aclnnPermute

📄 View Source Code

Applicable Products

Function

Transposes arbitrary dimensions of a tensor. For example, if the input self is a tensor with shape [2, 3, 5] and dims is (2, 0, 1), the output is a tensor with shape [5, 2, 3].

Function Prototype

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

aclnnStatus aclnnPermuteGetWorkspaceSize(
    const aclTensor*   self,
    const aclIntArray* dims,
    aclTensor*         out,
    uint64_t*          workspaceSize,
    aclOpExecutor**    executor)

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

aclnnPermuteGetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-Contiguous Tensor
  self (aclTensor*)	Input	Input tensor.	-	FLOAT、FLOAT16、DOUBLE、UINT64、INT64、UINT32、INT32、UINT16、INT16、UINT8、INT8、BOOL、COMPLEX64、COMPLEX128、BFLOAT16、HIFLOAT8、FLOAT8_E5M2、FLOAT8_E4M3FN	ND	≤8	√
  dims (aclIntArray*)	Input	Integer array representing the dimensions of the original tensor, specifying the new axis order.	The value must be within the range of [-number of dimensions of self, number of dimensions of self - 1].	INT64	-	-	-
  out (aclTensor*)	Output	Output tensor.	Determines the shape based on dims and the original shape of self. The dtype must be consistent with self.	FLOAT, FLOAT16, DOUBLE, UINT64, INT64, UINT32, INT32, UINT16, INT16, UINT8, INT8, BOOL, COMPLEX64, COMPLEX128, BFLOAT16, HIFLOAT8, FLOAT8_E5M2, FLOAT8_E4M3FN.	ND	≤8	√
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be applied for on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

  • Atlas training products: The data types COMPLEX128, BFLOAT16, HIFLOAT8, FLOAT8_E5M2, and FLOAT8_E4M3FN are not supported.

  • Atlas A2 training products/Atlas A2 inference products, Atlas A3 training products/Atlas A3 inference products: HIFLOAT8, FLOAT8_E5M2, and FLOAT8_E4M3FN are 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 Value	Return Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The passed self, dims, or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of self or out is not within the supported range.
  		The data types of self and out are inconsistent.
  		The input self exceeds 8 dimensions.
  		The value of dims is outside the range [-number of dimensions of self, number of dimensions of self - 1].

aclnnPermute

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Specifies the workspace memory address applied for on the Device side.
  workspace_size	Input	Specifies the workspace size applied for on the Device side, which is obtained by the first-phase API aclnnPermuteGetWorkspaceSize.
  executor	Input	Operator executor that contains the operator computation flow.
  stream	Input	Specifies the stream for task execution.

• Return Value

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

Constraints

• Deterministic computation:

  • aclnnPermute 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_permute.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: 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 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);
  // Call aclrtMemcpy to copy host-side data to the device-side 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.
  // 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 input and output. Custom construction is required based on the API.
  std::vector<int64_t> selfShape = {4, 2};
  std::vector<int64_t> dimsData = {1, 0};
  std::vector<int64_t> outShape = {2, 4};
  void* selfDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {1, 2, 3, 4, 5, 6, 7, 8};
  std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
  // Create the self aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the dims aclIntArray.
  aclIntArray *dims = aclCreateIntArray(dimsData.data(), dimsData.size());
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 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 aclnnPermute.
  ret = aclnnPermuteGetWorkspaceSize(self, dims, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnPermuteGetWorkspaceSize 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 aclnnPermute.
  ret = aclnnPermute(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnPermute failed. ERROR: %d\n", ret); return ret);

  // 4. (boilerplate) Synchronize and wait for task execution 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 based on the specific API definition.
  auto size = GetShapeSize(outShape);
  std::vector<float> 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: %f\n", i, resultData[i]);
  }

  // 6. Release aclTensor and aclIntArray. Modify based on the specific API definition.
  aclDestroyTensor(self);
  aclDestroyIntArray(dims);
  aclDestroyTensor(out);

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

  return 0;
}