A Look Inside Intel®: The Core (Nehalem) Microarchitecture
Beeman Strong Intel® Core™ microarchitecture (Nehalem) Architect Intel Corporation
Agenda • Intel® Core™ Microarchitecture (Nehalem) Design Overview • Enhanced Processor Core • Performance Features • Intel® Hyper-Threading Technology
• New Platform • New Cache Hierarchy • New Platform Architecture
• Performance Acceleration • Virtualization • New Instructions
• Power Management Overview • Minimizing Idle Power Consumption • Performance when it counts
2
Scalable Cores Same core for all segments
Intel® Core™ Microarchitecture (Nehalem)
45nm
Common software optimization
Common feature set
Servers/Workstations Energy Efficiency, Performance, Virtualization, Reliability, Capacity, Scalability
Desktop Performance, Graphics, Energy Efficiency, Idle Power, Security
Mobile Battery Life, Performance, Energy Efficiency, Graphics, Security
Optimized cores to meet all market segments 3
The First Intel® Core™ Microarchitecture (Nehalem) Processor Memory Controller M i s c I O Q P I 0
Core
Core
Q u e u e
Core
Shared L3 Cache
A Modular Design for Flexibility 4
Core
M i s c I O Q P I 1
QPI: Intel® QuickPath Interconnect (Intel® QPI)
Agenda • Intel® Core™ Microarchitecture (Nehalem) Design Overview • Enhanced Processor Core • Performance Features • Intel® Hyper-Threading Technology
• New Platform • New Cache Hierarchy • New Platform Architecture
• Performance Acceleration • Virtualization • New Instructions
• Power Management Overview • Minimizing Idle Power Consumption • Performance when it counts
5
Intel® Core™ Microarchitecture Recap • Wide Dynamic Execution – 4-wide decode/rename/retire
• Advanced Digital Media Boost – 128-bit wide SSE execution units
• Intel HD Boost – New SSE4.1 Instructions
• Smart Memory Access – Memory Disambiguation – Hardware Prefetching
• Advanced Smart Cache – Low latency, high BW shared L2 cache Nehalem builds on the great Core microarchitecture
6
Designed for Performance New SSE4.2 Instructions
Improved Lock Support
L1 Data Cache Execution Units
Deeper Buffers Out-of-Order Scheduling & Retirement
Simultaneous Multi-Threading
Memory Ordering & Execution
Instruction Decode & Microcode
Faster Virtualization
7
Additional Caching Hierarchy
L2 Cache & Interrupt Servicing Paging
Improved Loop Branch Prediction Streaming Instruction Fetch & L1 Cache
Better Branch Prediction
Macrofusion • Introduced in Intel® Core™2 microarchitecture • TEST/CMP instruction followed by a conditional branch treated as a single instruction – Decode/execute/retire as one instruction
• Higher performance & improved power efficiency – Improves throughput/Reduces execution latency – Less processing required to accomplish the same work
• Support all the cases in Intel Core 2 microarchitecture PLUS – CMP+Jcc macrofusion added for the following branch conditions – – – –
JL/JNGE JGE/JNL JLE/JNG JG/JNLE
– Intel® Core™ microarchitecture (Nehalem) supports macrofusion in both 32-bit and 64-bit modes – Intel Core2 microarchitecture only supports macrofusion in 32-bit mode
Increased macrofusion benefit on Intel® Core™ microarchitecture (Nehalem) 8
Intel® Core™ Microarchitecture (Nehalem) Loop Stream Detector • Loop Stream Detector identifies software loops – Stream from Loop Stream Detector instead of normal path – Disable unneeded blocks of logic for power savings – Higher performance by removing instruction fetch limitations • Higher performance: Expand the size of the loops detected (vs Core 2) • Improved power efficiency: Disable even more logic (vs Core 2)
Intel Core Microarchitecture (Nehalem) Loop Stream Detector Branch Prediction
Fetch
Decode
Loop Stream Detector
28 Micro-Ops
9
Branch Prediction Improvements • Focus on improving branch prediction accuracy each CPU generation – Higher performance & lower power through more accurate prediction
• Example Intel® Core™ microarchitecture (Nehalem) improvements – L2 Branch Predictor – Improve accuracy for applications with large code size (ex. database applications)
– Advanced Renamed Return Stack Buffer (RSB) – Remove branch mispredicts on x86 RET instruction (function returns) in the common case
Greater Performance through Branch Prediction
10
Execution Unit Overview Execute 6 operations/cycle
Unified Reservation Station • Schedules operations to Execution units
• 3 Memory Operations • 1 Load
• Single Scheduler for all Execution Units
• 1 Store Address
• Can be used by all integer, all FP, etc.
• 1 Store Data • 3 “Computational” Operations
Unified Reservation Station
FP Multiply
FP Add
Divide
Complex
SSE Integer ALU
SSE Integer
Integer Shuffles
Multiply
Port 5
LEA
Load
Port 4
Shift
Port 3
Integer ALU &
Port 2
Port 1
Port 0 Integer ALU &
Store
Store
Integer ALU &
Address
Data
Shift
Branch FP Shuffle
Integer
SSE Integer ALU Integer Shuffles
11
Increased Parallelism Concurrent uOps Possible
• Goal: Keep powerful execution engine fed • Nehalem increases size of out of order window by 33% • Must also increase other corresponding structures
1
128 112 96 80 64 48 32 16 0
Dothan
Merom
Nehalem
Structure
Intel® Core™ microarchitecture (formerly Merom)
Intel® Core™ microarchitecture (Nehalem)
Comment
Reservation Station
32
36
Dispatches operations to execution units
Load Buffers
32
48
Tracks all load operations allocated
Store Buffers
20
32
Tracks all store operations allocated
Increased Resources for Higher Performance Intel® Pentium® M processor (formerly Dothan) Intel® Core™ microarchitecture (formerly Merom) Intel® Core™ microarchitecture (Nehalem) 1
12
Enhanced Memory Subsystem • Responsible for: – Handling of memory operations (loads/stores)
• Key Intel® Core™2 Features – Memory Disambiguation – Hardware Prefetchers – Advanced Smart Cache
• New Intel® Core™ Microarchitecture (Nehalem) Features – New TLB Hierarchy (new, low latency 2nd level unified TLB) – Fast 16-Byte unaligned accesses – Faster Synchronization Primitives
13
Intel® Hyper-Threading Technology • Also known as Simultaneous MultiThreading (SMT)
w/o SMT
SMT
– Run 2 threads at the same time per core – Keep it fed with multiple threads – Hide latency of a single thread
• Most power efficient performance feature – Very low die area cost – Can provide significant performance benefit depending on application – Much more efficient than adding an entire core
• Intel® Core™ microarchitecture (Nehalem) advantages – Larger caches – Massive memory BW
Simultaneous multi-threading enhances performance and energy efficiency 14
Time (proc. cycles)
• Take advantage of 4-wide execution engine
Note: Each box represents a processor execution unit
SMT Performance Chart Performance Gain SMT enabledvs disabled
40%
34%
35% 29%
30% 25% 20% 13%
15% 10%
16%
10%
7%
5% 0% FloatingPoint
3dsMax*
Integer
Cinebench* 10POV-Ray* 3.7 3DMark* beta25 Vantage* CPU
Intel®Core™i7
Floating Point is based on SPECfp_rate_base2006* estimate Integer is based on SPECint_rate_base2006* estimate SPEC, SPECint, SPECfp, and SPECrate are trademarks of the Standard Performance Evaluation Corporation. For more information on SPEC benchmarks, see: http://www.spec.org Source: Intel. Configuration: pre-production Intel® Core™ i7 processor with 3 channel DDR3 memory. 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, visit http://www.intel.com/performance/
15
Agenda • Intel® Core™ Microarchitecture (Nehalem) Design Overview • Enhanced Processor Core • Performance Features • Intel® Hyper-Threading Technology
• New Platform • New Cache Hierarchy • New Platform Architecture
• Performance Acceleration • Virtualization • New Instructions
• Power Management Overview • Minimizing Idle Power Consumption • Performance when it counts
16
Designed For Modularity C O R E
