Specs HP AMD Opteron 2380 processor 2.5 GHz 6 MB L3 Processors (510457-001)
This is a demo of a seamless insert of an Icecat LIVE product data-sheet in your website. Imagine that this responsive data-sheet is included in the product page of your webshop. How to integrate Icecat LIVE JavaScript.
Embed the product datasheet into your content.
Icecat LIVE: JS for HP 510457-001
Icecat Live DOC
CSV product data for HP 510457-001
CSV DOC
Download images pack
Icecat Add-ons
Download the free Open Icecat data-sheets
Download Icecat taxonomy for »Processors»
Icecat PDF
Long product name HP AMD Opteron 2380 processor 2. 5 GHz 6 MB L3
:
The short editorial description of HP AMD Opteron 2380 processor 2.5 GHz 6 MB L3
2.5 GHz, 75 W, 6 MB L3, Socket F (1207)
More>>>
HP AMD Opteron 2380 processor 2.5 GHz 6 MB L3:
The official marketing text of HP AMD Opteron 2380 processor 2.5 GHz 6 MB L3 as supplied by the manufacturer
Power your cloud with AMD Opteron™ processors
When demanding workloads push the limits of your data center, push back with AMD Opteron 6300 series processors built to deliver the performance you need at the price you want.
— Low acquisition costs that help reduce overall TCO
— Scalable architecture ideal for cloud deployments
Short summary description HP AMD Opteron 2380 processor 2. 5 GHz 6 MB L3:
This short summary of the HP AMD Opteron 2380 processor 2.5 GHz 6 MB L3 data-sheet is auto-generated and uses the product title and the first six key specs.
HP AMD Opteron 2380, AMD Opteron, Socket F (1207), 45 nm, 2.5 GHz, 64-bit, Server/workstation
Long summary description HP AMD Opteron 2380 processor 2.5 GHz 6 MB L3:
This is an auto-generated long summary of HP AMD Opteron 2380 processor 2.5 GHz 6 MB L3 based on the first three specs of the first five spec groups.
HP AMD Opteron 2380. Processor family: AMD Opteron, Processor socket: Socket F (1207), Processor lithography: 45 nm. Market segment: Server
Embed the product datasheet into your content.
Icecat LIVE: JS for HP 510457-001
Icecat Live DOC
CSV product data for HP 510457-001
CSV DOC
Download images pack
Icecat Add-ons
Download the free Open Icecat data-sheets
Download Icecat taxonomy for »Processors»
Report mistake
Access to this product is restricted. Please contact your account manager at Icecat.
Specs
Processor
Processor
*
2380
Processor base frequency
*
2.5 GHz
Processor family
*
AMD Opteron
Processor number of cores
*
4
Processor socket
*
Socket F (1207)
Component for
Server/workstation
Processor lithography
*
45 nm
Processor threads
4
Processor operating modes
*
64-bit
Processor cache
6 MB
Processor
Processor cache type
L3
L2 cache speed
2. 5 GHz
Thermal Design Power (TDP)
75 W
Stepping
C2
Graphics
On-board graphics card
*
Features
Market segment
Server
Processor special features
AMD Virtualization Technology
500060-B21 HP 2.50GHz 6MB L3 Cache AMD Opteron 2380 Quad Core Processor for ProLiant DL165 G5 Server
-
Overview -
Warranty -
Shipping -
Q & A -
Reviews
500060-B21 HP 2.50GHz 6MB L3 Cache AMD Opteron 2380 Quad Core Processor for ProLiant DL165 G5 Server
Item Condition: Refurbished (for new please contact)
What does Refurbished mean?
Refurbished means that the item was sent back to the original
manufacturer, and it has been rechecked or reassembled and to provide cost-effective solution and to provide end-of-life products.
Reason to buy refurbished IT devices:
- Better quality
- Lower costs
- Extend the Life of your Current Technology
- A More Reliable Warranty
- A Greener Solution
- Save IT budget
Warranty may vary according to item condition.
