aclnnComplex
Applicable Products
| Product | Supported |
|---|---|
| โ | |
| โ | |
| โ | |
| โ | |
| โ | |
| โ |
Function
Description: Inputs two tensors, real and imag, with the same shape and data type, representing the real and imaginary parts of a complex number, and returns a complex tensor: out.
Formula:
Function Prototype
Each operator is divided into a two-phase API. The "aclnnComplexGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnComplex" API is called to perform the computation.
aclnnStatus aclnnComplexGetWorkspaceSize(
const aclTensor* real,
const aclTensor* imag,
aclTensor* out,
uint64_t* workspaceSize,
aclOpExecutor** executor)aclnnStatus aclnnComplex(
void* workspace,
uint64_t workspaceSize,
aclOpExecutor* executor,
aclrtStream stream)aclnnComplexGetWorkspaceSize
Parameters:
Atlas A3 training products/Atlas A3 inference products : The Output data type supports COMPLEX64 (input can only be FLOAT), COMPLEX32 (input can only be FLOAT16), and COMPLEX128 (input can only be DOUBLE).
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 real, imag, or out pointer passed in is null. ACLNN_ERR_PARAM_INVALID 161002 The data type and data format of real and imag are not within the supported range. The shapes of real and imag cannot be broadcast. The number of dimensions of real and imag exceeds 8. The data types of real and imag are different.
aclnnComplex
Parameters:
Parameter Input/Output Description workspace Input Address of the workspace memory applied for on the device side. workspaceSize Input Size of the workspace applied for on the device side, obtained through the first-phase API aclnnComplexGetWorkspaceSize. executor Input Operator executor, which contains the operator computation flow. stream Input Specifies the stream for executing tasks. Return value
aclnnStatus: return code. For details, see aclnn Return Codes.
Constraints
Deterministic computation:
- aclnnComplex 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 <complex>
#include "acl/acl.h"
#include "aclnnop/aclnn_complex.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 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 data from host-side memory 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 strides for 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 the input and output. Custom construction is required based on the API.
std::vector<int64_t> realShape = {4, 2};
std::vector<int64_t> imagShape = {4, 2};
std::vector<int64_t> outShape = {4, 2};
void* realDeviceAddr = nullptr;
void* imagDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* real = nullptr;
aclTensor* imag = nullptr;
aclTensor* out = nullptr;
std::vector<float> realHostData = {0, 1, 2, 3, 4, 5, 6, 7};
std::vector<float> imagHostData = {1, 1, 1, 2, 2, 2, 3, 3};
std::vector<std::complex<float>> outHostData(8, 0);
// Create the real aclTensor.
ret = CreateAclTensor(realHostData, realShape, &realDeviceAddr, aclDataType::ACL_FLOAT, &real);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the imag aclTensor.
ret = CreateAclTensor(imagHostData, imagShape, &imagDeviceAddr, aclDataType::ACL_FLOAT, &imag);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the out aclTensor.
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_COMPLEX64, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. Call the CANN operator library API. Replace with the actual API name.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnComplex.
ret = aclnnComplexGetWorkspaceSize(real, imag, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnComplexGetWorkspaceSize 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 aclnnComplex.
ret = aclnnComplex(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnComplex 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 device memory to the host side. Modify 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(real);
aclDestroyTensor(imag);
aclDestroyTensor(out);
// 7. Release device resources.
aclrtFree(realDeviceAddr);
aclrtFree(imagDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}