C O R E
C O R E
…
Core
L3 Cache
DRAM
…
IM C
Intel ® QPI
…
Power & Clock
Intel ® QPI
Uncore
Intel QPI
…
Intel® QPI: Intel® QuickPath Interconnect (Intel® QPI)
Differentiation in the “Uncore”: # cores
# mem channels
#QPI Links
Size of cache
Type of Memory
Power Management
2008 – 2009 Servers & Desktops
Optimal price / performance / energy efficiency for server, desktop and mobile products 17
Integrated graphics
Intel® Smart Cache – 3rd Level Cache • Shared across all cores • Size depends on # of cores – Quad-core: Up to 8MB (16-ways) – Scalability: – Built to vary size with varied core counts – Built to easily increase L3 size in future parts
• Perceived latency depends on frequency ratio between core & uncore • Inclusive cache policy for best performance – Address residing in L1/L2 must be present in 3rd level cache
18
Core
Core
Core
L1 Caches L1 Caches
L1 Caches
… L2 Cache
L2 Cache
L3 Cache
L2 Cache
Why Inclusive? • Inclusive cache provides benefit of an on-die snoop filter • Core Valid Bits – 1 bit per core per cache line – If line may be in a core, set core valid bit – Snoop only needed if line is in L3 and core valid bit is set – Guaranteed that line is not modified if multiple bits set
• Scalability – Addition of cores/sockets does not increase snoop traffic seen by cores
• Latency – Minimize effective cache latency by eliminating cross-core snoops in the common case – Minimize snoop response time for cross-socket cases
19
Intel® Core™ Microarchitecture (Nehalem-EP) Platform Architecture • Integrated Memory Controller – 3 DDR3 channels per socket – Massive memory bandwidth – Memory Bandwidth scales with # of processors – Very low memory latency
Nehalem EP
Nehalem EP
Tylersburg EP
• Intel® QuickPath Interconnect (Intel® QPI) – – – – – –
New point-to-point interconnect Socket to socket connections Socket to chipset connections Build scalable solutions Up to 6.4 GT/sec (12.8 GB/sec) Bidirectional (=> 25.6 GB/sec)
memory
Significant performance
memory
CPU
IOH
CPU
CPU IOH
leap from new platform Intel® Core™ microarchitecture (Nehalem-EP) Intel® Next Generation Server Processor Technology (Tylersburg-EP)
20
CPU
memory
memory
Non-Uniform Memory Access (NUMA) • FSB architecture
– All memory in one location
Nehalem EP
• Starting with Intel Core™ microarchitecture (Nehalem) ®
Nehalem EP
– Memory located in multiple places
Ensure software is NUMAoptimized for best performance
Intel® Core™ microarchitecture (Nehalem-EP) Intel® Next Generation Server Processor Technology (Tylersburg-EP)
21
Relative Memory Latency Comparison Relative Memory Latency
• Latency to memory dependent on location • Local memory has highest BW, lowest latency • Remote Memory still very fast
Tylersburg EP
1.00 0.80 0.60 0.40 0.20 0.00 Harpertown (FSB 1600)
Nehalem (DDR3-1067)
Nehalem (DDR3-1067)
Local
Remote
Memory Bandwidth – Initial Intel® Core™ Microarchitecture (Nehalem) Products • • • •
3 memory channels per socket ≥ DDR3-1066 at launch Massive memory BW Scalability
Stream Bandwidth – Mbytes/Sec (Triad) 33376
3.4X
– Design IMC and core to take advantage of BW – Allow performance to scale with cores – Core enhancements
9776
– Support more cache misses per core – Aggressive hardware prefetching w/ throttling enhancements
6102
HTN 3.16/ BF1333/ 667 MHz mem
– Example IMC Features – Independent memory channels – Aggressive Request Reordering
HTN 3.00/ SB1600/ 800 MHz mem
Source: Intel Internal measurements – August 20081
Massive memory BW provides performance and scalability 1
NHM 2.66/ 6.4 QPI/ 1066 MHz mem
HTN: Intel® Xeon® processor 5400 Series (Harpertown)
NHM: Intel® Core™ microarchitecture (Nehalem)
22
Agenda • Intel® Core™ Microarchitecture (Nehalem) Design Overview • Enhanced Processor Core • Performance Features • Intel® Hyper-Threading Technology
• New Platform • New Cache Hierarchy • New Platform Architecture
• Performance Acceleration • Virtualization • New Instructions
• Power Management Overview • Minimizing Idle Power Consumption • Performance when it counts
23
Virtualization • To get best virtualized performance
Round Trip Virtualization Latency
– Have best native performance – Reduce transitions to/from virtual machine – Reduce latency of transitions
• Intel® Core™ microprocessor (Nehalem) virtualization features – Reduced latency for transitions – Virtual Processor ID (VPID) to reduce effective cost of transitions – Extended Page Table (EPT) to reduce # of transitions
24
Relative Latency
100% 80% 60% 40% 20% 0%
Merom
Penryn
Nehalem
1
EPT Solution EPT CR3 Guest Linear Address
Base Pointer Intel® 64 Page Tables
Guest Physical Address
EPT Page Tables
Host Physical Address
• Intel® 64 Page Tables – Map Guest Linear Address to Guest Physical Address – Can be read and written by the guest OS • New EPT Page Tables under VMM Control – Map Guest Physical Address to Host Physical Address – Referenced by new EPT base pointer • No VM Exits due to Page Faults, INVLPG or CR3 accesses
25
Extending Performance and Energy Efficiency
- Intel® SSE4.2 Instruction Set Architecture (ISA) Leadership in 2008
Accelerated String and Text Processing
Faster XML parsing Faster search and pattern matching Novel parallel data matching and comparison operations
Accelerated Searching & Pattern Recognition of Large Data Sets
Improved performance for Genome Mining, Handwriting recognition. Fast Hamming distance / Population count
New Communications Capabilities
Hardware based CRC instruction Accelerated Network attached storage Improved power efficiency for Software I-SCSI, RDMA, and SCTP
SSE4
STTNI
(45nm CPUs)
SSE4.1
(Penryn Core)
ATA
SSE4.2
(Nehalem Core)
STTNI e.g. XML e.g. XML acceleration
ATA
(Application Targeted Accelerators)
POPCNT e.g. Genome Mining
What should the applications, OS and VMM vendors do?: Understand the benefits & take advantage of new instructions in 2008. Provide us feedback on instructions ISV would like to see for next generation of applications
26
CRC32 e.g. iSCSI Application
Agenda • Intel® Core™ Microarchitecture (Nehalem) Design Overview • Enhanced Processor Core • Performance Features • Intel® Hyper-Threading Technology
• New Platform • New Cache Hierarchy • New Platform Architecture
• Performance Acceleration • Virtualization • New Instructions
• Power Management Overview • Minimizing Idle Power Consumption • Performance when it counts
27
Intel® Core™ Microarchitecture (Nehalem) Design Goals World class performance combined with superior energy efficiency – Optimized for: Dynamically scaled performance when Single Thread Multithreads
Existing Apps Emerging Apps All Usages
needed to maximize energy efficiency A single, scalable, foundation optimized across each segment and power envelope
Workstation / Server
Desktop / Mobile
A Dynamic and Design Scalable Microarchitecture 28
Power Control Unit Vcc
BCLK
Core PLL
Vcc Freq. Freq. Sensors
PLL
Core Vcc Freq. Freq. Sensors
PLL
Core
PCU
Vcc Freq. Freq. Sensors
PLL
Core Vcc Freq. Freq. Sensors
PLL
Uncore, Uncore, LLC
29
Integrated proprietary microcontroller Shifts control from hardware to embedded firmware Real time sensors for temperature, current, power Flexibility enables sophisticated algorithms, tuned for current operating conditions
Minimizing Idle Power Consumption • Operating system notifies CPU when no tasks are ready for execution – Execution of MWAIT instruction
• MWAIT arguments hint at expected idle duration Idle Power (W)
– Higher numbered C-states lower power, but also longer exit latency
• CPU idle states referred to as “C-States”
C0
C1
Cn
Exit Latency (us)
30
C6 on Intel® Core™ Microarchitecture (Nehalem)
31
C6 on Intel® Core™ Microarchitecture (Nehalem) Core Power
0
Cores 0, 1, 2, and 3 running applications.
