aclnnAdaptiveMaxPool2d
Applicable Products
| Product | Supported |
|---|---|
| √ | |
| √ | |
| √ | |
| × | |
| × | |
| √ |
Function
Computes the kernel size for each operation based on the input outputSize, performs 2D max pooling on the input self, and outputs the pooled values out and indices indices. The difference between aclnnAdaptiveMaxPool2d and aclnnMaxPool2d is that you only need to specify the outputSize, and the pooling regions are divided according to the outputSize.
Function Prototype
Each operator is divided into a two-phase API. The "aclnnAdaptiveMaxPool2dGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnAdaptiveMaxPool2d" API is called to perform the computation.
aclnnStatus aclnnAdaptiveMaxPool2dGetWorkspaceSize(
const aclTensor *self,
const aclIntArray *outputSize,
aclTensor *outputOut,
aclTensor *indicesOut,
uint64_t *workspaceSize,
aclOpExecutor **executor)aclnnStatus aclnnAdaptiveMaxPool2d(
void *workspace,
uint64_t workspaceSize,
aclOpExecutor *executor,
aclrtStream stream)aclnnAdaptiveMaxPool2dGetWorkspaceSize
Parameters:
Parameter Input/Output Description Instruction Data Type Data Format Dimension (Shape) Non-Contiguous Tensor self Input The tensor to be computed. Must have the same data type as outputOut. FLOAT32, FLOAT16, BFLOAT16, DOUBLE NCHW, NCL, NHWC 3-4 √ outputSize Input Specifies the spatial size of the output in the H and W dimensions. An INT32 array of length 2, where each element must be greater than or equal to 0. INT32 - - - outputOut Output The result after pooling. Has the same data type as self, and the same shape as indicesOut. FLOAT32, FLOAT16, BFLOAT16, DOUBLE NCHW, NCL, NHWC 3-4 √ indicesOut Output Index position of the outputOut element in the input self. The shape is consistent with outputOut. INT64 NCHW, NCL, NHWC 3-4 √ workspaceSize Output Returns the workspace size to be requested on the Device side. - - - - - executor Output Returns the operator 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 Code Error Code Description ACLNN_ERR_PARAM_NULLPTR 161001 The passed self, outputSize, outputOut, or indicesOut is a null pointer. ACLNN_ERR_PARAM_INVALID 161002 The data type of self is not within the supported range. The data types of self and outputOut are inconsistent. The data type of indicesOut is not int64. The shape of self is not 3D or 4D. The size of self in a non-first dimension is less than 1. The shapes of outputOut and indicesOut are inconsistent. The size of outputSize is not equal to 2. An element value in outputSize is less than or equal to 0. The shape of outputOut does not match the actual output shape. The format of self is not NCHW, NHWC, or NCL. ACLNN_ERR_INNER_NULLPTR 561103 An internal API validation error, typically caused by input data or attribute specifications that are outside the supported range.
aclnnAdaptiveMaxPool2d
Parameters:
Parameter Input/Output Description workspace Input Workspace memory address applied for on the device. workspaceSize Input Workspace size applied for on the device, obtained from the first-phase API aclnnAdaptiveMaxPool2dGetWorkspaceSize. executor Input Operator executor, which contains the operator computation flow. stream Input Specifies the stream for task execution. Return value
aclnnStatus: return code. For details, see aclnn Return Code.
Constraints
Deterministic computation:
- aclnnAdaptiveMaxPool2d defaults to a deterministic implementation.
Shape description:
self.shape = (N, C, Hin, Win) or (C, Hin, Win) or (N, Hin, Win, C)
outputSize = [Hout, Wout]
outputOut.shape = (N, C, Hout, Wout) or (C, Hout, Wout) or (N, Hout, Wout, C)
indicesOut.shape = (N, C, Hout, Wout) or (C, Hout, Wout) or (N, Hout, Wout, C)
Example
The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.
#include <cstdio>
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_adaptive_max_pool2d.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 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 host-side data to 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);
// 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_NCHW,
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. Custom construction is required based on the API.
std::vector<int64_t> selfShape = {1, 1, 4, 4};
std::vector<int64_t> outShape = {1, 1, 2, 2};
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
void* indDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* out = nullptr;
aclTensor* indices = nullptr;
std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7,
8, 9, 10, 11, 12, 13, 14, 15};
std::vector<float> outHostData = {0, 0, 0, 0.0};
std::vector<int64_t> indicesHostData = {0, 0, 0, 0};
// Create the self aclTensor.
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
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 indices aclTensor.
ret = CreateAclTensor(indicesHostData, outShape, &indDeviceAddr, aclDataType::ACL_INT64, &indices);
CHECK_RET(ret == ACL_SUCCESS, return ret);
std::vector<int64_t> arraySize = {2, 2};
const aclIntArray *outputSize = aclCreateIntArray(arraySize.data(), arraySize.size());
CHECK_RET(outputSize != nullptr, return ACL_ERROR_INTERNAL_ERROR);
// 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 aclnnAdaptiveMaxPool2d.
ret = aclnnAdaptiveMaxPool2dGetWorkspaceSize(self, outputSize, out, indices, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdaptiveMaxPool2dGetWorkspaceSize 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 aclnnAdaptiveMaxPool2d.
ret = aclnnAdaptiveMaxPool2d(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdaptiveMaxPool2d failed. ERROR: %d\n", ret); return ret);
// 4. (Boilerplate) Synchronize and wait for task completion.
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 this step based on the specific API definition.
auto size = GetShapeSize(outShape);
std::vector<float> outData(size, 0);
std::vector<int64_t> indicesData(size, 0);
ret = aclrtMemcpy(outData.data(), outData.size() * sizeof(outData[0]), outDeviceAddr,
size * sizeof(outData[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);
ret = aclrtMemcpy(indicesData.data(), indicesData.size() * sizeof(indicesData[0]), indDeviceAddr,
size * sizeof(indicesData[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("out[%ld] is: %f\n", i, outData[i]);
}
for (int64_t i = 0; i < size; i++) {
LOG_PRINT("indices[%ld] is: %ld\n", i, indicesData[i]);
}
// 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
aclDestroyTensor(self);
aclDestroyTensor(out);
aclDestroyTensor(indices);
aclDestroyIntArray(outputSize);
// 7. Release device resources.
aclrtFree(selfDeviceAddr);
aclrtFree(outDeviceAddr);
aclrtFree(indDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}