Resource WG Update PRAGMA 14 Mason Katz, Yoshio Tanaka, Cindy Zheng.
2015/5/31 Fifty Years of Japanese HPC ─From transistor to Exascale─ Yoshio Oyanagi Education...
-
Upload
cecilia-doubleday -
Category
Documents
-
view
216 -
download
0
Transcript of 2015/5/31 Fifty Years of Japanese HPC ─From transistor to Exascale─ Yoshio Oyanagi Education...
23/04/21 1
Fifty Years of Japanese HPC─From transistor to Exascale─
Yoshio OyanagiEducation Center for Computational Sciences
Kobe University
Fifty years of Japanese HPC
Outline of my talk Historical overview of HPC in Japan, as
contrasted to US, Europe, China, ….. What is the difference between Japan and US
trends?– In Japan, big electronic companies manufactured
vector and parallel supercomputers besides main frames.
– In US, venture companies were active in vector (Cray, Convex etc.) as well as parallel (TMC, FPS, Meiko, nCUBE, KSR, ….) machines.
23/04/21 2Fifty years of Japanese HPC
“50 Years of HPC”A Column in HPCwire Japan
(Since July, 2014. Updated every Monday.)
23/04/21 3
http://www.hpcwire.jp(Sorry in Japanese)
Fifty years of Japanese HPC
1960’s in Japan
OKITAC-5090 (1961) Transistors + Diodes +
core memory
Floating point (decimal 10+2)– Add/sub 0.4 ms– Mult 4.9 ms (peak 0.4 kFlops)
23/04/21 4
Not very high performance !!
Fifty years of Japanese HPC
http://museum.ipsj.or.jp/computer/dawn/0037.html
1960’s in US CDC6600 IBM System/360
– 4 Mflops (peak)
Contract with DARPA for the ILLIAC IV
23/04/21 5
Pictures from Wikipedia
Fifty years of Japanese HPC
1960’sJapan USA
FACOM 270 HITAC 5020, 8000 TOSBAC 3400 NEAC 2200 MELCOM 3100, 9100 OUK 9400 FACOM 230-60
IBM 360 model 91 (1967)
IBM 360 model 85 (1968)
Intel founded (1968) IBM 2938 array proc.
(1969) CDC7600 (1969) AMD founded (1969)
23/04/21 6Fifty years of Japanese HPC
23/04/21 7
Primordial Ages(1970’s)Japan USA/Europe
1970 IBM System/370
1971 CDC STAR-100 announced
1972 Goodyear STARAN
1974 DAP, BSP and HEP started
1975 ILLIAC IV operational
1976 Cray-1 shipped to LLNL
1976 FPS AP-120B
1977 Siemens SMS-201
1979 HEP single processor operational
(red: vector architecture)
1970 FACOM 230-75
1977 FACOM 230-75 APU
1978 HITAC M-180 IAP
1978 PAX project started
1979 HITAC M-200H IAP
1979 MELCOM COSMOIIIIAP
1981 MITI Supercomputer Project started( ~ 89)
(green: parallel architecture)Fifty years of Japanese HPC
23/04/21 8
Characteristics of Japanese vectors1. Japanese vector processors only a couple of years after Cray-1.
