2002 avidemux MPEG-4 : : : G99P045-1
|
|
|
- らむ すすむ
- 6 years ago
- Views:
Transcription
1 2002 avidemux MPEG-4 : : : G99P045-1
2 MPEG-4 MPEG-4 PC MPEG-4 MPI XviD MPEG-4 MPEG avidemux MPI MPEG-4 PE
3 MPEG MPEG PE Myrinet OS SCore avidemux avidemux 29 i
4 Pass ii
5 MPEG-4 VOP Folon-III/Folon-IV SCore avidemux iii
6 2.1 MPEG FOLON-III FOLON-IV MPI DivX 640x frames to DivX CQ Avi 320x frames to DivX CQ iv
7 1 1.1 MPEG-4 MPEG-4 PC MPEG-4 PC Cluster Folon3 Folon4 MPEG-4 avidemux MPI(Message Passing Interface) RWCP(: Real World Computing Partnership) SCore MPEG-4 avidemux 3 PC Cluster folon3 folon4 4 avidemux 5 avidemux 6 1
8 2 avidemux MPEG-4 MPE MPEG-4 MPEG Moving Picture Expert Group ISO( ) MPEG MPEG MPEG-4 MPEG-4 / MPEG-4 MPEG-1/2 MPEG-4 2.1: MPEG MPEG-1 384kbps 4Mbps VideoCD MPEG-2 1Mbps 100Mbps DVD MPEG-4 10Mbps MPEG-7 - EPG 2
9 I B B P I I P : 2.1: (AC/DC 8x8 ) ( ) ( ) MPEG-4 VO(Video Object) VO VOP(Video Object Plane) VOP 4 I-VOP( VOP) P-VOP( VOP) B-VOP( VOP) S-VOP( VOP) VOP I-VOP VOP P-VOP I P-VOP VOP B-BOP I P-VOP I P-VOP VOP S-VOP VOP 3
10 2.2 MPEG-4 API ( ) MPEG-4 XviD API 1. API PE PE 1 1PE ( ) 4
11 2.2: MPEG-4 VOP 2.4 MPEG-4 GOV(Group Of Video Object Plane) I,B,P,S-VOP MPEG-4 GOV 2-Pass ( 1-Pass 2-Pass ) I-VOP I-VOP MPEG-4 5
12 3 PC FOLON-III FOLON-IV PE FOLON-III 9 CPU PC Myrinet BASE-TX Ethernet Pentium-III 1GHz 1152MB FOLON-IV 17 CPU PC FOLON-III Myrinet BASE- TX Ethernet Myrinet2000 FOLON-III serial FOLON-IV fiber CPU Pentium-III-S 1.26GHz 4096MB MB FOLON-III Myrinet Myrinet Myricom Gigabit LAN Ethernet Myrinet 1. Ethernet 6
13 3.1: FOLON-III CPU L2 chache main memory PE0 roquefort Pentium-III 1GHz 256kB 1152MB PE1 roquefort01 Pentium-III 1GHz 256kB 1152MB PE2 roquefort02 Pentium-III 1GHz 256kB 1152MB PE3 roquefort03 Pentium-III 1GHz 256kB 1152MB PE4 roquefort04 Pentium-III 1GHz 256kB 1152MB PE5 roquefort05 Pentium-III 1GHz 256kB 1152MB PE6 roquefort06 Pentium-III 1GHz 256kB 1152MB PE7 roquefort07 Pentium-III 1GHz 256kB 1152MB PE8 roquefort08 Pentium-III 1GHz 512kB 1152MB 3.2: FOLON-IV CPU L2 chache main memory comte Pentium-III 1.26GHz 512kB 4096MB PE0, PE1 comte00 Pentium-III 1.26GHz 512kB 2048MB PE2, PE3 comte01 Pentium-III 1.26GHz 512kB 2048MB PE4, PE5 comte02 Pentium-III 1.26GHz 512kB 2048MB PE6, PE7 comte03 Pentium-III 1.26GHz 512kB 2048MB PE8, PE9 comte04 Pentium-III 1.26GHz 512kB 2048MB PE10, PE11 comte05 Pentium-III 1.26GHz 512kB 2048MB PE12, PE13 comte06 Pentium-III 1.26GHz 512kB 2048MB PE14, PE15 comte07 Pentium-III 1.26GHz 512kB 2048MB PE16, PE17 comte08 Pentium-III 1.26GHz 512kB 2048MB PE18, PE19 comte09 Pentium-III 1.26GHz 512kB 2048MB PE20, PE21 comte10 Pentium-III 1.26GHz 512kB 2048MB PE22, PE23 comte11 Pentium-III 1.26GHz 512kB 2048MB PE24, PE25 comte12 Pentium-III 1.26GHz 512kB 2048MB PE26, PE27 comte13 Pentium-III 1.26GHz 512kB 2048MB PE28, PE29 comte14 Pentium-III 1.26GHz 512kB 2048MB PE30, PE31 comte15 Pentium-III 1.26GHz 512kB 2048MB 7
14 backborn network NIS Server, NFS Server, Router comte15 Ethernet Hub Myrinet Switch comte00 comte folon-iv Ethernet Hub roquefort07 Myrinet Switch roquefort folon-iii 3.1: Folon-III/Folon-IV 8
15 Myrinet 16 Myrinet Myrinet 2. NIC Myrinet NIC LANai LANai NIC NIC NIC NIC NIC NIC 4 3. Gigabit Ethernet 1Gbps Myrinet Gbps 4Gbps OS FOLON Redhat Linux7.3 SCore5.2 SCore SCore 5.2 Score (RCWP) PC PC SCore SCore 9
16 3.2: SCore PMv2 PMv2 PMv2 Myrinet Ethernet UDP Shmem SCore-D SCore-D Linux PM SCore-D SCore-D SCore-D MPICH-SCore MPICH-SCore MPI MPICH PMv2 MPI MPICH-SCore Version 1.0 Version 2.0 MPICH MPICH MPICH-SCore Version
17 MPICH-SCore Version 1.0 Version 1.0 PVM-SCore PVM SCore PVM3.4 PVM PVM-SCore SCore PVM SCACH SCACH PMv2 PBS MRJ ( : ) NASA PBS(Protable Batch System) SCore MPC++ C++ C++ / Omni OpenMP OpenMP API RWCP Omni OpenMP SCASH OpenMP TACO C++ TACO 11
