FT_DSP.gitlink.net/master/html/functionlib/dsplib/reduce.html

602 lines
89 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!DOCTYPE html>
<html class="writer-html5" lang="zh-CN">
<head>
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Reduce &mdash; MindSpore Signal+ 使用手册 alpha 文档</title>
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=03e43079" />
<link rel="stylesheet" type="text/css" href="../../_static/css/theme.css?v=e59714d7" />
<link rel="stylesheet" type="text/css" href="../../_static/table.css?v=72b86d3e" />
<link rel="stylesheet" type="text/css" href="../../_static/pageviews.css?v=ff0ce7dc" />
<script src="../../_static/jquery.js?v=5d32c60e"></script>
<script src="../../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
<script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js?v=595569a8"></script>
<script src="../../_static/doctools.js?v=888ff710"></script>
<script src="../../_static/sphinx_highlight.js?v=4825356b"></script>
<script src="../../_static/translations.js?v=beaddf03"></script>
<script src="../../_static/table.js?v=99ed15ba"></script>
<script src="../../_static/js/theme.js"></script>
<link rel="index" title="索引" href="../../genindex.html" />
<link rel="search" title="搜索" href="../../search.html" />
<link rel="next" title="ReduceScatter" href="reducescatter.html" />
<link rel="prev" title="Reciprocal" href="reciprocal.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../index.html" class="icon icon-home">
MindSpore Signal+ 使用手册
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
<input type="text" name="q" placeholder="搜索文档" aria-label="搜索文档" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="导航菜单">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../quickstart/index.html">快速入门</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../appdevelop/index.html">应用开发示例</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">算子库支持</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../supported_op.html">算子库支持情况</a></li>
<li class="toctree-l2"><a class="reference internal" href="../custom_op/index.html">自定义算子列表</a></li>
<li class="toctree-l2 current"><a class="reference internal" href="dsplib_index.html">DSP Library C API Reference</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="abs.html">Abs</a></li>
<li class="toctree-l3"><a class="reference internal" href="abs_grad.html">AbsGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="activation_grad.html">ActivationGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="adam.html">Adam</a></li>
<li class="toctree-l3"><a class="reference internal" href="adamweightdecay.html">AdamWeightDecay</a></li>
<li class="toctree-l3"><a class="reference internal" href="adder.html">Adder</a></li>
<li class="toctree-l3"><a class="reference internal" href="addfusion.html">Addfusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="addgrad.html">Addgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="addn.html">AddN</a></li>
<li class="toctree-l3"><a class="reference internal" href="affine.html">Affine</a></li>
<li class="toctree-l3"><a class="reference internal" href="all.html">All</a></li>
<li class="toctree-l3"><a class="reference internal" href="allgather.html">AllGather</a></li>
<li class="toctree-l3"><a class="reference internal" href="apply_momentum.html">ApplyMomentum</a></li>
<li class="toctree-l3"><a class="reference internal" href="argmax.html">Argmax</a></li>
<li class="toctree-l3"><a class="reference internal" href="argmin.html">Argmin</a></li>
<li class="toctree-l3"><a class="reference internal" href="assert.html">Assert</a></li>
<li class="toctree-l3"><a class="reference internal" href="assign.html">Assign</a></li>
<li class="toctree-l3"><a class="reference internal" href="assignadd.html">AssignAdd</a></li>
<li class="toctree-l3"><a class="reference internal" href="attention.html">Attention</a></li>
<li class="toctree-l3"><a class="reference internal" href="audio_spectrogram.html">AudioSpectrogram</a></li>
<li class="toctree-l3"><a class="reference internal" href="avgpooling.html">Avgpooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="avg_pool_grad.html">AvgPoolGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="batchnorm.html">BatchNorm</a></li>
<li class="toctree-l3"><a class="reference internal" href="batchnormgrad.html">Batchnormgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="batch_to_space.html">BatchToSpace</a></li>
<li class="toctree-l3"><a class="reference internal" href="batchtospacend.html">BatchToSpaceND</a></li>
<li class="toctree-l3"><a class="reference internal" href="biasadd.html">Biasadd</a></li>
<li class="toctree-l3"><a class="reference internal" href="biasaddgrad.html">Biasaddgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="binarycrossentropy.html">Binarycrossentropy</a></li>
<li class="toctree-l3"><a class="reference internal" href="binary_cross_entropy_grad.html">BinaryCrossEntropyGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="broadcastto.html">BroadcastTo</a></li>
<li class="toctree-l3"><a class="reference internal" href="cast.html">Cast</a></li>
<li class="toctree-l3"><a class="reference internal" href="ceil.html">Ceil</a></li>
<li class="toctree-l3"><a class="reference internal" href="clip.html">Clip</a></li>
<li class="toctree-l3"><a class="reference internal" href="concat.html">Concat</a></li>
<li class="toctree-l3"><a class="reference internal" href="constant_of_shape.html">ConstantOfShape</a></li>
<li class="toctree-l3"><a class="reference internal" href="conv2d.html">Conv2d</a></li>
<li class="toctree-l3"><a class="reference internal" href="conv2d_transpose.html">Conv2dTranspose</a></li>
<li class="toctree-l3"><a class="reference internal" href="conv2dbackpropfilterfusion.html">Conv2DBackpropFilterFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="conv2dbackpropinputfusion.html">Conv2DBackpropInputFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="cos.html">Cos</a></li>
<li class="toctree-l3"><a class="reference internal" href="crop.html">Crop</a></li>
<li class="toctree-l3"><a class="reference internal" href="crop_and_resize.html">CropAndResize</a></li>
<li class="toctree-l3"><a class="reference internal" href="cumsum.html">Cumsum</a></li>
<li class="toctree-l3"><a class="reference internal" href="customextractfeatures.html">CustomExtractFeatures</a></li>
<li class="toctree-l3"><a class="reference internal" href="customnormalize.html">Customnormalize</a></li>
<li class="toctree-l3"><a class="reference internal" href="custompredict.html">CustomPredict</a></li>
<li class="toctree-l3"><a class="reference internal" href="deconvgradfilter.html">DeconvGradFilter</a></li>
<li class="toctree-l3"><a class="reference internal" href="depthtospace.html">DepthToSpace</a></li>
<li class="toctree-l3"><a class="reference internal" href="detection_post_process.html">DetectionPostProcess</a></li>
<li class="toctree-l3"><a class="reference internal" href="div_fusion.html">DivFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="divgrad.html">Divgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="dropout.html">Dropout</a></li>
<li class="toctree-l3"><a class="reference internal" href="dropoutgrad.html">Dropoutgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="dynamicquant.html">DynamicQuant</a></li>
<li class="toctree-l3"><a class="reference internal" href="eltwise.html">Eltwise</a></li>
<li class="toctree-l3"><a class="reference internal" href="elu.html">Elu</a></li>
