LCOV - code coverage report
Current view: top level - legacy/ascend950/service/collective/alg/coll_alg_factory/alg_template/ins_alg_template - ins_temp_reduce_nhr.cc (source / functions) Coverage Total Hit
Test: coverage.info Lines: 0.0 % 192 0
Test Date: 2026-07-28 12:11:00 Functions: 0.0 % 15 0

            Line data    Source code
       1              : /**
       2              :  * Copyright (c) 2025 Huawei Technologies Co., Ltd.
       3              :  * This program is free software, you can redistribute it and/or modify it under the terms and conditions of
       4              :  * CANN Open Software License Agreement Version 2.0 (the "License").
       5              :  * Please refer to the License for details. You may not use this file except in compliance with the License.
       6              :  * THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
       7              :  * INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
       8              :  * See LICENSE in the root of the software repository for the full text of the License.
       9              :  */
      10              : 
      11              : #include "log.h"
      12              : #include "alg_data_trans_wrapper.h"
      13              : #include "ins_temp_reduce_nhr.h"
      14              : 
      15              : namespace Hccl {
      16            0 : InsTempReduceNHR::InsTempReduceNHR(const RankId virtualRank, const u32 tempRankSize,
      17              :                                          const std::vector<std::vector<RankId>> &tempVTopo,
      18            0 :                                          const std::map<RankId, u32>            &tempVirtRankMap)
      19            0 :     : InsAlgTemplateBase(virtualRank, tempRankSize, tempVTopo, tempVirtRankMap)
      20              : {
      21            0 : }
      22              : 
      23            0 : InsTempReduceNHR::~InsTempReduceNHR()
      24              : {
      25            0 : }
      26              : 
      27            0 : HcclResult InsTempReduceNHR::CalcRes(AlgTempResReq &tempResReq)
      28              : {
      29              :     // NHR 需要的 que Num 为 1
      30            0 :     tempResReq.queNum = 1;
      31            0 :     tempResReq.streamNum = tempResReq.queNum;
      32            0 :     tempResReq.queNotifys = CreateMasterSlaveQueNotifiesRequest(tempResReq.queNum);
      33              : 
      34            0 :     CHK_PRT_RET(CalcResLinksNHR(myRank_, tempRankSize_, tempVTopo_, tempResReq) != HcclResult::HCCL_SUCCESS,
      35              :                 HCCL_ERROR("[CollAlgFactory] [InsTempReduceNHR] Rank [%d], resLinks calculation error!", myRank_),
      36              :                 HcclResult::HCCL_E_INTERNAL);
      37              : 
      38            0 :     return HcclResult::HCCL_SUCCESS;
      39              : }
      40              : 
      41              : /*
      42              :  * Desc: 将数据按照rank切分为chuck 块,给后续的reduce操作使用
      43              :  * param: dataSize: 待处理的输入数据大小
      44              :  * return: sliceInfoVec: 存储数据切分结果
      45              :  * return: HcclResult
      46              :  */
      47            0 : HcclResult InsTempReduceNHR::CalcSlice(const u64 dataSize, RankSliceInfo &sliceInfoVec)
      48              : {
      49              :     // 按 rank 切分数据(与 AllReduceNHR 保持一致)
      50            0 :     std::vector<SliceInfo> tmp(tempVTopo_.size());
      51            0 :     sliceInfoVec.resize(tempRankSize_, tmp);
      52              : 
      53            0 :     u64 unitAlignSize = DataTypeSizeGet(dataType_);
      54            0 :     u64 chunkSize = RoundUp(dataSize, (tempRankSize_ * unitAlignSize)) * unitAlignSize;
      55              : 
      56            0 :     u64 accumOff = 0;
      57            0 :     for (u32 rankIdx = 0; rankIdx < tempRankSize_; rankIdx++) {
      58            0 :         u64 currChunkSize = ((dataSize - accumOff) > chunkSize) ? chunkSize : (dataSize - accumOff);