18 4 avidemux 4.1 PE PE GUI PE PE avidemux pre MPI MPI MPI C++ mpic++ mpic++ [ options ] filename... mpic++ MPICH-SCore MPI PATH 4.2 configure make./configure CC=mpicc CXX=mpic++ 12
19 mpicc mpic++ mpif77 mpif90 C MPI C++ MPI Fortran77 MPI Fortran90 4.1: MPI /usr/bin/ld: BFD assertion fail elf-strtab.c:262 make SCore checkpointing SCore checkpointing static avidemux static configure./configure CC="mpicc -nostatic" CXX="mpic++ -nostatic" source= oss_out.cpp object= oss_out.o libtool=no \ depfile=.deps/oss_out.po tmpdepfile=.deps/oss_out.tpo \ depmode=gcc3 /bin/sh../../admin/depcomp \ mpic++ -DHAVE_CONFIG_H -I. -I. -I../.. -I/usr/include/kde/ar ( ) -fno-check-new -c -o oss_out.o test -f oss_out.cpp echo./ oss_out.cpp mv: cannot stat.deps/oss_out.tpo : ar cru libadm_audiodevice.a ADM_deviceArts.o ADM_audiodevice.o ADM_deviceoss.o oss_out.o ar: oss_out.o: gcc 2.96 dependency style gcc3 configure Makefile avidemux/adm audiodevice/ MPI configure avidemux/adm audiodevice/makefile 13
20 CC = gcc CPP = gcc -E CXX = g++ CXXXPP = g++ -E 4.3 avidemux GTK+ Gtk-WARNING **: cannot open display: localhost:10.0 ssh X Forwarding ssh ( :4.3) DISPLAY scout scout ( :4.3) MPI C++ #include <mpi++.h> C #include <mpi.h> include MPI PE PE main.cpp myid( ),nprocs( PE ) 14
21 ssh login user s console cluster host DISPLAY=localhost:10.0 cluster host DISPLAY=localhost:10.0 "scout -g pcc" environment variables copied cluster host DISPLAY=localhost:10.0 X Forwarding user s console cluster host "scrun avidemux" DISPLAY=localhost:10.0 cluster host avidemux DISPLAY=localhost:10.0 cluster host avidemux DISPLAY=localhost: : 15
22 ssh login user s console cluster host DISPLAY=user s console:10.0 "scout -g pcc" cluster host DISPLAY=user s console:10.0 environment variables cop cluster host DISPLAY=user s console:10.0 user s console cluster host "scrun avidemux" DISPLAY=user s console:10.0 cluster host avidemux DISPLAY=user s console:10.0 cluster host avidemux DISPLAY=use s console: : 16
23 int myid,nprocs; int main(int argc, char *argv[]) { extern int myid; // extern int nprocs; // PE MPI MPI Init MPI PE main MPI Init MPI Comm rank MPI Comm size int main(int argc, char *argv[]) { pthread_t tid; FCT_VOID *thread; MPI_Init(&argc,&argv); MPI_Comm_rank(MPI_COMM_WORLD,&myid); MPI_Comm_size(MPI_COMM_WORLD,&nprocs); dll GTK+ gtk init PE avidemux GTK+ atexit 17
24 atexit(onexit); gtk_set_locale(); gtk_init(&argc, &argv); gdk_rgb_init(); PE gtk main PE PE children main PE gtk widget show PE0 window1 if(myid==0) { gtk_widget_show(window1); gtk_main(); } else { children_main(); } return 0; } PE GUI avidemux/gtk gui.cpp void HandleAction(Action action) (avidemux/gui action.hxx enum ) switch PE action MPI Isend PE GUI 18
25 void HandleAction(Action action) { uint32_t nf=0; mybcast_pe0(null, 0, MPI_CHAR, (int)action, MPI_COMM_WORLD); switch(action) { case ACT_LoadWork: GUI_FileSelRead("Select workbench to load ", A_loadWorkbench); updateloaded(); return; break; case ACT_VideoConfigure: printf("\n **\n"); videocodecconfigure(); return; break; PE PE switch gtk main children main HandleAction event switcher void children_main(void) { int eventtag; printf("node %d stand by ok.\n",myid); while(1){ eventtag = MPI_ANY_TAG; mybcast_children(null, 0, MPI_CHAR, &eventtag, MPI_COMM_WORLD); event_switcher(eventtag); } } 19
