aclnnMultiScaleDeformableAttnFunction
支持的产品型号
- 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“aclnnMultiScaleDeformableAttnFunctionGetWorkspaceSize”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“aclnnMultiScaleDeformableAttnFunction”接口执行计算。
aclnnStatus aclnnMultiScaleDeformableAttnFunctionGetWorkspaceSize(const aclTensor *value, const aclTensor *spatialShape, const aclTensor *levelStartIndex, const aclTensor *location, const aclTensor *attnWeight, aclTensor *output, uint64_t *workspaceSize, aclOpExecutor **executor)
aclnnStatus aclnnMultiScaleDeformableAttnFunction(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)
功能描述
- 功能描述: MultiScaleDeformableAttention算子功能主要通过采样位置(sample location)、注意力权重(attention weights)、映射后的value特征、多尺度特征起始索引位置、多尺度特征图的空间大小(便于将采样位置由归一化的值变成绝对位置)等参数来遍历不同尺寸特征图的不同采样点。
aclnnMultiScaleDeformableAttnFunctionGetWorkspaceSize
参数说明:
- value(aclTensor*, 计算输入):特征图的特征值,Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16,shape为(bs, spatial_size, mum_heads, channels),支持非连续的Tensor,数据格式支持ND
- spatialShape(aclTensor*, 计算输入):存储每个尺度特征图的高和宽,Device侧的aclTensor,数据类型支持INT32、INT64,shape为(num_levels, 2),支持非连续的Tensor,数据格式支持ND
- levelStartIndex(aclTensor*, 计算输入):每张特征图的起始索引,Device侧的aclTensor,数据类型支持INT32、INT64,shape为(num_levels,),支持非连续的Tensor,数据格式支持ND
- location(aclTensor*, 计算输入):采样点位置tensor,存储每个采样点的坐标位置,Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16,数据类型需要和value保持一致,shape为(bs, num_queries, num_heads, num_levels, num_points, 2),支持非连续的Tensor,数据格式支持ND
- attnWeight(aclTensor*, 计算输入):采样点权重tensor,Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16,数据类型需要和value保持一致,shape为(bs, num_queries, num_heads, num_levels, num_points),支持非连续的Tensor,数据格式支持ND
- output(aclTensor*, 计算输入):算子计算输出,Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16,数据类型需要和value保持一致,shape为(bs, num_queries, num_heads, channels),支持非连续的Tensor,数据格式支持ND
- 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): 1. 传入的输入或输出是空指针。 返回161002(ACLNN_ERR_PARAM_INVALID): 1. 输入和输出的数据类型不在支持的范围之内。 2. 输入输出数据类型不一致。 3. value的shape不是4维。 4. spatialShape的shape不是2维。 5. levelStartIndex的shape不是1维。 6. location的shape不是6维。 7. attnWeight的shape不是5维。 8. spatialShape的最后一轴不是2。 9. location的最后一轴不是2。 10. 不满足接口约束与限制的情况。
aclnnMultiScaleDeformableAttnFunction
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aclnnMultiScaleDeformableAttnFunctionGetWorkspaceSize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
channels % 8 == 0,且channels<=256 32 <= num_queries < 500000 num_level <= 16 mum_heads <= 16 num_points <= 16
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_multi_scale_deformable_attn_function.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acl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根据自己的需要处理
CHECK_RET(ret == 0, 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
std::vector<int64_t> valueShape = {1, 1, 1, 8};
std::vector<int64_t> spatialShapeShape = {1, 2};
std::vector<int64_t> levelStartIndexShape = {1};
std::vector<int64_t> locationShape = {1, 32, 1, 1, 1, 2};
std::vector<int64_t> attnWeightShape = {1, 32, 1, 1, 1};
std::vector<int64_t> outputShape = {1, 32, 8};
void* valueDeviceAddr = nullptr;
void* spatialShapeDeviceAddr = nullptr;
void* levelStartIndexDeviceAddr = nullptr;
void* locationDeviceAddr = nullptr;
void* attnWeightDeviceAddr = nullptr;
void* outputDeviceAddr = nullptr;
aclTensor* value = nullptr;
aclTensor* spatialShape = nullptr;
aclTensor* levelStartIndex = nullptr;
aclTensor* location = nullptr;
aclTensor* attnWeight = nullptr;
aclTensor* output = nullptr;
std::vector<float> valueHostData = {1, 1, 1, 1, 1, 1, 1, 1};
std::vector<float> spatialShapeHostData = {1, 1};
std::vector<float> levelStartIndexHostData = {0};
std::vector<float> locationHostData(GetShapeSize(GetShapeSize), 0);
std::vector<float> attnWeightHostData = {GetShapeSize(attnWeightShape), 1};
std::vector<float> outputHostData = {GetShapeSize(outputShape), 1};
// value aclTensor
ret = CreateAclTensor(valueHostData, valueShape, &valueDeviceAddr, aclDataType::ACL_FLOAT, &value);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建spatialShape aclTensor
ret = CreateAclTensor(spatialShapeHostData, spatialShapeShape, &spatialShapeDeviceAddr, aclDataType::ACL_INT32, &spatialShape);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建levelStartIndex aclTensor
ret = CreateAclTensor(levelStartIndexHostData, levelStartIndexShape, &levelStartIndexDeviceAddr, aclDataType::ACL_INT32, &levelStartIndex);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建location aclTensor
ret = CreateAclTensor(locationHostData, locationShape, &locationDeviceAddr, aclDataType::ACL_FLOAT, &location);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建attnWeight aclTensor
ret = CreateAclTensor(attnWeightHostData, attnWeightShape, &attnWeightDeviceAddr, aclDataType::ACL_FLOAT, &attnWeight);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建output aclTensor
ret = CreateAclTensor(outputHostData, outputShape, &outputDeviceAddr, aclDataType::ACL_FLOAT, &output);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3.调用CANN算子库API,需要修改为具体的API
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// 调用aclnnAdd第一段接口
ret = aclnnMultiScaleDeformableAttnFunctionGetWorkspaceSize(value, spatialShape, levelStartIndex, location, attnWeight, output,
&workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMultiScaleDeformableAttnFunctionGetWorkspaceSize 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aclnnAdd第二段接口
ret = aclnnMultiScaleDeformableAttnFunction(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMultiScaleDeformableAttnFunction 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 size = GetShapeSize(outputShape);
std::vector<float> resultData(size, 0);
ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outputDeviceAddr, size * sizeof(float),
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.释放aclTensor和aclScalar,需要根据具体API的接口定义修改
aclDestroyTensor(value);
aclDestroyTensor(spatialShape);
aclDestroyTensor(levelStartIndex);
aclDestroyTensor(location);
aclDestroyTensor(attnWeight);
aclDestroyTensor(output);
// 7.释放device资源,需要根据具体API的接口定义修改
aclrtFree(valueDeviceAddr);
aclrtFree(spatialShapeDeviceAddr);
aclrtFree(levelStartIndexDeviceAddr);
aclrtFree(locationDeviceAddr);
aclrtFree(attnWeightDeviceAddr);
aclrtFree(outputDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}