      59            0 :         SliceInfo slice = {accumOff, currChunkSize};
      60            0 :         sliceInfoVec[rankIdx][0] = slice;
      61            0 :         accumOff += currChunkSize;
      62              :     }
      63              : 
      64            0 :     CHK_PRT_RET((sliceInfoVec[tempRankSize_ - 1][0].offset + sliceInfoVec[tempRankSize_ - 1][0].size != dataSize),
      65              :                 HCCL_ERROR("[InsTempReduceNHR] chunkSize:[%llu], Rank:[%d], SliceInfo calculation error!", chunkSize, myRank_),
      66              :                 HcclResult::HCCL_E_INTERNAL);
      67              : 
      68            0 :     return HcclResult::HCCL_SUCCESS;
      69            0 : }
      70              : 
      71              : /*
      72              : * Desc: 返回当前rank能处理的数据量和scratch buffer之间的比例关系
      73              : * param: input: 输入数据位置
      74              : * param: output 输出数据位置
      75              : */
      76            0 : u32 InsTempReduceNHR::CalcScratchMultiple(BufferType input, BufferType output)
      77              : {
      78              :     (void)input;
      79              :     (void)output;
      80              :     // 单算子模式下需要 1 倍的 scratch(ccl buffer),图/流水(OFFLOAD)模式下不需要
      81            0 :     u32 multiple = 0;
      82            0 :     if (op_.opMode == OpMode::OPBASE) {
      83            0 :         multiple = 1;
      84              :     }
      85            0 :     return multiple;
      86              : }
      87              : 
      88            0 : HcclResult InsTempReduceNHR::GenExtIns(const TempFuncs &tempFuncs, const TemplateDataParams &tempAlgParams,
      89              :     const ResLinks &tempLinks, std::vector<InsQuePtr> &tempInsQues)
      90              : {
      91            0 :     HCCL_INFO("[InsTempReduceNHR][GenExtIns] ReduceNHR begin: rank[%d] start", myRank_);
      92            0 :     if (IsPcieLink(tempLinks)) {
      93            0 :         dmaMode_ = DmaMode::GET;
      94              :     }
      95            0 :     opMode_ = tempFuncs.opMode;
      96            0 :     enableCounterNotify_ = tempFuncs.enableCounterNotify;
      97            0 :     queNum_ = tempVTopo_.size();
      98              : 
      99            0 :     CHK_PRT_RET(queNum_ != tempInsQues.size(),
     100              :                 HCCL_ERROR("[CollAlgFactory] [InsTempReduceNHR] Rank [%d], requiredQue Error.", myRank_),
     101              :                 HcclResult::HCCL_E_INTERNAL);
     102              : 
     103              :     // 1. 切片
     104            0 :     RankSliceInfo sliceInfoVec;
     105            0 :     CHK_RET(CalcSlice(tempAlgParams.sliceSize, sliceInfoVec));
     106              : 
     107              :     // 2. PreCopy (OPBASE 模式下将 userIn -> scratch)
     108            0 :     CHK_RET(PreCopy(tempAlgParams, tempInsQues));
     109              : 
     110              :     // 3. ReduceScatter 阶段 (pairwise reduce)
     111            0 :     CHK_RET(RunReduceScatter(sliceInfoVec, tempLinks, tempInsQues));
     112              : 
     113              :     // 4. PrepareDataForGather 阶段
     114            0 :     CHK_RET(PrepareDataForGather(sliceInfoVec, tempInsQues));
     115              : 
     116              :     // 5. Gather 阶段 (将每个 chunk 聚合到 root)
     117            0 :     CHK_RET(RunGather(sliceInfoVec, tempLinks, tempInsQues));
     118              : 
     119              :     // 6. PostCopy (OPBASE 且在 root 上将 scratch -> userOut)
     120            0 :     CHK_RET(PostCopy(tempAlgParams, tempInsQues));
     121              : 
     122            0 :     HCCL_INFO("[InsTempReduceNHR][GenExtIns] ReduceNHR finished: rank[%d] end", myRank_);
     123            0 :     return HcclResult::HCCL_SUCCESS;
     124            0 : }
     125              : 