<li class="toctree-l3"><a class="reference internal" href="embeddinglookup.html">EmbeddingLookup</a></li>
<li class="toctree-l3"><a class="reference internal" href="equal.html">Equal</a></li>
<li class="toctree-l3"><a class="reference internal" href="erf.html">Erf</a></li>
<li class="toctree-l3"><a class="reference internal" href="expand_dims.html">ExpandDims</a></li>
<li class="toctree-l3"><a class="reference internal" href="expfusion.html">ExpFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="fake_quant_with_min_max_vars.html">FakeQuantWithMinMaxVars</a></li>
<li class="toctree-l3"><a class="reference internal" href="fake_quant_with_min_max_vars_per_channel.html">FakeQuantWithMinMaxVarsPerChannel</a></li>
<li class="toctree-l3"><a class="reference internal" href="fftimag.html">FFTImag</a></li>
<li class="toctree-l3"><a class="reference internal" href="fftreal.html">FFTReal</a></li>
<li class="toctree-l3"><a class="reference internal" href="fill.html">Fill</a></li>
<li class="toctree-l3"><a class="reference internal" href="fillv2.html">FillV2</a></li>
<li class="toctree-l3"><a class="reference internal" href="flatten.html">Flatten</a></li>
<li class="toctree-l3"><a class="reference internal" href="flattengrad.html">FlattenGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="floor.html">Floor</a></li>
<li class="toctree-l3"><a class="reference internal" href="floordiv.html">FloorDiv</a></li>
<li class="toctree-l3"><a class="reference internal" href="floormod.html">Floormod</a></li>
<li class="toctree-l3"><a class="reference internal" href="formattranspose.html">FormatTranspose</a></li>
<li class="toctree-l3"><a class="reference internal" href="fullconnection.html">FullConnection</a></li>
<li class="toctree-l3"><a class="reference internal" href="fusedbatchnorm.html">FusedBatchNorm</a></li>
<li class="toctree-l3"><a class="reference internal" href="gather.html">Gather</a></li>
<li class="toctree-l3"><a class="reference internal" href="gatherd.html">GatherD</a></li>
<li class="toctree-l3"><a class="reference internal" href="gather_nd.html">GatherNd</a></li>
<li class="toctree-l3"><a class="reference internal" href="glu.html">GLU</a></li>
<li class="toctree-l3"><a class="reference internal" href="greater.html">Greater</a></li>
<li class="toctree-l3"><a class="reference internal" href="greaterequal.html">GreaterEqual</a></li>
<li class="toctree-l3"><a class="reference internal" href="groupnormfusion.html">GroupNormFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="gru.html">GRU</a></li>
<li class="toctree-l3"><a class="reference internal" href="hashtablelookup.html">HashtableLookup</a></li>
<li class="toctree-l3"><a class="reference internal" href="instancenorm.html">InstanceNorm</a></li>
<li class="toctree-l3"><a class="reference internal" href="invert_permutation.html">InvertPermutation</a></li>
<li class="toctree-l3"><a class="reference internal" href="isfinite.html">Isfinite</a></li>
<li class="toctree-l3"><a class="reference internal" href="l2norm.html">L2norm</a></li>
<li class="toctree-l3"><a class="reference internal" href="layernormfusion.html">LayerNormFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="layernormgrad.html">Layernormgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="leaky_relu.html">LeakyReLu</a></li>
<li class="toctree-l3"><a class="reference internal" href="less.html">Less</a></li>
<li class="toctree-l3"><a class="reference internal" href="lessequal.html">LessEqual</a></li>
<li class="toctree-l3"><a class="reference internal" href="lin_space.html">LinSpace</a></li>
<li class="toctree-l3"><a class="reference internal" href="log.html">Log</a></li>
<li class="toctree-l3"><a class="reference internal" href="log1p.html">Log1p</a></li>
<li class="toctree-l3"><a class="reference internal" href="loggrad.html">LogGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="logicaland.html">LogicalAnd</a></li>
<li class="toctree-l3"><a class="reference internal" href="logical_not.html">LogicalNot</a></li>
<li class="toctree-l3"><a class="reference internal" href="logical_or.html">LogicalOr</a></li>
<li class="toctree-l3"><a class="reference internal" href="logsoftmax.html">LogSoftmax</a></li>
<li class="toctree-l3"><a class="reference internal" href="lpnormalization.html">LpNormalization</a></li>
<li class="toctree-l3"><a class="reference internal" href="lrn.html">Lrn</a></li>
<li class="toctree-l3"><a class="reference internal" href="lsh_projection.html">LshProjection</a></li>
<li class="toctree-l3"><a class="reference internal" href="lstm.html">LSTM</a></li>
<li class="toctree-l3"><a class="reference internal" href="lstmgrad.html">LstmGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="lstmgraddata.html">LstmGradData</a></li>
<li class="toctree-l3"><a class="reference internal" href="lstmgradweight.html">LstmGradWeight</a></li>
<li class="toctree-l3"><a class="reference internal" href="matmulfusion.html">MatMulFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="maximum.html">Maximum</a></li>
<li class="toctree-l3"><a class="reference internal" href="maximumgrad.html">Maximumgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="maxpoolfusion.html">MaxPoolFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="maxpoolgrad.html">MaxPoolGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="mfcc.html">MFCC</a></li>
<li class="toctree-l3"><a class="reference internal" href="minimum.html">Minimum</a></li>
<li class="toctree-l3"><a class="reference internal" href="minimumgrad.html">Minimumgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="mod.html">Mod</a></li>
<li class="toctree-l3"><a class="reference internal" href="mul.html">Mul</a></li>
<li class="toctree-l3"><a class="reference internal" href="mulgrad.html">Mulgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="neg.html">Neg</a></li>
<li class="toctree-l3"><a class="reference internal" href="neg_grad.html">NegGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="nllloss.html">NLLLoss</a></li>
<li class="toctree-l3"><a class="reference internal" href="nlllossgrad.html">NLLLossGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="non_max_suppression.html">NonMaxSuppression</a></li>
<li class="toctree-l3"><a class="reference internal" href="nonzero.html">NonZero</a></li>
<li class="toctree-l3"><a class="reference internal" href="not_equal.html">NotEqual</a></li>
<li class="toctree-l3"><a class="reference internal" href="onehot.html">OneHot</a></li>
<li class="toctree-l3"><a class="reference internal" href="ones_like.html">OnesLike</a></li>
<li class="toctree-l3"><a class="reference internal" href="padfusion.html">PadFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="power_grad.html">PowerGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="pow_fusion.html">PowFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="prelufusion.html">PReLUFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="priorbox.html">Priorbox</a></li>
<li class="toctree-l3"><a class="reference internal" href="quantdtypecast.html">QuantDTypeCast</a></li>
<li class="toctree-l3"><a class="reference internal" href="raggedrange.html">RaggedRange</a></li>
<li class="toctree-l3"><a class="reference internal" href="random_normal.html">RandomNormal</a></li>
<li class="toctree-l3"><a class="reference internal" href="random_standard_normal.html">RandomStandardNormal</a></li>
<li class="toctree-l3"><a class="reference internal" href="range.html">Range</a></li>
<li class="toctree-l3"><a class="reference internal" href="rank.html">Rank</a></li>
