aclnnFakeQuantPerTensorAffineCachemask

Applicable Products

Function

• Description:

  • fake_quant_enabled >= 1: For the input data self, performs fake quantization on the input self using scale and zero_point, clamps the fake quantization output to the range defined by quant_min and quant_max, and finally returns the result out and the corresponding position mask.

  • fake_quant_enabled < 1: Returns out as a self.clone() object, with the mask being all True.

• Formula: When fake_quant_enabled >= 1, a temporary variable qval is first computed based on the operator functionality, and then out and mask are derived from it.

  $$qval = Round(std::nearby\_int(self / scale) + zero\_point)$$ $$out = (Min(quant\_max, Max(quant\_min, qval)) - zero\_point) * scale$$ $$mask = (qval >= quant\_min) \& (qval <= quant\_max)$$

Function Prototype

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

aclnnStatus aclnnFakeQuantPerTensorAffineCachemaskGetWorkspaceSize(
  const aclTensor   *self,
  const aclTensor   *scale,
  const aclTensor   *zeroPoint,
  float              fakeQuantEnabled,
  int64_t            quantMin,
  int64_t            quantMax,
  aclTensor         *out,
  aclTensor         *mask,
  uint64_t          *workspaceSize,
  aclOpExecutor     **executor)

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

aclnnFakeQuantPerTensorAffineCachemaskGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  self	Input	self in the formula.	-	FLOAT16, FLOAT32	ND	0-8	√
  scale	Input	The scale in the formula, representing the scaling factor for input fake quantization.	The size is 1.	FLOAT16, FLOAT32	ND	1	√
  zeroPoint	Input	The zero_point in the formula, representing the zero-reference parameter for the input fake quantization.	The size is 1.	INT32	ND	1	√
  fakeQuantEnabled	Input	Indicates whether to perform fake quantization computation.	-	FLOAT32	-	-	-
  quantMin	Input	Represents the minimum value of the input data after fake quantization.	Must be less than or equal to quantMax.	INT64	-	-	-
  quantMax	Input	Represents the maximum value of the input data after fake quantization.	Must be greater than or equal to quantMin.	INT64	-	-	-
  out	Output	The out in the formula.	The shape must be consistent with `self`.	FLOAT16, FLOAT32	ND	0-8	√
  mask	Output	The mask in the formula.	The shape must be consistent with `self`.	BOOL	ND	0-8	√
  workspaceSize	Output	Returns the workspace size to be allocated on the Device side.	-	-	-	-	-
  executor	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 input self, scale, zeroPoint, out, or mask is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of self, scale, zeroPoint, out, or mask is not within the supported range.
  		The size of scale or zeroPoint is not 1.
  		The shape of out or mask is inconsistent with that of self.
  		quantMin is greater than quantMax.

aclnnFakeQuantPerTensorAffineCachemask

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Workspace memory address applied for on the Device side.
  workspaceSize	Input	Workspace size applied for on the Device side, obtained by the first-phase API aclnnFakeQuantPerTensorAffineCachemaskGetWorkspaceSize.
  executor	Input	The 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:

  • aclnnFakeQuantPerTensorAffineCachemask 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_fake_quant_per_tensor_affine_cachemask.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 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 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 host-side data to device-side memory by calling 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];
  }

  // Create an aclTensor by calling aclCreateTensor.
  *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. Customize the construction based on the API.
  std::vector<int64_t> selfShape = {1};
  std::vector<int64_t> scaleShape = {1};
  std::vector<int64_t> zeroPointShape = {1};
  std::vector<int64_t> outShape = {1};
  std::vector<int64_t> maskShape = {1};
  void* selfDeviceAddr = nullptr;
  void* scaleDeviceAddr = nullptr;
  void* zeroPointDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  void* maskDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* scale = nullptr;
  aclTensor* zeroPoint = nullptr;
  aclTensor* out = nullptr;
  aclTensor* mask = nullptr;
  std::vector<float> selfHostData{1};
  std::vector<float> scaleHostData{1};
  std::vector<int32_t> zeroPointHostData{1};
  std::vector<float> outHostData{1};
  std::vector<char> maskHostData{1};
  int64_t quantMin = 1;
  int64_t quantMax = 3;
  float fakeQuantEnabled = 1.0f;
  // Create an aclTensor.
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(scaleHostData, scaleShape, &scaleDeviceAddr, aclDataType::ACL_FLOAT, &scale);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(zeroPointHostData, zeroPointShape, &zeroPointDeviceAddr, aclDataType::ACL_INT32, &zeroPoint);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(maskHostData, maskShape, &maskDeviceAddr, aclDataType::ACL_BOOL, &mask);
  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 aclnnEye.
  ret = aclnnFakeQuantPerTensorAffineCachemaskGetWorkspaceSize(self, scale, zeroPoint, fakeQuantEnabled, quantMin, quantMax, out, mask, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFakeQuantPerTensorAffineCachemaskGetWorkspaceSize 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 aclnnFakeQuantPerTensorAffineCachemask.
  ret = aclnnFakeQuantPerTensorAffineCachemask(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFakeQuantPerTensorAffineCachemask 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. Modify based on the specific API definition.
  aclDestroyTensor(self);
  aclDestroyTensor(scale);
  aclDestroyTensor(zeroPoint);
  aclDestroyTensor(out);
  aclDestroyTensor(mask);

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