     126            0 : HcclResult InsTempReduceNHR::PreCopy(const TemplateDataParams &tempAlgParams, std::vector<InsQuePtr> &tempInsQues)
     127              : {
     128              :     // 单算子模式,需要先将数据拷贝到cclBuffer
     129            0 :     if (opMode_ == OpMode::OPBASE) {
     130            0 :         reduceInBuffType_ = BufferType::SCRATCH;
     131            0 :         reduceInBuffBaseOff_ = tempAlgParams.buffInfo.inBuffBaseOff;
     132              : 
     133            0 :         if (tempAlgParams.buffInfo.inBuffType != BufferType::SCRATCH) {
     134            0 :             HCCL_INFO("[InsTempReduceNHR][PreCopy] Opbase copy from userIn to scratchBuffer");
     135            0 :             DataSlice usrInSlices = DataSlice(tempAlgParams.buffInfo.inBuffType, tempAlgParams.buffInfo.inBuffBaseOff, tempAlgParams.sliceSize);
     136            0 :             DataSlice scratchSlices = DataSlice(BufferType::SCRATCH, tempAlgParams.buffInfo.scratchBuffBaseOff, tempAlgParams.sliceSize);
     137            0 :             CHK_RET(LocalCopy(tempInsQues[0], usrInSlices, scratchSlices));
     138            0 :             reduceInBuffBaseOff_ = tempAlgParams.buffInfo.scratchBuffBaseOff;
     139              :         } else {
     140            0 :             HCCL_INFO("[InsTempReduceNHR][PreCopy] skip precopy");
     141              :         }
     142              :     } else {
     143              :         // OFFLOAD 图模式直接在用户 buffer 上操作
     144            0 :         HCCL_INFO("[InsTempReduceNHR][PreCopy] offload skip precopy");
     145            0 :         reduceInBuffType_ = tempAlgParams.buffInfo.inBuffType;
     146            0 :         reduceInBuffBaseOff_ = tempAlgParams.buffInfo.inBuffBaseOff;
     147              :     }
     148              : 
     149            0 :     reduceOutBuffType_ = tempAlgParams.buffInfo.outBuffType;
     150            0 :     reduceOutBuffBaseOff_ = tempAlgParams.buffInfo.outBuffBaseOff;
     151              : 
     152            0 :     return HcclResult::HCCL_SUCCESS;
     153              : }
     154              : 
     155              : // 将reduceScatter之后的数据先放到usrOut
     156            0 : HcclResult InsTempReduceNHR::PrepareDataForGather(const RankSliceInfo &sliceInfoVec, std::vector<InsQuePtr> &tempInsQues)
     157              : {
     158              :     // 如果是单算子模式,在原来的位置要先做完Gather,然后postCopy把数据放到usrOut
     159              :     // 如果是图模式,直接把数据放到usrOUt,然后在usrOut上做Gather
     160            0 :     HCCL_INFO("[InsTempReduceNHR][PrepareDataForGather] prepare data for Gather");
     161              : 
     162            0 :     if (opMode_ == OpMode::OFFLOAD) {
     163            0 :         u64 size = sliceInfoVec[tempVirtRankMap_[myRank_]][0].size;
     164            0 :         u64 srcOffset = sliceInfoVec[tempVirtRankMap_[myRank_]][0].offset;
     165            0 :         u64 dstOffset = sliceInfoVec[tempVirtRankMap_[myRank_]][0].offset;
     166            0 :         DataSlice srcSlice = DataSlice(reduceInBuffType_, reduceInBuffBaseOff_ + srcOffset, size);
     167            0 :         DataSlice dstSlice = DataSlice(reduceOutBuffType_, reduceOutBuffBaseOff_ + dstOffset, size);
     168            0 :         CHK_RET(LocalCopy(tempInsQues[0], srcSlice, dstSlice));
     169            0 :         reduceInBuffType_ = reduceOutBuffType_;
     170            0 :         reduceInBuffBaseOff_ =  reduceOutBuffBaseOff_;
     171              :     }
     172              : 
     173            0 :     return HcclResult::HCCL_SUCCESS;
     174              : }
     175              : 
     176            0 : HcclResult InsTempReduceNHR::PostCopy(const TemplateDataParams &tempAlgParams, std::vector<InsQuePtr> &tempInsQues)
     177              : {
     178              :     // PostCopy 仅在 OPBASE 并且在 root 上执行(root 收到完整结果后写回用户 out)
     179            0 :     RankId rootRank = this->root_; // Executor 在 CreateTemplates 时已调用 SetRoot(op_.root)
     180              : 