<li class="toctree-l3"><a class="reference internal" href="real_div.html">RealDiv</a></li>
<li class="toctree-l3"><a class="reference internal" href="reciprocal.html">Reciprocal</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">Reduce</a></li>
<li class="toctree-l3"><a class="reference internal" href="reducescatter.html">ReduceScatter</a></li>
<li class="toctree-l3"><a class="reference internal" href="reshape.html">Reshape</a></li>
<li class="toctree-l3"><a class="reference internal" href="resize.html">Resize</a></li>
<li class="toctree-l3"><a class="reference internal" href="resizegrad.html">Resizegrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="reverse_sequence.html">ReverseSequence</a></li>
<li class="toctree-l3"><a class="reference internal" href="reversev2.html">ReverseV2</a></li>
<li class="toctree-l3"><a class="reference internal" href="rfft.html">RFFT</a></li>
<li class="toctree-l3"><a class="reference internal" href="roipooling.html">ROIPooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="round.html">Round</a></li>
<li class="toctree-l3"><a class="reference internal" href="rsqrt.html">Rsqrt</a></li>
<li class="toctree-l3"><a class="reference internal" href="rsqrtgrad.html">Rsqrtgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="scale_fusion.html">ScaleFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="scatter_elements.html">ScatterElements</a></li>
<li class="toctree-l3"><a class="reference internal" href="scatter_nd.html">ScatterNd</a></li>
<li class="toctree-l3"><a class="reference internal" href="scatter_nd_update.html">ScatterNdUpdate</a></li>
<li class="toctree-l3"><a class="reference internal" href="select.html">Select</a></li>
<li class="toctree-l3"><a class="reference internal" href="sgd.html">SGD</a></li>
<li class="toctree-l3"><a class="reference internal" href="shape.html">Shape</a></li>
<li class="toctree-l3"><a class="reference internal" href="sigmoidcrossentropywithlogits.html">SigmoidCrossEntropyWithLogits</a></li>
<li class="toctree-l3"><a class="reference internal" href="sigmoidcrossentropywithlogitsgrad.html">SigmoidCrossEntropyWithLogitsGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="sin.html">Sin</a></li>
<li class="toctree-l3"><a class="reference internal" href="size.html">Size</a></li>
<li class="toctree-l3"><a class="reference internal" href="skipgram.html">Skipgram</a></li>
<li class="toctree-l3"><a class="reference internal" href="slice.html">Slice</a></li>
<li class="toctree-l3"><a class="reference internal" href="smooth1loss.html">SmoothL1Loss</a></li>
<li class="toctree-l3"><a class="reference internal" href="smoothl1lossgrad.html">Smoothl1lossgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="softmax.html">Softmax</a></li>
<li class="toctree-l3"><a class="reference internal" href="softmax_cross_entropy_with_logits.html">SoftmaxCrossEntropyWithLogits</a></li>
<li class="toctree-l3"><a class="reference internal" href="spacetobatch.html">SpaceToBatch</a></li>
<li class="toctree-l3"><a class="reference internal" href="spacetobatchnd.html">SpaceToBatchND</a></li>
<li class="toctree-l3"><a class="reference internal" href="spacetodepth.html">SpaceToDepth</a></li>
<li class="toctree-l3"><a class="reference internal" href="sparsefillemptyrows.html">SparseFillEmptyRows</a></li>
<li class="toctree-l3"><a class="reference internal" href="sparsereshape.html">Sparsereshape</a></li>
<li class="toctree-l3"><a class="reference internal" href="sparsesegmentsum.html">Sparsesegmentsum</a></li>
<li class="toctree-l3"><a class="reference internal" href="sparse_softmax_cross_entropy_with_logits.html">SparseSoftmaxCrossEntropyWithLogits</a></li>
<li class="toctree-l3"><a class="reference internal" href="sparsetodense.html">Sparsetodense</a></li>
<li class="toctree-l3"><a class="reference internal" href="splice.html">Splice</a></li>
<li class="toctree-l3"><a class="reference internal" href="split.html">Split</a></li>
<li class="toctree-l3"><a class="reference internal" href="split_with_overlap.html">SplitWithOverlap</a></li>
<li class="toctree-l3"><a class="reference internal" href="sqrt.html">Sqrt</a></li>
<li class="toctree-l3"><a class="reference internal" href="sqrt_grad.html">SqrtGrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="square.html">Square</a></li>
<li class="toctree-l3"><a class="reference internal" href="squaredifference.html">Squaredifference</a></li>
<li class="toctree-l3"><a class="reference internal" href="squeeze.html">Squeeze</a></li>
<li class="toctree-l3"><a class="reference internal" href="stack.html">Stack</a></li>
<li class="toctree-l3"><a class="reference internal" href="stridedslice.html">Stridedslice</a></li>
<li class="toctree-l3"><a class="reference internal" href="stridedslicegrad.html">Stridedslicegrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="subfusion.html">Subfusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="subgrad.html">Subgrad</a></li>
<li class="toctree-l3"><a class="reference internal" href="switch.html">Switch</a></li>
<li class="toctree-l3"><a class="reference internal" href="switchlayer.html">Switchlayer</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensorarray.html">Tensorarray</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensorarrayread.html">Tensorarrayread</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensorarraywrite.html">TensorarrayWrite</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensorlistfromtensor.html">Tensorlistfromtensor</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensorlistgetitem.html">Tensorlistgetitem</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensorlistreserve.html">Tensorlistreserve</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensorlistsetitem.html">Tensorlistsetitem</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensorliststack.html">Tensorliststack</a></li>
<li class="toctree-l3"><a class="reference internal" href="tensor_scatter_add.html">TensorScatterAdd</a></li>
<li class="toctree-l3"><a class="reference internal" href="tile.html">Tile</a></li>
<li class="toctree-l3"><a class="reference internal" href="topkfusion.html">TopkFusion</a></li>
<li class="toctree-l3"><a class="reference internal" href="transpose.html">Transpose</a></li>
<li class="toctree-l3"><a class="reference internal" href="tril.html">Tril</a></li>
<li class="toctree-l3"><a class="reference internal" href="triu.html">Triu</a></li>
<li class="toctree-l3"><a class="reference internal" href="uniform_real.html">UniformReal</a></li>
<li class="toctree-l3"><a class="reference internal" href="unique.html">Unique</a></li>
<li class="toctree-l3"><a class="reference internal" href="unsortedsegmentsum.html">UnsortedSegmentSum</a></li>
<li class="toctree-l3"><a class="reference internal" href="unstack.html">Unstack</a></li>
<li class="toctree-l3"><a class="reference internal" href="unsqueeze.html">UnSqueeze</a></li>
<li class="toctree-l3"><a class="reference internal" href="where.html">Where</a></li>
<li class="toctree-l3"><a class="reference internal" href="zeroslike.html">ZerosLike</a></li>
<li class="toctree-l3"><a class="reference internal" href="call.html">Call</a></li>
<li class="toctree-l3"><a class="reference internal" href="custom.html">Custom</a></li>
<li class="toctree-l3"><a class="reference internal" href="depend.html">Depend</a></li>
<li class="toctree-l3"><a class="reference internal" href="genop.html">GenOp</a></li>
