iii. multicore processors (5)
DESCRIPTION
III. Multicore Processors (5). Dezső Sima Spring 2007. (Ver. 2.0). Dezső Sima, 2007. 10.3 IBM’s MC processors. 10.3.1 POWER line. 10.3.2 Cell BE. 10.3 IBM’s MC processors. 10.3.1 POWER line. POWER4. 180 nm. 10 /200 1. 130 nm. POWER4+. 11 /200 2. POWER5. 130 nm. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/1.jpg)
III. Multicore Processors (5)
Dezső Sima
Spring 2007
(Ver. 2.0) Dezső Sima, 2007
![Page 3: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/3.jpg)
10.3 IBM’s MC processors
• POWER4 180 nm10/2001• POWER4+ 130 nm11/2002
10.3.1 POWER line
• POWER5 130 nm 5/2004
• POWER5+ 90 nm10/2005• POWER6 65 nm2007
![Page 4: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/4.jpg)
Figure: The evolution of IBM’s major RISC lines
92 93 94 95 96 97 98 999190 02 030100 04 058988
OS/400
Commercial computing
IMPI/48
AIX
Technical computing
PowerPC/32
PowerPC AS/64
PowerPC/64
POWER/32
A10 A30
A50 Pulsar SStar
601 604 604e
POWER POWER2
Power3
Power3-II
P2SC
AS/400 e-Server iSeries
RS/6000 e-Server pSeries
(Scalar CISC)
(~2.G. superscalar)
(~1.G. superscalar)
(3.G. superscalar)
(3.G. superscalar)
(1.-2.G. superscalar)
Upwards binary compatible extension
Transition
Derived from
Northstar SStar
POWER4 POWER5
PowerPC/64 ext.
PowerPC AS/64 ext.(1.G. superscalar)
PSC
AS/400-line
06 07
POWER4+ POWER5+
POWER6
10.3.1 Evolution of IBM’s major RISC lines
![Page 5: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/5.jpg)
Figure : POWER4 chip logical view
Built-In-SelfTest
Service Processor
Power On Reset
Core interface Unit(crossbar)
Non-CacheableUnit
MultiChip Module
10.3.1 POWER4 (1)
Tendler, J.M., Dodson, S., Fields S., Le H., Sinharoy B.: Power4 System Microarchitecture,, IBM J. Res. & Dev. Vol. 46, No. 1, Jan. 2002, pp. 5-25,
http://www.research.ibm.com/journal/rd/461/tendler.pdf
![Page 6: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/6.jpg)
Source: Power4 System Microarchitecture, Technical White Paper, 2001, IBM Corp., http://www-03.ibm.com/servers/eserver/pseries/hardware/whitepapers/power4.pdf
Figure: Logical view of the L3 controller
10.3.1 POWER4 (2)
![Page 7: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/7.jpg)
Figure: The memory cotroller of the POWER4
Source: Power4 System Microarchitecture, Technical White Paper, 2001, IBM Corp., http://www-03.ibm.com/servers/eserver/pseries/hardware/whitepapers/power4.pdf
10.3.1 POWER4 (3)
![Page 8: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/8.jpg)
Figure: I/O controller of the POWER4
Source: Power4 System Microarchitecture, Technical White Paper, 2001, IBM Corp., http://www-03.ibm.com/servers/eserver/pseries/hardware/whitepapers/power4.pdf
Fabric Controller
10.3.1 POWER4 (4)
![Page 9: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/9.jpg)
Figure: POWER4 chip
Source: R. Kalla, B. Sinharoy, J. Tendler: Simultaneous Multi-threading Implementation in Power5 – IBM’s Next Generation POWER Microprocessor, 2003
http://www.hotchips.org/archives/hc15/3_Tue/11.ibm.pdf
10.3.1 POWER4 (5)
![Page 10: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/10.jpg)
10.3.1 POWER4 (6)
Table: Main features of IBM’s dual-core POWER line
Off-chipMem. contr.
