aclnnIndexFill&aclnnInplaceIndexFill
Applicable Products
| Product | Supported |
|---|---|
| × | |
| √ | |
| √ | |
| × | |
| × | |
| × |
Function
Description: Replaces the values at the positions specified by index along the given axis dim of the input self with value. The computation is deterministic.
Example: The input self is:
[[1, 2, 3], [4, 5, 6], [7, 8, 9]]If dim = 0, index = [0, 2], and value = 0, the operator's computation result is:
[[0, 0, 0], [4, 5, 6], [0, 0, 0]]If dim = 1, index = [0, 2], and value = 0, the operator's computation result is:
[[0, 2, 0], [0, 5, 0], [0, 8, 0]]
Function Prototype
aclnnIndexFill and aclnnInplaceIndexFill implement the same function. The differences in usage are as follows. Select the appropriate operator based on your actual scenario.
aclnnIndexFill: Create a new output tensor object to store the computation result.
aclnnInplaceIndexFill: No need to create a new output tensor object. The computation result is stored directly in the memory of the input tensor.
Each operator is divided into a two-phase API. You must first call the "aclnnIndexFillGetWorkspaceSize" or "aclnnInplaceIndexFillGetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnIndexFill" or "aclnnInplaceIndexFill" API to execute the computation.
aclnnStatus aclnnIndexFillGetWorkspaceSize(
const aclTensor* self,
int64_t dim,
const aclTensor* index,
const aclScalar* value,
aclTensor* out,
uint64_t* workspaceSize,
aclOpExecutor** executor)aclnnStatus aclnnIndexFill(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnStatus aclnnInplaceIndexFillGetWorkspaceSize(
aclTensor* selfRef,
int64_t dim,
const aclTensor* index,
const aclScalar* value,
uint64_t* workspaceSize,
aclOpExecutor** executor)aclnnStatus aclnnInplaceIndexFill(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnIndexFillGetWorkspaceSize
Parameters
Parameter Input/Output Description Instruction Data Type Data Format Dimension (Shape) Non-contiguous Tensor self Input The self in the function example, i.e., the tensor whose values at specified positions are to be replaced with value. - FLOAT16, FLOAT, INT32, INT64, BOOL, BFLOAT16 ND 0-8 √ dim Input Specifies the dimension along which self is to be filled. When self is 1-8 dimensional, the value range of dim is [-self.dim(), self.dim()). When self is 0-dimensional, the value range of dim is [-1, 1). int64 - - - index Input Specifies the indices of self to be filled along the dim dimension. Each element value is less than the dimension size of self corresponding to dim. Negative values are supported. Out-of-bounds values are supported and will be skipped directly. INT32, INT64 - - - value Input. Specifies the fill data value. Must be convertible to the data type of self. Consistent with self. - - - out Output Specified output tensor. - Consistent with self. ND Consistent with self. √ workspaceSize Output Returns the workspace size to be applied for on the Device Side. - - - - - executor Output Returns the op executor, which contains the operator computation process. - - - - - Return Value
aclnnStatus: return code. For details, see aclnn Return Code.
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 input self, index, value, or out is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of self, index, or value is not within the supported range. The absolute value of dim exceeds the maximum dimension of self or exceeds 8 dimensions. The shapes of self and out are not equal. The data types of self and out are not equal.
aclnnIndexFill
Parameters
Parameter Input/Output Description workspace Input Address of the workspace memory applied on the Device side. workspaceSize Input Size of the workspace memory applied on the Device side, obtained from the first-phase API aclnnIndexFillGetWorkspaceSize. executor Input Operator executor, which contains the operator computation process. stream Input Specifies the stream for executing the task. Return Value
aclnnStatus: return code. For details, see aclnn Return Code.
