CANN/sip插值算子文档

asdInterpWithCoeff【免费下载链接】sip本项目是CANN提供的一款高效、可靠的高性能信号处理算子加速库基于华为Ascend AI处理器专门为信号处理领域而设计。项目地址: https://gitcode.com/cann/sip产品支持情况产品是否支持Atlas 200I/500 A2 推理产品×Atlas 推理系列产品×Atlas 训练系列产品×Atlas A3 训练系列产品/Atlas A3 推理系列产品√Atlas A2 训练系列产品/Atlas A2 推理系列产品√Ascend 950PR/Ascend 950DT×功能说明接口功能asdInterpWithCoeffGetWorkspaceSize计算asdInterpWithCoeff算子所需的workspace大小。asdInterpWithCoeff支持向量插值操作主要用于数据符号的信道估计或者均衡系数插值。计算公式$$ resultA \odot\ B (A){ij}(B){ij} $$示例输入“A”为[ [ 11i, 11i ],[ 22i, 22i ] ]输入“B”为[ [ 11i, 11i ],[ 22i, 22i ] ]调用asdInterpWithCoeff算子后输出“result”为[ [ 02i, 02i ],[ 08i, 08i ] ]函数原型AspbStatus asdInterpWithCoeffGetWorkspaceSize( size_t workspaceSize)AspbStatus asdInterpWithCoeff( const aclTensor * x, const aclTensor * coefficient, aclTensor * y, void * stream, void * workSpace nullptr)asdInterpWithCoeffGetWorkspaceSize参数说明参数名输入/输出描述workspaceSizesize_t 输出算子所需要的workspace。返回值返回状态码具体参见SiP返回码。asdInterpWithCoeff参数说明参数名输入/输出描述xaclTensor *输入对应公式中的B。数据类型支持COMPLEX32、COMPLEX64数据格式支持ND。shape为[batchnRs, totalSubcarrier]。batch波束数量取值范围是1~1024 6G时最大取值为16(终端的流数)*64(基站接收的波束数)1024。nRs参考信号数取值是2、4。totalSubcarrier nRB*12。nRB资源块数取值范围是1~2730 每RB包含12个子载波5G时取值范围是1~2736G时取值是5G的4倍到10倍。coefficientaclTensor *输入对应公式中的A。数据类型支持COMPLEX32、COMPLEX64数据格式支持ND。shape为[batch, 14-nRs, nRs]。batch波束数量取值范围是1~1024 6G时最大取值为16(终端的流数)*64(基站接收的波束数)1024。nRs参考信号数取值是2、4。yaclTensor *输出对应公式中的result。数据类型支持COMPLEX32、COMPLEX64数据格式支持ND。shape为[batch14-nRs, totalSubcarrier]。batch波束数量取值范围是1~1024 6G时最大取值为16(终端的流数)*64(基站接收的波束数)1024。nRs参考信号数取值是2、4。totalSubcarrier nRB*12。nRB资源块数取值范围是1~2730 每RB包含12个子载波5G时取值范围是1~273, 6G时取值是5G的4倍到10倍。streamvoid *输入npu执行流。workspacevoid *输入asdInterpWithCoeff算子所需要的workspace。返回值返回状态码具体参见SiP返回码。约束说明无调用示例示例代码如下该样例旨在提供快速上手、开发和调试算子的最小化实现其核心目标是使用最精简的代码展示算子的核心功能而非提供生产级的安全保障。不推荐用户直接将示例代码作为业务代码若用户将示例代码应用在自身的真实业务场景中且发生了安全问题则需用户自行承担。#include iostream #include complex #include vector #include interp_api.h #include acl/acl.h #include acl_meta.h using namespace AsdSip; int64_t GetShapeSize(const std::vectorint64_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acl初始化 aclInit(nullptr); aclrtSetDevice(deviceId); aclrtCreateStream(stream); return 0; } template typename T int CreateAclTensor(const std::vectorT hostData, const std::vectorint64_t shape, void **deviceAddr, aclDataType dataType, aclTensor **tensor) { auto size GetShapeSize(shape) * sizeof(T) * 2; // 2 : complex // 调用aclrtMalloc申请device侧内存 aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST); // 调用aclrtMemcpy将host侧数据复制到device侧内存上 aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE); // 计算连续tensor的strides std::vectorint64_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(int argc, char **argv) { // 设置算子使用的device id int deviceId 0; //固定写法创造执行流 aclrtStream stream; Init(deviceId, stream); // 创造tensor的Host侧数据 int64_t batch 1; int64_t nRs 2; int64_t totalSubcarrier 32; int64_t nSignal 14; int64_t xSize batch * nRs * totalSubcarrier * 2; std::vectorfloat tensorInXData; tensorInXData.reserve(xSize); for (int64_t i 0; i xSize; i) { tensorInXData[i] 1.0 i; } int64_t coeffSize batch * (nSignal - nRs) * nRs * 2; std::vectorfloat coeffData; coeffData.reserve(xSize); for (int64_t i 0; i coeffSize; i) { coeffData[i] 1; } int64_t resultSize batch * (nSignal - nRs) * totalSubcarrier * 2; std::vectorfloat resultData; resultData.reserve(resultSize); for (int64_t i 0; i resultSize; i) { resultData[i] 2; } // int64_t xSize batch * nRs * totalSubcarrier; // std::vectorstd::complexfloat tensorInXData(xSize, std::complexfloat(0, 0)); // for (int i 0; i xSize; i) { // tensorInXData[i] std::complexfloat(i * 2, i * 2 1); // } // int64_t coeffSize batch * (nSignal - nRs) * nRs; // std::vectorstd::complexfloat coeffData(xSize, std::complexfloat(0, 0)); // for (int i 0; i coeffSize; i) { // coeffData[i] std::complexfloat(1, 1); // } // int64_t resultSize batch * (nSignal - nRs) * totalSubcarrier; // std::vectorstd::complexfloat resultData(xSize, std::complexfloat(0, 0)); // for (int i 0; i resultSize; i) { // resultData[i] std::complexfloat(2, 2); // } std::cout ------- input x ------- std::endl; for (int64_t i 0; i xSize; i) { std::cout tensorInXData[i] ; } std::cout std::endl; std::cout ------- input coeff ------- std::endl; for (int64_t i 0; i coeffSize; i) { std::cout coeffData[i] ; } std::cout std::endl; // 创造输入/输出tensor aclTensor *inputX nullptr; aclTensor *inputCoeff nullptr; aclTensor *result nullptr; void *inputXDeviceAddr nullptr; void *inputYDeviceAddr nullptr; void *resultDeviceAddr nullptr; CreateAclTensor(tensorInXData, {batch, nRs, totalSubcarrier}, inputXDeviceAddr, aclDataType::ACL_COMPLEX64, inputX); CreateAclTensor(coeffData, {batch, nSignal-nRs, nRs}, inputYDeviceAddr, aclDataType::ACL_COMPLEX64, inputCoeff); CreateAclTensor(resultData, {batch, nSignal-nRs, totalSubcarrier}, resultDeviceAddr, aclDataType::ACL_COMPLEX64, result); size_t lwork 0; void *buffer nullptr; AsdSip::asdInterpWithCoeffGetWorkspaceSize(lwork); if (lwork 0) { aclrtMalloc(buffer, static_castint64_t(lwork), ACL_MEM_MALLOC_HUGE_FIRST); } asdInterpWithCoeff(inputX, inputCoeff, result, stream, buffer); aclrtSynchronizeStream(stream); // 将输出tensor的Device侧数据复制到Host侧内存上 aclrtMemcpy(resultData.data(), resultSize * sizeof(float), resultDeviceAddr, resultSize * sizeof(float), ACL_MEMCPY_DEVICE_TO_HOST); std::cout ------- result ------- std::endl; for (int64_t i 0; i nSignal - nRs; i) { for (int64_t j 0; j totalSubcarrier * 2; j) { std::cout resultData[i * totalSubcarrier * 2 j] ; } std::cout std::endl; } // 资源释放 aclDestroyTensor(inputX); aclDestroyTensor(inputCoeff); aclDestroyTensor(result); aclrtFree(inputXDeviceAddr); aclrtFree(inputYDeviceAddr); aclrtFree(resultDeviceAddr); if (lwork 0) { aclrtFree(buffer); } // 调度算子后重置算子使用的deviceId aclrtDestroyStream(stream); aclrtResetDevice(deviceId); aclFinalize(); return 0; }【免费下载链接】sip本项目是CANN提供的一款高效、可靠的高性能信号处理算子加速库基于华为Ascend AI处理器专门为信号处理领域而设计。项目地址: https://gitcode.com/cann/sip创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考