L3
L21.44 MB/sharedSize/allocation
On-chipImplementation
32 MBSize
32 MB
Tags on-chip
SCM1/MCM2
115/125
Tags on-chip, data off-chip
1.3
174 mtrs
412 mm2
180 nm
10/2001
DC
POWER4
L3 size
L3 impl.
Power management
Dual threaded
Packaging
TDP [W]
Implementation
fc [GHz]
Nr. of transistors
Die size
Technology
Introduced
Dual/Quad-Core
POWER line
1 SMC: Single Chip Module2 MCM: Multi Chip Module3 DCM: Dual Chip Module
4 DCM: Dual Core Module5 QCM: Quad Core Module6 DPM: Dynamic Power Management
![Page 11: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/11.jpg)
10.3.2 POWER4+ (1)
Figure: New features of the POWER5+
Source: Grassl C., „New IBM Components for HPCx”, Dec. 2003,http://www.hpcx.ac.uk/about/events/annual2003/Grassl.pdf
![Page 12: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/12.jpg)
10.3.1 POWER4+ (2)
Table: Main features of IBM’s dual-core POWER line
On-chipOff-chipMem. contr.
L3
L21.5 MB/shared1.44 MB/sharedSize/allocation
On-chipOn-chipImplementation
32 MB32 MBSize
SCM1/MCM2
70
1.7
184 mtrs
380 mm2
130 nm
11/2002
DC
POWER4+
32 MB
Tags on-chip
SCM1/MCM2
115/125
Tags on-chip, data off-chip
1.3
174 mtrs
412 mm2
180 nm
10/2001
DC
POWER4
L3 size
L3 impl.
Power management
Dual threaded
Packaging
TDP [W]
Implementation
fc [GHz]
Nr. of transistors
Die size
Technology
Introduced
Dual/Quad-Core
POWER line
1 SMC: Single Chip Module2 MCM: Multi Chip Module3 DCM: Dual Chip Module
4 DCM: Dual Core Module5 QCM: Quad Core Module6 DPM: Dynamic Power Management
![Page 13: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/13.jpg)
Figure 5.14: Contrasting POWER4 and POWER5 system structures
Source:Barney B., „IBM POWER Systems Overview”, Livermore Computing, 2006, http://www.llnl.gov/computing/tutorials/ibm_sp/
10.3.1 POWER5 (1)
![Page 14: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/14.jpg)
Figure: Block diagram of the POWER5 (1)
Source:Barney B., „IBM POWER Systems Overview”, Livermore Computing, 2006, http://www.llnl.gov/computing/tutorials/ibm_sp/
10.3.1 POWER5 (2)
![Page 15: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/15.jpg)
http://studies.ac.upc.edu/ETSETB/SEGPAR/microprocessors/power5%20(2)%20(mpr).pdf
Figure: Block diagram of the POWER5 (2)
10.3.1 POWER5 (3)
![Page 16: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/16.jpg)
10.3.1 POWER5 (4)
Figure: Floorplan of the POWER5
Source: Shinharoy B., Kalla R.N., Tendler J.M., Eickenmeyer R.J., Joyner J.B., „POWER5 system microarchitecture,” IBM J. R&D, Vol. 49, No. 4/5, 2005, pp. 505-521
![Page 17: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/17.jpg)
POWER4 POWER5
180 nm, 412 mm2 130 nm, 389 mm2 (enlarged)
10.3.1 POWER5 (6)
Figure: Contrasting the floor plans of the POWER4 and POWER5 dies
Shinharoy B., Kalla R.N., Tendler J.M., Eickenmeyer R.J., Joyner J.B., „POWER5 system microarchitecture,” IBM J. R&D, Vol. 49, No. 4/5, 2005, pp. 505-521
Sources: R. Kalla, B. Sinharoy, J. Tendler: Simultaneous Multi-threading Implementation in Power5 – IBM’s Next Generation POWER Microprocessor, 2003http://www.hotchips.org/archives/hc15/3_Tue/11.ibm.pdf
![Page 18: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/18.jpg)