2. Manufactured by main-frame vendors with semiconductor facilities (not ventures)
Vector processors are attached to mainframes
3. FACOM 230-75 APU (first Japanese vector)
a) CPU and APU share the main memory (1 MW×36bits)Heterogeneous architecture
b) Vector register of 1792 words
c) list vector and DO-loop with IF supported
d) 22 Mflops (single), 11 Mflops (double)
e) installed in NAL in August 1977
Fifty years of Japanese HPC
Characteristics of Japanese vectors4. HITAC IAP (1978-)
a) memory-to-memory (no vector registers)
b) summation, inner product and 1st order recurrence could be vectorized in FORTRAN
c) vectorization of loops with IF’s (M280)
d) M-200H IAP (1979): 48 Mflops,
M-280H IAP (1982): 67 MFlops
5. NEC ACOS 1000 IAP (1982)a) 36 bit machine
b) peak 28 MFlops
23/04/21 9Fifty years of Japanese HPC
23/04/21 10
1st Generation (1H of 1980’s)Japan US/others
1981 CDC Cyber 2051982 Cosmic Cube Project1982 Cray X-MP/2 (420 MF)1982 Alliant FX/8 delivered1982 HEP installed1983 Encore, Sequent and TMC
founded, 1983 ETA span off from CDC1984 Cray X-MP/4 (820 MF)1984 Legend group in China started1985 Convex C11985 Intel iPSC/1, T414, nCUBE/1,
Stellar, Ardent1985 Cray-2 (1.952 GF)1986 CM-1 shipped1986 FPS T-series
1980 PAX-32
1981 MITI Supercomputer
Project ( ~ 89)
1982 Fifth Generation Project ( ~ 92)
1982 NEC ACOS-1000 IAP
1982 HITAC M280H IAP
1983 HITAC S-810/20 (630 MF)
1983 FACOM VP-2001984 PAX-64J
1985 FACOM VP-400 (1.142 GF)
1985 NEC SX-2 (1.3 GF)
Fifty years of Japanese HPC
23/04/21 11
Characteristics of Japanese SC in the 1st Generation
1. Compatibility with the mainframes
2. Single processor with multiple pipes
3. Large main memory (256MB vs. X-MP 32MB)
4. Large vector registers
5. List-directed vector instructions (gather/scat)
6. Different control of vector units
7. No commercial parallel machines
Fifty years of Japanese HPC
Characteristics of Japanese SC’s in the 1st Generation
8. Aggressive installation of SC’s in universities and laboratories
– 7 SC centers open to all university people– Laboratory SC’s for physics, chemistry, …
In US, most SC’s are in DOE, DOD, NASA,not available for university researchersLax Report (1982)
– 5 NSF centers in 1985-6
23/04/21 12Fifty years of Japanese HPC
23/04/21 13
Characteristics of Japanese SC’s in the 1st Generation
9. MITI Supercomputer Project (1981-89fy) Started before the Japanese supers (S810, VP,
SX) Targets:
– 10 GFlops parallel vector machine (PHI),– Dataflow machine (sigma-1)– Josephson device, MPP etc.
In alliance with six companies
Fifty years of Japanese HPC
23/04/21 14
2nd Generation (2H of 1980’s)Japan US and Europe etc.
1986 “863” Plan in China1986 Manheim Supercomputer
seminar (→ISC)1987 ETA-10 (10 GF)1987 CM-21988 Cray Y-MP (2.66 GF)1988 Intel ipsc/21988 First Supercomputing
Conference in Orlando1989 ETA shut down, JvN SC
shut down1989 BBN TC2000, Myrias
SPS-2, Meiko CS, NCube21990 Intel ipsc/860, MasPar
MP-1
1987 HITAC S-820 (3 GF)1989 FACOM VP2600 (5 GF)1990 MITI Supercomputer
Project ended1990 NEC SX-3 (22 GF)1990 QCDPAX completed
Fifty years of Japanese HPC
23/04/21 15
Characteristics of Japanese SC in the 2nd Generation
1. Vector multiprocessor appeared in Japan
with modest multiplicity 2-4 vs. 8 (Y-MP, ETA)
2. The semiconductor technology developed for the vector is transferred to mainframes
(Used to be: mainframe→vector)
3. Still no commercial MPP’s in Japan, although parallel research was active in academia
Fifty years of Japanese HPC
Installation of SC’s in Japan (1987-8) Cray Research (Cray-1, X-MP):10 ETA (ETA-10): 1 Hitachi (S810):15 NEC (SX-1/2):7 Fujitsu (VP-50, 100, 200, 400):36
23/04/21 16Fifty years of Japanese HPC
US-Japan Trade Conflicts
1985/9: Plaza Accord (G5) 1985: SX-2 was cancelled by NCAR after
bidding 1986/9: US-Japan Semiconductor Agreement 1987: Japanese SC was cancelled by MIT after
bidding
23/04/21 17Fifty years of Japanese HPC
23/04/21 18
Super 301 Act
In 1989, US government decided to apply “Super 301 Act” (Omnibus Trade and Competitiveness Act of 1988) to Japan and identified three items including supercomputers.