     181            0 :     if (myRank_ != rootRank) {
     182            0 :         HCCL_DEBUG("[InsTempReduceNHR][PostCopy] not root, skip postcopy rank[%d]", myRank_);
     183            0 :         return HcclResult::HCCL_SUCCESS;
     184              :     }
     185              : 
     186            0 :     if (opMode_ == OpMode::OPBASE) {
     187            0 :         HCCL_INFO("[InsTempReduceNHR][PostCopy] Opbase root copy from scratchBuffer to userOut");
     188            0 :         DataSlice scratchSlices = DataSlice(reduceInBuffType_, reduceInBuffBaseOff_, tempAlgParams.sliceSize);
     189            0 :         DataSlice usrOutSlices = DataSlice(reduceOutBuffType_, reduceOutBuffBaseOff_, tempAlgParams.sliceSize);
     190            0 :         CHK_RET(LocalCopy(tempInsQues[0], scratchSlices, usrOutSlices));
     191              :     } else {
     192            0 :         HCCL_INFO("[InsTempReduceNHR][PostCopy] offload skip postcopy");
     193              :     }
     194              : 
     195            0 :     return HcclResult::HCCL_SUCCESS;
     196              : }
     197              : 
     198            0 : HcclResult InsTempReduceNHR::RunReduceScatter(const RankSliceInfo &sliceInfoVec, const ResLinks &tempLinks,
     199              :     std::vector<InsQuePtr> &tempInsQues)
     200              : {
     201            0 :     std::vector<AicpuNHRStepInfo> stepInfoList;
     202            0 :     CHK_RET(GetStepInfoList(stepInfoList));
     203              : 
     204            0 :     for (auto &stepInfo : stepInfoList) {
     205            0 :         HCCL_DEBUG("[InsTempReduceNHR][RunReduceScatter] step[%u], myRank[%u], toRank[%u], fromRank[%u], nSlices[%u].",
     206              :             stepInfo.step, stepInfo.myRank, stepInfo.toRank, stepInfo.fromRank, stepInfo.nSlices);
     207              : 
     208            0 :         const std::vector<LinkData> &linkRecv = tempLinks.at(GetRankFromMap(stepInfo.fromRank));
     209            0 :         const std::vector<LinkData> &linkSend = tempLinks.at(GetRankFromMap(stepInfo.toRank));
     210              : 
     211            0 :         std::vector<DataSlice> txSlices;
     212            0 :         std::vector<DataSlice> rxSlices;
     213              : 
     214              :         // 发送和接收 slice 都发生在 reduceInBuffType_ 上(scratch 或用户 buffer)
     215            0 :         for (u32 i = 0; i < stepInfo.nSlices; i++) {
     216            0 :             u64 txOffset = sliceInfoVec[stepInfo.txSliceIdxs[i]][0].offset + reduceInBuffBaseOff_;
     217            0 :             u64 txSize   = sliceInfoVec[stepInfo.txSliceIdxs[i]][0].size;
     218            0 :             u64 rxOffset = sliceInfoVec[stepInfo.rxSliceIdxs[i]][0].offset + reduceInBuffBaseOff_;
     219            0 :             u64 rxSize   = sliceInfoVec[stepInfo.rxSliceIdxs[i]][0].size;
     220              : 
     221            0 :             txSlices.push_back(DataSlice(reduceInBuffType_, txOffset, txSize));
     222            0 :             rxSlices.push_back(DataSlice(reduceInBuffType_, rxOffset, rxSize));
     223              :         }
     224              : 
     225              :         SendRecvReduceInfo sendRecvReduceInfo{
     226            0 :             {linkSend[0], linkRecv[0]},
     227              :             {{txSlices, txSlices}, {rxSlices, rxSlices}},
     228              :             dataType_, redOp_
     229            0 :         };
     230              : 
     231            0 :         CHK_PRT_RET(SendRecvReduce(sendRecvReduceInfo, tempInsQues[0], 0, true, dmaMode_) != HcclResult::HCCL_SUCCESS,
     232              :             HCCL_ERROR("[InsTempReduceNHR] RunReduceScatter SendRecvReduce failed"),
     233              :             HcclResult::HCCL_E_INTERNAL);
     234            0 :     }
     235              : 
     236            0 :     return HcclResult::HCCL_SUCCESS;
     237            0 : }