Figure: Packaging alternatives of the POWER4/5 processors
Source: Partridge R. and Ghatpande S., IBM Introduces POWER5+ and Quad-Core Modules in System p5,” Tech Trends Monthly, Nov./Dec. 2005,
POWER5+Dual-Core Module
10.3.1 POWER5 (7)
![Page 19: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/19.jpg)
POWER4 MCM Photo 32-way System Showing 4 MCMs and L3 Cache
Figure: Quad–Chip POWER4 module (MCM) and a 32-way POWER4 system
Source:Barney B., „IBM POWER Systems Overview”, Livermore Computing, 2006, http://www.llnl.gov/computing/tutorials/ibm_sp/
10.3.1 POWER5 (8)
![Page 20: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/20.jpg)
Source:Barney B., „IBM POWER Systems Overview”, Livermore Computing, 2006, http://www.llnl.gov/computing/tutorials/ibm_sp/
Figure: Interpretation of Dual-Chip Modules (DCMs) and Multi-Chip Modules (MCM) of the POWER5
10.3.1 POWER5 (9)
![Page 21: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/21.jpg)
Source:Barney B., „IBM POWER Systems Overview”, Livermore Computing, 2006, http://www.llnl.gov/computing/tutorials/ibm_sp/
Figure: Photos of Dual-Chip Modules (DCMs) and Multi-Chip Modules (MCM) of the POWER5
10.3.1 POWER5 (10)
![Page 22: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/22.jpg)
Source: Kalla R., „IBM’s POWER5 Microprocessor Design and Methodology,” 2003,www-csl.csres.utexas.edu/users/billmark/teach/cs352-05-spring/lectures/Lecture22-RonKallaIBM.pdf
Figure: The Multi-chip module of the POWER5
10.3.1 POWER5 (11)
![Page 23: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/23.jpg)
10.3.1 POWER5 (12)
Table: Main features of IBM’s dual-core POWER line
On-chipOn-chipOff-chipMem. contr.
L3
L21.9 MB/shared1.5 MB/shared1.44 MB/sharedSize/allocation
On-chipOn-chipOn-chipImplementation
36 MB32 MB32 MBSize
36 MB
Tags on-chip
DPM6
DCM3/MCM2
80 (est)
1.65/1.9
276 mtrs
389 mm2
130 nm
5/2004
DC
POWER5
SCM1/MCM2
70
1.7
184 mtrs
380 mm2
130 nm
11/2002
DC
POWER4+
32 MB
Tags on-chip
SCM1/MCM2
115/125
Tags on-chip, data off-chip
1.3
174 mtrs
412 mm2
180 nm
10/2001
DC
POWER4
L3 size
L3 impl.
Power management
Dual threaded
Packaging
TDP [W]
Implementation
fc [GHz]
Nr. of transistors
Die size
Technology
Introduced
Dual/Quad-Core
POWER line
1 SMC: Single Chip Module2 MCM: Multi Chip Module3 DCM: Dual Chip Module
4 DCM: Dual Core Module5 QCM: Quad Core Module6 DPM: Dynamic Power Management
![Page 24: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/24.jpg)
Source: Vetter S. et al., IBM System p5 Quad-Core Module Based on POWER5+ Technology,” Redbooks paper, IBM Corp. 2006, http://www.redbooks.ibm.com/redpapers/pdfs/redp4150.pdf
Figure: Block diagram of the POWER5+
10.3.1 POWER5+ (1)
![Page 25: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/25.jpg)
Figure: Dual-Core Modules (DCMs) and Quad-Core Modules (QCM) of the POWER5+
Source: Vetter S. et al., IBM System p5 Quad-Core Module Based on POWER5+ Technology,” Redbooks paper, IBM Corp. 2006, http://www.redbooks.ibm.com/redpapers/pdfs/redp4150.pdf
10.3.1 POWER5+ (2)
![Page 26: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/26.jpg)
10.3.1 POWER5+ (3)
Table: Main features of IBM’s dual-core POWER line
On-chipOn-chipOn-chipOff-chipMem. contr.