Core 3 Core 2
0
Core 1 0
Core 0 0
Time
32
C6 on Intel® Core™ Microarchitecture (Nehalem) Core Power
Task completes. No work waiting. OS executes MWAIT(C6) instruction.
Core 3
0
Core 2 0
Core 1 0
Core 0 0
Time 33
C6 on Intel® Core™ Microarchitecture (Nehalem) Core Power
0
Execution stops. Core architectural state saved. Core clocks stopped. Cores 0, 1, and 3 continue execution undisturbed.
Core 3 Core 2
0
Core 1 0
Core 0 0
Time
34
C6 on Intel® Core™ Microarchitecture (Nehalem) Core Power
0
Core power gate turned off. Core voltage goes to 0. Cores 0, 1, and 3 continue execution undisturbed.
Core 3 Core 2
0
Core 1 0
Core 0 0
Time 35
C6 on Intel® Core™ Microarchitecture (Nehalem) Core Power Core 3 0
Core 2 0
0
Task completes. No work waiting. OS executes MWAIT(C6) instruction. Core 0 enters C6. Cores 1 and 3 continue execution undisturbed.
0
Time 36
Core 1 Core 0
C6 on Intel® Core™ Microarchitecture (Nehalem) Core Power
0
Interrupt for Core 2 arrives. Core 2 returns to C0, execution resumes at instruction following MWAIT(C6). Cores 1 and 3 continue execution undisturbed.
Core 3 Core 2
0
Core 1 0
Core 0 0
Time 37
C6 on Intel® Core™ Microarchitecture (Nehalem) Core Power Core 3 0
0
0
Interrupt for Core 0 arrives. Power gate turns on, core clock turns on, core state restored, core resumes execution at instruction following MWAIT(C6). Cores 1, 2, and 3 continue execution undisturbed.
0
Time Core independent C6 on Intel Core microarchitecture (Nehalem) extends benefits 38
Core 2 Core 1 Core 0
Intel® Core™ Microarchitecture (Nehalem)based Processor
I O
Core
Q P I
Core
Q u e u e
Core
Core
1
• Significant logic outside core – – – –
I O Q P I
Shared L3 Cache
0
M Total CPU Power Consumption i s c Core
Integrated memory controller Large shared cache High speed interconnect Arbitration logic
QPI = Intel® QuickPath Interconnect (Intel® QPI)
39
Cores (x N)
M i s c
Memory Controller
Clocks and Logic
Core Clock Distribution Core Leakage Uncore Logic I/O Uncore Clock Distribution Uncore Leakage
Intel® Core™ Microarchitecture (Nehalem) Package C-State Support Active CPU Power Core Clocks and Logic
• All cores in C6 state:
Cores (x N)
– Core power to ~0
Core Clock Distribution Core Leakage Uncore Logic I/O Uncore Clock Distribution Uncore Leakage
40
Intel® Core™ Microarchitecture (Nehalem) Package C-State Support Active CPU Power
• All cores in C6 state: – Core power to ~0
• Package to C6 state: – Uncore logic stops toggling
Uncore Logic I/O Uncore Clock Distribution Uncore Leakage
41
Intel® Core™ Microarchitecture (Nehalem) Package C-State Support Active CPU Power
• All cores in C6 state: – Core power to ~0
• Package to C6 state: – Uncore logic stops toggling – I/O to lower power state
I/O Uncore Clock Distribution Uncore Leakage
42
Intel® Core™ Microarchitecture (Nehalem) Package C-State Support Active CPU Power
• All cores in C6 state: – Core power to ~0
• Package to C6 state: – Uncore logic stops toggling – I/O to lower power state – Uncore clock grids stopped
Substantial reduction in idle CPU power 43
I/O Uncore Clock Distribution Uncore Leakage
Managing Active Power • Operating system changes frequency as needed to meet performance needs, minimize power – Enhanced Intel SpeedStep® Technology – Referred to as processor P-States
• PCU tunes voltage for given frequency, operating conditions, and silicon characteristics
PCU automatically optimizes operating voltage
44
Turbo Mode: Key to Scalability Goal • Intel® Core™ microarchitecture (Nehalem) is a scalable architecture
Nehalem
– High frequency core for performance in less constrained form factors – Retain ability to use that frequency in very small form factors – Retain ability to use that frequency when running lightly threaded or lower power workloads
• Turbo utilizes available frequency: – Maximizes both single-thread and multithread performance in the same part
Turbo Mode provides performance when you need it 45
Turbo Mode Enabling • Turbo Mode exposed as additional Enhanced Intel SpeedStep® Technology operating point – Operating system treats as any other P-state, requesting Turbo Mode when it needs more performance – Performance benefit comes from higher operating frequency – no need to enable or tune software
• Turbo Mode is transparent to system – Frequency transitions handled completely in hardware – PCU keeps silicon within existing operating limits – Systems designed to same specs, with or without Turbo Mode
Performance benefits with existing applications and operating systems 46
Summary • Intel® Core™ microarchitecture (Nehalem) – The 45nm Tock • Designed for – Power Efficiency – Scalability – Performance
• Key Innovations: – Enhanced Processor Core – Brand New Platform Architecture – Sophisticated Power Management
High Performance When You Need It Lower Power When You Don’t
47
Q&A
48
Legal Disclaimer • INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL® PRODUCTS. NO LICENSE, EXPRESS OR IMPLIED, BY ESTOPPEL OR OTHERWISE, TO ANY INTELLECTUAL PROPERTY RIGHTS IS GRANTED BY THIS DOCUMENT. EXCEPT AS PROVIDED IN INTEL’S TERMS AND CONDITIONS OF SALE FOR SUCH PRODUCTS, INTEL ASSUMES NO LIABILITY WHATSOEVER, AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY, RELATING TO SALE AND/OR USE OF INTEL® PRODUCTS INCLUDING LIABILITY OR WARRANTIES RELATING TO FITNESS FOR A PARTICULAR PURPOSE, MERCHANTABILITY, OR INFRINGEMENT OF ANY PATENT, COPYRIGHT OR OTHER INTELLECTUAL PROPERTY RIGHT. INTEL PRODUCTS ARE NOT INTENDED FOR USE IN MEDICAL, LIFE SAVING, OR LIFE SUSTAINING APPLICATIONS. • Intel may make changes to specifications and product descriptions at any time, without notice. • All products, dates, and figures specified are preliminary based on current expectations, and are subject to change without notice. • Intel, processors, chipsets, and desktop boards may contain design defects or errors known as errata, which may cause the product to deviate from published specifications. Current characterized errata are available on request. • Merom, Penryn, Hapertown, Nehalem, Dothan, Westmere, Sandy Bridge, and other code names featured are used internally within Intel to identify products that are in development and not yet publicly announced for release. Customers, licensees and other third parties are not authorized by Intel to use code names in advertising, promotion or marketing of any product or services and any such use of Intel's internal code names is at the sole risk of the user • 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. • Intel, Intel Inside, Intel Core, Pentium, Intel SpeedStep Technology, and the Intel logo are trademarks of Intel Corporation in the United States and other countries. • *Other names and brands may be claimed as the property of others. • Copyright © 2008 Intel Corporation.