Our usual warranty is:
- Refurbished 30 days
- New Open Box 90 days
- New Factory Sealed 1 year or standard manufacturer warranty
Our items undergo a series of rigorous tests! All used or refurbished products are examined by our fulfillment team to ensure that any cosmetic issues will not affect the performance of your order. Our warehouse technicians also perform diagnostic tests to make sure you get exactly what you ordered and that it functions properly. If you have any issues with your purchase, contact us and we’ll do our best to resolve them.
Our goal at JBS Devices is to provide customer service that is better than any other and to do this we must offer what you need. Our staff will help you with warranty questions if needed or assist you with information on purchasing aftermarket accessories, so please give us a call at +1 469-459-9688 or email us [email protected]
Read More…
Our list of shipping services with their corresponding cut-off time:
Ground | In the US ONLY, the transit time is between 3-7 business days, cut-off time stands at 1 PM Central Time. Depending on your location, Ground orders may be delivered by either UPS or USPS. |
UPS 3 Day | UPS orders take 3 business days in transit, however ONLY in the US. UPS 3 Day’s cut-off time is 1 PM Central Time. |
FedEx 2 Day | FedEx takes 2 business days in transit for orders placed ONLY in the US, and the cut-off time is 1 PM Central Time. |
Standard Overnight | Standard delivery service takes about 1 business day in transit for orders placed ONLY in the US. Cut-off time is 1 PM Central Time. Depending on the location, we may deliver the order by UPS Red Saver or FedEx Standard Overnight service. |
Priority Overnight | 1 business day transit time for orders placed in the US ONLY, with the cut-off time at 1 PM Central Time. Depending on the location, we may deliver by UPS Red or FedEx P1 Overnight service, guaranteeing the delivery by 10:30 AM on the same day. |
International Shipping | Cut-off time for all international orders is 1 PM Central Time. We ship international orders using FedEx International Economy method. |
APO/FPO | JBS Drives ships all APO/FPO orders using USPS Registered Mail. |
Puerto Rico/Canada | All orders delivered to Puerto Rico/Canada are shipped by the delivery system of FedEx’s International Economy, although their cut-off time is 1 PM Central Time |
Saturday Shipping | JBS Drives ships all APO/FPO orders using USPS Registered Mail. |
Countries we ship to | USA, Canada, Australia, New Zealand United Kingdom, Ireland, Germany, France, Sweden, UAE, Oman, Singapore, and China |
Read more https://jbsdevices.com/shipping
Order placed during the business hours usually process within 1-2 working days, but it also depends on the type of shipping you choose during checkout.
All the refurbished items got tested include a full cleaning and cosmetic evaluation by our certified technicians before shipping to the customer.
Yes, we ship internationally including Asia, Europe, South America and Australia. You can contact us if you need more details.
We have multiple warehouses all over the world including USA, UK, Canada, and some parts of Europe. We ship inventory from the closest location.
Yes, We Accept PO’s from SMEs, Fortune 500 Companies, Government Agencies, Universities, and Schools.
Refurbished means that the item was sent back to the original manufacturer, and it has been rechecked or reassembled and to provide cost effective solution and to provide end of life products.
Reason to buy refurbished IT devices:
- Better quality
- Lower costs
- Extend the Life of your Current Technology
- A More Reliable Warranty
- A Greener Solution
- Save IT budget
We have an inventory of 500,000+ SKUs and it’s not possible to keep all the data up to date on our website, you can contact us with all the details and we will try to correct information or procure required part for you.