Washington threatened Japanese governmental institutions to purchase US supercomputers. (Titech ETA10, ETL X-MP)
On the other hand, US governmental institutions had no Japanese supercomputers at all.
Fifty years of Japanese HPC
23/04/21 19
3rd Generation (1H of 1990’s)Japan USA/Europe
1990 MasPar MP-11990 Intel iPSC/8601991 HPCC started (-96)1991 Cray Y-MP C90 (16 GF)1991 Intel Paragon, TMC CM-51992 FPS bankrupt 1992 MasPar MP-21993 Top500 started1993 HPCN started ( ~ 2001)1993 Cray T3D, CS6400, nCUBE2, KSR11993 SSI shut down1993 IBM SP-11993 Cray-31994 SP-21994 TMC, KSR Chapter 11
1992 RWCP started
1992 CP-PACS started
1993 Fujitsu NWT
1993 Fujitsu VPP500
1993 HITAC S-3800 (32 GF)
1993 NEC Cenju-3
1994 Fujitsu AP1000
1995 NEC SX-4
Fifty years of Japanese HPC
23/04/21 20
Characteristics of Japanese SC in the 3rd Generation
Drastic changes in Japanese vectors1. Hitachi (S3800)
Shared memory vector parallel processorusing ECL technology
2. Fujitsu (VPP500)Distributed memory vector parallel proc.using GaAs as well as silicon tech.
3. NEC (SX-3)Cluster of shared memory vector parallelUnix as host OS
4. No action to “Attack of killer micros.”(SC90)
◆ Commercial MPPs, sold as a parallel testbed
Fifty years of Japanese HPC
Trends in US (1st half of 1990’s) Active vector machines: Cray Y-MP, C90 and
Convex C2 MPP:
Performance of COTS CPU’s was increasing drastically custom CPU → commodity CPU chips ventures company → big companies (IBM, Cray, Intel)
Strong national initiative:HPCC, NII, HPC Act 1991
23/04/21 21Fifty years of Japanese HPC
HPCC in US Blue Book (1991/2, G.W.Bush)
– “Grand Challenges: High Performance Computing and Communications”
The High Performance Computing Act of 1991 Trade conflicts:
– “Japan should buy more US supers” (M. Kantor, 1993/4) Otherwise, possible retaliation.
– 6 out of 11 in public sector bought US machines in the 1994 supplementary budget.
In Europe, Rubbia Report (1991/1)– European Teraflop Initiative
23/04/21 22Fifty years of Japanese HPC
23/04/21 23
4th Generation (2H of 1990’s)Japan USA/Europe/China
1995 DOE: ASCI started1995 Cray T90 (57.6 GF)
1995 Cray Computer bankrupt1996 Dawning in China started1996 Cray T3E 1996 Cray Research merged into SGI1996/10 Serymour died1996 nCUBE merged into Oracle1996 MasPar went out of HPC1997 ASCI Red (Intel)1997 NSF: NPACI started1998 Cray SV11998 ASCI Blue Pacific (IBM)1998 ASCI Blue Mountain (SGI)
1995 Fujitsu VPP300
1996 cp-pacs completed
1996 Hitachi SR2201
1996 Fujitsu VPP700
1996 Fujitsu AP30001997 NEC Cenju-41998 Hitachi SR80001998 NEC SX-5
Fifty years of Japanese HPC
23/04/21 24
Characteristics of Japanese SC in the 4th G.