49
Risk Factors This presentation contains forward-looking statements that involve a number of risks and uncertainties. These statements do not reflect the potential impact of any mergers, acquisitions, divestitures, investments or other similar transactions that may be completed in the future. The information presented is accurate only as of today’s date and will not be updated. In addition to any factors discussed in the presentation, the important factors that could cause actual results to differ materially include the following: Demand could be different from Intel's expectations due to factors including changes in business and economic conditions, including conditions in the credit market that could affect consumer confidence; customer acceptance of Intel’s and competitors’ products; changes in customer order patterns, including order cancellations; and changes in the level of inventory at customers. Intel’s results could be affected by the timing of closing of acquisitions and divestitures. Intel operates in intensely competitive industries that are characterized by a high percentage of costs that are fixed or difficult to reduce in the short term and product demand that is highly variable and difficult to forecast. Revenue and the gross margin percentage are affected by the timing of new Intel product introductions and the demand for and market acceptance of Intel's products; actions taken by Intel's competitors, including product offerings and introductions, marketing programs and pricing pressures and Intel’s response to such actions; Intel’s ability to respond quickly to technological developments and to incorporate new features into its products; and the availability of sufficient supply of components from suppliers to meet demand. The gross margin percentage could vary significantly from expectations based on changes in revenue levels; product mix and pricing; capacity utilization; variations in inventory valuation, including variations related to the timing of qualifying products for sale; excess or obsolete inventory; manufacturing yields; changes in unit costs; impairments of long-lived assets, including manufacturing, assembly/test and intangible assets; and the timing and execution of the manufacturing ramp and associated costs, including start-up costs. Expenses, particularly certain marketing and compensation expenses, vary depending on the level of demand for Intel's products, the level of revenue and profits, and impairments of long-lived assets. Intel is in the midst of a structure and efficiency program that is resulting in several actions that could have an impact on expected expense levels and gross margin. Intel's results could be impacted by adverse economic, social, political and physical/infrastructure conditions in the countries in which Intel, its customers or its suppliers operate, including military conflict and other security risks, natural disasters, infrastructure disruptions, health concerns and fluctuations in currency exchange rates. Intel's results could be affected by adverse effects associated with product defects and errata (deviations from published specifications), and by litigation or regulatory matters involving intellectual property, stockholder, consumer, antitrust and other issues, such as the litigation and regulatory matters described in Intel's SEC reports. A detailed discussion of these and other factors that could affect Intel’s results is included in Intel’s SEC filings, 50 June 28, 2008. including the report on Form 10-Q for the quarter ended
Backup Slides
51
Intel® Core™ Microarchitecture (Nehalem) Design Goals World class performance combined with superior energy efficiency – Optimized for: Dynamically scaled performance when Single Thread Multithreads
Existing Apps Emerging Apps All Usages
needed to maximize energy efficiency A single, scalable, foundation optimized across each segment and power envelope
Workstation / Server
Desktop / Mobile
A Dynamic and Design Scalable Microarchitecture 52
Tick-Tock Development Model Merom1
Penryn
Nehalem
Westmere
Sandy Bridge
NEW Microarchitecture
NEW Process
NEW Microarchitecture
NEW Process
NEW Microarchitecture
65nm
45nm
45nm
32nm
32nm
TOCK
TICK
TOCK
TICK
TOCK
Forecast
Intel® Core™ microarchitecture (formerly Merom) 45nm next generation Intel® Core™ microarchitecture (Penryn) Intel® Core™ Microarchitecture (Nehalem) Intel® Microarchitecture (Westmere) 53 Intel® Microarchitecture (Sandy Bridge) 1
All dates, product descriptions, availability and plans are forecasts and subject to change without notice.
53
Enhanced Processor Core Instruction Fetch and Pre Decode
ITLB
32kB Instruction Cache
Front End Execution Engine Memory
Instruction Queue Decode
4
2nd Level TLB
Rename/Allocate Retirement Unit (ReOrder Buffer)
256kB 2nd Level Cache
4
Reservation Station 6 Execution Units DTLB
32kB Data Cache
54
L3 and beyond
Front-end • Responsible for feeding the compute engine – Decode instructions – Branch Prediction
• Key Intel® Core™2 microarchitecture Features – 4-wide decode – Macrofusion – Loop Stream Detector Instruction Fetch and
ITLB
Pre Decode Instruction Queue Decode
55
32kB Instruction Cache
Loop Stream Detector Reminder • Loops are very common in most software • Take advantage of knowledge of loops in HW – Decoding the same instructions over and over – Making the same branch predictions over and over
• Loop Stream Detector identifies software loops – Stream from Loop Stream Detector instead of normal path – Disable unneeded blocks of logic for power savings – Higher performance by removing instruction fetch limitations
Intel® Core™2 Loop Stream Detector
Branch Prediction
Loop
Fetch
Stream Detector
18 Instructions
56
Decode
Branch Prediction Reminder • Goal: Keep powerful compute engine fed • Options: – Stall pipeline while determining branch direction/target – Predict branch direction/target and correct if wrong
• Minimize amount of time wasted correcting from incorrect branch predictions – Performance: – Through higher branch prediction accuracy – Through faster correction when prediction is wrong
– Power efficiency: Minimize number of speculative/incorrect micro-ops that are executed Continued focus on branch prediction improvements
57
L2 Branch Predictor • Problem: Software with a large code footprint not able to fit well in existing branch predictors – Example: Database applications
• Solution: Use multi-level branch prediction scheme • Benefits: – Higher performance through improved branch prediction accuracy – Greater power efficiency through less mis-speculation
58
Advanced Renamed Return Stack Buffer (RSB) • Instruction Reminder – CALL: Entry into functions – RET: Return from functions
• Classical Solution – Return Stack Buffer (RSB) used to predict RET – RSB can be corrupted by speculative path
• The Renamed RSB – No RET mispredicts in the common case
59
Execution Engine • Responsible for: – Scheduling operations – Executing operations
• Powerful Intel® Core™2 microarchitecture execution engine – Dynamic 4-wide Execution – Intel® Advanced Digital Media Boost – 128-bit wide SSE