<li class="toctree-l3"><a class="reference internal" href="partialfusion.html">PartialFusion</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../refdoc/index.html">参考资料</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="移动版导航菜单" >
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../index.html">MindSpore Signal+ 使用手册</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="页面导航">
<ul class="wy-breadcrumbs">
<li><a href="../../index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item"><a href="../index.html">算子库支持</a></li>
<li class="breadcrumb-item"><a href="dsplib_index.html">DSP Library C API Reference</a></li>
<li class="breadcrumb-item active">Reduce</li>
<li class="wy-breadcrumbs-aside">
<a href="../../_sources/functionlib/dsplib/reduce.rst.txt" rel="nofollow"> 查看页面源码</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<section id="reduce">
<h1>Reduce<a class="headerlink" href="#reduce" title="此标题的永久链接"></a></h1>
<p>对指定维度进行归约。</p>
<dl class="simple">
<dt>输入:</dt><dd><ul class="simple">
<li><p><strong>src_data</strong> - 输入数据的地址</p></li>
<li><p><strong>param</strong> - 算子计算所需参数的结构体。其各成员见下述。</p></li>
<li><p><strong>core_mask</strong> - 核掩码。</p></li>
</ul>
</dd>
</dl>
<p><strong>ReduceParameter定义</strong></p>
<div class="highlight-c notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="k">typedef</span><span class="w"> </span><span class="k">struct</span><span class="w"> </span><span class="nc">ReduceParameter</span><span class="w"> </span><span class="p">{</span>
<span class="linenos"> 2</span><span class="w"> </span><span class="kt">void</span><span class="o">**</span><span class="w"> </span><span class="n">data_buffers_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 用于存储中间计算结果</span>
<span class="linenos"> 3</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">outer_sizes_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 处理某个规约轴时,该轴之前所有轴的元素数</span>
<span class="linenos"> 4</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">inner_sizes_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 某个规约轴之后的所有元素数</span>
<span class="linenos"> 5</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">axis_sizes_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 规约轴的元素数</span>
<span class="linenos"> 6</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">total_num_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 输入张量的总元素数</span>
<span class="linenos"> 7</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_axes_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 待规约轴的数目</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">mode_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 规约模式</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">output_num_</span><span class="p">;</span><span class="w"> </span><span class="c1">// 输出张量的总元素数</span>
<span class="linenos">10</span><span class="w"> </span><span class="cm">/**该算子会根据ReduceParameter中的mode_参数选择实际规约所使用的方法。共有如下几种方法</span>
<span class="linenos">11</span><span class="cm"> Reduce_Mean=0,</span>
<span class="linenos">12</span><span class="cm"> Reduce_Max=1,</span>
<span class="linenos">13</span><span class="cm"> Reduce_Min=2,</span>
<span class="linenos">14</span><span class="cm"> Reduce_Prod=3,</span>
<span class="linenos">15</span><span class="cm"> Reduce_Sum=4,</span>
<span class="linenos">16</span><span class="cm"> Reduce_SumSquare=5,</span>
<span class="linenos">17</span><span class="cm"> Reduce_ASum=6,</span>
<span class="linenos">18</span><span class="cm"> Reduce_L2Norm=7</span>
<span class="linenos">19</span><span class="cm"> **/</span>
<span class="linenos">20</span><span class="p">}</span><span class="w"> </span><span class="n">ReduceParameter</span><span class="p">;</span>
</pre></div>
</div>
<dl class="simple">
<dt>输出:</dt><dd><ul class="simple">
<li><p><strong>dst_data</strong> - 输出地址。</p></li>
</ul>
</dd>
<dt>支持平台:</dt><dd><p><code class="docutils literal notranslate"><span class="pre">FT78NE</span></code>
<code class="docutils literal notranslate"><span class="pre">MT7004</span></code></p>
</dd>
</dl>
<div class="admonition note">
<p class="admonition-title">备注</p>
<ul class="simple">
<li><p>FT78NE 支持int8, int16, int32, fp32, fp64</p></li>
<li><p>MT7004 支持fp16, fp32, int16, int32</p></li>
</ul>
</div>
<p><strong>共享存储版本:</strong></p>
<dl class="c function">
<dt class="sig sig-object c" id="c.i8_reduce_s">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">i8_reduce_s</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i8_reduce_s" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.i16_reduce_s">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">i16_reduce_s</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i16_reduce_s" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.i32_reduce_s">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">i32_reduce_s</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i32_reduce_s" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.hp_reduce_s">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">hp_reduce_s</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.hp_reduce_s" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.fp_reduce_s">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">fp_reduce_s</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.fp_reduce_s" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.dp_reduce_s">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">dp_reduce_s</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.dp_reduce_s" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<p><strong>C调用示例</strong></p>
<div class="highlight-c notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="kt">void</span><span class="w"> </span><span class="nf">PackParam</span><span class="p">(</span><span class="n">ReduceParameter</span><span class="o">*</span><span class="w"> </span><span class="n">param</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">ndim</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">input_shape</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_axes</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">axes</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos"> 2</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="mi">8</span><span class="p">];</span>
<span class="linenos"> 3</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">total_num</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos"> 4</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">i</span><span class="p">,</span><span class="w"> </span><span class="n">j</span><span class="p">,</span><span class="w"> </span><span class="n">k</span><span class="p">;</span>
<span class="linenos"> 5</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">ndim</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos"> 6</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">input_shape</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
<span class="linenos"> 7</span><span class="w"> </span><span class="n">total_num</span><span class="w"> </span><span class="o">*=</span><span class="w"> </span><span class="n">input_shape</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="p">}</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">total_num_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">total_num</span><span class="p">;</span>
<span class="linenos">10</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">offset_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span>