Yes, but only if the order has not been processed already (check your order status). To change your order, you must get in touch with our Customer Service Department via chat or call +1 469-459-9688
If you still have question(s) please write us at [email protected] or call +1 469-459-9688
AMD Opteron 2210 (Dual-Core) (1.8G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2210 (Dual-Core) (1. 8G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2210HE (Dual-Core) (1.8G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2212 (Dual-Core) (2. 0G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2212 (Dual-Core) (2.0G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2212HE (Dual-Core) (2. 0G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2212HE (Dual-Core) (2.0G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2214 (Dual-Core) (2. 2G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2214 (Dual-Core) (2.2G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2214HE (Dual-Core) (2. 2G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2214HE (Dual-Core) (2.2G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2216 (Dual-Core) (2. 4G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2216 (Dual-Core) (2.4G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2216HE (Dual-Core) (2. 4G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2216HE (Dual-Core) (2.4G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2218 (Dual-Core) (2. 6G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2218 (Dual-Core) (2.6G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2218HE (Dual-Core) (2. 6G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2220 (Dual-Core) (2.8G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2220SE (Dual-Core) (2. 8G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 2220SE (Dual-Core) (2.8G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2222 (Dual-Core) (3. 0G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2222SE (Dual-Core) (3.0G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2224SE (Dual-Core) (3. 2G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 2344HE (Quad-Core) (1.7G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2346HE (Quad-Core) (1. 8G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2347HE (Quad-Core) (1.9G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2350 (Quad-Core) (2. 0G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2350HE (Quad-Core) (2.0G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2352 (Quad-Core) (2. 1G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2354 (Quad-Core) (2.2G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2356 (Quad-Core) (2. 3G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2358SE (Quad-Core) (2.4G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2360SE (Quad-Core) (2. 5G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 2372HE (Quad-Core) (2.1G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2373EE (Quad-Core) (2. 1G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2374HE (Quad-Core) (2.2G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2376 (Quad-Core) (2. 3G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2376HE (Quad-Core) (2.3G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2377EE (Quad-Core) (2. 3G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2378 (Quad-Core) (2.4G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2379HE (Quad-Core) (2. 4G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2380 (Quad-Core) (2.5G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2381HE (Quad-Core) (2. 5G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2382 (Quad-Core) (2.6G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2384 (Quad-Core) (2. 7G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2386SE (Quad-Core) (2.8G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2387 (Quad-Core) (2. 8G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2389 (Quad-Core) (2.9G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2393SE (Quad-Core) (3. 1G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 2423HE (Six-Core) (2.0G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 2425HE (Six-Core) (2. 1G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 2427 (Six-Core) (2.2G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 2431 (Six-Core) (2. 4G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 2435 (Six-Core) (2.6G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 2439SE (Six-Core) (2. 8G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 8212 (Dual-Core) (2.0G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 8212 (Dual-Core) (2. 0G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8212HE (Dual-Core) (2.0G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 8212HE (Dual-Core) (2. 0G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8214 (Dual-Core) (2.2G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 8214 (Dual-Core) (2. 2G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8214HE (Dual-Core) (2.2G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 8214HE (Dual-Core) (2. 2G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8216 (Dual-Core) (2.4G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 8216 (Dual-Core) (2. 4G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8216HE (Dual-Core) (2.4G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 8216HE (Dual-Core) (2. 4G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8218 (Dual-Core) (2.6G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 8218 (Dual-Core) (2. 6G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8218HE (Dual-Core) (2.6G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8220 (Dual-Core) (2. 8G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8220SE (Dual-Core) (2.8G) (F2) |
1.05G |
1109 GO |
|
AMD Opteron 8220SE (Dual-Core) (2. 8G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8222 (Dual-Core) (3.0G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8222SE (Dual-Core) (3. 0G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8224SE (Dual-Core) (3.2G) (F3) |
1.05G |
1109 GO |
|
AMD Opteron 8346HE (Quad-Core) (1. 8G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 8347HE (Quad-Core) (1.9G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 8350 (Quad-Core) (2. 0G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 8350HE (Quad-Core) (2.0G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 8354 (Quad-Core) (2. 2G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 8356 (Quad-Core) (2.3G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 8358SE (Quad-Core) (2. 4G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 8360SE (Quad-Core) (2.5G) (B3) |
1.05G |
1109 GO |
|
AMD Opteron 8374HE (Quad-Core) (2. 2G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8376HE (Quad-Core) (2.3G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8378 (Quad-Core) (2. 4G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8379HE (Quad-Core) (2.4G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8380 (Quad-Core) (2. 5G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8381HE (Quad-Core) (2.5G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8382 (Quad-Core) (2. 6G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8384 (Quad-Core) (2.7G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8386SE (Quad-Core) (2. 8G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8387 (Quad-Core) (2.8G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8389 (Quad-Core) (2. 9G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8393SE (Quad-Core) (3.1G) (C2) |
1.05G |
1109 GO |
|
AMD Opteron 8425HE (Six-Core) (2. 1G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 8431 (Six-Core) (2.4G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 8435 (Six-Core) (2. 6G) (D0) |
1.05G |
1109 GO |
|
AMD Opteron 8439SE (Six-Core) (2.8G) (D0) |
1.05G |
1109 GO |
|
Dell Inc.