– Super Shuffler (45nm next generation Intel® Core™ microarchitecture (Penryn))
60
Intel® Smart Cache – Core Caches • New 3-level Cache Hierarchy • 1st level caches – 32kB Instruction cache – 32kB, 8-way Data Cache
Core
– Support more L1 misses in parallel than Intel® Core™2 microarchitecture
32kB L1
32kB L1
Data Cache Inst. Cache
• 2nd level Cache – New cache introduced in Intel® Core™ microarchitecture (Nehalem) – Unified (holds code and data) – 256 kB per core (8-way) – Performance: Very low latency – 10 cycle load-to-use
– Scalability: As core count increases, reduce pressure on shared cache
61
256kB L2 Cache
New TLB Hierarchy • Problem: Applications continue to grow in data size • Need to increase TLB size to keep the pace for performance • Nehalem adds new low-latency unified 2nd level TLB # of Entries 1st Level Instruction TLBs Small Page (4k)
128
Large Page (2M/4M)
7 per thread
1st Level Data TLBs Small Page (4k)
64
Large Page (2M/4M)
32
New 2nd Level Unified TLB Small Page Only
512
62
Fast Unaligned Cache Accesses • Two flavors of 16-byte SSE loads/stores exist – Aligned (MOVAPS/D, MOVDQA) -- Must be aligned on a 16-byte boundary – Unaligned (MOVUPS/D, MOVDQU) -- No alignment requirement
• Prior to Intel® Core™ microarchitecture (Nehalem) – Optimized for Aligned instructions – Unaligned instructions slower, lower throughput -- Even for aligned accesses! – Required multiple uops (not energy efficient)
– Compilers would largely avoid unaligned load – 2-instruction sequence (MOVSD+MOVHPD) was faster
• Intel Core microarchitecture (Nehalem) optimizes Unaligned instructions – Same speed/throughput as Aligned instructions on aligned accesses – Optimizations for making accesses that cross 64-byte boundaries fast – Lower latency/higher throughput than Core 2
– Aligned instructions remain fast
• No reason to use aligned instructions on Intel Core microarchitecture (Nehalem)! • Benefits: – Compiler can now use unaligned instructions without fear – Higher performance on key media algorithms – More energy efficient than prior implementations
63
Faster Synchronization Primitives LOCK CMPXCHG Perform ance
Relative Latency
• Multi-threaded software becoming more prevalent • Scalability of multi-thread applications can be limited by synchronization • Synchronization primitives: LOCK prefix, XCHG • Reduce synchronization latency for legacy software
1
1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0 Pentium 4
Core 2
Nehalem
Greater thread scalability with Nehalem Intel® Pentium® 4 processor Intel® Core™2 Duo processor Intel® Core™ microarchitecture (Nehalem)-based processor 1
64
Intel® Core™ Microarchitecture (Nehalem) SMT Implementation Details Policy
Description
Intel® Core™ Microarchitecture (Nehalem) Examples
Replicated
Duplicate logic per thread
Register State Renamed RSB Large Page ITLB
Partitioned
Statically allocated between threads
Load Buffer Store Buffer Reorder Buffer Small Page ITLB
Competitively Shared
Depends on thread’s dynamic behavior
Reservation Station Caches Data TLB 2nd level TLB
Unaware
No SMT impact
Execution units
SMT efficient due to minimal replication of logic 65
Feeding the Execution Engine • Powerful 4-wide dynamic execution engine • Need to keep providing fuel to the execution engine • Intel® Core™ Microarchitecture (Nehalem) Goals – Low latency to retrieve data – Keep execution engine fed w/o stalling
– High data bandwidth – Handle requests from multiple cores/threads seamlessly
– Scalability – Design for increasing core counts
• Combination of great cache hierarchy and new platform
Intel® Core™ microarchitecture (Nehalem) designed to feed the execution engine
66
Inclusive vs. Exclusive Caches – Cache Miss Exclusive
Inclusive
L3 Cache
L3 Cache
Core
Core
Core
Core
Core
Core
Core
Core
0
1
2
3
0
1
2
3
Data request from Core 0 misses Core 0’s L1 and L2 Request sent to the L3 cache
67
Inclusive vs. Exclusive Caches – Cache Miss Exclusive
Inclusive
L3 Cache
L3 Cache
MISS!
MISS!
Core
Core
Core
Core
Core
Core
Core
Core
0
1
2
3
0
1
2
3
Core 0 looks up the L3 Cache Data not in the L3 Cache
68
Inclusive vs. Exclusive Caches – Cache Miss Exclusive
Inclusive
L3 Cache
L3 Cache
MISS!
MISS!
Core
Core
Core
Core
Core
Core
Core
Core
0
1
2
3
0
1
2
3
Guaranteed data is not on-die
Must check other cores
Greater scalability from inclusive approach
69
Inclusive vs. Exclusive Caches – Cache Hit Exclusive
Inclusive
L3 Cache
L3 Cache HIT!
HIT!
Core
Core
Core
Core
Core
Core
Core
Core
0
1
2
3
0
1
2
3
No need to check other cores
Data could be in another core BUT Intel® CoreTM microarchitecture (Nehalem) is smart…
70
Inclusive vs. Exclusive Caches – Cache Hit Inclusive • Maintain a set of “core valid” bits per cache line in the L3 cache • Each bit represents a core
L3 Cache
• If the L1/L2 of a core may contain the cache line, then core valid bit is set to “1”
HIT! 0 0 0 0
• No snoops of cores are needed if no bits are set • If more than 1 bit is set, line cannot be in Modified state in any core
Core
Core
Core
Core
0
1
2
3
Core valid bits limit unnecessary snoops
71
Inclusive vs. Exclusive Caches – Read from other core Exclusive
Inclusive
L3 Cache
L3 Cache
MISS!
HIT! 0 0 1 0
Core
Core
Core
Core
Core
Core
Core
Core
0
1
2
3
0
1
2
3
Only need to check the core
Must check all other cores
whose core valid bit is set
72
Local Memory Access • CPU0 requests cache line X, not present in any CPU0 cache – CPU0 requests data from its DRAM – CPU0 snoops CPU1 to check if data is present
• Step 2:
– DRAM returns data – CPU1 returns snoop response
• Local memory latency is the maximum latency of the two responses • Intel® Core™ microarchitecture (Nehalem) optimized to keep key latencies close to each other
Intel® DRAM
CPU0
QPI
Intel® QPI = Intel® QuickPath Interconnect
73
CPU1
DRAM
Remote Memory Access • CPU0 requests cache line X, not present in any CPU0 cache – CPU0 requests data from CPU1 – Request sent over Intel® QuickPath Interconnect (Intel® QPI) to CPU1 – CPU1’s IMC makes request to its DRAM – CPU1 snoops internal caches – Data returned to CPU0 over Intel QPI
• Remote memory latency a function of having a low latency interconnect Intel® DRAM
CPU0
QPI
74
CPU1
DRAM
Hardware Prefetching (HWP) • HW Prefetching critical to hiding memory latency • Structure of HWPs similar as in Intel® Core™2 microarchitecture – Algorithmic improvements in Intel® Core™ microarchitecture (Nehalem) for higher performance
• L1 Prefetchers – Based on instruction history and/or load address pattern
• L2 Prefetchers – Prefetches loads/RFOs/code fetches based on address pattern – Intel Core microarchitecture (Nehalem) changes: – Efficient Prefetch mechanism – Remove the need for Intel® Xeon® processors to disable HWP
– Increase prefetcher aggressiveness – Locks on address streams quicker, adapts to change faster, issues more prefetchers more aggressively (when appropriate)
75
Today’s Platform Architecture Front-Side Bus Evolution CPU
memory
CPU
memory
CPU
CPU
CPU
MCH
CPU ICH
memory
CPU
MCH
CPU
CPU
MCH
CPU ICH
CPU
CPU
76
ICH
