aclnnInplaceMaskedFillScalar
Applicable Products
| Product | Supported |
|---|---|
| √ | |
| √ | |
| √ | |
| × | |
| √ | |
| √ |
Function
Description: Fills the elements in selfRef that correspond to positions where the mask matrix value is true with value.
Formula:
Function Prototype
Each operator consists of a two-phase API. You must first call the "aclnnInplaceMaskedFillScalarGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnInplaceMaskedFillScalar" API to perform the computation.
aclnnStatus aclnnInplaceMaskedFillScalarGetWorkspaceSize(
aclTensor *selfRef,
const aclTensor *mask,
const aclScalar *value,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnInplaceMaskedFillScalar(
void* workspace,
uint64_t workspace_size,
aclOpExecutor* executor,
aclrtStream stream)aclnnInplaceMaskedFillScalarGetWorkspaceSize
Parameters
Atlas inference products ,Atlas training products : The BFLOAT16 data type is not supported for selfRef and value.
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 Error Code Description ACLNN_ERR_PARAM_NULLPTR 161001 The passed selfRef, mask, and value are null pointers. ACLNN_ERR_PARAM_INVALID 161002 The data type or data format of selfRef or mask is not within the supported range. The shapes of selfRef and mask cannot be broadcast. The data type of value cannot be converted to the data type of selfRef.
aclnnInplaceMaskedFillScalar
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 from the first-phase API aclnnInplaceMaskedFillScalarGetWorkspaceSize. 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:
- aclnnInplaceMaskedFillScalar 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_masked_fill_scalar.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 allocate 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. Refer to the acl API manual.
// Enter 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 the input and output. Custom construction is required based on the API.
std::vector<int64_t> selfRefShape = {4, 2};
std::vector<int64_t> maskShape = {4, 2};
void* selfRefDeviceAddr = nullptr;
void* maskDeviceAddr = nullptr;
aclTensor* selfRef = nullptr;
aclTensor* mask = nullptr;
aclScalar* value = nullptr;
std::vector<float> selfHostData = {1.1, 1.1, 1.1, 1.1, 1.1, 1.1, 1.1, 1.1};
std::vector<char> maskHostData = {0, 0, 0, 0, 1, 1, 1, 1};
float valueVal = 2.2f;
// Create the selfRef aclTensor.
ret = CreateAclTensor(selfHostData, selfRefShape, &selfRefDeviceAddr, aclDataType::ACL_FLOAT, &selfRef);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the mask aclTensor.
ret = CreateAclTensor(maskHostData, maskShape, &maskDeviceAddr, aclDataType::ACL_BOOL, &mask);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the value aclScalar.
value = aclCreateScalar(&valueVal, aclDataType::ACL_FLOAT);
CHECK_RET(value != nullptr, 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 aclnnInplaceMaskedFillScalar.
ret = aclnnInplaceMaskedFillScalarGetWorkspaceSize(selfRef, mask, value, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceMaskedFillScalarGetWorkspaceSize 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 aclnnInplaceMaskedFillScalar.
ret = aclnnInplaceMaskedFillScalar(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceMaskedFillScalar 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(selfRefShape);
std::vector<float> resultData(size, 0);
ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfRefDeviceAddr,
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(selfRef);
aclDestroyTensor(mask);
aclDestroyScalar(value);
// 7. Release device resources.
aclrtFree(selfRefDeviceAddr);
aclrtFree(maskDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}