1. Fujitsu and NEC seem to follow the line of conventional vector supercomputers in CMOS
Fujitsu: distributed memory
NEC: cluster of shared memory nodes
2. Hitachi adopted RISC (pseudo)vector architecture.
SR2201: sliding window (proposed by Tsukuba)
SR8000: 8 tightly coupled CPUs in one node
(self-developed CPU with Power architecture)
Fifty years of Japanese HPC
US Trends ASCI Project (originally 1995-2004)
– SC’s in LANL, LLNL, SNL– Red (1+), Blue (3+), White (10+), Q(30+),
Purple (100+) --- every 2 years PITAC (I:1997-2001, II: 2003-2005)
– IT2 project NPACI (1997-2004) Petaflops I in Pasadena (1994)
Petaflops II in Santa Barbara (1999)
23/04/21 25Fifty years of Japanese HPC
NCAR Procurement 1996/5/20 UCAR selected SX-4 for NCAR
– finalists were C90, SX-4, VPP700 Criticism by Cray and Obey
– Tax from US people should be used for US competitiveness
– NEC (and Fujitsu) was dumping 1996/7/29 Cray filed an apeal to DoC and ITC for
dumping 1997
– 454% anti-dumping customs to NEC supercomputers
– 388.7% to Fujitsu
23/04/21 26Fifty years of Japanese HPC
23/04/21 27
9306 9311 9406 9411 9506 9511 9606 9611 9706 9711 9806 9811 9906 9911 0006 0011 0106 01111 NWT NWT NWT NWT Todai cp- p2 NWT NWT NWT cp- p3 Todai NWT4 Todai cp- p Todai5 NEC ATP ATP KEK KEK Todai LRZ Todai6 AES NEC Tsuku Tsuk Todai cp- p KEK7 AES Riken Riken J AERI KEK NWT LRZ Todai8 KEK ECMW Osak9 NEC Kyush Todai KEK
10 HitachHitac NEC ECMW11 Todai Todai J AERI Stutt12 NEC Nagoy AES TAC ECMWLRZ Osak13 Toho Toho Todai14 ATP Gene J AERI Todai cp- p KEK15 AES Tsuk ISS Nagoy NWT Kyoto16 NEC Riken ECMW17 Toho Toho Gene NEC Kyush TAC ISS Todai LRZ18 AES Toho ISS Osaka KEK AES cp- p J MA19 IMS AES ATP Osaka ECMWFZJ KEK20 IMS Tsuk Stutt
Fifty years of Japanese HPC
Japanese machines in Top 20
23/04/21 28
Fifth Generation (1H of 2000)Japan US/Europe
2000: Tera became Cray
2000: SGI: Origin 3000
2000: ASCI White (LLNL, IBM) 12 TF
2001: NSF: TeraGrid stared
2002: ASCI Q (LANL, HP) 20TF
2002: DOD: HPCS started
2002: Cray (NEC) SX-6 to ARSC
2004: NASA Columbia (SGI) 64TF
2004: BlueGene/L at IBM 90TF
2004: “The Path to Extreme Computing” conf. (to Exa)
2005: BlueGene/L (360TF)
2005: ASCI Red Storm (SNL)Cray XT3/XT4
2001: NEC: anti-dumping customs cleared
2001: Fujitsu PRIMEPOWER 2000
2001: NEC SX-6
2002: Earth Simulator 40TF
2002: Fujitsu PRIMEPOWER HPC2500
2003: NEC SX-7
2004: NEC SX-8
2004: Hitachi SR11000
Fifty years of Japanese HPC
Japan Trends NEC kept making vector machines after the Earth
Simulator Fujitsu: PRIMEPOWER (Sparc) and PRIMERGFY
(x86) Hitachi: OEM of IBM servers. SR11000 (Power4+,
6.8 GF/CPU) NAREGI (2003-8): Grid project
23/04/21 29Fifty years of Japanese HPC
Japan Trends
IT Strategic Headquarter (2001): e-Japan, but only network was emphasized.– At this stage, level up of supercomputers was to be
promoted according to the needs of each field (not a national project).
Earth Simulator attained 36 Tflops (2002) Information Science and Technology committee in
Mext has been discussing the measures to promote computational science and technology since August 2004.