L3
L21.9 MB/shared1.9 MB/shared1.5 MB/shared1.44 MB/sharedSize/allocation
On-chipOn-chipOn-chipOn-chipImplementation
36 MB36 MB32 MB32 MBSize
36 MB
Tags on-chip
DPM6
DCM3/MCM2
80 (est)
1.65/1.9
276 mtrs
389 mm2
130 nm
5/2004
DC
POWER5
SCM1/MCM2
70
1.7
184 mtrs
380 mm2
130 nm
11/2002
DC
POWER4+
32 MB
Tags on-chip
SCM1/MCM2
115/125
Tags on-chip, data off-chip
1.3
174 mtrs
412 mm2
180 nm
10/2001
DC
POWER4
36 MB
Tags on-chip
DPM6
DCM4/QCM5
70
1.92
276 mtrs
230 mm2
90 nm
10/2005
DC
POWER5+
L3 size
L3 impl.
Power management
Dual threaded
Packaging
TDP [W]
Implementation
fc [GHz]
Nr. of transistors
Die size
Technology
Introduced
Dual/Quad-Core
POWER line
10.3
1 SMC: Single Chip Module2 MCM: Multi Chip Module3 DCM: Dual Chip Module
4 DCM: Dual Core Module5 QCM: Quad Core Module6 DPM: Dynamic Power Management
![Page 27: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/27.jpg)
POWER6 POWER5+
Figure: Contrasting the block diagrams of the POWER5 and POWER6 processors
Source: Kanter D., „IBM Previews the Power6,” Oct. 2006, [email protected]
Hardware support of decimal arithmetic
10.3.1 POWER6 (1)
![Page 28: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/28.jpg)
10.3.1 POWER6 (2)
Table: Main features of IBM’s dual-core POWER line
On-chipOn-chipOn-chipOff-chipMem. contr.
L3
L22*4 MB/private1.9 MB/shared1.9 MB/shared1.5 MB/shared1.44 MB/sharedSize/allocation
On-chipOn-chipOn-chipOn-chipOn-chipImplementation
64 MB?36 MB36 MB32 MB32 MBSize
36 MB
Tags on-chip
DPM6
DCM3/MCM2
80 (est)
1.65/1.9
276 mtrs
389 mm2
130 nm
5/2004
DC
POWER5
SCM1/MCM2
70
1.7
184 mtrs
380 mm2
130 nm
11/2002
DC
POWER4+
32 MB
Tags on-chip
SCM1/MCM2
115/125
Tags on-chip, data off-chip
1.3
174 mtrs
412 mm2
180 nm
10/2001
DC
POWER4
36 MB
Tags on-chip
DPM6
DCM4/QCM5
70
1.92
276 mtrs
230 mm2
90 nm
10/2005
DC
POWER5+
32 MBL3 size
Tags on-chipL3 impl.
n.a.Power management
Dual threaded
n.a.Packaging
~100TDP [W]
Implementation
4-5fc [GHz]
750 mtrsNr. of transistors
341 mm2Die size
65 nmTechnology
2007Introduced
DCDual/Quad-Core
POWER6POWER line
1 SMC: Single Chip Module2 MCM: Multi Chip Module3 DCM: Dual Chip Module
4 DCM: Dual Core Module5 QCM: Quad Core Module6 DPM: Dynamic Power Management
![Page 29: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/29.jpg)
10.3 IBM’s MC processors
• Cell BE 90 nm2/2006
10.3.2 Cell BE
![Page 30: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/30.jpg)
Hofstee H. P., „Cell today and tomorrow,” 2005, http://www.stanford.edu/class/ee380/Abstracts/Cell_060222.pdf
Sources: Brochard L., A Cell History,” Cell Workshop, April, 2006 http://www.irisa.fr/orap/Constructeurs/Cell/Cell%20Short%20Intro%20Luigi.pdf
Figure: The history and development cost of the Cell BE
10.3.2 Cell BE (1)
![Page 31: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/31.jpg)
AUC: Atomic Update Cache
BIC: Bus Interface Contr.
