Intel 64bit Server Technology

1
Intel 64-bit Server Technology

• Philip King
• Solution Specialist
• Intel Corporation
• November 10, 2009

2
Agenda

• Intel Server Processors
• Intel Xeon and Itanium Platforms
• Extended Memory 64 Technology
• Micro-architecture comparisons
• Performance and Scalability
• Dual and Multi-core plans
• 64-bit Platform selection guidance

3
Intel Server Processor Roadmap
. . .

• 90nm
• 24MB iL3 cache
• Dual-core

• Future Direction
• Larger Caches
• 65nm process
• Multiple cores
• Multi-threading
• Virtualization
• gt1 billion trans.

Montecito (Q305)

• .13µ
• 9MB iL3 cache

Itanium 2 Processor (Madison Refresh)
. . .

• .13µ
• 6MB iL3 cache

Performance , RAS, Scalability
Potomac (Q205)
Itanium 2 Processor (Madison)

• .18µ
• 3MB iL3 cache

Nocona (8/6/04)
Itanium 2 Processor

• HT EM64T
• 4MB iL3 cache
• gt 3 Ghz 90nm

Xeon Processor

• HT EM64T
• 1MB iL2 cache
• gt 3.6 Ghz 90nm

• HT
• .13µ
• 2MB iL3 cache

2006-Beyond

2002
2004
2005
2003

4
Intel Xeon Platform
2003 Prior Enhancements

• Hyper-Threading Technology
• Intel Netburst micro-architecture
• SSE SSE2 instructions

Future Enhancement

• Virtualization
• User defined power thresholds
• Dual core CPUs
• Fully buffered DIMMs

2004 Enhancements

• New SSE3 instructions
• PCI Express
• 800MHz FSB
• 64-bit extension technology

• Power management technology
• Demand Based Switching (DBS)
• DDR2 memory
• Higher capacity performance w/ lower power

Intel, Netburst and Xeon are trademarks or
registered trademarks of Intel Corporation or its
subsidiaries in the United States and other
countries.
Other names and brands may be claimed as the
property of others.
5
Intel Itanium Platform
Future Enhancements
2004 Prior Enhancements

• Multi-core
• Virtualization
• I/O and memory
• Enhanced RAS
• Cost parity with Xeon processor based platforms
  (via common platform infrastructure)
• Up to 2X higher performance than Xeon based
  platforms

• EPIC architecture
• Enhanced Machine Check Architecture
• FMAC for floating-point leadership
• Largest on-die resources for demanding workloads

2005 Planned Enhancements

• Dual-core
• Multi-threading
• Power management technology
• Demand Based Switching (DBS)
• Automatic Control Power Consumption (ACPC)
• Enhanced system bus Bandwidth

• Foxton Technology (performance feature)
• Pellston Technology (cache reliability)
• PCI Express
• Fully-buffered DIMMS (FBD) , DDR2

And lower power than today
6
What is Intel Extended Memory 64 Technology?
Features
Modes
Extended Memory Addressability 64-bit Pointers,
64-bit Registers
Legacy Mode 32 OS / 32 Apps



Additional Registers 8-SSE 8-Gen Purpose
Compatibility Mode 64 OS / 32 Apps 64-bit
Mode 64 OS / 64 Apps
64-bit Integer Support (Double Length)
64-bit 64/64
With Intel EM64T
Support for flat virtual Address space
Evolutionary IA-32 architectural enhancements to
support extended memory past 4 GB
7
Intel Itanium architecture built from the ground
up to meet the needs of the most demanding
applications
Intel Itanium Processor Age 2
Next Enterprise Architecture
EPIC

• Largest, most demanding workloads requires new
  approach
• Benefits from the experience of past
  architectures
• A convergence of the best minds in the industry

IBM PowerPC Age 9
Superscalar
Sun SPARC, MIPS R4000 Age 10-15
RISC
Performance
IBM 370, VAX 11 Age 20
CISC
Source Computer Organization and Architecture,
1999 W. Stallings
Time
Massive on-chip resources
Performance through parallelism
Scalable

• Maximizes instructions executed in parallel
• Multiple execution units and issue ports

• Large and fast on-die cache
• 128 general registers, 128 floating point
  registers, 8 branch
• Efficient management engine
• Register stack engine
• 4 GB page size

• Modular
• Able to seamlessly add execution resources, issue
  ports

8
Characteristics of High-end ProcessorsHigh-end
Processors Require Significant Resources,
Capabilities
Itanium 2 processor
6 MB ? 9 MB on-die cache
IBM Power 4
Sun UltraSPARC IIIi
264 Registers
AMD Opteron
Up to 1.5 MB on-die cache
160 Registers
4 GB page size
1 MB on-die cache
1 MB on-die cache
72 Registers
4 MB page size
Source IBM.com
Source sun.com
Source AMD.com,
9
Intel Enterprise Micro-Architectures
Xeon EM64T
Itanium 2 Processor 6M
1024 TB
1TB 40 bit
6.4 GB/s
6.4 GB/s
1 MB
On-die Cache
6 MB
Hyper-Threading Technology
Hyper-Threading Technology
8
Pipeline Stages
264 Application Registers 64 Predicate
Registers
1
2
3
4
24 Registers
2 2x Integer 1 1x Integer, 1 MMx SSE
2 Floating Point
2 FP, 1 SIMD
2 Load and 2 Store
6 Integer, 3 Branch
1.5 GHz
3.6 GHz
3 Instructions / Cycle
6 Instructions / Cycle

