aclnnCdist
Applicable Products
| Product | Supported |
|---|---|
| √ | |
| √ | |
| √ | |
| × | |
| × | |
| × |
Function
Operator function: Computes the p-norm distance between each pair of points in two vector sets.
Formula:
Function Prototype
Each operator is divided into a two-phase API. The "aclnnCdistGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnCdist" API is called to perform the computation.
aclnnStatus aclnnCdistGetWorkspaceSize(
const aclTensor* x1,
const aclTensor* x2,
float p,
int64_t compute_mode,
aclTensor *out,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnCdist(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnCdistGetWorkspaceSize
Parameters:
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 grad, x1, x2, or cdist is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of x1, x2, or out is not within the supported range. The data types of x1 or x2 and out are inconsistent. The dimension of x1, x2, or out is not within the supported range. The point feature dimension of x1 is inconsistent with that of x2. p is negative or NaN.
aclnnCdist
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 through the first-phase API aclnnInplaceAddGetWorkspaceSize. executor Input Operator executor, which contains the operator computation flow. stream Input Specifies the stream that executes the task. Return value
aclnnStatus: return code. For details, see aclnn Return Codes.
Constraints
Deterministic computation:
- aclnnCdist 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_cdist.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 allocate memory on the device side.
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 the host side to the 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 the device/stream. Refer to the ACL API manual.
// Set 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> x1Shape = {3, 2};
std::vector<int64_t> x2Shape = {2, 2};
std::vector<int64_t> outShape = {3, 2};
void* x1DeviceAddr = nullptr;
void* x2DeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* x1 = nullptr;
aclTensor* x2 = nullptr;
aclTensor* out = nullptr;
std::vector<float> x1HostData = {0.9041, 0.0196, -0.3108, -2.4423, -0.4821, 1.059};
std::vector<float> x2HostData = {-2.1763, -0.4713, -0.6986, 1.3702};
std::vector<float> outHostData = {3.1193, 2.0959, 2.7138, 3.8322, 2.2830, 0.3791};
float p = 2.0f;
int64_t compute_mode = 2;
// Create the x1 aclTensor.
ret = CreateAclTensor(x1HostData, x1Shape, &x1DeviceAddr, aclDataType::ACL_FLOAT, &x1);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the x2 aclTensor.
ret = CreateAclTensor(x2HostData, x2Shape, &x2DeviceAddr, aclDataType::ACL_FLOAT, &x2);
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);
// 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 aclnnCdist.
ret = aclnnCdistGetWorkspaceSize(x1, x2, p, compute_mode, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCdistGetWorkspaceSize 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 aclnnCdist.
ret = aclnnCdist(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCdist 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(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(x1);
aclDestroyTensor(x2);
aclDestroyTensor(out);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(x1DeviceAddr);
aclrtFree(x2DeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}