EIB: Element Interface Bus
LS: Local Store of 256 KB
MFC: Memory Flow Controller
MIC: Memory Interface Contr.
PPE: Power Processing Element
PXU: POWER Execution Unit
SMF: Synergistic Memory Flow
Unit
SPU: Synergistic Processor Unit
SXU: Synergistic Execution Unit
XDR: Rambus DRAM
Source: Gshwind M., „Chip Multiprocessing and the Cell BE,” ACM Computing Frontiers, 2006, http://beatys1.mscd.edu/compfront//2006/cf06-gschwind.pdf
Figure: Block diagram of the Cell BE
10.3.2 Cell BE (2)
![Page 32: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/32.jpg)
PPE: dual-threaded > 200 GFLOPS (SP) > 20 GFLOPS (DP) > 25 GB/s memory BW > 75 GB/s I/O BW > 300 GB/s EIB BW fc > 4 GHz (lab)
publib.boulder.ibm.com/.../stgv1r0/topic/com.ibm.iea.cbe/cbe/1.0/Overview/L1T1H1_02_CellOverview.pdf Source: IBM „Cell Broadband Engine Overview,” Course Code L1T1H1-02, Mai 2006
Figure: Main design parameters of the Cell BE
10.3.2 Cell BE (3)
Design parameters of the Cell BE:
![Page 33: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/33.jpg)
Figure 5.16: Cell SPE architecture
Source: Blachford N.: „Cell Architecture Explained Version 2”, http://www.blachford.info/computer/Cell/Cell1_v2.html
10.3.2 Cell BE (4)
![Page 34: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/34.jpg)
Source: Gshwind M., „Chip Multiprocessing and the Cell BE,” ACM Computing Frontiers, 2006, http://beatys1.mscd.edu/compfront//2006/cf06-gschwind.pdf
Figure: Block diagram of the SPE
10.3.2 Cell BE (5)
![Page 35: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/35.jpg)
Source: Gshwind M., „Chip Multiprocessing and the Cell BE,” ACM Computing Frontiers, 2006, http://beatys1.mscd.edu/compfront//2006/cf06-gschwind.pdf
Figure: Pipeline stages of the Cell BE
10.3.2 Cell BE (6)
![Page 36: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/36.jpg)
Source: Gshwind M., „Chip Multiprocessing and the Cell BE,” ACM Computing Frontiers, 2006, http://beatys1.mscd.edu/compfront//2006/cf06-gschwind.pdf
Figure: Floor plan of a single SPE
10.3.2 Cell BE (7)
![Page 37: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/37.jpg)
Source: Keable C., „And we also have hardware...” 17th Machine Evaluation Workshop, Dec. 2006, http://www.cse.clrc.ac.uk/disco/mew17/talks/Keable_IBM_MEW17.pdf
Principle of operation of the Element Interface Bus (EIB)
10.3.2 Cell BE (8)
![Page 38: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/38.jpg)
Source: Gshwind M., „Chip Multiprocessing and the Cell BE,” ACM Computing Frontiers, 2006, http://beatys1.mscd.edu/compfront//2006/cf06-gschwind.pdf
Figure: The Element Interface Bus EIB)
10.3.2 Cell BE (9)
![Page 39: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/39.jpg)
Figure: The Synergistic Memory Flow unit (SMF)
Source: Gshwind M., „Chip Multiprocessing and the Cell BE,” ACM Computing Frontiers, 2006, http://beatys1.mscd.edu/compfront//2006/cf06-gschwind.pdf
