aclnnRemainderScalarTensor
Applicable Products
| Product | Supported |
|---|---|
| โ | |
| โ | |
| โ | |
| ร | |
| ร | |
| โ |
Function
Description: After broadcasting the scalar self into a tensor of the same shape as the tensor other, each element is converted to the remainder obtained by dividing it by the corresponding element of other. The result has the same sign as the divisor other, and its absolute value is less than the absolute value of other.
Formula: The actual computation of remainder(self, other) is equivalent to the following formula:
Example:
self = 5.0 # float other = tensor([[-1, -2], [-3, -4]]).type(int32) result = remainder(self, other) # Value of result # tensor([[ 0., -1.], # [-1., -3.]]) float # For the element -4 in other, the calculation result is 5 - floor(5 / -4) * -4 = -3 # As can be seen, the absolute value of the final result -3 is less than the absolute value of the original -4.
Function Prototype
Each operator is divided into a two-phase API. The "aclnnRemainderScalarTensorGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnRemainderScalarTensor" API is called to perform the computation.
aclnnStatus aclnnRemainderScalarTensorGetWorkspaceSize(
const aclScalar* self,
const aclTensor* other,
aclTensor* out,
uint64_t* workspaceSize,
aclOpExecutor** executor)aclnnStatus aclnnRemainderScalarTensor(
void* workspace,
uint64_t workspaceSize,
aclOpExecutor* executor,
aclrtStream stream)aclnnRemainderScalarTensorGetWorkspaceSize
Parameters:
Atlas training products : BFLOAT16 data type is not supported.
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 passed self, other, or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The shapes of other and out are different. Data type deduction cannot be performed on self and other. The data type deduced from self and other is not a supported data type. The data type deduced from self and other cannot be converted to the specified output out type. The number of dimensions of other or out exceeds 8.
aclnnRemainderScalarTensor
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 from the first-phase API aclnnRemainderScalarTensorGetWorkspaceSize. 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:
- aclnnRemainderScalarTensor defaults to a deterministic implementation.
When the data type of self is INT32, functionality and precision within the range [-2^24, 2^24] are prioritized.
When other is 0 and the data type of self is an integer type, the result in out is self.
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_remainder.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 apply for 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 the 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. Refer to 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. Customize the construction based on the API.
std::vector<int64_t> otherShape = {3, 3};
std::vector<int64_t> outShape = {3, 3};
void* otherDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclScalar* self = nullptr;
aclTensor* other = nullptr;
aclTensor* out = nullptr;
std::vector<int64_t> otherHostData = {0, 1, 2, 3, 4, 5, 6, 7, 8};
std::vector<int64_t> outHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0};
int64_t Self = 3;
// Create the self aclScalar.
self = aclCreateScalar(&Self, aclDataType::ACL_INT64);
CHECK_RET(self != nullptr, return ret);
// Create the other aclTensor.
ret = CreateAclTensor(otherHostData, otherShape, &otherDeviceAddr, aclDataType::ACL_INT64, &other);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the out aclTensor.
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_INT64, &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 aclnnRemainderScalarTensor.
ret = aclnnRemainderScalarTensorGetWorkspaceSize(self, other, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnRemainderScalarTensorGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
// Apply for 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 aclnnRemainderScalarTensor.
ret = aclnnRemainderScalarTensor(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnRemainderScalarTensor 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 side to the host side. Modify based on the specific API definition.
auto size = GetShapeSize(outShape);
std::vector<int64_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: %ld\n", i, resultData[i]);
}
// 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
aclDestroyScalar(self);
aclDestroyTensor(other);
aclDestroyTensor(out);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(otherDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}