PowerEdge R805 (AMD Opteron 2380, 2.50 GHz)
Copyright 2006-2014 Standard Performance Evaluation Corporation
Dell Inc.
PowerEdge R805 (AMD Opteron 2380, 2.50 GHz)
SPECfp®2006 =
21.6
SPECfp_base2006 =
17.6
CPU2006 license: | 55 | Test date: | Nov-2008 |
---|---|---|---|
Hardware Availability: | Nov-2008 | ||
Tested by: | Dell Inc. | Software Availability: | Oct-2008 |
Hardware | |
---|---|
CPU Name: | AMD Opteron 2380 |
CPU Characteristics: | |
CPU MHz: | 2500 |
FPU: | Integrated |
CPU(s) enabled: | 8 cores, 2 chips, 4 cores/chip |
CPU(s) orderable: | 2 chips |
Primary Cache: | 64 KB I + 64 KB D on chip per core |
Secondary Cache: | 512 KB I+D on chip per core |
L3 Cache: | 6 MB I+D on chip per chip |
Other Cache: | None |
Memory: | 32 GB (8 x 4 GB DDR2-800) |
Disk Subsystem: | 1 x 73 GB 10000 RPM SAS |
Other Hardware: | None |
Software | |
---|---|
Operating System: | SUSE Linux Enterprise Server 10 (x86_64) SP2, Kernel 2. 6.16.60-0.21-smp |
Compiler: | PGI Server Complete Version 7.2 PathScale Compiler Suite Version 3.2 |
Auto Parallel: | Yes |
File System: | ReiserFS |
System State: | Run level 3 (multi-user) |
Base Pointers: | 64-bit |
Peak Pointers: | 32/64-bit |
Other Software: | binutils 2.18 32-bit and 64-bit libhugetlbfs libraries |
Benchmark | Base | Peak | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | Seconds | Ratio | |
Results appear in the order in which they were run. Bold underlined text indicates a median measurement. | ||||||||||||
410.bwaves | 585 | 23.2 | 585 | 23.2 | 585 | 23.2 | 599 | 22.7 | 599 | 22.7 | 600 | 22.7 |
416.gamess | 1263 | 15.5 | 1262 | 15.5 | 1262 | 15.5 | 1138 | 17.2 | 1133 | 17.3 | 1132 | 17.3 |
433.milc | 492 | 18.6 | 493 | 18.6 | 492 | 18.7 | 492 | 18.6 | 493 | 18.6 | 492 | 18.7 |
434.zeusmp | 600 | 15.2 | 600 | 15.2 | 600 | 15.2 | 543 | 16. 8 | 543 | 16.8 | 544 | 16.7 |
435.gromacs | 504 | 14.2 | 504 | 14.2 | 504 | 14.2 | 411 | 17.4 | 411 | 17.4 | 410 | 17.4 |
436.cactusADM | 612 | 19.5 | 671 | 17.8 | 611 | 19.6 | 102 | 118 | 102 | 117 | 106 | 113 |
437.leslie3d | 545 | 17.2 | 546 | 17.2 | 546 | 17.2 | 515 | 18.3 | 515 | 18.2 | 515 | 18.2 |
444.namd | 667 | 12.0 | 666 | 12.0 | 666 | 12.0 | 575 | 14. 0 | 576 | 13.9 | 576 | 13.9 |
447.dealII | 587 | 19.5 | 587 | 19.5 | 590 | 19.4 | 439 | 26.1 | 439 | 26.0 | 439 | 26.0 |
450.soplex | 614 | 13.6 | 614 | 13.6 | 616 | 13.5 | 544 | 15.3 | 542 | 15.4 | 542 | 15.4 |
453.povray | 325 | 16.4 | 326 | 16.3 | 324 | 16.4 | 278 | 19.1 | 281 | 18.9 | 281 | 18.9 |
454.calculix | 491 | 16.8 | 492 | 16.8 | 491 | 16.8 | 412 | 20. 0 | 412 | 20.0 | 412 | 20.0 |