<span class="linenos">11</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">num_axes</span><span class="p">;</span><span class="w"> </span><span class="o">++</span><span class="n">i</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">12</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">axis</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">axes</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
<span class="linenos">13</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">outer_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">14</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">j</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">j</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">axis</span><span class="p">;</span><span class="w"> </span><span class="n">j</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">15</span><span class="w"> </span><span class="n">outer_size</span><span class="w"> </span><span class="o">*=</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">j</span><span class="p">];</span>
<span class="linenos">16</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">17</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">outer_sizes_</span><span class="p">[</span><span class="n">offset_size</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">outer_size</span><span class="p">;</span>
<span class="linenos">18</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">inner_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">19</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">k</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">axis</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span><span class="w"> </span><span class="n">k</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">ndim</span><span class="p">;</span><span class="w"> </span><span class="n">k</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">20</span><span class="w"> </span><span class="n">inner_size</span><span class="w"> </span><span class="o">*=</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">k</span><span class="p">];</span>
<span class="linenos">21</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">22</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">inner_sizes_</span><span class="p">[</span><span class="n">offset_size</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">inner_size</span><span class="p">;</span>
<span class="linenos">23</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">axis_sizes_</span><span class="p">[</span><span class="n">offset_size</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">axis</span><span class="p">];</span>
<span class="linenos">24</span><span class="w"> </span><span class="n">offset_size</span><span class="o">++</span><span class="p">;</span>
<span class="linenos">25</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">axis</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">26</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">27</span><span class="p">}</span>
<span class="linenos">28</span>
<span class="linenos">29</span><span class="kt">void</span><span class="w"> </span><span class="nf">TestReduceSMCFp32</span><span class="p">(</span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">input_shape</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">ndim</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">axes</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_axes</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">mode</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">keep_dims</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">30</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_id</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">get_core_id</span><span class="p">();</span>
<span class="linenos">31</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">logic_core_id</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">GetLogicCoreId</span><span class="p">(</span><span class="n">core_mask</span><span class="p">,</span><span class="w"> </span><span class="n">core_id</span><span class="p">);</span>
<span class="linenos">32</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_num</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">GetCoreNum</span><span class="p">(</span><span class="n">core_mask</span><span class="p">);</span>
<span class="linenos">33</span><span class="w"> </span><span class="kt">float</span><span class="o">*</span><span class="w"> </span><span class="n">input</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88000000</span><span class="p">;</span>
<span class="linenos">34</span><span class="w"> </span><span class="kt">float</span><span class="o">*</span><span class="w"> </span><span class="n">output</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="o">*</span><span class="p">)</span><span class="mh">0x98000000</span><span class="p">;</span>
<span class="linenos">35</span><span class="w"> </span><span class="n">ReduceParameter</span><span class="o">*</span><span class="w"> </span><span class="n">param</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="n">ReduceParameter</span><span class="o">*</span><span class="p">)</span><span class="mh">0xA8480000</span><span class="p">;</span>
<span class="linenos">36</span><span class="w"> </span><span class="k">if</span><span class="w"> </span><span class="p">(</span><span class="n">logic_core_id</span><span class="w"> </span><span class="o">==</span><span class="w"> </span><span class="mi">0</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">37</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">num_axes_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">num_axes</span><span class="p">;</span>
<span class="linenos">38</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">mode_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">mode</span><span class="p">;</span>
<span class="linenos">39</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">data_buffers_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">**</span><span class="p">)</span><span class="mh">0xA8483000</span><span class="p">;</span>
<span class="linenos">40</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">inner_sizes_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">int</span><span class="o">*</span><span class="p">)</span><span class="mh">0xA8484000</span><span class="p">;</span>
<span class="linenos">41</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">outer_sizes_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">int</span><span class="o">*</span><span class="p">)</span><span class="mh">0xA8485000</span><span class="p">;</span>
<span class="linenos">42</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">axis_sizes_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">int</span><span class="o">*</span><span class="p">)</span><span class="mh">0xA8486000</span><span class="p">;</span>
<span class="linenos">43</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">i</span><span class="p">;</span>
<span class="linenos">44</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">num_axes</span><span class="w"> </span><span class="o">-</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">45</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">data_buffers_</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)(</span><span class="mh">0xA8490000</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="mh">0x1000000</span><span class="p">);</span>
