aclnnGridSampler3DBackwardBackward
支持的产品型号
- Atlas 训练系列产品。
- Atlas A2训练系列产品/Atlas 800I A2推理产品。
接口原型
每个算子分为两段式接口,必须先调用“aclnnGridSampler3DBackwardGetWorkspaceSize”接口获取计算所需workspace大小以及包含了算子计算流程的执行器,再调用“aclnnGridSampler3DBackward”接口执行计算。
aclnnStatus aclnnGridSampler3DBackwardGetWorkspaceSize(const aclTensor* gradOutput, const aclTensor* input, const aclTensor* grid, int64_t interpolationMode, int64_t paddingMode, bool alignCorners, const aclBoolArray* outputMask, aclTensor* inputGrad, aclTensor* gridGrad, uint64_t* workspaceSize, aclOpExecutor** executor)
aclnnStatus aclnnGridSampler3DBackward(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)
功能描述
- 算子功能:aclnnGridSampler3D的反向传播,完成张量input与张量grid的梯度计算。
aclnnGridSampler3DBackwardGetWorkspaceSize
参数说明:
- gradOutput(aclTensor*, 计算输入):表示反向传播过程中上一层的输出梯度,Device侧的aclTensor。数据类型支持FLOAT16、FLOAT、DOUBLE,且数据类型与input的数据类型一致。支持非连续的Tensor,数据格式支持NCDHW、NDHWC。
- input(aclTensor*, 计算输入):表示输入张量,Device侧的aclTensor。数据类型支持FLOAT16、FLOAT、DOUBLE。支持非连续的Tensor,数据格式支持NCDHW、NDHWC。
- grid(aclTensor*, 计算输入):表示输入归一化的采用像素位置,Device侧的aclTensor。数据类型支持FLOAT16、FLOAT、DOUBLE,且数据类型与input数据类型一致。支持非连续的Tensor,数据格式支持NCDHW、NDHWC。
- interpolationMode(int64_t, 计算输入):表示计算输出的插值模式,Host侧的整型。支持0('bilinear') | 1('nearest')。
- paddingMode(int64_t, 计算输入):表示grid范围外填充模式,Host侧的整型。即当grid有超过[-1, 1]范围的值,则按照paddingMode定义的方式处理相应的输出,支持0('zeros') | 1('border') | 2('reflection')。
- alignCorners(bool, 计算输入):表示对齐角像素点的方式,Host侧的bool类型。如果为True,则将极值-1和1视为参考输入的角像素点的中心点。如果为False,则视为参考输入的角像素点的角点。
- outputMask(aclBoolArray*, 计算输入):表示输出的掩码,Host侧的aclBoolArray类型。
- inputGrad(aclTensor*, 计算输出):表示反向传播的输出梯度,Device侧的aclTensor。数据类型支持FLOAT16、FLOAT、DOUBLE。支持非连续的Tensor,数据格式支持NCDHW、NDHWC。
- gridGrad(aclTensor*, 计算输出):表示grid梯度,Device侧的aclTensor。数据类型支持FLOAT16、FLOAT、DOUBLE。支持非连续的Tensor,数据格式支持NCDHW、NDHWC。
- workspaceSize(uint64_t*, 出参):返回需要在Device侧申请的workspace大小。
- executor(aclOpExecutor**, 出参):返回op执行器,包含了算子计算流程。
返回值:
aclnnStatus:返回状态码,具体参见aclnn返回码。
第一段接口完成入参校验,出现以下场景时报错:
返回161001(ACLNN_ERR_PARAM_NULLPTR): 传入的gradOutput、input、grid、inputGrad或gridGrad是空指针。
返回161002(ACLNN_ERR_PARAM_INVALID): 1. gradOutput、input、grid、inputGrad或gridGrad的数据类型不在支持的范围之内或数据类型不一致。
2. interpolationMode和paddingMode的值不在支持范围内。
3. gradOutput、input、grid、inputGrad、gridGrad的维度关系不匹配。
aclnnGridSampler3DBackward
参数说明:
- workspace(void*, 入参):在Device侧申请的workspace内存地址。
- workspaceSize(uint64_t, 入参):在Device侧申请的workspace大小,由第一段接口aclnnGridSampler3DBackwardGetWorkspaceSize获取。
- executor(aclOpExecutor*, 入参):op执行器,包含了算子计算流程。
- stream(aclrtStream, 入参):指定执行任务的AscendCL Stream流。
返回值:
aclnnStatus:返回状态码,具体参见aclnn返回码。
约束与限制
无
调用示例
示例代码如下,仅供参考,具体编译和执行过程请参考编译与运行样例。
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_grid_sampler3d_backward.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) {
// 固定写法,AscendCL初始化
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);
// 调用aclrtMalloc申请device侧内存
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);
// 调用aclrtMemcpy将host侧数据拷贝到device侧内存上
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);
// 计算连续tensor的strides
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];
}
// 调用aclCreateTensor接口创建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. (固定写法)device/stream初始化,参考AscendCL对外接口列表
// 根据自己的实际device填写deviceId
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. 构造输入与输出,需要根据API的接口自定义构造
int64_t interpolationMode = 0;
int64_t paddingMode = 0;
bool alignCorners = false;
aclBoolArray* outputMask = nullptr;
std::vector<int64_t> gradOutputShape = {1, 1, 1, 2, 2};
std::vector<int64_t> inputShape = {1, 1, 1, 3, 3};
std::vector<int64_t> gridShape = {1, 1, 2, 2, 3};
std::vector<int64_t> inputGradShape = {1, 1, 1, 3, 3};
std::vector<int64_t> gridGradShape = {1, 1, 2, 2, 3};
void* gradOutputDeviceAddr = nullptr;
void* inputDeviceAddr = nullptr;
void* gridDeviceAddr = nullptr;
void* inputGradDeviceAddr = nullptr;
