aclnnInplaceZero
Applicable Products
| Product | Supported |
|---|---|
| √ | |
| √ | |
| √ | |
| × | |
| √ | |
| √ |
Function
Description: Fills the selfRef tensor with zeros.
Formula:
Example:
Input selfRef： tensor([[1, 2], [3, 4]]) OutputselfRef： tensor([[0, 0], [0, 0]])
Function Prototype
Each operator uses a two-phase API. You must first call the "aclnnInplaceZeroGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the computation process, and then call the "aclnnInplaceZero" API to perform the computation.
aclnnStatus aclnnInplaceZeroGetWorkspaceSize(
aclTensor *selfRef,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnInplaceZero(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnInplaceZeroGetWorkspaceSize
Parameters
Parameter Input/Output Description Instruction Data Type Data Format Dimension (shape) Non-contiguous Tensor selfRef Input/Output selfRef in the formula. - INT8, INT32, INT64, UINT8, FLOAT16, FLOAT32, BOOL, DOUBLE, INT16, UINT16, COMPLEX128, COMPLEX64, BFLOAT16, FLOAT8_E5M2, FLOAT8_E4M3FN, HIFLOAT8, FLOAT4_E1M2, FLOAT4_E2M1 ND - √ workspaceSize Output Returns the workspace size to be requested on the Device side. - - - - - executor Output Returns the op executor, which contains the operator computation flow. - - - - - Atlas inference products ,Atlas training products : Supports the following data types: INT8, INT32, INT64, UINT8, FLOAT16, FLOAT32, BOOL, DOUBLE, INT16, UINT16, COMPLEX128, COMPLEX64.Atlas A2 training products/Atlas A2 inference products ,Atlas A3 training products/Atlas A3 inference products : Supports the following data types: INT8, INT32, INT64, UINT8, FLOAT16, FLOAT32, BOOL, DOUBLE, INT16, UINT16, COMPLEX128, COMPLEX64, BFLOAT16.Ascend 950PR/Ascend 950DT : Supports the following data types: INT8, INT32, INT64, UINT8, FLOAT16, FLOAT32, BOOL, DOUBLE, INT16, UINT16, COMPLEX128, COMPLEX64, BFLOAT16, FLOAT8_E5M2, FLOAT8_E4M3FN, HIFLOAT8, FLOAT4_E1M2, FLOAT4_E2M1.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 input selfRef is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of selfRef is not within the supported range.
aclnnInplaceZero
Parameters
Parameter Input/Output Description workspace Input The workspace memory address applied for on the Device side. workspaceSize Input The workspace size applied for on the Device side, obtained through the first-phase API aclnnInplaceZeroGetWorkspaceSize. 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:
- aclnnInplaceZero 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_zero.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 shape_size = 1;
for (auto i : shape) {
shape_size *= i;
}
return shape_size;
}
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 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 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.
// Fill in the deviceId based on your actual device.
int32_t deviceId = 0;
aclrtStream stream;
auto ret = Init(deviceId, &stream);
// Handle the check based on your needs.
CHECK_RET(ret == 0, 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};
void* selfRefDeviceAddr = nullptr;
aclTensor* selfRef = nullptr;
std::vector<float> selfRefHostData = {0, 1, 2, 3, 4, 5, 6, 7};
// Create the selfRef aclTensor.
ret = CreateAclTensor(selfRefHostData, selfRefShape, &selfRefDeviceAddr, aclDataType::ACL_FLOAT, &selfRef);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. Call the CANN operator library API. Modify to the specific API as needed.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnInplaceZero.
ret = aclnnInplaceZeroGetWorkspaceSize(selfRef, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceZeroGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
// Allocate 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 aclnnInplaceZero.
ret = aclnnInplaceZero(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceZero failed. ERROR: %d\n", ret); return ret);
// 4. (Boilerplate) Synchronously 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(float),
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);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(selfRefDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}