Intel® QuickPath Interconnect • Intel® Core™ microarchitecture (Nehalem) introduces new Intel® QuickPath Interconnect (Intel® QPI) • High bandwidth, low latency point to point interconnect • Up to 6.4 GT/sec initially – 6.4 GT/sec -> 12.8 GB/sec – Bi-directional link -> 25.6 GB/sec per link – Future implementations at even higher speeds
• Highly scalable for systems with varying # of sockets
Nehalem EP
memory
memory
CPU
Nehalem EP
IOH
CPU
CPU IOH
Intel® CoreTM microarchitecture (Nehalem-EP) 77
CPU
memory
memory
Integrated Memory Controller (IMC) • Memory controller optimized per market segment • Initial Intel® Core™ microarchitecture (Nehalem) products – – – – – –
Native DDR3 IMC Up to 3 channels per socket Massive memory bandwidth Designed for low latency Support RDIMM and UDIMM RAS Features
DDR3
• Future products
Nehalem EP
Nehalem EP
DDR3
Tylersburg EP
– Scalability
– Vary # of memory channels – Increase memory speeds – Buffered and Non-Buffered solutions
– Market specific needs
– Higher memory capacity – Integrated graphics
Significant performance through new IMC Intel® Core™ microarchitecture (Nehalem-EP) Intel® Next Generation Server Processor Technology (Tylersburg-EP)
78
Memory Latency Comparison • • • •
Low memory latency critical to high performance Design integrated memory controller for low latency Need to optimize both local and remote memory latency Intel® Core™ microarchitecture (Nehalem) delivers – Huge reduction in local memory latency – Even remote memory latency is fast
• Effective memory latency depends per application/OS
– Percentage of local vs. remote accesses – Intel Core microarchitecture (Nehalem) has lower latency regardless of mix
Relative Memory Latency
Relative M emory Latency Comparison 1.00 0.80 0.60 0.40 0.20 0.00 Harpertow n (FSB 1600)
1
1
Nehalem (DDR3-1067) Local
Next generation Quad-Core Intel® Xeon® processor (Harpertown)
Intel® CoreTM microarchitecture (Nehalem)
79
Nehalem (DDR3-1067) Remote
Latency of Virtualization Transitions • Microarchitectural
Round Trip Virtualization Latency
– Huge latency reduction generation over generation – Nehalem continues the trend
Relative Latency
100%
• Architectural – Virtual Processor ID (VPID) added in Intel® Core™ microarchitecture (Nehalem) – Removes need to flush TLBs on transitions
80% 60% 40% 20% 0%
Merom
Penryn
Nehalem
Higher Virtualization Performance Through Lower Transition Latencies Intel® Core™ microarchitecture (formerly Merom) 45nm next generation Intel® Core™ microarchitecture (Penryn) Intel® Core™ microarchitecture (Nehalem) 1
80
1
Extended Page Tables (EPT) Motivation VM1
Guest OS
• A VMM needs to protect physical memory • Multiple Guest OSs share the same physical memory • Protections are implemented through page-table virtualization
CR3 Guest Page Table
Guest page table changes cause exits into the VMM
VMM
CR3
• Page table virtualization accounts for a significant portion of virtualization overheads
Active Page Table
VMM maintains the active page table, which is used by the CPU
• VM Exits / Entries
• The goal of EPT is to reduce these overheads
81
STTNI - STring & Text New Instructions Operates on strings of bytes or words (16b) Equal Each Instruction True for each character in Src2 if same position in Src1 is equal Src1: Test\tday Src2: tad tseT Mask: 01101111
STTNI MODEL Source2 (XMM / M128)
Bit 0
True for each character in Src2 if any character in Src1 matches Src1: Example\n Src2: atad tsT Mask: 10100000
Ranges Instruction True if a character in Src2 is in at least one of up to 8 ranges in Src1 Src1: AZ’0’9zzz Src2: taD tseT Mask: 00100001
Equal Ordered Instruction Finds the start of a substring (Src1) within another string (Src2) Src1: ABCA0XYZ Src2: S0BACBAB Mask: 00000010
Source1 (XMM)
Equal Any Instruction
T e s t \t d a y
t ad t s eT xxxx xxxT x x x x x xTx xxxx xTxx xxxxTxxx xxxFxxxx xxTx xxxx xTxx xxxx Fxxxxxxx 01101111
Projected 3.8x kernel speedup on XML parsing & 2.7x savings on instruction cycles 82
Bit 0 Check each bit in the diagonal
IntRes1
STTNI Model
EQUAL EACH
EQUAL ANY
Source2 (XMM / M128)
Source1 (XMM)
Bit 0
E x a m p l e \n
a F F T F F F F F
t ad FFF FFF FTF FFF FFF FFF FFF FFF
F F F F F F F F
t F F F F F F F F
s F F F F F F F F
T F F F F F F F F
Bit 0 OR results down each column
Bit 0
Source1 (XMM)
Source2 (XMM / M128)
10100000
T e s t \t d a y
IntRes1
RANGES
t aD t s e T A FFTFFFTT Z F FTTF F FT ‘0’ T T T F T T T T 9 FFFTFFFF z FFFFFFFF z TTTTTTTT z FFFFFFFF z TTTTTTTT 00100001
Check each bit in the diagonal
IntRes1
Source2 (XMM / M128) Bit 0 •First Compare does GE, next does LE
Bit 0
•AND GE/LE pairs of results •OR those results
IntRes1
83
S0BACBAB
Bit 0
Source1 (XMM)
Source1 (XMM)
Bit 0
Bit 0
EQUAL ORDERED
Source1 (XMM)
Source2 (XMM / M128)
t ad t seT xxxxxxxT xxxxxxTx xxxxxTxx xxxxTxxx xxxFxxxx xxTxxxxx xTxxxxxx Fxxxxxxx 01101111
A B C A 0 X Y Z
fF fF F T F fF fF T F F fF fF F F T fF fF F T F fTfTfTfT x fTfTfT x x fTfT x x x
F T F x x x x
T F x x x x x
F x x x x x x
fT x x x x x x x 00000010
Bit 0
AND the results
AND the along results each along each diagonal diagonal
IntRes1
ATA - Application Targeted Accelerators
CRC32
POPCNT POPCNT determines the number of nonzero
Accumulates a CRC32 value using the iSCSI polynomial
bits in the source. 63 DST
SRC
32 31 X
63
0
0 1 0
Old CRC
10
Bit
... 0 0 1 1
RAX
Data 8/16/32/64 bit Σ 0 63 DST
32 31 0
0x3
0
RBX
New CRC =? 0
One register maintains the running CRC value as a software loop iterates over data. Fixed CRC polynomial = 11EDC6F41h
0
ZF
POPCNT is useful for speeding up fast matching in data mining workloads including: • DNA/Genome Matching • Voice Recognition
Replaces complex instruction sequences for CRC in Upper layer data protocols: • iSCSI, RDMA, SCTP
ZFlag set if result is zero. All other flags (C,S,O,A,P) reset
Enables enterprise class data assurance with high data rates in networked storage in any user environment. 84
Tools Support of New Instructions •
Intel® Compiler 10.x supports the new instructions – – – –
•
Intel® XML Software Suite – – –
•
SSE4.2 supported via intrinsics Inline assembly supported on IA-32 only Necessary to include required header files in order to access intrinsics VC++ 2008 tools masm, msdis, and debuggers recognize the new instructions
Sun Studio Express* 7/08 – – –
•
High performance C++ and Java runtime libraries Version 1.0 (C++), version 1.01 (Java) available now Version 1.1 w/SSE4.2 optimizations planned for September 2008
Microsoft Visual Studio* 2008 VC++ – – – –
•
Nehalem specific compiler optimizations SSE4.2 supported via vectorization and intrinsics Inline assembly supported on both IA-32 and Intel® 64 architecture targets Necessary to include required header files in order to access intrinsics
Supports Intel® CoreTM microarchitecture (Merom), 45nm next generation Intel® Core™ microarchitecture (Penryn), Intel® CoreTM microarchitecture (Nehalem) SSE4.1, SSE4.2 through intrinsics Nehalem specific compiler optimizations
GCC* 4.3.1 – – –
Support Intel Core microarchitecture (Merom), 45nm next generation Intel Core microarchitecture (Penryn), Intel Core microarchitecture (Nehalem) via –mtune=generic. Support SSE4.1 and SSE4.2 through vectorizer and intrinsics