Fifty years of Japanese HPC 3023/04/21
Japanese machines in top 20
23/04/21 Fifty years of Japanese HPC 31
0206 0211 0306 0311 0406 0411 0506 0511 0606 0611 0706 0711 0806 0811 0906 0911 1006 1011 1106 1111 1206 1211 1306 13111 ES ES ES ES ES K K2 K3 ES K4 ES TIT K K5 TIT TIT6 NAL ES7 Riken TIT8 AIST9 TIT
10 ES11 J AXA TIT12 AIST Roku13 Todai TIT14 LRZ Riken ES TIT15 J AERI AIST TIT Todai Roku1617 KEK TIT18 KEK Todai19 Osak AIST20 ES Tsuk Roku
US Trends DOE: ASCI continues
– BlueGene and Red Storm added NSF: Teragrid (2001-10) DOD: HPCS (High Productivity Computing Systems)
– 2002: Phase I (IBM, Cray, Sun, HP, SGI)
– 2003: Phase II (Cray, IBM, Sun)
– 2006: Phase III (Cray: XC, IBM: PERCS) HEC Revitalization Act of 2004 and 2005 Exa started in “The Path to Extreme Computing” in
Santa Fe (2004/10)
23/04/21 32Fifty years of Japanese HPC
Sixth Generation (2H of 2000 and later)Japan US/Europe/China
2006-12: K Computer P.– 2011: 10 PF attained
2006: T2K open SC– 2008: installed in 3 univ.
2006: TSUBAME 1.0– 2010: TSUBAME 2.0
2009: Fujitsu fx-1 to JAXA
Cray XT/XE/XC 2005: ASCI Purple (LLNL, IBM) 2006: Rangers (TACC) 2007: NCSA, BlueWaters started
(IBM→2011 Cray) 2007: Kraken (Tennessee) 2008: Roadrunner (LANL) 2010: Tianhe-1A (NUDT) 2010: PRACE started 2011: NSF, SXEDE 2013 America COMPETES Act
23/04/21 33Fifty years of Japanese HPC
History of the K Computer Recommendation to a Mext committee (2005):
– Promote a national project to construct a leading edge supercomputer
– Government decision (July 25, 2005) Riken started the project (October 2005) Mext funded four projects to promote “Element
Technologies for Future Supercomputers” in 2005-2007. $40M per year (in total)– Four groups were accepted1. System Interconnect (Kyushu U and Fujitsu)2. Interconnect by IP (U of Tokyo, Keio U etc)3. Low Power Device and Circuits (Hitachi, U of Tokyo, U of Tsukuba)4. Optical Connection of CPU and Memory (NEC and Titech)
Fifty years of Japanese HPC 3423/04/21
History of the K Computer 2005: Proposed architectures and killer applications 2007: Hybrid machine with vector and scalar 2009: Five strategic application fields defined 2009: Withdrawal of vector machine 2009: the Government Revitalization Unit proposed
to shutdown the Next Generation Supercomputer Project (Nov. 13, 2009)
2009: HPCI started(High Performance Computing Infrastructure, alliance of supercomputer centers and users)
Fifty years of Japanese HPC 3523/04/21
Original ProposalLarge scale processing Scalar computer
Special-purpose computerFifty years of Japanese HPC 3623/04/21
Fifty years of Japanese HPC
Friday, November 13, 2009
The 3rd WG of the Government Revitalization Unit
“Why should it be No.1 in the world?”
“Is No.2 not enough?”
Vote :Abolish 1Postpone 6Budget shrink 5
ConclusionFreeze the project!
← 村田 ( 謝 ) 蓮舫 (Hsieh Lien Fang)Picture from www.rehabilitate.jp
3723/04/21
No.1 in the world 8.162 Pflops attained using 80% of the system
ー No.1 in the Top500 (ISC2011) June 20, 2011
10.51 Pflops in SC2011 (Seattle) Open to users: September 2012
– 1st period: 2012/9 to 2014/3– 2nd period: 2014/4 to 2015/3
RIST is to manage K Computer users(Research Organization for Information Science & Technology)
Fifty years of Japanese HPC 3823/04/21
What’s next?Toward EXA FLOPS!!
