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              : 
      13              : #include "alg_data_trans_wrapper.h"
      14              : #include "ins_temp_reduce_scatter_aicpu_reduce.h"
      15              : 
      16              : namespace Hccl {
      17            0 : InsTempReduceScatterAicpuReduce::InsTempReduceScatterAicpuReduce(const RankId virtualRank, const u32 tempRankSize,
      18              :                                    const std::vector<std::vector<RankId>> &tempVTopo,
      19            0 :                                    const std::map<RankId, u32>            &tempVirtRankMap)
      20            0 :     : InsAlgTemplateBase(virtualRank, tempRankSize, tempVTopo, tempVirtRankMap)
      21              : {
      22            0 : }
      23              : 
      24            0 : InsTempReduceScatterAicpuReduce::~InsTempReduceScatterAicpuReduce()
      25              : {
      26            0 : }
      27              : 
      28            0 : HcclResult InsTempReduceScatterAicpuReduce::CalcRes(AlgTempResReq &tempResReq)
      29              : {
      30            0 :     tempResReq.queNum = tempVTopo_[0].size();
      31            0 :     tempResReq.streamNum = tempResReq.queNum;
      32            0 :     tempResReq.queNotifys = CreateMasterSlaveQueNotifiesRequest(tempResReq.queNum);
      33            0 :     QId centerQ = 0;
      34            0 :     tempResReq.localWaitGroupCntNotify.emplace_back(centerQ, 0);
      35            0 :     tempResReq.localBcastPostCntNotify.emplace_back(centerQ, 0);
      36            0 :     CHK_RET(CalcResLinksMesh(myRank_, tempRankSize_, tempVTopo_, linkNumBtwPeers_, tempResReq));
      37            0 :     HCCL_DEBUG("[InsTempReduceScatterAicpuReduce]CalcRes: queNum[%u], myRank[%d], tempRankSize[%u]", tempResReq.queNum, myRank_, tempRankSize_);
      38            0 :     return HcclResult::HCCL_SUCCESS;
      39              : }
      40              : 
      41            0 : u32 InsTempReduceScatterAicpuReduce::CalcScratchMultiple(BufferType inBuffType, BufferType outBuffType) const
      42              : {
      43              :     (void) inBuffType;
      44              :     (void) outBuffType;
      45            0 :     return tempRankSize_;
      46              : }
      47              : 
      48            0 : HcclResult InsTempReduceScatterAicpuReduce::RunAlltoAllMesh(const TempFuncs &tempFuncs, const TemplateDataParams &templateDataParams,
      49              :                         const ResLinks &tempLinks, std::vector<InsQuePtr> &tempInsQues)
      50              : {
      51              :     (void) tempFuncs;
      52            0 :     CHK_RET(PreSyncInterQueues(tempInsQues));
      53              :     // 本端rank数据从本端input -> 本端scratch
      54            0 :     u64       srcOffset = templateDataParams.inputSliceStride * u32(myRank_) + templateDataParams.buffInfo.inBuffBaseOff;
      55            0 :     u64       srcSize   = templateDataParams.sliceSize;
      56            0 :     u64       dstOffset = templateDataParams.sliceSize * u32(myRank_);
      57            0 :     DataSlice srcSlice  = DataSlice(BufferType::INPUT, srcOffset, srcSize);
      58            0 :     DataSlice dstSlice  = DataSlice(BufferType::SCRATCH, dstOffset, srcSize);
      59            0 :     std::unique_ptr<Instruction> insLocalCopy = std::make_unique<InsLocalCopy>(srcSlice, dstSlice);
      60            0 :     tempInsQues[0]->Append(std::move(insLocalCopy));
      61              : 
      62              :     // 本端rank数据从本端input -> 对端scratch
      63              : 
      64              :     u32 myAlgRank;
      65            0 :     CHK_RET(GetAlgRank(myRank_, tempVTopo_[0], myAlgRank));
      66            0 :     for (u32 queIdx = 1; queIdx < tempVTopo_[0].size(); queIdx++) {
      67            0 :         RankId neighborRank = tempVTopo_[0][(myAlgRank + queIdx) % tempRankSize_];
      68            0 :         LinkData neighborLinkData = tempLinks.at(neighborRank)[0];
      69            0 :         TxRxLinks sendRecvLinks(neighborLinkData, neighborLinkData);
      70              :         //send
      71            0 :         std::vector<DataSlice> txSrcSlices;
      72            0 :         std::vector<DataSlice> txDstSlices;
      73              :         DataSlice currSendSliceSrc
      74            0 :             = DataSlice(BufferType::INPUT, templateDataParams.inputSliceStride * u32(neighborRank) + templateDataParams.buffInfo.inBuffBaseOff,
      75            0 :                         templateDataParams.sliceSize);