26 void event_switcher(int eventtag) { uint32_t nf=0; switch(eventtag) { case : exit(0); case ACT_LoadWork: recvfile(eventtag); updateloaded(); return; case ACT_VideoConfigure: videocodecconfigure(); return; event switcher HandleAction case GUI FileSelRead recvfile mybcast pe0 mybcast children MPI MPI Isend, MPI Irecv PE0 void mybcast_pe0(void *buff, int count, MPI_Datatype datatype, int tag, MPI_Comm MPI_Request mpirequest; MPI_Status mpistatus; int dest = 1; while(1) { if(dest > nprocs -1) break; MPI_Isend(buff, count, datatype, dest, tag, comm, &mpirequest); MPI_Wait(&mpirequest, &mpistatus); dest = dest * 2; } } 20
27 void mybcast_children(void *buff, int buffsize, MPI_Datatype datatype, int *retu MPI_Request mpirequest; MPI_Status mpistatus; int tag, count, distance, dest; tag = *returntag; MPI_Irecv(buff, buffsize, datatype, MPI_ANY_SOURCE, tag, comm, &mpirequest); MPI_Wait(&mpirequest, &mpistatus); if(tag== MPI_ANY_TAG) { *returntag=mpistatus.mpi_tag; } distance = myid-mpistatus.mpi_source; MPI_Get_count(&mpistatus, datatype, &count); while(1) { distance = distance * 2; dest = myid + distance; if(dest > nprocs -1) break; MPI_Isend(buff, count, datatype, dest, *returntag, comm, &mpirequest); MPI_Wait(&mpirequest, &mpistatus); } } atexit atexit onexit PE PE
28 void onexit( void ) { MPI_Request mpirequest; MPI_Status mpistatus; if(myid==0) mybcast_pe0(null,0,mpi_char,444444,mpi_comm_world); filtercleanup(); printf("node %d exiting...\n",myid); MPI_Finalize(); } PE exit(0) onexit PE PE PE PE PE PE PE PE PE avidemux case ACT_LoadWork: GUI_FileSelRead("Select workbench to load ", A_loadWorkbench); GUI FileSelRead GUI FileSelRead A loadworkbench GUI FileSelRead avidemux/adm tookkit/filesel.cpp start thread PE 22
29 void start_thread(void *ptr) { ( ) fd=fopen(selected_file,"rb"); if(!fd) { GUI_Alert("Cannot open this file!"); /* PE */ filesize = -1; mybcast_pe0(&filesize, 1, MPI_INT, 0, MPI_COMM_WORLD); return; } else { fseek(fd, 0, SEEK_END); filesize = ftell(fd); fseek(fd, 0, SEEK_SET); buff = (char *)malloc(filesize); fread(buff, filesize, 1, fd); // mybcast_pe0(&filesize, 1, MPI_INT, 0, MPI_COMM_WORLD); // mybcast_pe0(buff, filesize, MPI_CHAR, 1, MPI_COMM_WORLD); free(buff); } fclose(fd); _callback(selected_file); PE GUI FileSelRead recvfile recvfile PE switch GUI FileSelRead 23
30 void recvfile(int action) { ( ) mpitag = 0; // mybcast_children(&buffsize,1,mpi_int,&mpitag,mpi_comm_world); // if(buffsize < 0) return; buff = (char *)malloc(buffsize); mpitag = 1; // mybcast_children(buff,buffsize,mpi_char,&mpitag,mpi_comm_world); ( ) fd = fopen(tmpfilename, "wb"); if(!fd) { printf("node: %d can t make the tmpfile\n", myid); return; } if(!(fwrite(buff, buffsize, 1, fd))) { return; } free(buff); fclose(fd); switch(action) { case ACT_LoadWork: A_loadWorkbench(tmpfilename); break; ( ) } return; } Save AVI PE PE 24
31 avidemux/gui savenew.cpp A SaveAudioNVideo PE 1PE = ( - ) / PE PE = + (1PE x ) PE = PE + 1PE - 1 PE PE PE PE PE PE PE PE if(myid==0)filegather_recvfiles(); else filegather_sendfile(); PE filegather sendfile 1. PE ( PE ) 2. PE 25
32 void filegather_recvfiles(void) { ( ) for(i = 1; i<nprocs; i++) { // MPI_Recv(&buffsize,1,MPI_INT,MPI_ANY_SOURCE,0,MPI_COMM_WORLD,&mpistatus); source = mpistatus.mpi_source; ( ) buff = (char *)malloc(buffsize); // MPI_Recv(buff,buffsize,MPI_CHAR,source,1,MPI_COMM_WORLD,&mpistatus); ofstream out(tmpsaveavifilename, ios::out ios::binary); out.write(buff,buffsize); out.close(); free(buff); } } PE filegather recvfiles 1. PE ( PE ) 2. PE 3. PE 1 26
33 void filegather_sendfile(void) { ( ) ifstream in(tmpsaveavifilename, ios::in ios::binary); in.seekg(0,ios::end); filesize = in.tellg(); in.seekg(0,ios::beg); buff = (char *)malloc(filesize); in.read(buff,filesize); MPI_Send(&filesize,1,MPI_INT,0,0,MPI_COMM_WORLD); // MPI_Send(buff,filesize,MPI_CHAR,0,1,MPI_COMM_WORLD); // free(buff); in.close(); } MPI Gather PE PE avidemux A openavi(avi ) A appendavi( AVI ) A SaveAudioNVideo( audioprocessmode videoprocessmode 0 AVI ) 27