void* gridGradDeviceAddr = nullptr;
aclTensor* gradOutput = nullptr;
aclTensor* input = nullptr;
aclTensor* grid = nullptr;
aclTensor* inputGrad = nullptr;
aclTensor* gridGrad = nullptr;
std::vector<float> gradOutputHostData = {1, 1, 1, 1};
std::vector<float> inputHostData = {1, 2, 3, 4, 5, 6, 7, 8, 9,};
std::vector<float> gridHostData = {-1, -1, 0, -1, 1, -1, -1, 0, 0, 0, 1, 0};
std::vector<float> inputGradHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0};
std::vector<float> gridGradHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
bool maskValue[2] = {true, true};
outputMask = aclCreateBoolArray(&(maskValue[0]), 2);
// 创建gradOutput aclTensor
ret = CreateAclTensor(gradOutputHostData, gradOutputShape, &gradOutputDeviceAddr, aclDataType::ACL_FLOAT, &gradOutput);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建input aclTensor
ret = CreateAclTensor(inputHostData, inputShape, &inputDeviceAddr, aclDataType::ACL_FLOAT, &input);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建grid aclTensor
ret = CreateAclTensor(gridHostData, gridShape, &gridDeviceAddr, aclDataType::ACL_FLOAT, &grid);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建inputGrad aclTensor
ret = CreateAclTensor(inputGradHostData, inputGradShape, &inputGradDeviceAddr, aclDataType::ACL_FLOAT, &inputGrad);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建gridGrad aclTensor
ret = CreateAclTensor(gridGradHostData, gridGradShape, &gridGradDeviceAddr, aclDataType::ACL_FLOAT, &gridGrad);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. 调用CANN算子库API,需要修改为具体的Api名称
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// 调用aclnnGridSampler3DBackward第一段接口
ret = aclnnGridSampler3DBackwardGetWorkspaceSize(gradOutput, input, grid, interpolationMode, paddingMode,
alignCorners, outputMask, inputGrad, gridGrad,
&workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGridSampler3DBackwardGetWorkspaceSize failed. ERROR: %d\n", ret);
return ret);
// 根据第一段接口计算出的workspaceSize申请device内存
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);
}
// 调用aclnnGridSampler3DBackward第二段接口
ret = aclnnGridSampler3DBackward(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGridSampler3DBackward failed. ERROR: %d\n", ret); return ret);
// 4. (固定写法)同步等待任务执行结束
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
// 5. 获取输出的值,将device侧内存上的结果拷贝至host侧,需要根据具体API的接口定义修改
auto inputGradSize = GetShapeSize(inputGradShape);
std::vector<float> inputGradResultData(inputGradSize, 0);
ret = aclrtMemcpy(inputGradResultData.data(), inputGradResultData.size() * sizeof(inputGradResultData[0]),
inputGradDeviceAddr, inputGradSize * sizeof(inputGradResultData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy inputGradResultData from device to host failed. ERROR: %d\n", ret);
return ret);
for (int64_t i = 0; i < inputGradSize; i++) {
LOG_PRINT("inputGradResultData[%ld] is: %f\n", i, inputGradResultData[i]);
}
auto gridGradSize = GetShapeSize(gridGradShape);
std::vector<float> gridGradResultData(gridGradSize, 0);
ret = aclrtMemcpy(gridGradResultData.data(), gridGradResultData.size() * sizeof(gridGradResultData[0]),
gridGradDeviceAddr, gridGradSize * sizeof(gridGradResultData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy gridGradResultData from device to host failed. ERROR: %d\n", ret);
return ret);
for (int64_t i = 0; i < gridGradSize; i++) {
LOG_PRINT("gridGradResultData[%ld] is: %f\n", i, gridGradResultData[i]);
}
// 6. 释放aclTensor和aclBoolArray,需要根据具体API的接口定义修改
aclDestroyTensor(gradOutput);
aclDestroyTensor(input);
aclDestroyTensor(grid);
aclDestroyTensor(inputGrad);
aclDestroyTensor(gridGrad);
aclDestroyBoolArray(outputMask);
// 7. 释放device资源,需要根据具体API的接口定义修改
aclrtFree(gradOutputDeviceAddr);
aclrtFree(inputDeviceAddr);
aclrtFree(gridDeviceAddr);
aclrtFree(inputGradDeviceAddr);
aclrtFree(gridGradDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}