Broad Software Support for Intel® Core™ Microarchitecture (Nehalem) 85
Software Optimization Guidelines • Most optimizations for Intel® Core™ microarchitecture still hold • Examples of new optimization guidelines: – 16-byte unaligned loads/stores – Enhanced macrofusion rules – NUMA optimizations
• Intel® Core™ microarchitecture (Nehalem) SW Optimization Guide will be published • Intel® Compiler will support settings for Intel Core microarchitecture (Nehalem) optimizations
86
Example Code For strlen() string equ [esp + 4] mov ecx,string ; ecx -> string je short byte_2 test ecx,3 ; test if string is aligned on 32 bits test eax,0ff000000h je short main_loop ; is it byte 3 str_misaligned: je short byte_3 ; simple byte loop until string is aligned jmp short main_loop mov al,byte ptr [ecx] ; taken if bits 24-30 are clear and bit add ecx,1 ; 31 is set test al,al byte_3: je short byte_3 lea eax,[ecx - 1] test ecx,3 mov ecx,string jne short str_misaligned eax,ecx add eax,dword ptr 0 ; 5 byte nop tosub align label below ret align 16 ; should be redundant byte_2: main_loop: eax,[ecx - 2] mov eax,dword ptr [ecx] ; read 4 byteslea mov ecx,string mov edx,7efefeffh sub eax,ecx add edx,eax ret xor eax,-1 byte_1: xor eax,edx lea eax,[ecx - 3] add ecx,4 mov ecx,string test eax,81010100h sub eax,ecx je short main_loop ret ; found zero byte in the loop byte_0: mov eax,[ecx - 4] lea eax,[ecx - 4] test al,al ; is it byte 0 mov ecx,string je short byte_0 sub eax,ecx test ah,ah ; is it byte 1 ret je short byte_1 strlen endp test eax,00ff0000h ; is it byte 2 end
Current Code:
STTNI Version int sttni_strlen(const char * src) { char eom_vals[32] = {1, 255, 0}; __asm{ mov
eax, src
movdqu xor
xmm2, eom_vals ecx, ecx
topofloop: add
eax, ecx
movdqu
xmm1, OWORD PTR[eax]
pcmpistri xmm2, xmm1, imm8 jnz
topofloop
endofstring: add
eax, ecx
sub ret
eax, src
} Minimum of 11 instructions; Inner loop processes 4 bytes with 8 instructions }
STTNI Code: Minimum of 10 instructions; A single inner loop processes 16 bytes with only 4 instructions
87
CRC32 Preliminary Performance CRC32 optimized Code
Preliminary tests involved Kernel code implementing CRC algorithms commonly used by iSCSI drivers.
crc32c_sse42_optimized_version(uint32 crc, unsigned char const *p, size_t len)
32-bit and 64-bit versions of the Kernel under test
{ // Assuming len is a multiple of 0x10 asm("pusha");
32-bit version processes 4 bytes of data using 1 CRC32 instruction
asm("mov %0, %%eax" :: "m" (crc)); asm("mov %0, %%ebx" :: "m" (p));
64-bit version processes 8 bytes of data using 1 CRC32 instruction
asm("mov %0, %%ecx" :: "m" (len)); asm("1:");
Input strings of sizes 48 bytes and 4KB used for the test
// Processing four byte at a time: Unrolled four times: asm("crc32 %eax, 0x0(%ebx)"); asm("crc32 %eax, 0x4(%ebx)");
32 - bit
64 - bit
Input Data Size = 48 bytes
6.53 X
9.85 X
Input Data Size = 4 KB
9.3 X
18.63 X
asm("crc32 %eax, 0x8(%ebx)"); asm("crc32 %eax, 0xc(%ebx)"); asm("add $0x10, %ebx")2; asm("sub $0x10, %ecx"); asm("jecxz 2f"); asm("jmp 1b"); asm("2:"); asm("mov %%eax, %0" : "=m" (crc)); asm("popa"); return crc; }}
Preliminary Results show CRC32 instruction out-performing the fastest CRC32C software algorithm by a big margin 88
Idle Power Matters • Data center operating costs1 – 41M physical servers by 2010, average utilization < 10% – $0.50 spent on power and cooling for every $1 spent on server hardware
• Regulatory requirements affect all segments – ENERGY STAR* and related requirements
• Environmental responsibility
Idle power consumption not just mobile concern 1.
IDC’s Datacenter Trends Survey, January 2007
89
CPU Core Power Consumption
• High frequency processes are leaky – Reduced via high-K metal gate process, design technologies, manufacturing optimizations
90
Leakage
CPU Core Power Consumption
• High frequency designs require high performance global clock distribution • High frequency processes are leaky – Reduced via high-K metal gate process, design technologies, manufacturing optimizations
91
Clock Distribution Leakage
CPU Core Power Consumption Total Core Power Consumption
• Remaining power in logic, local clocks – Power efficient microarchitecture, good clock gating minimize waste
• High frequency designs require high performance global clock distribution • High frequency processes are leaky – Reduced via high-K metal gate process, design technologies, manufacturing optimizations
Local Clocks and Logic Clock Distribution Leakage
Challenge – Minimize power when idle
92
C-State Support Before Intel® Core™ Microarchitecture (Nehalem) Active Core Power
• C0: CPU active state
Local Clocks and Logic Clock Distribution Leakage
93
C-State Support Before Intel® Core™ Microarchitecture (Nehalem) • C0: CPU active state • C1, C2 states (early 1990s): • Stop core pipeline • Stop most core clocks
Active Core Power
Local Clocks and Logic Clock Distribution Leakage
94
C-State Support Before Intel® Core™ Microarchitecture (Nehalem) • C0: CPU active state • C1, C2 states (early 1990s):
Active Core Power
• Stop core pipeline • Stop most core clocks
• C3 state (mid 1990s): • Stop remaining core clocks
Clock Distribution Leakage
95
C-State Support Before Intel® Core™ Microarchitecture (Nehalem) • C0: CPU active state • C1, C2 states (early 1990s):
Active Core Power
• Stop core pipeline • Stop most core clocks
• C3 state (mid 1990s): • Stop remaining core clocks
• C4, C5, C6 states (mid 2000s): • Drop core voltage, reducing leakage • Voltage reduction via shared VR
Leakage
Existing C-states significantly reduce idle power
96
C-State Support Before Intel® Core™ Microarchitecture (Nehalem) • Cores share a single voltage plane – All cores must be idle before voltage reduced – Independent VR’s per core prohibitive from cost and form factor perspective
• Deepest C-states have relatively long exit latencies – System / VR handshake, ramp voltage, restore state, restart pipeline, etc.
Deepest C-states available in mobile products
97
Intel® Core™ Microarchitecture (Nehalem) Core C-State Support Active Core Power
• C0: CPU active state
Local Clocks and Logic Clock Distribution Leakage
98
Intel® Core™ Microarchitecture (Nehalem) Core C-State Support Active Core Power
• C0: CPU active state • C1 state:
Local Clocks and Logic
• Stop core pipeline • Stop most core clocks
Clock Distribution Leakage
99
Intel® Core™ Microarchitecture (Nehalem) Core C-State Support Active Core Power
• C0: CPU active state • C1 state: • Stop core pipeline • Stop most core clocks
• C3 state: • Stop remaining core clocks
Clock Distribution Leakage
100
Intel® Core™ Microarchitecture (Nehalem) Core C-State Support Active Core Power
• C0: CPU active state • C1 state: • Stop core pipeline • Stop most core clocks
• C3 state: • Stop remaining core clocks
• C6 state: • Processor saves architectural state • Turn off power gate, eliminating leakage
Core idle power goes to ~0
101
Leakage
C6 Support on Intel® Core™2 Duo Mobile Processor (Penryn)
102
C6 Support on Intel® Core™2 Duo Mobile Processor (Penryn) Core Power
Cores running applications.