34 A_openAvi_pe0(tmpsaveavifilename00); for(i=1;i<nprocs;i++) { tmpsaveavifilename[filename_length] = 0 + (int)(i / 10); tmpsaveavifilename[filename_length+1] = 0 +(i % 10); tmpsaveavifilename[filename_length+2] = \0 ; A_appendAvi_pe0(tmpsaveavifilename); } tmpsaveavifilename[filename_length] = \0 ; framestart = tmpframestart; frameend = tmpframeend; A_SaveAudioNVideo_pe0(realname); 28
35 5 avidemux avidemux 640x360, DivX 320x240, 900 AVI DivX CQ( ) 4 3 folon4 SMP 1 1PE 5.1 PE PE 1 / PE 5.1 sec total bcasting merging gathering PE0 enctime max PE enctime min PE enctime pe0 PE0 enctime avg PE waittime max PE PE0 PE DivX PE PE avidemux Avi PE 29
36 PE total bcasting merging gathering enctime max enctime min PE enctime pe0 enctime avg waittime max : DivX 640x frames to DivX CQ4 30
37 PE total bcasting merging gathering enctime max enctime min PE enctime pe0 enctime avg waittime max : Avi 320x frames to DivX CQ4 31
38 5.1: avidemux 32
39 6 6.1 PE PE MPEG PE PE MPEG-1/2/4 GOP(GOV) 1/ PE I/O I/O MPEG AVI I/O mmap HDD 33
40 Pass 2-Pass PE 1-Pass 1-Pass PE 1-Pass PE GUI GUI PE 34
41 Folon avidemux mean 35
42 [1] P., :MPI,,2001. [2],,,,, : Linux,, [3] PC Cluster Consortium, 2001, [4] : GIMP,, [5] : MPI GIMP core,, [6] avidemux, 2002, [7] MPEG Home Page, 2003, [8] ISO/IEC JTC1/SC29/WG11 N2564 Overview of the MPEG-4 Standard, [9] PIONEER R&D, 2002, 36
WinHPC ppt
MPI.NET C# 2 2009 1 20 MPI.NET MPI.NET C# MPI.NET C# MPI MPI.NET 1 1 MPI.NET C# Hello World MPI.NET.NET Framework.NET C# API C# Microsoft.NET java.net (Visual Basic.NET Visual C++) C# class Helloworld
MPI usage
MPI (Version 0.99 2006 11 8 ) 1 1 MPI ( Message Passing Interface ) 1 1.1 MPI................................. 1 1.2............................... 2 1.2.1 MPI GATHER.......................... 2 1.2.2
44 6 MPI 4 : #LIB=-lmpich -lm 5 : LIB=-lmpi -lm 7 : mpi1: mpi1.c 8 : $(CC) -o mpi1 mpi1.c $(LIB) 9 : 10 : clean: 11 : -$(DEL) mpi1 make mpi1 1 % mpiru
43 6 MPI MPI(Message Passing Interface) MPI 1CPU/1 PC Cluster MPICH[5] 6.1 MPI MPI MPI 1 : #include 2 : #include 3 : #include 4 : 5 : #include "mpi.h" 7 : int main(int argc,
2 T 1 N n T n α = T 1 nt n (1) α = 1 100% OpenMP MPI OpenMP OpenMP MPI (Message Passing Interface) MPI MPICH OpenMPI 1 OpenMP MPI MPI (trivial p
22 6 22 MPI MPI 1 1 2 2 3 MPI 3 4 7 4.1.................................. 7 4.2 ( )................................ 10 4.3 (Allreduce )................................. 12 5 14 5.1........................................
演習 II 2 つの講義の演習 奇数回 : 連続系アルゴリズム 部分 偶数回 : 計算量理論 部分 連続系アルゴリズム部分は全 8 回を予定 前半 2 回 高性能計算 後半 6 回 数値計算 4 回以上の課題提出 ( プログラム + 考察レポート ) で単位
演習 II ( 連続系アルゴリズム ) 第 1 回 : MPI 須田研究室 M2 本谷徹 [email protected] 2012/10/05 2012/10/18 補足 訂正 演習 II 2 つの講義の演習 奇数回 : 連続系アルゴリズム 部分 偶数回 : 計算量理論 部分 連続系アルゴリズム部分は全 8 回を予定 前半 2 回 高性能計算 後半 6 回 数値計算 4 回以上の課題提出
±é½¬£²¡§£Í£Ð£É½éÊâ
2012 8 7 1 / 52 MPI Hello World I ( ) Hello World II ( ) I ( ) II ( ) ( sendrecv) π ( ) MPI fortran C wget http://www.na.scitec.kobe-u.ac.jp/ yaguchi/riken2012/enshu2.zip unzip enshu2.zip 2 / 52 FORTRAN
目 目 用方 用 用 方
大 生 大 工 目 目 用方 用 用 方 用 方 MS-MPI MPI.NET MPICH MPICH2 LAM/MPI Ver. 2 2 1 2 1 C C++ Fortan.NET C# C C++ Fortan 用 行 用 用 用 行 用 言 言 言 行 生 方 方 一 行 高 行 行 文 用 行 If ( rank == 0 ) { // 0 } else if (rank == 1) {
Microsoft PowerPoint - 講義:片方向通信.pptx
MPI( 片方向通信 ) 09 年 3 月 5 日 神戸大学大学院システム情報学研究科計算科学専攻横川三津夫 09/3/5 KOBE HPC Spring School 09 分散メモリ型並列計算機 複数のプロセッサがネットワークで接続されており, れぞれのプロセッサ (PE) が, メモリを持っている. 各 PE が自分のメモリ領域のみアクセス可能 特徴数千から数万 PE 規模の並列システムが可能
( CUDA CUDA CUDA CUDA ( NVIDIA CUDA I