10.3.2 Cell BE (10)
![Page 40: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/40.jpg)
Source: Gshwind M., „Chip Multiprocessing and the Cell BE,” ACM Computing Frontiers, 2006, http://beatys1.mscd.edu/compfront//2006/cf06-gschwind.pdf
Figure: Floor plan of the Cell BE processor
235 mm2
241 mtrs
10.3.2 Cell BE (11)
![Page 41: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/41.jpg)
10.3.2 Cell BE (12)
Table: Main features of the IBM’s Cell BE
L3
On-chipMemory controller
Ring basedInterconnection network
Up to 75 MB/sI/O bandwidth
PPE: 2-waySPE:
Multithreading
95 W @ 3GHzTDP [W]
25 GB/sMemory bandwidth
PPE: 512 KBSPE: 256 KB Local Store (128*128 bit)
L2
3.0/3.2fc [GHz]
234 mtrsNr. of transistors
221 mm2Die size
90 nmTechnology
9/2006 (in the QS20 BladeCenter)Introduction
PPE: 64-bit RISCSPE: Dual-issue 32-bit SIMD with 128 bit capability
Cores
PowerPC 2.02Architecture
Heterogeneous1xPPE, 8*SPE
Implementation
Cell BESeries
![Page 42: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/42.jpg)
Source: Brochard L., A Cell History,” Cell Workshop, April, 2006 http://www.irisa.fr/orap/Constructeurs/Cell/Cell%20Short%20Intro%20Luigi.pdf
Figure: Cell BE Blade Roadmap
10.3.2 Cell BE (13)
![Page 43: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/43.jpg)
Source: Hofstee H. P., „Real-time Superconputing and Technology for Games and Entertainment,” 2006, http://www.cercs.gatech.edu/docs/SC06_Cell_111606.pdf
Figure: Roadmap of the Cell BE
10.3.2 Cell BE (14)
![Page 44: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/44.jpg)
10.3 Literature (1)
POWER4, POWER4+
Grassl C., „New IBM Components for HPCx”, Dec. 2003,http://www.hpcx.ac.uk/about/events/annual2003/Grassl.pdf
Barney B., „IBM POWER Systems Overview”, Livermore Computing, 2006, http://www.llnl.gov/computing/tutorials/ibm_sp/
DeMone P., „Sizing Up the Super Heavyweights,” Real Word Technologies, Sept. 2004, http://h21007.www2.hp.com/dspp/files/unprotected/Itanium/sizingsuperheavys.pdf
Krevell K., „IBM’s POWER4 Unveiling Continuues”, Microprocessor Report, Nov. 20. 2000, pp- 1-4
Tendler, J.M., Dodson, S., Fields S., Le H., Sinharoy B.: Power4 System Microarchitecture, IBM Server, Technical White Paper, October 2001
http://www-03.ibm.coom/servers/eserver/pseries/hardware/whitepapers/power4.pdf
POWER5, POWER5+
Grassl C., „New IBM Components for HPCx”, Dec. 2003,http://www.hpcx.ac.uk/about/events/annual2003/Grassl.pdf
Barney B., „IBM POWER Systems Overview”, Livermore Computing, 2006, http://www.llnl.gov/computing/tutorials/ibm_sp/
DeMone P., „Sizing Up the Super Heavyweights,” Real Word Technologies, Sept. 2004, http://h21007.www2.hp.com/dspp/files/unprotected/Itanium/sizingsuperheavys.pdf
Kalla R., „IBM’s POWER5 Microprocessor Design and Methodology,” 2003,www-csl.csres.utexas.edu/users/billmark/teach/cs352-05-spring/lectures/Lecture22-RonKallaIBM.pdf