     238              : 
     239            0 : HcclResult InsTempReduceNHR::RunGather(const RankSliceInfo &sliceInfoVec, const ResLinks &tempLinks,
     240              :     std::vector<InsQuePtr> &tempInsQues)
     241              : {
     242            0 :     u32 nSteps = GetNHRStepNum(tempRankSize_);
     243            0 :     for (u32 step = 0; step < nSteps; step++) {
     244            0 :         AicpuNHRStepInfo stepInfo;
     245            0 :         CHK_RET(GetStepInfo(step, nSteps, stepInfo));
     246              : 
     247            0 :         const std::vector<LinkData> &linkRecv = tempLinks.at(GetRankFromMap(stepInfo.fromRank));
     248            0 :         const std::vector<LinkData> &linkSend = tempLinks.at(GetRankFromMap(stepInfo.toRank));
     249              : 
     250            0 :         std::vector<DataSlice> txSlices;
     251            0 :         std::vector<DataSlice> rxSlices;
     252            0 :         for (u32 i = 0; i < stepInfo.nSlices; i++) {
     253            0 :             u64 txOffset = sliceInfoVec[stepInfo.txSliceIdxs[i]][0].offset + reduceInBuffBaseOff_;
     254            0 :             u64 txSize   = sliceInfoVec[stepInfo.txSliceIdxs[i]][0].size;
     255            0 :             u64 rxOffset = sliceInfoVec[stepInfo.rxSliceIdxs[i]][0].offset + reduceInBuffBaseOff_;
     256            0 :             u64 rxSize   = sliceInfoVec[stepInfo.rxSliceIdxs[i]][0].size;
     257              : 
     258            0 :             txSlices.push_back(DataSlice(reduceInBuffType_, txOffset, txSize));
     259            0 :             rxSlices.push_back(DataSlice(reduceInBuffType_, rxOffset, rxSize));
     260              :         }
     261              : 
     262            0 :         TxRxLinks sendRecvLinks(linkSend[0], linkRecv[0]);
     263            0 :         TxRxSlicesList sendRecvSlicesList({txSlices, txSlices}, {rxSlices, rxSlices});
     264              : 
     265            0 :         SendRecvInfo sendRecvInfo(sendRecvLinks, sendRecvSlicesList);
     266            0 :         CHK_PRT_RET(SendRecv(sendRecvInfo, tempInsQues[0], 0, true, dmaMode_) != HcclResult::HCCL_SUCCESS,
     267              :             HCCL_ERROR("[InsTempReduceNHR] RunGather send/recv failed"),
     268              :             HcclResult::HCCL_E_INTERNAL);
     269            0 :     }
     270              : 
     271            0 :     return HcclResult::HCCL_SUCCESS;
     272              : }
     273              : 
     274            0 : HcclResult InsTempReduceNHR::GetStepInfo(u32 step, u32 nSteps, AicpuNHRStepInfo &stepInfo)
     275              : {
     276            0 :     u32 rankIdx = tempVirtRankMap_[myRank_];
     277            0 :     stepInfo.txSliceIdxs.clear();
     278            0 :     stepInfo.rxSliceIdxs.clear();
     279            0 :     stepInfo.step = step;
     280            0 :     stepInfo.myRank = rankIdx;
     281              : 
     282              :     // 计算通信对象
     283            0 :     u32 deltaRank = 1 << (nSteps - 1 - step);
     284            0 :     u32 recvFrom = (rankIdx + tempRankSize_ - deltaRank) % tempRankSize_;
     285            0 :     u32 sendTo = (rankIdx + deltaRank) % tempRankSize_;
     286              : 
     287              :     // 数据份数和数据编号增量
     288            0 :     u32 nSlices = (tempRankSize_ - 1 + (1 << (nSteps - 1 - step))) / (1 << (nSteps - step));
     289            0 :     u32 deltaSliceIndex = 1 << (nSteps - step);
     290            0 :     u32 txSliceIdx = rankIdx;
     291            0 :     u32 rxSliceIdx = (rankIdx - (1 << (nSteps - 1 - step)) + tempRankSize_) % tempRankSize_;
     292              : 
     293            0 :     stepInfo.nSlices = nSlices;
     294            0 :     stepInfo.toRank = sendTo;
     295            0 :     stepInfo.fromRank = recvFrom;
     296              : 
     297            0 :     for (u32 i = 0; i < nSlices; i++) {