GPGPU (II) GPGPU CUDA 1 GPGPU CUDA(CUDA Unified Device Architecture) CUDA NVIDIA GPU *1 C/C++ (nvcc) CUDA NVIDIA GPU GPU CUDA CUDA 1 CUDA CUDA 2 CUDA NVIDIA GPU PC Windows Linux MaxOSX CUDA GPU CUDA NVIDIA
Microsoft PowerPoint 並列アルゴリズム04.ppt
並列アルゴリズム 2005 年後期火曜 2 限 青柳睦 [email protected] http://server-500.cc.kyushu-u.ac.jp/ 11 月 8 日 ( 火 ) 5. MPI の基礎 6. 並列処理の性能評価 1 もくじ 1. 序並列計算機の現状 2. 計算方式およびアーキテクチュアの分類 3. 並列計算の目的と課題 4. 数値計算における各種の並列化
install
SCore SCore 5.0 2001.03.19 [email protected] SCore Backbone LAN Ethernet EEPRO100 Myrinet-2000 Fibre 02/03/20 2 1 NIC (Network Interface Card) NIC 100Mbps Ethernet EEPRO100 Tulip 3C905B Network Trunking
MPI MPI MPI.NET C# MPI Version2
MPI.NET C# 2 2009 2 27 MPI MPI MPI.NET C# MPI Version2 MPI (Message Passing Interface) MPI MPI Version 1 1994 1 1 1 1 ID MPI MPI_Send MPI_Recv if(rank == 0){ // 0 MPI_Send(); } else if(rank == 1){ // 1
Krylov (b) x k+1 := x k + α k p k (c) r k+1 := r k α k Ap k ( := b Ax k+1 ) (d) β k := r k r k 2 2 (e) : r k 2 / r 0 2 < ε R (f) p k+1 :=
127 10 Krylov Krylov (Conjugate-Gradient (CG ), Krylov ) MPIBNCpack 10.1 CG (Conjugate-Gradient CG ) A R n n a 11 a 12 a 1n a 21 a 22 a 2n A T = =... a n1 a n2 a nn n a 11 a 21 a n1 a 12 a 22 a n2 = A...
Microsoft PowerPoint - 演習2:MPI初歩.pptx
演習 2:MPI 初歩 - 並列に計算する - 2013 年 8 月 6 日 神戸大学大学院システム情報学研究科計算科学専攻横川三津夫 MPI( メッセージ パッシング インターフェース ) を使おう! [ 演習 2 の内容 ] はじめの一歩課題 1: Hello, world を並列に出力する. 課題 2: プロセス 0 からのメッセージを受け取る (1 対 1 通信 ). 部分に分けて計算しよう課題
SystemC言語概論
SystemC CPU S/W 2004/01/29 4 SystemC 1 SystemC 2.0.1 CPU S/W 3 ISS SystemC Co-Simulation 2004/01/29 4 SystemC 2 ISS SystemC Co-Simulation GenericCPU_Base ( ) GenericCPU_ISS GenericCPU_Prog GenericCPU_CoSim
nakayama15icm01_l7filter.pptx
Layer-7 SDN SDN NFV 50 % 3 MVNO 1 2 ICM @ 2015/01/16 2 1 1 2 2 1 2 2 ICM @ 2015/01/16 3 2 Service Dependent Management (SDM) SDM Simple Management of Access-Restriction Translator Gateway (SMART-GW) ICM
C/C++ FORTRAN FORTRAN MPI MPI MPI UNIX Windows (SIMD Single Instruction Multipule Data) SMP(Symmetric Multi Processor) MPI (thread) OpenMP[5]
MPI ( ) [email protected] 1 ( ) MPI MPI Message Passing Interface[2] MPI MPICH[3],LAM/MPI[4] (MIMDMultiple Instruction Multipule Data) Message Passing ( ) (MPI (rank) PE(Processing Element)
double float
2015 3 13 1 2 2 3 2.1.......................... 3 2.2............................. 3 3 4 3.1............................... 4 3.2 double float......................... 5 3.3 main.......................
¥Ñ¥Ã¥±¡¼¥¸ Rhpc ¤Î¾õ¶·
Rhpc COM-ONE 2015 R 27 12 5 1 / 29 1 2 Rhpc 3 forign MPI 4 Windows 5 2 / 29 1 2 Rhpc 3 forign MPI 4 Windows 5 3 / 29 Rhpc, R HPC Rhpc, ( ), snow..., Rhpc worker call Rhpc lapply 4 / 29 1 2 Rhpc 3 forign
Second-semi.PDF
PC 2000 2 18 2 HPC Agenda PC Linux OS UNIX OS Linux Linux OS HPC 1 1CPU CPU Beowulf PC (PC) PC CPU(Pentium ) Beowulf: NASA Tomas Sterling Donald Becker 2 (PC ) Beowulf PC!! Linux Cluster (1) Level 1:
120802_MPI.ppt
CPU CPU CPU CPU CPU SMP Symmetric MultiProcessing CPU CPU CPU CPU CPU CPU CPU CPU CPU CPU CPU CPU CP OpenMP MPI MPI CPU CPU CPU CPU CPU CPU CPU CPU CPU CPU MPI MPI+OpenMP CPU CPU CPU CPU CPU CPU CPU CP
main() {... } main() { main() { main() {......... } } } main() { main() { main() {......... } } } main() { if(rank==)... } main() { if(rank==)... } main() { if(rank==x)... } P(N) P(N) / P(M) * ( M / N
86
86 86 86 main() {... } main() { main() { main() {......... } } } 86 main() { main() { main() {......... } } } main() { if(rank==)... } main() { if(rank==)... } main() { if(rank==x)... } 86 P(N) P(N) /
C
C 1 2 1.1........................... 2 1.2........................ 2 1.3 make................................................ 3 1.4....................................... 5 1.4.1 strip................................................