<span class="linenos">46</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">47</span><span class="w"> </span><span class="n">PackParam</span><span class="p">(</span><span class="n">param</span><span class="p">,</span><span class="w"> </span><span class="n">ndim</span><span class="p">,</span><span class="w"> </span><span class="n">input_shape</span><span class="p">,</span><span class="w"> </span><span class="n">num_axes</span><span class="p">,</span><span class="w"> </span><span class="n">axes</span><span class="p">);</span>
<span class="linenos">48</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">49</span><span class="w"> </span><span class="n">sys_bar</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span><span class="w"> </span><span class="n">core_num</span><span class="p">);</span><span class="w"> </span><span class="c1">// 初始化参数完成后进行同步</span>
<span class="hll"><span class="linenos">50</span><span class="w"> </span><span class="n">fp_reduce_s</span><span class="p">(</span><span class="n">input</span><span class="p">,</span><span class="w"> </span><span class="n">check</span><span class="p">,</span><span class="w"> </span><span class="n">param</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
</span><span class="linenos">51</span><span class="p">}</span>
<span class="linenos">52</span>
<span class="linenos">53</span><span class="kt">void</span><span class="w"> </span><span class="nf">main</span><span class="p">(){</span>
<span class="linenos">54</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_shape</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">{</span><span class="mi">4</span><span class="p">,</span><span class="w"> </span><span class="mi">5</span><span class="p">,</span><span class="w"> </span><span class="mi">5</span><span class="p">};</span>
<span class="linenos">55</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">ndim</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">3</span><span class="p">;</span>
<span class="linenos">56</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">axes</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">{</span><span class="mi">1</span><span class="p">};</span>
<span class="linenos">57</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_axes</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">58</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">mode</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">7</span><span class="p">;</span>
<span class="linenos">59</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">keep_dims</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">60</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mb">0b1111</span><span class="p">;</span>
<span class="linenos">61</span><span class="w"> </span><span class="n">TestReduceSMCFp32</span><span class="p">(</span><span class="n">input_shape</span><span class="p">,</span><span class="w"> </span><span class="n">ndim</span><span class="p">,</span><span class="w"> </span><span class="n">axes</span><span class="p">,</span><span class="w"> </span><span class="n">num_axes</span><span class="p">,</span><span class="w"> </span><span class="n">mode</span><span class="p">,</span><span class="w"> </span><span class="n">keep_dims</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
<span class="linenos">62</span><span class="p">}</span>
</pre></div>
</div>
<p><strong>私有存储版本:</strong></p>
<dl class="c function">
<dt class="sig sig-object c" id="c.i8_reduce_p">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">i8_reduce_p</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="n"><span class="pre">int8_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_src_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i8_reduce_p" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.i16_reduce_p">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">i16_reduce_p</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">int16_t</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_src_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i16_reduce_p" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.i32_reduce_p">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">i32_reduce_p</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_src_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.i32_reduce_p" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.hp_reduce_p">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">hp_reduce_p</span></span></span><span class="sig-paren">(</span><span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="n"><span class="pre">half</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_src_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.hp_reduce_p" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.fp_reduce_p">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">fp_reduce_p</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="kt"><span class="pre">float</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_src_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.fp_reduce_p" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<dl class="c function">
<dt class="sig sig-object c" id="c.dp_reduce_p">
<span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="sig-name descname"><span class="n"><span class="pre">dp_reduce_p</span></span></span><span class="sig-paren">(</span><span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">src_data</span></span>, <span class="kt"><span class="pre">double</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">dst_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_src_data</span></span>, <span class="kt"><span class="pre">void</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">tmp_dst_data</span></span>, <span class="n"><span class="pre">ReduceParameter</span></span><span class="w"> </span><span class="p"><span class="pre">*</span></span><span class="n"><span class="pre">param</span></span>, <span class="kt"><span class="pre">int</span></span><span class="w"> </span><span class="n"><span class="pre">core_mask</span></span><span class="sig-paren">)</span><a class="headerlink" href="#c.dp_reduce_p" title="永久链接至目标"></a><br /></dt>
<dd></dd></dl>
<p><strong>C调用示例</strong></p>
<div class="highlight-c notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="kt">void</span><span class="w"> </span><span class="nf">PackParam</span><span class="p">(</span><span class="n">ReduceParameter</span><span class="o">*</span><span class="w"> </span><span class="n">param</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">ndim</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">input_shape</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_axes</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">axes</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos"> 2</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="mi">8</span><span class="p">];</span>
<span class="linenos"> 3</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">total_num</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos"> 4</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">i</span><span class="p">,</span><span class="w"> </span><span class="n">j</span><span class="p">,</span><span class="w"> </span><span class="n">k</span><span class="p">;</span>