     298            0 :         stepInfo.txSliceIdxs.push_back(txSliceIdx);
     299            0 :         stepInfo.rxSliceIdxs.push_back(rxSliceIdx);
     300              : 
     301            0 :         HCCL_DEBUG("[InsTempReduceNHR][GetStepInfo] i[%u] txSliceIdx[%u] rxSliceIdx[%u]", i, txSliceIdx, rxSliceIdx);
     302              : 
     303            0 :         txSliceIdx = (txSliceIdx + tempRankSize_ - deltaSliceIndex) % tempRankSize_;
     304            0 :         rxSliceIdx = (rxSliceIdx + tempRankSize_ - deltaSliceIndex) % tempRankSize_;
     305              :     }
     306            0 :     return HcclResult::HCCL_SUCCESS;
     307              : }
     308              : 
     309              : //  计算每轮收发的对端以及slice编号
     310            0 : HcclResult InsTempReduceNHR::GetStepInfoList(std::vector<AicpuNHRStepInfo> &stepInfoList)
     311              : {
     312              :     // 将本 rank 号转换成算法使用的索引号
     313            0 :     u32 rankIdx = tempVirtRankMap_[myRank_];
     314            0 :     stepInfoList.clear();
     315              : 
     316            0 :     u32 nSteps = GetNHRStepNum(tempRankSize_);
     317            0 :     stepInfoList.resize(nSteps);
     318            0 :     for (u32 step = 0; step < nSteps; step++) {
     319              :         // 计算通信对象
     320            0 :         u32 deltaRank = 1 << step;
     321            0 :         u32 sendTo = (rankIdx + tempRankSize_ - deltaRank) % tempRankSize_;
     322            0 :         u32 recvFrom = (rankIdx + deltaRank) % tempRankSize_;
     323              : 
     324              :         // 数据份数和数据编号增量
     325            0 :         u32 nSlices = (tempRankSize_ - 1 + (1 << step)) / (1 << (step + 1));
     326            0 :         u32 deltaSliceIndex = 1 << (step + 1);
     327            0 :         u32 txSliceIdx = sendTo;
     328            0 :         u32 rxSliceIdx = rankIdx;
     329              : 
     330            0 :         AicpuNHRStepInfo &currStepInfo = stepInfoList[step];
     331            0 :         currStepInfo.step = step;
     332            0 :         currStepInfo.myRank = rankIdx;
     333            0 :         currStepInfo.nSlices = nSlices;
     334            0 :         currStepInfo.toRank = sendTo;
     335            0 :         currStepInfo.fromRank = recvFrom;
     336              : 
     337              :         // 计算本rank在每轮收/发中的slice编号
     338            0 :         currStepInfo.txSliceIdxs.reserve(nSlices);
     339            0 :         currStepInfo.rxSliceIdxs.reserve(nSlices);
     340            0 :         for (u32 i = 0; i < nSlices; i++) {
     341            0 :             currStepInfo.txSliceIdxs.push_back(txSliceIdx);
     342            0 :             currStepInfo.rxSliceIdxs.push_back(rxSliceIdx);
     343            0 :             HCCL_DEBUG("[InsTempReduceNHR][GetStepInfoList] i[%u] txSliceIdx[%u] rxSliceIdx[%u]", i, txSliceIdx, rxSliceIdx);
     344            0 :             txSliceIdx = (txSliceIdx + tempRankSize_ - deltaSliceIndex) % tempRankSize_;
     345            0 :             rxSliceIdx = (rxSliceIdx + tempRankSize_ - deltaSliceIndex) % tempRankSize_;
     346              :         }
     347              :     }
     348            0 :     return HcclResult::HCCL_SUCCESS;
     349              : }
     350              : 
     351            0 : RankId InsTempReduceNHR::GetRankFromMap(const u32 rankIdx)
     352              : {
     353            0 :     RankId rank = -1;
     354            0 :     for (auto &pair : tempVirtRankMap_) {
     355            0 :         if (pair.second == rankIdx) {
     356            0 :             rank = pair.first;
     357            0 :             break;
     358              :         }
     359              :     }
     360            0 :     return rank;
     361              : }
     362              : 
     363              : } // namespace Hccl
        

Generated by: LCOV version 2.0-1