XcalableMP入門
XcalableMP 1 HPC-Phys@, 2018 8 22 XcalableMP XMP XMP Lattice QCD!2 XMP MPI MPI!3 XMP 1/2 PCXMP MPI Fortran CCoarray C++ MPIMPI XMP OpenMP http://xcalablemp.org!4 XMP 2/2 SPMD (Single Program Multiple Data)
PowerPoint プレゼンテーション
AICS 公開ソフトウェア講習会 15 回 表題通信ライブラリと I/O ライブラリ 場所 AICS R104-2 時間 2016/03/23 ( 水 ) 13:30-17:00 13:30-13:40 全体説明 13:40-14:10 PRDMA 14:10-14:40 MPICH 14:40-15:10 PVAS 15:10-15:30 休憩 15:30-16:00 Carp 16:00-16:30
VNSTProductDes3.0-1_jp.pdf
Visual Nexus Secure Transport 2005/10/18 Visual Nexus http:// www.visualnexus.com/jp/support.htm Visual Nexus Secure Transport 2005/02/25 1 2005/10/18 Ver3.0-1 2005 10 18 108-0075 21119 2 Visual Nexus
SystemC 2.0を用いた簡易CPUバスモデルの設計
SystemC 2.0 CPU CPU CTD&SW CT-PF 2002/1/23 1 CPU BCA UTF GenericCPU IO (sc_main) 2002/1/23 2 CPU CPU CQ 1997 11 Page 207 4 Perl Verilog-HDL CPU / Verilog-HDL SystemC 2.0 (asm) ROM (test.hex) 2002/1/23
£Ã¥×¥í¥°¥é¥ß¥ó¥°ÆþÌç (2018) - Â裵²ó ¨¡ À©¸æ¹½Â¤¡§¾ò·ïʬ´ô ¨¡
(2018) 2018 5 17 0 0 if switch if if ( ) if ( 0) if ( ) if ( 0) if ( ) (0) if ( 0) if ( ) (0) ( ) ; if else if ( ) 1 else 2 if else ( 0) 1 if ( ) 1 else 2 if else ( 0) 1 if ( ) 1 else 2 (0) 2 if else
<4D F736F F F696E74202D C097F B A E B93C782DD8EE682E890EA97705D>
並列アルゴリズム 2005 年後期火曜 2 限青柳睦 [email protected] http//server-500.cc.kyushu-u.ac.jp/ 11 月 29( 火 ) 7. 集団通信 (Collective Communication) 8. 領域分割 (Domain Decomposition) 1 もくじ 1. 序並列計算機の現状 2. 計算方式およびアーキテクチュアの分類
Quickstart Guide 3rd Edition
10 QNX QNX 1 2 3 4 5 QNX Momentics QNX Neutrino RTOS QNX Neutrino 6 7 8 QNX Neutrino 9 10 1 1 QNX Neutrino RTOS QNX Momentics Windows Vista Windows 2000 Windows XP Linux QNX Neutrino QNX Momentics CD http://www.qnx.co.jp/
第3回戦略シンポジウム緑川公開用
2010 5 15 - - (SDSM) SMS MpC DLM Top500 Top 500 list of Supercomputers (http://www.top500.org) Top 500 list of Supercomputers (http://www.top500.org) 1998 11 SMP Symmetric Multiprocessor CPU CPU CPU CPU
programmingII2019-v01
II 2019 2Q A 6/11 6/18 6/25 7/2 7/9 7/16 7/23 B 6/12 6/19 6/24 7/3 7/10 7/17 7/24 x = 0 dv(t) dt = g Z t2 t 1 dv(t) dt dt = Z t2 t 1 gdt g v(t 2 ) = v(t 1 ) + g(t 2 t 1 ) v v(t) x g(t 2 t 1 ) t 1 t 2
Intel® Compilers Professional Editions
2007 6 10.0 * 10.0 6 5 Software &Solutions group 10.0 (SV) C++ Fortran OpenMP* OpenMP API / : 200 C/C++ Fortran : OpenMP : : : $ cat -n main.cpp 1 #include 2 int foo(const char *); 3 int main()
コードのチューニング
MPI による並列化実装 ~ ハイブリッド並列 ~ 八木学 ( 理化学研究所計算科学研究センター ) KOBE HPC Spring School 2019 2019 年 3 月 14 日 MPI とは Message Passing Interface 分散メモリのプロセス間の通信規格(API) SPMD(Single Program Multi Data) が基本 - 各プロセスが 同じことをやる
115 9 MPIBNCpack 9.1 BNCpack 1CPU X = , B =
115 9 MPIBNCpack 9.1 BNCpack 1CPU 1 2 3 4 5 25 24 23 22 21 6 7 8 9 10 20 19 18 17 16 X = 11 12 13 14 15, B = 15 14 13 12 11 16 17 18 19 20 10 9 8 7 6 21 22 23 24 25 5 4 3 2 1 C = XB X dmat1 B dmat2 C dmat
£Ã¥×¥í¥°¥é¥ß¥ó¥°ÆþÌç (2018) - Â裶²ó ¨¡ À©¸æ¹½Â¤¡§·«¤êÊÖ¤· ¨¡
(2018) 2018 5 24 ( ) while ( ) do while ( ); for ( ; ; ) while int i = 0; while (i < 100) { printf("i = %3d\n", i); i++; while int i = 0; i while (i < 100) { printf("i = %3d\n", i); i++; while int i =
