Presentation Title

Report
Intel® Xeon® Processor E5-2600 v2 Product Family
Ivy Bridge Improvements
Feature
Cores/Threads
Last-level Cache
Max Memory Speed
(MHz)
Max DIMM Capacity
PCIe* Lanes /
Controllers/Speed
TDP (W)
Xeon E5-2600
Xeon E5-2600 v2
Up to 8 cores /16
Threads
Up to 12 Cores/24
Threads
Up to 20 MB
Up to 30 MB
Up to 1600
Up to 1866
12 Slots/Processor
40 / 10 (PCIe* 3.0 at 8 GT/s)
150 (Workstation only), 130, 115, 95, 80, 70, 60
Additional Feature Improvements:
•
Intel® Secure Key & Intel® OS Guard
•
Advanced Programmable Interrupt Controller virtualization (APICv)
*Other names and brands may be claimed as the property of others.
Intel® Xeon® Processor E5-2600 v2 Product Family
Proposed SKU Stack
Advanced
8.0 GT/s QPI
DDR3-1866 (skt R)
DDR3-1600 (skt B2)
Intel® HT
Technology
 Intel® Turbo Boost
Technology




10C
130W
3.0GHz 25M E5-2690 v2
10C
115W
2.8GHz 25M E5-2680 v2
10C
115W
2.5GHz 25M E5-2670 v2
10C
95W
2.2GHz 25M E5-2660 v2
Standard
 7.2 GT/s QPI
 DDR3 1600
 Intel® HT
Technology
 Intel® Turbo Boost
Technology
Basic
 6.4 GT/s QPI
 DDR3 1333
 No Intel® HT
Technology
 No Intel® Turbo
Boost Technology
2
8C
2.6GHz 20M
E5-2650 v2
8C
2.0GHz 20M
E5-2640 v2
6C
2.6GHz 15M
6C
2.1GHz 15M
Segment
Optimized
 8.0 GT/s QPI
 DDR3-1866
 Intel® HT
Technology
 Intel® Turbo Boost
Technology
12C
130W
2.7GHz 30M E5-2697 v2
12C
115W
2.4GHz 30M E5-2695 v2
8C
150W
3.4GHz 20M E5-2687W v2
8C
130W
3.3GHz 25M E5-2667 v2
Workstation
Only SKU
6C
130W
3.5GHz 25M E5-2643 v2
95W
4C
130W
3.5GHz 15M E5-2637 v2
95W
80W
E5-2630 v2
80W
E5-2620 v2
4C
2.5GHz 10M
E5-2609 v2
80W
4C
1.8GHz 10M
E5-2603 v2
10C 8.0 GT/s QPI
6C 7.2 GT/s QPI
DDR3-1600
Intel® HT
Technology
 Intel® Turbo Boost
Technology




