aclnnSignbit
Applicable Products
- Ascend 950PR&950DT products: Supported
- Atlas A3 products: Supported
- Atlas A2 products: Supported
- Atlas 200I/500 A2 inference products: Not supported
- Atlas inference products: Not supported
- Atlas training products: Supported
Function
-
Description: Determines whether the sign bit of each element in the input self is 1 and returns a Tensor.
-
Formula:
outi=(selfi<0)?[True]:[False](returnsTruewhenselfiis−0)out_i = (self_i < 0) ? [True] : [False] (returns True when self_i is -0)
Function Prototype
Each operator uses a two-phase API. Call the "aclnnSignbitGetWorkspaceSize" API first to obtain the workspace size required for computation and the executor containing the operator computation process. Then call the "aclnnSignbit" API to perform the computation.
aclnnStatus aclnnSignbitGetWorkspaceSize(
const aclTensor *self,
aclTensor *out,
uint64_t *workspaceSize,
aclOpExecutor **executor)
aclnnStatus aclnnSignbit(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)
aclnnSignbitGetWorkspaceSize
-
Parameters:
Parameter Input/Output Description Instruction Data Type Data Format Dimension (shape) Non-contiguous Tensor self (aclTensor*) Input Input tensor. - FLOAT, FLOAT16, BFLOAT16, INT32, UINT32, INT64, UINT64, INT16, UINT16, INT8, UINT8, BOOL, DOUBLE ND Supports up to 8 dimensions. √ out (aclTensor*) Output Output tensor. - BOOL type or a data type that Cast supports converting to Bool ND Same as self - workspaceSize (uint64_t*) Output Returns the size of the workspace to be requested on the Device side. - - - - - executor (aclOpExecutor**) Output Returns the op executor containing the operator computation flow. - - - - - - Atlas training products: The BFLOAT16 data type is not supported.
-
Return value
aclnnStatus: return status 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 self or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data types and dimensions of self and out are not within the supported range. The deduced data type cannot be converted to the type of the specified output out. The shapes of self and out are inconsistent. The dimensions of self and out are greater than 8.
aclnnSignbit
-
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address allocated on the Device. workspaceSize Input Workspace size allocated on the Device, obtained by calling the first-phase API aclnnSignbitGetWorkspaceSize. executor Input op executor, which contains the operator computation flow. stream Input Specifies the Stream for executing tasks. -
Return value
aclnnStatus: return status code. For details, see aclnn Return Codes.
Constraints
- Deterministic computation:
- aclnnSignbit defaults to a deterministic implementation.
Example
The following sample code is for reference only. For details about compilation and execution, see Compile and Run Samples.
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_signbit.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); aclFinalize(); return ret);
ret = aclrtCreateStream(stream);
CHECK_RET(ret == ACL_SUCCESS,
LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret);
aclrtResetDevice(deviceId); aclFinalize(); 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 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 data to 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);
// 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 device/stream. For details, 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 as required by the API.
std::vector<int64_t> selfShape = {4, 2};
std::vector<int64_t> outShape = {4, 2};
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* out = nullptr;
std::vector<double> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
std::vector<uint8_t> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_DOUBLE, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the out aclTensor.
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_BOOL, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. Call the CANN operator library API.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnSignbit.
ret = aclnnSignbitGetWorkspaceSize(self, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSignbitGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
// Request device memory based on the workspaceSize computed 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 aclnnSignbit.
ret = aclnnSignbit(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSignbit 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 to the host. Modify it 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 it based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(out);
// 7. Release device resources. Modify it based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}