uses MtxExpr, MtxVec, MtxExprInt, MtxForLoop; var Data, cmpData, nearDistance: Matrix; nearIdx: MatrixInt; threads: TMtxForLoop; begin // 1.) Create once ahead of time. This is the thread pool and is slow to create. threads := TMtxForLoop.Create; threads.ThreadCount := Controller.CpuCores*2; //hyperthreaded core count threads.BlockGranularity := 4; //required // 2.) This sets the "minimum" required. Also slow and needs to be set upfront and // it can only be done before any allocations are made by MtxVec. Controller.ThreadDimension := Max(threads.ThreadCount + 1, Controller.ThreadDimension); // 3.) Compiler assertions switch needs to be "off", when compling the source code data := [[1,2,3], [2,3,1], [3,2,1]]; cmpData := [[2,2,3], [2,3,4]]; ClusteredKNN(threads, Data, cmpData, 2, nearIdx, nearDistance); // Results: // nearIdx = [[0, 1], // data rows 0 and 1 are closest vectors to cmpData row 0. // [0, 1]] // data rows 0 and 1 are closest vectors to cmpData row 1. // nearDistance = [[1, 5], // [0,0] = sqr(2-1) + sqr(2-2) + sqr(3-3), distance from cmpData row 0 to Data row 0 is 1 // [3, 9]] // [1,0] = sqr(2-1) + sqr(3-2) + sqr(4-3), distance from cmpData row 1 to Data row 0 is 3 threads.Free;