Low Power
10C
1.7GHz 25M
E5-2650L v2
70W
6C
2.4GHz 15M
E5-2630L v2
60W
Socket compatible with
SNB-EP top to bottom on the SKU stack
80W
All SKUs, frequencies and features
and can change without notice
Intel® Xeon® Processor E5-2600 v2 Product Family
6C, 10C, and 12C processors
6C
10C
12C
• 6C, 10C and 12C parts are sourced from different dies (see layouts above)
• 6C and 10C consist of 2 columns of 3 and 5 x (core + LLC slices) respectively and
one Memory Controller (MC). Single MC controls all 4 DDR channels.
- 10C has one more row of cores / LLC slices added over 8C E5-2600 (SNB-EP)
- 6C die is removing 2 rows of cores/LLC slices from 10C
- 8C variants are sourced from the 10C die as well
• 12C is a die with 3 columns of 4 x (core + LLC slices) with 2 MCs, each MC
controls 2 DDR channels only
3
Intel® Turbo Boost Technology: Frequency Bin upside by SKU†
Intel® Xeon® Processor E5-2600 v2 product family: Preliminary
4
Intel® Xeon® Processor E5-2600 v2 Product Family
Enterprise Performance Summary
Upside
expected
at POR
top bin
frequency
of 2.7
GHz
Intel® Xeon® Processor E5-26XX v2 (12C, 2.5GHz, 130W) vs.
Intel® Xeon® Processor E5-2690 (8C, 2.9GHz, 135W)
Higher is better
1.35
1.30
1.30
1.29
1.26
1.26
1.25
1.24
1.16
SPECjbb*2013
SAP-SD* 2-Tier
SPECWeb*_2009 PHP
VMmark* v2.1
SPECint*_rate_base2006
TPC-E*
SPECjbb*2005
SPECfp*_rate_base2006
TPC-C*
1.00
Intel® Xeon® Processor E5-2690
(8C, 2.9GHz) Qual Silicon Measurements
0.00
0.20
0.40
0.60
0.80
1.00
Relative Performance
1.20
1.40
(Normalized to 1.0 Baseline of previous generation)
Average gen-to-gen performance boost of up to 27% on B2 Silicon
Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems,
components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated
purchases, including the performance of that product when combined with other products.
Source: Intel Internal Measurements as of 28 March 2013. See back up slides for configuration details.
5
Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSE3 instruction sets and other optimizations. Intel does not
guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to
Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice revision #20110804
For more information go to http://www.intel.com/performance
*Other names and brands may be claimed as the property of others.
Intel® Xeon® Processor E5-2600 v2 Product Family
HPC Performance Summary
Upside
expected
at POR
top bin
frequency
of 2.7
GHz
Intel® Xeon® Processor E5-26XX v2 (12C, 2.5GHz, 130W) vs.
Intel® Xeon® Processor E5-2690 (8C, 2.9GHz, 135W)
Higher is better
1.35
1.33
1.32
1.28
1.28
1.28
1.28
1.23
1.16
Linpack
SPECompG*_base2012
STREAM
SPECmpiM*_base2007
Energy Apps
Life Sciences Apps
Financial Services Apps
Numerical Weather Simulation Apps
Computer Aided Engineering Apps
1.00
Intel® Xeon® Processor E5-2690
(8C, 2.9GHz) Qual Silicon Measurements
0.00
0.20
0.40
0.60
0.80
1.00
Relative Performance
1.20
1.40
(Normalized to 1.0 Baseline of previous generation)
Average gen-to-gen performance boost of up to 28% on B2 Silicon
Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems,
components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated
purchases, including the performance of that product when combined with other products.
Source: Intel Internal Measurements as of 28 March 2013. See back up slides for configuration details.
6
Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSE3 instruction sets and other optimizations. Intel does not
guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to
Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice revision #20110804
For more information go to http://www.intel.com/performance
*Other names and brands may be claimed as the property of others.
Intel® Xeon® processor E5-2600 v2 Product Family
Preliminary SKU performance
IVB Socket R
SNB Socket R
8C
135W
2.9 GHz E5-2690
503
8C
130W
2.7 GHz E5-2680
481
622
8C
115W
2.6 GHz E5-2670
473
592
8C
115W
2.4 GHz E5-2665
458
575
8C
95W
2.2 GHz E5-2660
524
681
33%, 27%
906
26%, 22%
855
22%, 20%
829
12C
130W
2.7GHz 30M E5-2697 v2
12C
115W
2.4GHz 30M E5-2695 v2
638
10C
3.0GHz
595
E5-2690 v2
10C
2.8GHz
E5-2680 v2
130W
24%, 22%
792
21%, 21%
743
10C
2.5GHz
E5-2670 v2
449
21%, 20%
693
10C
2.2GHz
E5-2660 v2
8C
95W
2.0 GHz E5-2650
428
23%, 15%
630
8C
2.6GHz
E5-2650 v2
447
6C
95W
2.5 GHz E5-2640
373
14%, 11%
495
8C
2.0GHz
E5-2640 v2
420
6C
95W
2.3 GHz E5-2630
355
12%, 13%
471
6C
2.6GHz
E5-2630 v2
382
6C
95W
2.0 GHz E5-2620
336
4%, 1%
396
6C
2.1GHz
E5-2620 v2
218
4C
80W
2.4 GHz E5-2609
220
8%, 6%
240
4C
2.5GHz
E5-2609 v2
169
4C
80W
1.8 GHz E5-2603
181
2%, 2%
172
4C
1.8GHz
E5-2603 v2
640
SPECint%, SPECfp%
Relative performance.
Source: Engineering estimates as of Jan’ 2013. Measurements from June 2013.
SPECint*_rate
_base2006
Estimates
115W
115W
95W
95W
95W
80W
80W
80W
80W
Measurements from C-step in black
Projections from C-step in red
613
SPECfp*_rate
_base2006
Estimates
563
540
517
492
403
401
339
234
184
All SKUs, pricing, frequencies and
features are PRELIMINARY and
can change without notice

similar documents