aclnnDropoutGenMask
Applicable Products
| Product | Supported |
|---|---|
| √ | |
| √ | |
| √ | |
| × | |
| √ | |
| √ |
Function
During training, a mask is generated based on the probability prob to zero out elements.
Function Prototype
Each operator is divided into a two-phase API. The "aclnnDropoutGenMaskGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnDropoutGenMask" API is called to perform the computation.
aclnnStatus aclnnDropoutGenMaskGetWorkspaceSize(
const aclIntArray* shape,
double prob,
int64_t seed,
int64_t offset,
aclTensor* out,
uint64_t* workspaceSize,
aclOpExecutor** executor)aclnnStatus aclnnDropoutGenMask(
void* workspace,
uint64_t workspaceSize,
aclOpExecutor* executor,
aclrtStream stream)aclnnDropoutGenMaskGetWorkspaceSize
Parameters:
Parameter Input/Output Description Instruction Data Type Data Format Dimension (shape) Non-contiguous Tensor shape (aclIntArray*) Input Indicates the amount of data to be processed. The number of array elements ranges from 1 to 8. INT32, INT64 - 1 - prob (double) Input Probability of setting elements to zero. - - - - - seed (int64_t) Input Random seed that affects the generated random number sequence. - - - - - offset (int64_t) Input. Offset of the random number, which affects the position in the generated random number sequence. - - - - - out (aclTensor*) Output Output tensor. Mask data of bit type stored in UINT8 format. The shape must be (align(number of input elements, 128) / 8). UINT8 ND 1 √ workspaceSize (uint64_t*) Output Returns the workspace size to be applied on the Device side. - - - - - executor（aclOpExecutor**） Output Returns the op executor, which includes the operator computation flow. - - - - - Atlas training products : The data type BFLOAT16 is 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 Code Error Code Description ACLNN_ERR_PARAM_NULLPTR 161001 The input shape or out is a null pointer. 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.
aclnnDropoutGenMask
Parameters:
Parameter Input/Output Description workspace Input Address of the workspace memory applied on the Device side. workspaceSize Input Size of the workspace applied on the Device side, obtained from the first-phase API aclnnDropoutGenMaskGetWorkspaceSize. 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:
- aclnnDropoutGenMask 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 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];
}
// 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/stream. For details, see the list of external ACL APIs.
// 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 = {4, 2};
std::vector<int64_t> outShape = {4, 2};
std::vector<int64_t> maskOutShape = {16};
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
void* maskOutDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* out = nullptr;
aclTensor* maskOut = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
std::vector<float> outHostData(8, 0);
std::vector<uint8_t> maskOutHostData(16, 0);
double p = 0.5;
int64_t seed = 1234;
int64_t offset = 0;
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 out aclTensor.
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the maskOut aclTensor.
ret = CreateAclTensor(maskOutHostData, maskOutShape, &maskOutDeviceAddr, aclDataType::ACL_UINT8, &maskOut);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. Call aclnnDropoutGenMask to generate the mask.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnDropoutGenMask.
ret = aclnnDropoutGenMaskGetWorkspaceSize(shapeArray, p, seed, offset, maskOut, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnDropoutGenMaskGetWorkspaceSize 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 aclnnDropoutGenMask.
ret = aclnnDropoutGenMask(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnDropoutGenMask failed. ERROR: %d\n", ret); return ret);
// 4. (Boilerplate) Synchronously wait for the 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. Modify this 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 aclScalar. Modify based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(out);
aclDestroyTensor(maskOut);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(outDeviceAddr);
aclrtFree(maskOutDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}