Core 1 0
Core 0 0
Time
103
C6 Support on Intel® Core™2 Duo Mobile Processor (Penryn) Core Power
Task completes. No work waiting. OS executes MWAIT(C6) instruction.
Core 1 0
Core 0 0
Time
104
C6 Support on Intel® Core™2 Duo Mobile Processor (Penryn) Core Power
Execution stops. Core architectural state saved. Core clocks stopped. Core 0 continues execution undisturbed.
Core 1
0
Core 0 0
Time
105
C6 Support on Intel® Core™2 Duo Mobile Processor (Penryn) Core Power
Core 1 0
Task completes. No work waiting. OS executes MWAIT(C6) instruction. Core enters C6.
0
Time
106
Core 0
C6 Support on Intel® Core™2 Duo Mobile Processor (Penryn) Core Power
Core 1 0 VR voltage reduced. Power drops.
Core 0 0
Time
107
C6 Support on Intel® Core™2 Duo Mobile Processor (Penryn) Core Power
Interrupt for Core 1 arrives. VR voltage increased. Core 1 clocks turn on, core state restored, and core resumes execution at instruction following MWAIT(C6). Cores 0 remains idle.
Core 1
0
Core 0 0
Time
108
C6 Support on Intel® Core™2 Duo Mobile Processor (Penryn) Core Power
0
Interrupt for Core 0 arrives. Core 0 returns to C0 and resumes execution at instruction following MWAIT(C6). Core 1 continues execution undisturbed.
Core 1
Core 0 0
C6 significantly reducesTime idle power consumption
109
Reducing Platform Idle Power • Dramatic improvements in CPU idle power increase importance of platform improvements • Memory power: – Memory clocks stopped between requests at low utilization – Memory to self refresh in package C3, C6
• Link power: – Intel® QuickPath Interconnect links to lower power states as CPU becomes less active – PCI Express* links on chipset have similar behavior
• Hint to VR to reduce phases during periods of low current demand Intel® Core™ microarchitecture (Nehalem) reduces CPU and platform power 110
Intel® Core™ Microarchitecture (Nehalem): Integrated Power Gate VCC
• Integrated power switch between VR output and core voltage supply – – –
•
Very low on-resistance Very high off-resistance Much faster voltage ramp than external VR
Core0
Core1
Core2
Memory System, Cache, I/O
Enables per core C6 state – –
Individual cores transition to ~0 power state Transparent to other cores, platform, software, and VR
Close collaboration with process technology to optimize device characteristics 111
111
Core3
VTT
Agenda • Intel® Core™ microarchitecture (Nehalem) power management overview • Minimizing idle power consumption • Performance when you need it
112
Turbo Mode Before Intel® Core™ Microarchitecture (Nehalem) Clock Stopped Power reduction in inactive cores
113
113
Core 0 Core 1
Workload Lightly Threaded
Frequency (F)
Core 0 Core 1
Frequency (F)
No Turbo
Turbo Mode Before Intel® Core™ Microarchitecture (Nehalem) Power reduction in inactive cores
In response to workload adds additional performance bins within headroom
114
Core 0 Core 1
Frequency (F)
No Turbo
Workload Lightly Threaded
114
Core 0
Turbo Mode
Frequency (F)
Clock Stopped
Intel® Core™ Microarchitecture (Nehalem) Turbo Mode Power Gating Zero power for inactive cores
115
115
Core 0 Core 1 Core 2 Core 3
Workload Lightly Threaded or < TDP
Frequency (F)
Core 0 Core 1 Core 2 Core 3
Frequency (F)
No Turbo
Intel® Core™ Microarchitecture (Nehalem) Turbo Mode Zero power for inactive cores
In response to workload adds additional performance bins within headroom
116
Core 0 Core 1 Core 2 Core 3
Frequency (F)
No Turbo
Workload Lightly Threaded or < TDP
116
Core 0 Core 1
Turbo Mode
Frequency (F)
Power Gating
Intel® Core™ Microarchitecture (Nehalem) Turbo Mode Zero power for inactive cores
In response to workload adds additional performance bins within headroom
117
Core 0 Core 1 Core 2 Core 3
Frequency (F)
No Turbo
Workload Lightly Threaded or < TDP
117
Core 0 Core 1
Turbo Mode
Frequency (F)
Power Gating
Intel® Core™ Microarchitecture (Nehalem) Turbo Mode Active cores running workloads < TDP
118
118
Core 0 Core 1 Core 2 Core 3
Workload Lightly Threaded or < TDP
Frequency (F)
Core 0 Core 1 Core 2 Core 3
Frequency (F)
No Turbo
Intel® Core™ Microarchitecture (Nehalem) Turbo Mode
119
Workload Lightly Threaded or < TDP
119
In response to workload adds additional performance bins within headroom
Core 0 Core 1 Core 2 Core 3
Core 0 Core 1 Core 2 Core 3
Frequency (F)
No Turbo
Turbo Mode
Frequency (F)
Active cores running workloads < TDP
Intel® Core™ Microarchitecture (Nehalem) Turbo Mode Zero power for inactive cores
In response to workload adds additional performance bins within headroom
Core 0 Core 1 Core 2 Core 3
Frequency (F)
No Turbo
Workload Lightly Threaded or < TDP
Core 0 Core 1 Core 2 Core 3
Turbo Mode
Frequency (F)
Power Gating
Dynamically Delivering Optimal Performance and Energy Efficiency 120
120
Additional Sources of Information on This Topic: • Other Sessions / Chalk Talks / Labs: – TCHS001: Next Generation Intel® Core™ Microarchitecture (Nehalem) Family of Processors: Screaming Performance, Efficient Power (8/19, 3:00 – 3:50) – DPTS001: High End Desktop Platform Design Overview for the Next Generation Intel® Microarchitecture (Nehalem) Processor (8/20, 2:40 – 3:30) – NGMS001: Next Generation Intel® Microarchitecture (Nehalem) Family: Architectural Insights and Power Management (8/19, 4:00 – 5:50) – NGMC001: Chalk Talk: Next Generation Intel® Microarchitecture (Nehalem) Family (8/19, 5:50 – 6:30) – NGMS002: Tuning Your Software for the Next Generation Intel® Microarchitecture (Nehalem) Family (8/20, 11:10 – 12:00) – PWRS003: Power Managing the Virtual Data Center with Windows Server* 2008 / Hyper-V and Next Generation Processor-based Intel® Servers Featuring Intel® Dynamic Power Technology (8/19, 3:00 – 3:50) – PWRS005: Platform Power Management Options for Intel® Next Generation Server Processor Technology (Tylersburg-EP) (8/21, 1:40 – 2:30) – SVRS002: Overview of the Intel® QuickPath Interconnect (8/21, 11:10 – 12:00)
121
Session Presentations - PDFs The PDF for this Session presentation is available from our IDF Content Catalog at the end of the day at: www.intel.com/idf or
https://intel.wingateweb.com/US08/scheduler/public.jsp
122
Please Fill out the Session Evaluation Form Place form in evaluation box at the back of session room Thank you for your input, we use it to improve future Intel Developer Forum events
123