Tendler, J.M., Dodson, S., Fields S., Le H., Sinharoy B.: Power4 System Microarchitecture,, IBM J. Res. & Dev. Vol. 46, No. 1, Jan. 2002, pp. 5-25,
http://www.research.ibm.com/journal/rd/461/tendler.pdf
![Page 45: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/45.jpg)
Kalla R., Sinharoy B., Tendler J.: Simultaneous Multi-threading Implementation in Power5 – IBM’s Next Generation POWER Microprocessor, 2003
http://www.hotchips.org/archives/hc15/3_Tue/11.ibm.pdf
Krevell K., „POWER5 Tops on Bandwidth”, Microprocessor Report, Dec. 2003http://studies.ac.upc.edu/ETSETB/SEGPAR/microprocessors/power5%20(2)%20(mpr).pdf
Shinharoy B., Kalla R.N., Tendler J.M., Eickenmeyer R.J., Joyner J.B., „POWER5 system microarchitecture,” IBM J. R&D, Vol. 49, No. 4/5, 2005, pp. 505-521
Kanter D., „IBM Previews the Power6,” Oct. 2006, [email protected]
Vetter S. et al., IBM System p5 Quad-Core Module Based on POWER5+ Technology,” Redbooks paper, IBM Corp. 2006, http://www.redbooks.ibm.com/redpapers/pdfs/redp4150.pdf
POWER6
POWER5, POWER5+ (cont.)
Cell BE
Brochard L., A Cell History,” Cell Workshop, April, 2006 http://www.irisa.fr/orap/Constructeurs/Cell/Cell%20Short%20Intro%20Luigi.pdf
Gshwind M., „Chip Multiprocessing and the Cell BE,” ACM Computing Frontiers, 2006, http://beatys1.mscd.edu/compfront//2006/cf06-gschwind.pdf
Blachford N.: „Cell Architecture Explained Version 2”, http://www.blachford.info/computer/Cell/Cell1_v2.html
Day M. and Hofstee P., „Hardware and Software Architectures for the Cell Broadband Engine processor, ”CODES, Sept. 2006, http://www.casesconference.org/cases2005/pdf/Cell-tutorial.pdf
10.3 Literature (2)
![Page 46: III. Multicore Processors (5)](https://reader036.vdocuments.net/reader036/viewer/2022070411/568146e3550346895db41cb8/html5/thumbnails/46.jpg)
10.3 Literature (3)
Cell BE (cont.)
Keable C., „And we also have hardware...” 17th Machine Evaluation Workshop, Dec. 2006, http://www.cse.clrc.ac.uk/disco/mew17/talks/Keable_IBM_MEW17.pdf
Hofstee H. P., „Real-time Superconputing and Technology for Games and Entertainment,” 2006, http://www.cercs.gatech.edu/docs/SC06_Cell_111606.pdf
Solie, D., „Technology Trends Presentation,” Power Symposium, Aug. 2006, http://www-03.ibm.com/procurement/proweb.nsf/objectdocswebview/ file14+-+darryl+solie+-+ibm+power+symposium+presentation/$file/ 14+-+darryl+solie-ibm-power+symposium+presentation+v2.pdf
- „Cell Broadband Engine processor – based systems,” White Paper, IBM Corp., 2006
Krewell K., „Cell Moves Into The Limelight,” Microprocessor Report, Febr. 14 2005, pp. 1-9
Gschwind M., Hofstee H. P., Flachs B. K., Hophkins M., Watanabe Y., Yamazaki T „Synergistic Processing in Cell's Multicore Architecture,” IEEE Micro, Vol. 26, No. 2, 2006, pp. 10-24
Krolak D., „Unleashing the Cell Broadband Engine Processor,” MPR Fall Proc. Forum, Nov. 2005, http://www-128.ibm.com/developerworks/power/library/pa-fpfeib/?ca=dgr-lnxwCellConnects