2 2 Gtk+ GUI (widget ) GUI Gtk+ GUI Gtk+ GUI 2.2 Gtk GUI sample1.c Web (http://www.cyber.t.u-tokyo.ac.jp/ tani/class/mech enshu/) enshu2009gui1.tar.gz
1 2009 B4 GUI TA http://www.cyber.t.u-tokyo.ac.jp/ tani/class/mech enshu/ 2008 6 11 1 1 1 4 C GUI(Graphical User Interface) X Window System GUI 5 GUI 2 Gtk+ GUI 2.1 GUI GUI GUI (event driven) GUI GUI GUI
II ( ) prog8-1.c s1542h017%./prog8-1 1 => 35 Hiroshi 2 => 23 Koji 3 => 67 Satoshi 4 => 87 Junko 5 => 64 Ichiro 6 => 89 Mari 7 => 73 D
II 8 2003 11 12 1 6 ( ) prog8-1.c s1542h017%./prog8-1 1 => 35 Hiroshi 2 => 23 Koji 3 => 67 Satoshi 4 => 87 Junko 5 => 64 Ichiro 6 => 89 Mari 7 => 73 Daisuke 8 =>. 73 Daisuke 35 Hiroshi 64 Ichiro 87 Junko
TA tani/class/mech enshu/ X Window System GUI(Graphical User Interface) GUI (event driven) 2 Gtk
1 2011 8 TA http://www.cyber.t.u-tokyo.ac.jp/ tani/class/mech enshu/ 2011 7 7 1 X Window System GUI(Graphical User Interface) GUI (event driven) 2 Gtk+ GUI 2.1 GUI GUI GUI (event driven) GUI GUI GUI GUI
Northern Lights Server
FirstStep Guide Northern Lights Server Intel Management Module (Advanced Module / ISM 8.4) 2 www.nlcomputer.com 1 FirstStep Guide 1.1. INTEL MANAGEMENT MODULE 2... 5 1.2.... 9 1.3.... 10 2.1. BMC...11
:30 12:00 I. I VI II. III. IV. a d V. VI
2018 2018 08 02 10:30 12:00 I. I VI II. III. IV. a d V. VI. 80 100 60 1 I. Backus-Naur BNF N N y N x N xy yx : yxxyxy N N x, y N (parse tree) (1) yxyyx (2) xyxyxy (3) yxxyxyy (4) yxxxyxxy N y N x N yx
Microsoft Word - C.....u.K...doc
C uwêííôöðöõ Ð C ÔÖÐÖÕ ÐÊÉÌÊ C ÔÖÐÖÕÊ C ÔÖÐÖÕÊ Ç Ê Æ ~ if eíè ~ for ÒÑÒ ÌÆÊÉÉÊ ~ switch ÉeÍÈ ~ while ÒÑÒ ÊÍÍÔÖÐÖÕÊ ~ 1 C ÔÖÐÖÕ ÐÊÉÌÊ uê~ ÏÒÏÑ Ð ÓÏÖ CUI Ô ÑÊ ÏÒÏÑ ÔÖÐÖÕÎ d ÈÍÉÇÊ ÆÒ Ö ÒÐÑÒ ÊÔÎÏÖÎ d ÉÇÍÊ
ネットワークビデオレコーダー VK-64/VK-16/VK-Lite v2.2 セットアップガイド
VK-64/VK-16/VK-Lite Ver. 2.2 VK-64 v2.2 VK-16 v2.2 ( VK-64/VK-16) VK-Lite v2.2 ( VK-Lite) VK-64/VK-16 VK-Lite 2 1. 2. 3. 4. 2. 3. ( ) ( ) canon.jp/webview Canon Canon Microsoft Windows Microsoft Internet
58 7 MPI 7 : main(int argc, char *argv[]) 8 : { 9 : int num_procs, myrank; 10 : double a, b; 11 : int tag = 0; 12 : MPI_Status status; 13 : 1 MPI_Init
57 7 MPI MPI 1 1 7.1 Bcast( ) allocate Bcast a=1 PE0 a=1 PE1 a=1 PE2 a=1 PE3 7.1: Bcast 58 7 MPI 7 : main(int argc, char *argv[]) 8 : { 9 : int num_procs, myrank; 10 : double a, b; 11 : int tag = 0; 12
インテル® MPI ライブラリー・ランタイム環境入門ガイド
MPI Intel's Terms and Conditions of Sales ( ) 2 IntelIntel Intel Corporation * 2006 Intel Corporation. MPI MPI * (ANL) MPI MPICH2* NBCL (Network-Based Computing Laboratory) MVAPICH2* InfiniBand* RDMA 3
ProLiant ML110 Generation 4 システム構成図
HP ProLiant ML110 Generation 5 2010 4 16 1 OVERVIEW ProLiant ML110 Generation 5 ProLiant ML110 Generation 5 1, 2 LED LED ( ) ( ) ( ) Lights-Out 100c ( ) 2 3 6 USB SATA ML110 G5 ProLiant ML110 G5 SATA /
I. Backus-Naur BNF S + S S * S S x S +, *, x BNF S (parse tree) : * x + x x S * S x + S S S x x (1) * x x * x (2) * + x x x (3) + x * x + x x (4) * *