• Performance via Megahertz

Performance via Parallelism
Intels EPIC technology includes 64 single-bit
predicate registers to accelerate loop unrolling
and branch intensive code execution.
10
Intel Server Processor Platforms
Performance 1
Platform Cost 2
On track to deliver 1.5-2X better performance
than Intel Xeon processor
While achieving platform cost parity via common
platform infrastructure
1 Data based on Intel projections. 2 04 Price
based on comparable OEM systems, HW only for
enterprise and technical computing applications.
Source www.ioncomputers.com, www.dell.com ION
SR4004, (4) Xeon processors 2.8 GHz, 2MB cache,
24 GB system memory, 36 GB HDD, no OS -
34,616 ION I2X4, (4) Itanium 2 processors 1.5
GHz, 6 MB cache, 24 GB system memory, 36 GB HDD,
no OS - 44, 950 Dell PowerEdge 2650, (2) Xeon
processors 3.2 GHz, 1 MB cache, 4 GB system
memory, 36 GB HDD, no OS - 6,143 Dell PowerEdge
3250, (2) Itanium 2 processors 1.4 GHz, 1.5 MB
cache, 4 GB system memory, 36 GB HDD, no OS -
9,499
All products, dates and information
are preliminary and subject to change without
notice.
11
Multi-Core Technology
2004 2005 2007 Single
Core Dual Core Multi-Core
4 or more cores
Cache
2X more cores
Cache
Cache
Core
2 or more cores
Cache
Cache
Core
Cache

• Intel manufacturing leadership (90nm, 65nm)
  enables leading multi-core
• Itanium architecture has smaller core size
  enabling up to 2x more cores per die than IA-32
  for higher performance at same cost

Itanium architecture expected to enable up to 2x
more cores per processor than Xeon processors by
2007
All products, dates and features are preliminary
and subject to change without notice
12
Which is the right Architecture?
Intel Xeon Processor
Intel Itanium 2 Processor Family
32bit Architecture
64bit Architecture
64 bit Addressability
64 bit Addressability
dont need 64bit addressability
need 64bit addressability
High Compute Servers
Legacy Apps
Port to EM64T or Port to IPF
Leave applications as 32Bit
By 2005 all Xeon processors will have memory
extensions
13
Platform Feature / Benefit Comparison
14
T H A N K Y O U
15
B A C K U P
16
Other 64-bit platform considerations
Xeon Processor with EM64T
Itanium 2 Processor

• Some tools available and will grow over time
• Effort needed to porting to 64 bit is the same
  regardless of architecture
• Strong 32-bit eco-systems in place, but needs to
  expand to EM64T
• OEMs are ramping volume quickly
• Best price point for servers
• Native 32 bit environment (drivers still need be
  ported to 64bit environment)

• Mature Tools and large selection
• Porting effort is about the same as on EM64T
• Eco-system in place and still growing
• OEMs shipping in volume
• Processor price delta between Xeon and IPF (top
  speed) is lt400 per CPU
• IA32-EL provides 32-bit execution environment
  perf. 50 of Xeon top speed

17
Server Architecture Reliability Comparisons
18
IA Scalability Performance Comparison
Transaction Processing (TPC-C)
100
Xeon Processor MP 3GHz 4MB L3
tpmC in thousands
Itanium 2 Processor 1.5GHz 6MB L3
33
Itanium 2 processor 6M scales better than Xeon
processor MP 3GHz

• 4P Source www.tpc.org IBM x365 102,667.42 tpmC,
  3.52/tpmC, available 3/31/2004, with 4 Intel
  Xeon processors MP at 3GHz, each with 4MB iL3
  cache, running, Microsoft Windows Server 2003
  Enterprise Server, Microsoft SQL Server 2000 EE
  SP3, 32GB memory. Itanium 2 processor results of
  136,111 tpmC at 4.09/tpmC on HP Integrity Server
  rx5670 with 4 Itanium 2 processors 6M at 1.5GHz,
  each with 6MB L3 cache, 96GB memory, Red Hat
  Enterprise Linux Advanced Server 3 and Oracle
  Database 10g Enterprise Edition TPC-C
  availability date 3/5/04.
• 32P Source www.tpc.org Unisys ES7000 Orion 540
  Enterprise Server 304,148.50 tpmC _at_ 6.18/tpmC,
  availability 4/28/04 with 32 Intel Xeon
  processors MP at 3GHz, each with 4MB iL3 cache,
  running Microsoft Windows Server 2003
  Datacenter Edition, Microsoft SQL Server 2000
  Enterprise Edition. Itanium 2 processor 6M
  results on NEC Express5800/1320Xd C/S
  w/Express5800/120Rf-2, 609,467tpmC, 6.78/tpmC,
  with thirty two (32) Intel Itanium 2 processors
  6M at 1.5 GHz, running SUSE LINUX Enterprise
  Server 9 and Oracle Database 10g Enterprise
  Edition, with 512 GB RAM Available 9/1/2004.
• Results as of 4/29/04.
• Performance tests and ratings are measured using
  specific computer systems and/or components and
  reflect the approximate performance of Intel
  products as measured by those tests. Any
  difference in system hardware or software design
  or configuration may affect actual performance.
  Buyers should consult other sources of
  information to evaluate the performance of
  systems or components they are considering
  purchasing. For more information on performance
  tests and on the performance of Intel products,
  reference www.intel.com/procs/perf/limits.htm or
  call (U.S.) 1-800-628-8686 or 1-916-356-3104

Other names and brands may be claimed as
property of others