aclnnDropoutGenMaskV2Tensor
Applicable Products
| Product | Supported |
|---|---|
| × | |
| √ | |
| √ | |
| × | |
| × | |
| × |
Function
During training, a mask is generated based on the probability prob to zero out elements.
Function Prototype
Each operator consists of a two-phase API. You must first call the "aclnnDropoutGenMaskV2TensorGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that encapsulates the operator computation process, and then call the "aclnnDropoutGenMaskV2Tensor" API to perform the computation.
aclnnStatus aclnnDropoutGenMaskV2TensorGetWorkspaceSize(
const aclIntArray* shape,
double prob,
const aclTensor* seedTensor,
const aclTensor* offsetTensor,
int64_t offset,
aclDataType probDataType,
aclTensor* out,
uint64_t* workspaceSize,
aclOpExecutor** executor)aclnnStatus aclnnDropoutGenMaskV2Tensor(
void* workspace,
uint64_t workspaceSize,
aclOpExecutor* executor,
aclrtStream stream)aclnnDropoutGenMaskV2TensorGetWorkspaceSize
Parameters:
Parameter Input/Output Description Instruction Data Type Data Format Dimension (shape) Non-Contiguous Tensor shape (aclIntArray*) Input Indicates the number of input elements, corresponding to the number of elements of input in the shape calculation formula of the output tensor. - - - - - prob（double） Input Probability of an element being zeroed. The value range is [0, 1]. DOUBLE - - - seedTensor (aclTensor*) Input Sets the seed value for the random number generator, which affects the generated random number sequence. - INT64 ND The shape is [1]. √ offsetTensor (aclTensor*) Input The accumulation result with the scalar offset serves as the offset for the random number operator, which affects the position in the generated random number sequence. - INT64 ND Shape is [1]. √ offset (int64_t) Input Accumulation amount for offsetTensor. - INT64 - - - probDataType (aclDataType) Input Indicates the data type of the input tensor. - FLOAT, FLOAT16, BFLOAT16 - - - out（aclTensor*） Output Output tensor. Mask data of bit type stored in UINT8 format. - UINT8 ND The shape must be (align(number of elements in input, 128) / 8). √ workspaceSize (uint64_t*) Output Returns the workspace size to be allocated on the Device side. - - - - - executor (aclOpExecutor**) Output Returns the operator executor, which includes the operator computation process. - - - - - 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 The input shape and out are null pointers. ACLNN_ERR_PARAM_INVALID 161002 The data type of out is not within the supported range. The value of prob is not between 0 and 1. The shape of out does not meet the condition.
aclnnDropoutGenMaskV2Tensor
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 through the first-phase API aclnnDropoutGenMaskV2TensorGetWorkspaceSize. executor Input Operator executor that contains the operator computation process. stream Input Specifies the stream that executes the task. Return value
aclnnStatus: return code. For details, see aclnn Return Codes.
Constraints
Deterministic computation:
- aclnnDropoutGenMaskV2Tensor 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_dropout_gen_mask.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 data from the host to the device 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);
// 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. See the ACL API manual.
// Fill in the deviceId 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 inputs and outputs. Customize the construction based on the API.
std::vector<int64_t> selfShape = {2, 2};
std::vector<int64_t> seedShape = {1};
std::vector<int64_t> offsetShape = {1};
std::vector<int64_t> outShape = {16};
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* out = nullptr;
void* seedDeviceAddr = nullptr;
aclTensor* seed = nullptr;
void* offsetDeviceAddr = nullptr;
aclTensor* offset = nullptr;
int64_t offset2 = 102;
std::vector<float> selfHostData = {0, 0, 0, 0};
std::vector<uint8_t> outHostData(16, 0);
std::vector<int64_t> seedHostData = {0};
std::vector<int64_t> offsetHostData = {392};
double p = 0.5;
aclDataType probDataType = aclDataType::ACL_FLOAT;
aclIntArray* shapeArray = aclCreateIntArray(selfShape.data(), 2);
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the seed aclTensor.
ret = CreateAclTensor(seedHostData, seedShape, &seedDeviceAddr, aclDataType::ACL_INT64, &seed);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the offset aclTensor.
ret = CreateAclTensor(offsetHostData, offsetShape, &offsetDeviceAddr, aclDataType::ACL_INT64, &offset);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the out aclTensor.
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_UINT8, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. Call aclnnDropoutGenMaskV2Tensor to generate the mask.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnDropoutGenMaskV2Tensor.
ret = aclnnDropoutGenMaskV2TensorGetWorkspaceSize(shapeArray, p, seed, offset, offset2, probDataType, out, &workspaceSize,
&executor);
CHECK_RET(ret == ACL_SUCCESS,
LOG_PRINT("aclnnDropoutGenMaskV2TensorGetWorkspaceSize 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 aclnnDropoutGenMaskV2Tensor.
ret = aclnnDropoutGenMaskV2Tensor(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnDropoutGenMaskV2Tensor 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<uint8_t> 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 based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(seed);
aclDestroyTensor(offset);
aclDestroyTensor(out);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(seedDeviceAddr);
aclrtFree(offsetDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}