<span class="linenos"> 5</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">ndim</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos"> 6</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">input_shape</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
<span class="linenos"> 7</span><span class="w"> </span><span class="n">total_num</span><span class="w"> </span><span class="o">*=</span><span class="w"> </span><span class="n">input_shape</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="p">}</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">total_num_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">total_num</span><span class="p">;</span>
<span class="linenos">10</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">offset_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span>
<span class="linenos">11</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">num_axes</span><span class="p">;</span><span class="w"> </span><span class="o">++</span><span class="n">i</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">12</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">axis</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">axes</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
<span class="linenos">13</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">outer_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">14</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">j</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">j</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">axis</span><span class="p">;</span><span class="w"> </span><span class="n">j</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">15</span><span class="w"> </span><span class="n">outer_size</span><span class="w"> </span><span class="o">*=</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">j</span><span class="p">];</span>
<span class="linenos">16</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">17</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">outer_sizes_</span><span class="p">[</span><span class="n">offset_size</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">outer_size</span><span class="p">;</span>
<span class="linenos">18</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">inner_size</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">19</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">k</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">axis</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span><span class="w"> </span><span class="n">k</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">ndim</span><span class="p">;</span><span class="w"> </span><span class="n">k</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">20</span><span class="w"> </span><span class="n">inner_size</span><span class="w"> </span><span class="o">*=</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">k</span><span class="p">];</span>
<span class="linenos">21</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">22</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">inner_sizes_</span><span class="p">[</span><span class="n">offset_size</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">inner_size</span><span class="p">;</span>
<span class="linenos">23</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">axis_sizes_</span><span class="p">[</span><span class="n">offset_size</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">axis</span><span class="p">];</span>
<span class="linenos">24</span><span class="w"> </span><span class="n">offset_size</span><span class="o">++</span><span class="p">;</span>
<span class="linenos">25</span><span class="w"> </span><span class="n">tmp_input_shape</span><span class="p">[</span><span class="n">axis</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">26</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">27</span><span class="p">}</span>
<span class="linenos">28</span>
<span class="linenos">29</span><span class="kt">void</span><span class="w"> </span><span class="nf">TestReduceL2Fp32</span><span class="p">(</span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">input_shape</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">ndim</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="o">*</span><span class="w"> </span><span class="n">axes</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_axes</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">mode</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">keep_dims</span><span class="p">,</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">30</span><span class="w"> </span><span class="kt">float</span><span class="o">*</span><span class="w"> </span><span class="n">input</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10000000</span><span class="p">;</span><span class="w"> </span><span class="c1">// 原始输入输出数据需分配在AM中</span>
<span class="linenos">31</span><span class="w"> </span><span class="kt">float</span><span class="o">*</span><span class="w"> </span><span class="n">output</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10010000</span><span class="p">;</span>
<span class="linenos">32</span><span class="w"> </span><span class="kt">float</span><span class="o">*</span><span class="w"> </span><span class="n">tmp_input</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="o">*</span><span class="p">)</span><span class="mh">0x88000000</span><span class="p">;</span><span class="w"> </span><span class="c1">// 临时输入输出空间需分配在DDR或SMC中</span>
<span class="linenos">33</span><span class="w"> </span><span class="kt">float</span><span class="o">*</span><span class="w"> </span><span class="n">tmp_output</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">float</span><span class="o">*</span><span class="p">)</span><span class="mh">0x98000000</span><span class="p">;</span>
<span class="linenos">34</span><span class="w"> </span><span class="n">ReduceParameter</span><span class="o">*</span><span class="w"> </span><span class="n">param</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="n">ReduceParameter</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10020000</span><span class="p">;</span>
<span class="linenos">35</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">num_axes_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">num_axes</span><span class="p">;</span>
<span class="linenos">36</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">mode_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">mode</span><span class="p">;</span>
<span class="linenos">37</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">data_buffers_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">**</span><span class="p">)</span><span class="mh">0x10021000</span><span class="p">;</span>
<span class="linenos">38</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">inner_sizes_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">int</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10022000</span><span class="p">;</span>
<span class="linenos">39</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">outer_sizes_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">int</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10023000</span><span class="p">;</span>
<span class="linenos">40</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">axis_sizes_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">int</span><span class="o">*</span><span class="p">)</span><span class="mh">0x10024000</span><span class="p">;</span>