Preliminary consideration among scientists(In US, since 2004)
Mext started a WG for future HPC (April 2011)– Hardware-System Software-Application co-design is
important.
– Should be science-driven.• We identified possible break throughts in science and technology.
Social needs are also considered.
• Linpack Exaflops is not our target.
– Limitation by budget, power, ….
– Several different architectures are considered.Fifty years of Japanese HPC 3923/04/21
Two subgroups worked
Application Subgroup– Application
– Numerical library
– Algorithm
– Automatic tuning
System Subgroup– CPU and architecture
– Compiler
– System software
Fifty years of Japanese HPC 41
Final Report in March 2012
23/04/21
Memory and memory bandwidthBig technical issue
Fifty years of Japanese HPC 42
Large B/FlopsSmall B/Flops
Large B/Flop
Small B/Flop
0.1
0.1standard
SoC
K
GPU
Small system
ES
23/04/21
WG for Future HPCI Policy
2012/4 ~ 2014/3 (25 meetings) 26 members, Chair: Oyanagi Recommendations
– Hierarchical deployment of supercomputers– Leading machines: Flagship system and its
complementary systems– Flagship: “exascale” machine toward 2020– Support to users, especially industry users
23/04/21 Fifty years of Japanese HPC 43
Flagship system
Complementary systems to the flagship
Universities and laboratories
Leading system
s
Allocated thru H
PCI
23/04/21 Fifty years of Japanese HPC 44
2014年 2015年 2016年 2017年 2018年 2019年 2020年
日本のスケジュール案
ハード・システム
アプリケーション
アメリカのスケジュール案
ハード
ソフト
ヨーロッパのスケジュール案(詳細不明)
システム
中国のスケジュール案
システム
基本設計 試作・詳細設計 製造(量産) 設置・調整 運用
エクサ向けアプリケーション開発・利用
システム・ノード設計 実験機 システム製造・設置
P環境設計 P 環境構築 ↓アプリ開発開始 ↓ P 環境更新
8th Framework Program (FP8) Horizon 2020
第 12 次 5 カ年計画 ↓ 100 PF 第 13 次 5 カ年計画 1 EF ↓
Development plans of exascale machines in the world(preliminary)
23/04/21 Fifty years of Japanese HPC 45
9 Key topics for the post-K(Komiyama Committee)
Healthy longevity1. Innovative drug design
2. Integrated computational bioscience Disaster mitigation and environment
3. Earthquake and tsunami
4. Advanced prediction of climate and environment
23/04/21 Fifty years of Japanese HPC 46
9 Key topics for the post-K Energy problem
5. New technology for energy production, storage and usage
6. Innovative clean energy system Industry competitiveness
7. New functional devices and materials
8. Innovative design and manufacturing Basic science
9. Fundamental law and evolution of the universe
23/04/21 Fifty years of Japanese HPC 47
23/04/21 48
Observation of Japanese HPC (1/3) Japan has manufactured vector supercomputers since
1977 Japanese vector computers were designed as an
extension of main frames.– In the early stage, development cost was amortized among
mainframes (US-Japan conflicts). Stress of easiness of use (compilers and tools)
– Very good vectorizing compilers.– Users exploited the power of vectorization.– Users were spoiled by them.– Application software development not enough.
Fifty years of Japanese HPC
Observation of Japanese HPC (2/3) Until late 1990’s, Japanese vendors focused on vector
machines. Late entry to parallel architectures. Vendors thought parallel machines were for
specialized purposes (eg. image processing). Most users dared not try to harness parallel machines
in the 80’s.– Users found difficulties in using message passing.
Some computer scientists were interested in building parallel machines, but they were not used for practical scientific computing.
Fifty years of Japanese HPC 4923/04/21
Observation of Japanese HPC (3/3) Practical parallel processing for scientific
computing was started by application users: QCDPAX, NWT, CP-PACS, GRAPE’s, ES.
After the K Computer, parallel users increased not only in academia but also in industry
We must prepare for the post-K exascale.– Hierarchical deployment– Home development– Co-design, Science-driven
Fifty years of Japanese HPC 5023/04/21