      76              :         DataSlice currSendSliceDst
      77            0 :             = DataSlice(BufferType::SCRATCH, templateDataParams.sliceSize * u32(myRank_), templateDataParams.sliceSize);
      78            0 :         txSrcSlices.push_back(currSendSliceSrc);
      79            0 :         txDstSlices.push_back(currSendSliceDst);
      80              :         //recv
      81              :         DataSlice currRecvSliceSrc
      82            0 :             = DataSlice(BufferType::SCRATCH, templateDataParams.inputSliceStride * u32(neighborRank),
      83            0 :                         templateDataParams.sliceSize);
      84              :         DataSlice currRecvSliceDst
      85            0 :             = DataSlice(BufferType::SCRATCH, templateDataParams.inputSliceStride * u32(neighborRank) + templateDataParams.buffInfo.inBuffBaseOff,
      86            0 :                         templateDataParams.sliceSize);
      87            0 :         std::vector<DataSlice> rxSrcSlices;
      88            0 :         std::vector<DataSlice> rxDstSlices;
      89            0 :         rxSrcSlices.push_back(currRecvSliceSrc);
      90            0 :         rxDstSlices.push_back(currRecvSliceDst);
      91            0 :         TxRxSlicesList sendRecvSlicesList({txSrcSlices, txDstSlices}, {rxSrcSlices, rxDstSlices});
      92            0 :         SendRecvInfo sendRecvInfo(sendRecvLinks, sendRecvSlicesList);
      93            0 :         CHK_PRT_RET(SendRecv(sendRecvInfo, tempInsQues[queIdx], 0, true, dmaMode_), HCCL_ERROR("[InsTempReduceScatterAicpuReduce] RunReduceScatter sendrecv failed"),
      94              :                     HcclResult::HCCL_E_INTERNAL);
      95            0 :     }
      96            0 :     CHK_RET(PostSyncInterQueues(tempInsQues));
      97            0 :     return HCCL_SUCCESS;
      98            0 : }
      99              : 
     100            0 : HcclResult InsTempReduceScatterAicpuReduce::RunAicpuLocalReduce(const TemplateDataParams &templateDataParams, std::vector<InsQuePtr> &tempInsQues)
     101              : {
     102            0 :     DataSlice dataSlice = DataSlice(BufferType::SCRATCH, 0, templateDataParams.sliceSize);
     103            0 :     for (u32 rankId = 1; rankId < tempRankSize_; rankId++) {
     104            0 :         DataSlice reduceSlice = DataSlice(BufferType::SCRATCH, templateDataParams.sliceSize * rankId, templateDataParams.sliceSize);
     105            0 :         AicpuReduce(tempInsQues[0], reduceSlice, dataSlice, dataType_, redOp_);
     106              :     }
     107            0 :     DataSlice outputSlice = DataSlice(BufferType::OUTPUT, templateDataParams.buffInfo.inBuffBaseOff, templateDataParams.sliceSize);
     108            0 :     LocalCopy(tempInsQues[0], dataSlice, outputSlice);
     109            0 :     return HCCL_SUCCESS;
     110              : }
     111              : 
     112            0 : HcclResult InsTempReduceScatterAicpuReduce::GenExtIns(const TempFuncs &tempFuncs, const TemplateDataParams &templateDataParams,
     113              :                         const ResLinks &tempLinks, std::vector<InsQuePtr> &tempInsQues)
     114              : {
     115            0 :     HCCL_INFO("[InsTempReduceScatterAicpuReduce] Run start");
     116            0 :     if (IsPcieLink(tempLinks)) {
     117            0 :         dmaMode_ = DmaMode::GET;
     118              :     } else {
     119            0 :         dmaMode_ = DmaMode::PUT;
     120              :     }
     121            0 :     if (tempVTopo_[0].size() == 1) {
     122            0 :         return HcclResult::HCCL_SUCCESS;
     123              :     }
     124            0 :     opMode_              = tempFuncs.opMode;
     125            0 :     queNum_ = tempVTopo_[0].size();
     126            0 :     CHK_PRT_RET(queNum_ != tempInsQues.size(),
     127              :         HCCL_ERROR("[CollAlgFactory] [InsTempReduceScatterAicpuReduce] Rank [%d], requiredQue Error.", myRank_),
     128              :         HcclResult::HCCL_E_INTERNAL);
     129              : 
     130            0 :     RunAlltoAllMesh(tempFuncs, templateDataParams, tempLinks, tempInsQues);
     131            0 :     StreamSync(tempInsQues);
     132            0 :     RunAicpuLocalReduce(templateDataParams, tempInsQues);
     133            0 :     HCCL_INFO("[InsTempReduceScatterAicpuReduce] Run finished");
     134            0 :     return HCCL_SUCCESS;
     135              : }
     136              : 
     137              : } // namespace Hccl