2015 2015 07 30 10:30 12:00 I. I VI II. III. IV. a d V. VI. 80 100 60 1 I. Backus-Naur BNF S + S S * S S x S +, *, x BNF S (parse tree) : * x + x x S * S x + S S S x x (1) * x x * x (2) * + x x x (3) +
DKA ( 1) 1 n i=1 α i c n 1 = 0 ( 1) 2 n i 1 <i 2 α i1 α i2 c n 2 = 0 ( 1) 3 n i 1 <i 2 <i 3 α i1 α i2 α i3 c n 3 = 0. ( 1) n 1 n i 1 <i 2 < <i
149 11 DKA IEEE754 11.1 DKA n p(x) = a n x n + a n 1 x n 1 + + a 0 (11.1) p(x) = 0 (11.2) p n (x) q n (x) = x n + c n 1 x n 1 + + c 1 x + c 0 q n (x) = 0 (11.3) c i = a i a n (i = 0, 1,..., n 1) (11.3)
ProLiant ML110 Generation 4 システム構成図
HP ProLiant ML110 Generation 4 2008 1 24 OVERVIEW ProLiant ML110 Generation 4 ProLiant ML110 Generation 4 1 2 SCSI USB 3 6 SATA SAS LED LED 4 Lights-Out 100c ( ) ProLiant ML110 G4 SATA / SAS ( ) Celeron
「産業上利用することができる発明」の審査の運用指針(案)
1 1.... 2 1.1... 2 2.... 4 2.1... 4 3.... 6 4.... 6 1 1 29 1 29 1 1 1. 2 1 1.1 (1) (2) (3) 1 (4) 2 4 1 2 2 3 4 31 12 5 7 2.2 (5) ( a ) ( b ) 1 3 2 ( c ) (6) 2. 2.1 2.1 (1) 4 ( i ) ( ii ) ( iii ) ( iv)
Condition DAQ condition condition 2 3 XML key value
Condition DAQ condition 2009 6 10 2009 7 2 2009 7 3 2010 8 3 1 2 2 condition 2 3 XML key value 3 4 4 4.1............................. 5 4.2...................... 5 5 6 6 Makefile 7 7 9 7.1 Condition.h.............................
1 (bit ) ( ) PC WS CPU IEEE754 standard ( 24bit) ( 53bit)
GNU MP BNCpack [email protected] 2002 9 20 ( ) Linux Conference 2002 1 1 (bit ) ( ) PC WS CPU IEEE754 standard ( 24bit) ( 53bit) 10 2 2 3 4 5768:9:; = %? @BADCEGFH-I:JLKNMNOQP R )TSVU!" # %$ & " #
A Responsive Processor for Parallel/Distributed Real-time Processing
E-mail: yamasaki@{ics.keio.ac.jp, etl.go.jp} http://www.ny.ics.keio.ac.jp etc. CPU) I/O I/O or Home Automation, Factory Automation, (SPARC) (SDRAM I/F, DMAC, PCI, USB, Timers/Counters, SIO, PIO, )
RedHat OpenFOAM OpenFOAM ver 2.3 RedHat(RHEL)
RedHat Linux OpenFOAM (OpenFOAM 2.2.x, 2.3.x) y.imagawa 14.3.8 RedHat OpenFOAM OpenFOAM ver 2.3 RedHat(RHEL) OpenFOAM OpenFOAM Linux git Repository RedHat Linux OpenFOAM centfoam? OpenFOAM OS CentOS 6.5
00.目次_ope
816XL ii iii iv iv User Entry 1 3 v vi vii viii 1 1 C: >VTTERM 1- 1 1-3 1 1-4 1 1-5 1 1-6 1 1-7 1 1-8 1 1-9 1 1-10 C: >VTN 1 Host Name: 1-11 1 01 1-1 0.0.0.0 1 1-13 1 1-14 - -3 Port status and configuration
ARM gcc Kunihiko IMAI 2009 1 11 ARM gcc 1 2 2 2 3 3 4 3 4.1................................. 3 4.2............................................ 4 4.3........................................
Java updated
Java 2003.07.14 updated 3 1 Java 5 1.1 Java................................. 5 1.2 Java..................................... 5 1.3 Java................................ 6 1.3.1 Java.......................
r07.dvi
19 7 ( ) 2019.4.20 1 1.1 (data structure ( (dynamic data structure 1 malloc C free C (garbage collection GC C GC(conservative GC 2 1.2 data next p 3 5 7 9 p 3 5 7 9 p 3 5 7 9 1 1: (single linked list 1
09中西
PC NEC Linux (1) (2) (1) (2) 1 Linux Linux 2002.11.22) LLNL Linux Intel Xeon 2300 ASCIWhite1/7 / HPC (IDC) 2002 800 2005 2004 HPC 80%Linux) Linux ASCI Purple (ASCI 100TFlops Blue Gene/L 1PFlops (2005)