<span class="linenos">41</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">i</span><span class="p">,</span><span class="w"> </span><span class="n">j</span><span class="p">;</span>
<span class="linenos">42</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">ndim</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">43</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">reduce_axis</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span>
<span class="linenos">44</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">j</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">j</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">num_axes</span><span class="p">;</span><span class="w"> </span><span class="n">j</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">45</span><span class="w"> </span><span class="k">if</span><span class="w"> </span><span class="p">(</span><span class="n">axes</span><span class="p">[</span><span class="n">j</span><span class="p">]</span><span class="w"> </span><span class="o">==</span><span class="w"> </span><span class="n">i</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">46</span><span class="w"> </span><span class="n">reduce_axis</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">47</span><span class="w"> </span><span class="k">break</span><span class="p">;</span>
<span class="linenos">48</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">49</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">50</span><span class="w"> </span><span class="k">if</span><span class="w"> </span><span class="p">(</span><span class="o">!</span><span class="n">reduce_axis</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">51</span><span class="w"> </span><span class="n">length</span><span class="w"> </span><span class="o">*=</span><span class="w"> </span><span class="n">input_shape</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
<span class="linenos">52</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">53</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">54</span><span class="w"> </span><span class="k">for</span><span class="w"> </span><span class="p">(</span><span class="n">i</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">0</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="w"> </span><span class="o">&lt;</span><span class="w"> </span><span class="n">num_axes</span><span class="w"> </span><span class="o">-</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span><span class="w"> </span><span class="n">i</span><span class="o">++</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">55</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">data_buffers_</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">(</span><span class="kt">void</span><span class="o">*</span><span class="p">)(</span><span class="mh">0xA8490000</span><span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="mh">0x1000000</span><span class="p">);</span><span class="w"> </span><span class="c1">// 每一个中间计算结果空间都需分配在DDR或SMC中</span>
<span class="linenos">56</span><span class="w"> </span><span class="p">}</span>
<span class="linenos">57</span><span class="w"> </span><span class="n">param</span><span class="o">-&gt;</span><span class="n">output_num_</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">length</span><span class="p">;</span>
<span class="linenos">58</span><span class="w"> </span><span class="n">PackParam</span><span class="p">(</span><span class="n">param</span><span class="p">,</span><span class="w"> </span><span class="n">ndim</span><span class="p">,</span><span class="w"> </span><span class="n">input_shape</span><span class="p">,</span><span class="w"> </span><span class="n">num_axes</span><span class="p">,</span><span class="w"> </span><span class="n">axes</span><span class="p">);</span>
<span class="hll"><span class="linenos">59</span><span class="w"> </span><span class="n">fp_reduce_p</span><span class="p">(</span><span class="n">input</span><span class="p">,</span><span class="w"> </span><span class="n">check</span><span class="p">,</span><span class="w"> </span><span class="n">param</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
</span><span class="linenos">60</span><span class="p">}</span>
<span class="linenos">61</span>
<span class="linenos">62</span><span class="kt">void</span><span class="w"> </span><span class="nf">main</span><span class="p">()</span><span class="w"> </span><span class="p">{</span>
<span class="linenos">63</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">input_shape</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">{</span><span class="mi">4</span><span class="p">,</span><span class="w"> </span><span class="mi">5</span><span class="p">,</span><span class="w"> </span><span class="mi">5</span><span class="p">};</span>
<span class="linenos">64</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">ndim</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">3</span><span class="p">;</span>
<span class="linenos">65</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">axes</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="p">{</span><span class="mi">1</span><span class="p">};</span>
<span class="linenos">66</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">num_axes</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">67</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">mode</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">7</span><span class="p">;</span>
<span class="linenos">68</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">keep_dims</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mi">1</span><span class="p">;</span>
<span class="linenos">69</span><span class="w"> </span><span class="kt">int</span><span class="w"> </span><span class="n">core_mask</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="mb">0b0001</span><span class="p">;</span><span class="w"> </span><span class="c1">// 私有存储版本只能设置为一个核心启动</span>
<span class="linenos">70</span><span class="w"> </span><span class="n">TestReduceL2Fp32</span><span class="p">(</span><span class="n">input_shape</span><span class="p">,</span><span class="w"> </span><span class="n">ndim</span><span class="p">,</span><span class="w"> </span><span class="n">axes</span><span class="p">,</span><span class="w"> </span><span class="n">num_axes</span><span class="p">,</span><span class="w"> </span><span class="n">mode</span><span class="p">,</span><span class="w"> </span><span class="n">keep_dims</span><span class="p">,</span><span class="w"> </span><span class="n">core_mask</span><span class="p">);</span>
<span class="linenos">71</span><span class="p">}</span>
</pre></div>
</div>
</section>
</div>
</div>
<div class="pageviews-container">
访问量:<span id="busuanzi_page_uv"></span>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="页脚">
<a href="reciprocal.html" class="btn btn-neutral float-left" title="Reciprocal" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> 上一页</a>
<a href="reducescatter.html" class="btn btn-neutral float-right" title="ReduceScatter" accesskey="n" rel="next">下一页 <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>&#169; 版权所有 2025 - 2026, NUDT-674。</p>
</div>
利用 <a href="https://www.sphinx-doc.org/">Sphinx</a> 构建,使用的
<a href="https://github.com/readthedocs/sphinx_rtd_theme">主题</a>
<a href="https://readthedocs.org">Read the Docs</a> 开发.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
<script src="//cdn.busuanzi.cc/busuanzi/3.6.9/busuanzi.min.js" defer></script>
</body>
</html>