aclnnInplaceIndexFillGetWorkspaceSize
Parameters
Parameter Input/Output Description Instruction Data Type Data Format Dimension (Shape) Non-contiguous Tensor selfRef Input Tensor whose values at specified positions are to be replaced with value. - FLOAT16, FLOAT, INT32, INT64, BOOL, BFLOAT16 ND 0-8 √ dim Input Specifies the dimension along which selfRef will be filled. When self is 1-8 dimensional, dim has a value range of [-self.dim(), self.dim()). When self is 0-dimensional, dim has a value range of [-1, 1). int64 - - - index Input Specifies the indices to be filled in self along the dim dimension. The element values are less than the dimension size of self corresponding to dim. Negative numbers are supported. Out-of-bounds values are supported and will be skipped directly. INT32, INT64 - - - value Input. Specifies the data value to fill. - INT32, INT64 - - - workspaceSize Output Returns the workspace size to be allocated on the Device Side. - - - - - Executor Output Returns the operator executor, which contains the operator computation flow. - - - - - Return Value
aclnnStatus: return code. For details, see aclnn Return Code.
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 selfRef, index, or value is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data types of selfRef, index, and value are not within the supported range. The absolute value of dim exceeds the maximum dimension of selfRef or exceeds 8 dimensions.
aclnnInplaceIndexFill
Parameters
Parameter Input/Output Description workspace Input Specifies the workspace memory address applied for on the Device Side. workspaceSize Input Specifies the workspace size applied for on the Device Side, which is obtained by the first-phase API aclnnInplaceIndexFillGetWorkspaceSize. Executor Input Operator executor, which contains the operator computation process. stream Input Specifies the stream for task execution. Return Value
aclnnStatus: return code. For details, see aclnn Return Code.
Constraints
Deterministic computation:
- aclnnIndexFill&aclnnInplaceIndexFill default 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_index_fill.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);
// Copy the host-side data to the device-side memory by calling aclrtMemcpy.
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);
// Calculate 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];
}
// Create an aclTensor by calling aclCreateTensor.
*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.
// 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. Customize the construction based on the API.
std::vector<int64_t> selfShape = {3, 3};
std::vector<int64_t> indexShape = {1};
std::vector<int64_t> outShape = selfShape;
void* selfDeviceAddr = nullptr;
void* indexDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* index = nullptr;
aclScalar* value = nullptr;
aclTensor* out = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7, 8};
std::vector<int> indexHostData = {0};
std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0};
int64_t dim = 1;
float fillVal = 10;
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the index aclTensor.
ret = CreateAclTensor(indexHostData, indexShape, &indexDeviceAddr, aclDataType::ACL_INT64, &index);
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);
// Create the value aclScalar.
value = aclCreateScalar(&fillVal, aclDataType::ACL_FLOAT);
CHECK_RET(value != nullptr, return ret);
// 3. Call the CANN operator library API. Replace with the specific API name.
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// Call the first-phase API of aclnnIndexFill.
ret = aclnnIndexFillGetWorkspaceSize(self, dim, index, value, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnIndexFillGetWorkspaceSize 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 aclnnIndexFill.
ret = aclnnIndexFill(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnIndexFill 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 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 the requested variables. Modify based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(index);
aclDestroyTensor(out);
aclDestroyScalar(value);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(indexDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}aclnnInplaceIndexFillTensor Example:
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_index_fill.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 apply for 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);
// Calculate 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. See the acl API manual.
// Fill in the 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. Customize the construction based on the API.
std::vector<int64_t> selfShape = {3, 3};
std::vector<int64_t> indexShape = {1};
void* selfDeviceAddr = nullptr;
void* indexDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* index = nullptr;
aclScalar* value = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7, 8};
std::vector<int> indexHostData = {0};
int64_t dim = 1;
float fillVal = 10;
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the index aclTensor.
ret = CreateAclTensor(indexHostData, indexShape, &indexDeviceAddr, aclDataType::ACL_INT64, &index);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// Create the value aclScalar.
value = aclCreateScalar(&fillVal, aclDataType::ACL_FLOAT);
CHECK_RET(value != nullptr, 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 aclnnInplaceIndexFill.
ret = aclnnInplaceIndexFillGetWorkspaceSize(self, dim, index, value, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnIndexFillGetWorkspaceSize 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 aclnnInplaceIndexFill.
ret = aclnnInplaceIndexFill(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnInplaceIndexFill 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 memory to the host side. Modify 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 the allocated variables. Modify based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(index);
aclDestroyScalar(value);
// 7. Release device resources. Modify based on the specific API definition.
aclrtFree(selfDeviceAddr);
aclrtFree(indexDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}