UC Berkeley
Par Lab
Technology Trends:
The Datacenter is the Computer,
The Cellphone/Laptop
is the Computer
David Patterson
Director, Reliable Adaptive Distributed Lab
Director, Parallel Computing Lab
Past President, ACM
October, 2007
1
Outline







LAN: 10X BW / link / 4-5 years
Internet: Data Centers = new Internet backbone
DRAM: 2X size / chip / 3 years, = latency, > BW
 Larger % chips, % power, % $ of systems
Flash: Threat to (small) disks?
Disk: 2X size / disk / 3 years , = latency, > BW
CPU: 2X cores / chip / 2 years,
≤ clock rate, = power
Cell phone/Laptop and Datacenter: Ends of
spectrum most interesting platforms of future?
2
Technology Trends: LAN
•
Ethernet: from shared media to switch and
twisted pair shortens time to new generation
–
•
But shorter distance per link using copper
Year of Standard
1983
10 Mbit/s
1995
100 Mbit/s
1999 1000 Mbit/s
2003 10000 Mbit/s
2006 10000 Mbit/s
•
•
IEEE 802.3
IEEE 802.3u
IEEE 802.3ab
IEEE 802.3ac (optical)
IEEE 802.3an (copper)
Expect 10 Gbit/s economical in 2007
100 Gbit/sec IEEE standard started 2006
–
Standard in 2008? Economical in 2012?
3
Technology Trends: Internet
• Datacenters: new Internet backbone
– Huge concentration of bandwidth & computation
– Shift in traffic pattern
• More and more traffic is hostDatacenter
• Huge data transfers between/within DCs are the norm
• Note: IP alone not designed for such networks
4
Technology Trends: DRAM
• DRAM capacity: decelerate capacity per chip
due in part to 32-bit address limit, investments
– 512 Mbit sold in 2002; still dominates as of Jan 07
– 2X capacity every 3 years? (vs. 4X/3yrs in 1990s)
– DRAM performance: only BW improvements (DDR-2,
DDR-3), little latency improvement, power worse
• 64-bit Addresses + Multiple cores/socket
 Majority % chips DRAM vs. Logic
 Majority % of power is DRAM vs. Logic
 Majority % of system $ DRAM vs. Logic
• Shift in % chips, power, $ to DRAM from CPU
and % increases over time
5
Technology Trends: Disk
• Disk: After capacity 100% per year ‘96 - ‘03,
slowdown recently: 30%? 50%? (1TB in 07)
– Consolidation of industry, lack of demand by PCs
– Home Video restart PC demand, capacity wars?
• Split: ATA best GB/$, SCSI best performance/$
– Reliability close (see 2007 Google and CMU papers)
• Performance: Interface switch from parallel to
serial: Serial ATA (SATA), Serial SCSI (SAS)
 Low Cost Disk arrays
• Disk performance: latency slow change,
bandwidth improves, but not as fast as capacity
 Takes longer to read whole disk (3 hours)
 Takes longer repair  Must handle 2 faults
 RAID 6 or 3X replication (power, space?)
6
Technology Trends: Flash
2007
SATA
SCSI
Flash
DRAM
GB/$
IOPS/GB
GB/Watt
3.33
0.2
50
0.50
4
5
0.08
200
100
0.01
5,000,000
0.5
• Flash Memory is credible threat to small disks
– Modular, 1000X latency, ≈ BW, < power, but 1M writes
• Camera, Ipod industry funds flash R&D
– Flash Improvement Rate: 2X GB/$ every 9 months?
• IF disk and flash rates continue, flash matches
GB/$ SCSI in 2009, GB/$ SATA in 2012
• Future: Phase-change RAM (PRAM); ≈ no write
limit, write 30X faster, archival; Samsung 2008?
7
A Parallel Revolution
• PC, Server: Power Wall + Memory Wall = Brick Wall
Par Lab
 End of way built microprocessors for last 40 years
 New Moore’s Law is 2X processors (“cores”) per
chip every technology generation (≈ 2 years),
but same (or slower) clock rate and simpler CPUs
– Conservative plan: 2007 4 cores/chip, 2009 8 cores,
2011 16 cores, … for laptop & server & embedded
– “This shift toward increasing parallelism is not a triumphant
stride forward based on breakthroughs; actually a retreat
from even greater challenges that thwart efficient
silicon implementation of traditional solutions.”
The Parallel Computing Landscape: A Berkeley View, Dec 2006
• Sea change for HW & SW industries since changing the
model of programming and debugging
• Every program(mer) is a parallel program(mer),
8
Sequential algorithms are slow algorithms
100+ Cores?
Par Lab
• 5-year research program aim 8+ years out
• Multicore: 2X / 2 yrs  ≈ 64 cores in 8 years
• Manycore: 8X multicore
1000
512
256
128
100
64
80x86
Uniprocessors
No longer sold
32
16
10
8
4
2
1
2003
64
16-way MP laptops
for sale in 2011
1
2005
2007
2009
2011
2013
2015
9
Revolution May Fail
Par Lab
• John Hennessy, President, Stanford University, 1/07:
“…when we start talking about parallelism and ease of use of truly
parallel computers, we're talking about a problem that's as hard as
any that computer science has faced. … I would be panicked if I
were in industry.”
“A Conversation with Hennessy & Patterson,” ACM Queue Magazine, 4:10, 1/07.
• 100% failure rate of Parallel Computer Companies
– Convex, Encore, MasPar, NCUBE, Kendall Square Research,
Sequent, (Silicon Graphics), Transputer, Thinking Machines, …
• What if IT goes from a
growth industry to a
replacement industry?
– If SW can’t effectively use
8, 16, 32, ... cores per chip
 SW no faster on new computer
 Only buy if computer wears out
• Accelerate trend to SaaS?
300
250
Millions of
PCs / year
200
150
100
50
0
1985
10
1995
2005
2015
Re-inventing
Client/Server

“The Datacenter is the Computer”


Par Lab
Building sized computers: Google, MS, …
“The Laptop/Handheld is the Computer”
2007: HP sales laptops > desktops
 1B+ Cell phones/yr, increasing in function
 Apple iPhone raises the bar for
quality and business for cellphones


Laptop/Handheld as future client,
Datacenter as future server
11
Trends Summary
Par Lab
CPU: 2X cores / chip / 2 years,
≤ clock rate, = power
 (La-Z-boy programmer era is over)
 DRAM: 2X size / chip / 3 years, = latency, > BW
 Larger % chips, % power, % $ of systems
 Flash: Threat to (small) disks?
 Disk: 2X size / disk / 3 years , = latency, > BW
 LAN: 10X BW / link / 4-5 years
 Internet: Data Centers = new Internet backbone
 Cell phone/Laptop and Datacenter: Ends of 12
spectrum most interesting platforms of future?
