape1 = {2, 3};
  std::vector<int64_t> outShape2 = {1, 3};
  std::vector<int64_t> alphaShape = {1};
  void* input1DeviceAddr = nullptr;
  void* input2DeviceAddr = nullptr;
  void* other1DeviceAddr = nullptr;
  void* other2DeviceAddr = nullptr;
  void* out1DeviceAddr = nullptr;
  void* out2DeviceAddr = nullptr;
  void* alphaDeviceAddr = nullptr;
  aclTensor* input1 = nullptr;
  aclTensor* input2 = nullptr;
  aclTensor* other1 = nullptr;
  aclTensor* other2 = nullptr;
  aclTensor* alpha = nullptr;
  aclTensor* out1 = nullptr;
  aclTensor* out2 = nullptr;
  std::vector<float> input1HostData = {3, 5, 7, 4, 5, 9};
  std::vector<float> input2HostData = {5, 4, 1};
  std::vector<float> other1HostData = {1, 2, 3, 4, 5, 6};
  std::vector<float> other2HostData = {7, 8, 9};
  std::vector<float> out1HostData(6, 0);
  std::vector<float> out2HostData(3, 0);
  std::vector<float> alphaValueHostData = {1.2f};
  // Create the input1 aclTensor.
  ret = CreateAclTensor(input1HostData, selfShape1, &input1DeviceAddr, aclDataType::ACL_FLOAT, &input1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the input2 aclTensor.
  ret = CreateAclTensor(input2HostData, selfShape2, &input2DeviceAddr, aclDataType::ACL_FLOAT, &input2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the other1 aclTensor.
  ret = CreateAclTensor(other1HostData, otherShape1, &other1DeviceAddr, aclDataType::ACL_FLOAT, &other1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the other2 aclTensor.
  ret = CreateAclTensor(other2HostData, otherShape2, &other2DeviceAddr, aclDataType::ACL_FLOAT, &other2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the alpha aclTensor.
  ret = CreateAclTensor(alphaValueHostData, alphaShape, &alphaDeviceAddr, aclDataType::ACL_FLOAT, &alpha);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out1 aclTensor.
  ret = CreateAclTensor(out1HostData, outShape1, &out1DeviceAddr, aclDataType::ACL_FLOAT, &out1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out2 aclTensor.
  ret = CreateAclTensor(out2HostData, outShape2, &out2DeviceAddr, aclDataType::ACL_FLOAT, &out2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  std::vector<aclTensor*> tempInput1{input1, input2};
  aclTensorList* tensorListInput1 = aclCreateTensorList(tempInput1.data(), tempInput1.size());
  std::vector<aclTensor*> tempInput2{other1, other2};
  aclTensorList* tensorListInput2 = aclCreateTensorList(tempInput2.data(), tempInput2.size());
  std::vector<aclTensor*> tempOutput{out1, out2};
  aclTensorList* tensorListOutput = aclCreateTensorList(tempOutput.data(), tempOutput.size());

  // 3. Call the CANN operator library API. Replace with the specific API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnForeachSubList.
  ret = aclnnForeachSubListGetWorkspaceSize(tensorListInput1, tensorListInput2, alpha, tensorListOutput, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachSubListGetWorkspaceSize 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 aclnnForeachSubList.
  ret = aclnnForeachSubList(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnForeachSubList failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Wait for 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 memory to the host memory. Modify based on the specific API definition.
  auto size = GetShapeSize(outShape1);
  std::vector<float> out1Data(size, 0);
  ret = aclrtMemcpy(out1Data.data(), out1Data.size() * sizeof(out1Data[0]), out1DeviceAddr,
                    size * sizeof(out1Data[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("out1 result[%ld] is: %f\n", i, out1Data[i]);
  }

  size = GetShapeSize(outShape2);
  std::vector<float> out2Data(size, 0);
  ret = aclrtMemcpy(out2Data.data(), out2Data.size() * sizeof(out2Data[0]), out2DeviceAddr,
                    size * sizeof(out2Data[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("out2 result[%ld] is: %f\n", i, out2Data[i]);
  }

  // 6. Release aclTensor. Modify based on the specific API definition.
  aclDestroyTensorList(tensorListInput1);
  aclDestroyTensorList(tensorListInput2);
  aclDestroyTensorList(tensorListOutput);
  aclDestroyTensor(alpha);

  // 7. Release device resources. Modify based on the specific API definition.
  aclrtFree(input1DeviceAddr);
  aclrtFree(input2DeviceAddr);
  aclrtFree(other1DeviceAddr);
  aclrtFree(other2DeviceAddr);
  aclrtFree(out1DeviceAddr);
  aclrtFree(out2DeviceAddr);
  aclrtFree(alphaDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();
  return 0;
}
This site uses cookies to improve your browsing experience. By continuing to browse this site, you agree to our use of cookies.View Details