aclnnInplaceRandomTensor
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: not supported
Function
Fills the selfRef tensor with numbers sampled from a discrete uniform distribution over [from, to-1].
Function Prototype
Each operator uses a two-phase API. You must first call the "aclnnInplaceRandomTensorGetWorkspaceSize" API to obtain the workspace size required for computation and the executor containing the operator computation process, and then call the "aclnnInplaceRandomTensor" API to perform the computation.
aclnnStatus aclnnInplaceRandomTensorGetWorkspaceSize(
const aclTensor* selfRef,
int64_t from,
int64_t to,
const aclTensor* seedTensor,
const aclTensor* offsetTensor,
int64_t offset,
uint64_t* workspaceSize,
aclOpExecutor** executor)
aclnnStatus aclnnInplaceRandomTensor(
void* workspace,
uint64_t workspaceSize,
aclOpExecutor* executor,
aclrtStream stream)
aclnnInplaceRandomTensorGetWorkspaceSize
-
Parameters:
Parameter Input/Output Description Instruction Data Type Data Format Dimensions (shape) Non-contiguous Tensor selfRef Input/Output Input and output tensor. Supports empty tensor use cases. BFLOAT16, FLOAT16, FLOAT32, DOUBLE, INT32, INT64, INT16, INT8, UINT8, BOOL, COMPLEX64, COMPLEX128 ND 0-8 √ from Input Lower bound of the discrete uniform distribution. The value of from must be within the value range of the selfRef data type and less than the value of to. INT64 - - - to Input Right bound of the discrete uniform distribution. The value of to-1 must be within the value range of the selfRef data type. INT64 - - - seedTensor Input Sets the seed value of the random number generator, affecting the generated random number sequence. - INT64 ND 1 × offsetTensor Input Represents the offset of random numbers. It affects the position of the generated random number sequence. After the offset is set, the generated random number sequence starts from the specified position. The accumulated result with the scalar offset is used as the offset of the random number operator. INT64 ND 1 × offset Input Serves as the accumulation amount of offsetTensor. - INT64 - - - workspaceSize Output Size of the workspace that the user needs to request on the Device. - - - - - executor Output Returns the op executor, which contains the operator computation process. - - - - -
- Ascend 950PR&950DT products: COMPLEX64 and COMPLEX128 are 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 The selfRef passed in is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of selfRef is not within the supported range. The value of from is greater than or equal to the value of to. The shape of selfRef, seedTensor, or offsetTensor exceeds 8 dimensions.
aclnnInplaceRandomTensor
-
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address on the Device side. workspaceSize Input Workspace memory size on the Device side, obtained by the first-phase API aclnnInplaceRandomTensorGetWorkspaceSize. executor Input Op executor containing the operator calculation process. stream Input Specifies the Stream for task execution. -
Return value
aclnnStatus: return status code. For details, see aclnn Return Codes.
Constraints
- Deterministic computation:
- aclnnInplaceRandomTensor defaults to a deterministic implementation.
- Ascend 950PR&950DT products:
- When the PyTorch-aligned mode is set through aclnnSetPytorchRandom, offset must be a multiple of 4.
- from must be less than to, and the range specified by from/to-1 must not exceed the range of the self data type.
Example
Sample code is as follows 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_random.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 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 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 the 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 aclCreateTensor 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. 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. Custom construction is required based on the API definition.
std::vector<int64_t> selfShape = {4, 2};
std::vector<int64_t> seedShape = {1};
std::vector<int64_t> offsetShape = {1};
void* selfDeviceAddr = nullptr;
aclTensor* self = nullptr;
void* seedDeviceAddr = nullptr;
aclTensor* seed = nullptr;
void* offsetDeviceAddr = nullptr;
aclTensor* offset = nullptr;
int64_t offset2 = 100;
std::vector<float> selfHostData = {1, 2, 3, 4, 5, 6, 7, 8};
std::vector<int64_t> seedHostData = {0};
std::vector<int64_t> offsetHostData = {392};
int64_t from = 0;
int64_t to = 10;
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the seed aclTensor.
ret = CreateAclTensor(seedHostData, seedShape, &seedDeviceAddr, aclDataType::ACL_INT64, &seed);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the offset aclTensor.
ret = CreateAclTensor(offsetHostData, offsetShape, &offsetDeviceAddr, aclDataType::ACL_INT64, &offset);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. Call the CANN operator library API. Replace it with the specific API name.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnInplaceRandomTensor.
ret = aclnnInplaceRandomTensorGetWorkspaceSize(self, from, to, seed, offset, offset2, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceRandomTensorGetWorkspaceSize 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 aclnnInplaceRandomTensor.
ret = aclnnInplaceRandomTensor(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceRandomTensor 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. Copy the result from device memory to host memory. Modify it based on the specific API definition.
auto size = GetShapeSize(selfShape);
std::vector<float> resultData(size, 0);
ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), selfDeviceAddr,
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(self);
aclDestroyTensor(seed);
aclDestroyTensor(offset);
// 7. Release Device resources. Modify based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(seedDeviceAddr);
aclrtFree(offsetDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}