459.GemsFDTD | 640 | 16.6 | 638 | 16.6 | 639 | 16.6 | 569 | 18.6 | 569 | 18.6 | 570 | 18.6 |
465.tonto | 615 | 16.0 | 618 | 15.9 | 615 | 16.0 | 485 | 20.3 | 486 | 20.2 | 487 | 20.2 |
470.lbm | 481 | 28.6 | 480 | 28.6 | 481 | 28.6 | 539 | 25.5 | 538 | 25.5 | 539 | 25.5 |
481.wrf | 548 | 20.4 | 550 | 20.3 | 547 | 20.4 | 495 | 22. 6 | 495 | 22.5 | 495 | 22.6 |
482.sphinx3 | 1050 | 18.6 | 889 | 21.9 | 888 | 21.9 | 826 | 23.6 | 924 | 21.1 | 864 | 22.6 |
The config file option 'submit' was used. 'numactl' was used to bind copies to the cores
The libhugetlbfs libraries were installed using the installation rpms that came with the distribution. 'ulimit -s unlimited' was used to set environment stack size 'ulimit -l 2097152' was used to set environment locked pages in memory limit Set vm/nr_hugepages=7146 in /etc/sysctl.conf mount -t hugetlbfs nodev /mnt/hugepages
Environment variables set by runspec before the start of the run: HUGETLB_MORECORE = "yes" LD_LIBRARY_PATH = "/root/cpu2006-1.1/amd909gh-libs/64:/root/cpu2006-1.1/amd909gh-libs/32" NCPUS = "8"
C benchmarks:
pgcc |
C++ benchmarks:
pgcpp |
Fortran benchmarks:
pgf95 |
Benchmarks using both Fortran and C:
pgcc pgf95 |
410. bwaves: | -DSPEC_CPU_LP64 |
416.gamess: | -DSPEC_CPU_LP64 |
433.milc: | -DSPEC_CPU_LP64 |
434.zeusmp: | -DSPEC_CPU_LP64 |
435.gromacs: |
-DSPEC_CPU_LP64 -Mnomain |
436.cactusADM: |
-DSPEC_CPU_LP64 -Mnomain |
437.leslie3d: | -DSPEC_CPU_LP64 |
444.namd: | -DSPEC_CPU_LP64 |
447.dealII: | -DSPEC_CPU_LP64 |
450.soplex: | -DSPEC_CPU_LP64 |
453.povray: | -DSPEC_CPU_LP64 |
454.calculix: |
-DSPEC_CPU_LP64 -Mnomain |
459.GemsFDTD: | -DSPEC_CPU_LP64 |
465.tonto: | -DSPEC_CPU_LP64 |
470. lbm: | -DSPEC_CPU_LP64 |
481.wrf: |
-DSPEC_CPU_LP64 -DSPEC_CPU_CASE_FLAG -DSPEC_CPU_LINUX |
482.sphinx3: | -DSPEC_CPU_LP64 |
C benchmarks:
-Mvect=cachesize:6291456 -fastsse -Msmartalloc=huge -Mfprelaxed -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi |
C++ benchmarks:
-Mvect=cachesize:6291456 -fastsse -Msmartalloc=huge -Mfprelaxed —zc_eh -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi |
Fortran benchmarks:
-Mvect=cachesize:6291456 -fastsse -Mfprelaxed -Msmartalloc=huge -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi |
Benchmarks using both Fortran and C:
-Mvect=cachesize:6291456 -fastsse -Msmartalloc=huge -Mfprelaxed -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi |
C benchmarks:
-Mipa=jobs:4 |
C++ benchmarks:
-Mipa=jobs:4 |
Fortran benchmarks:
-Mipa=jobs:4 |
Benchmarks using both Fortran and C:
-Mipa=jobs:4 |
C benchmarks:
pgcc |
C++ benchmarks (except as noted below):
pathCC | |
444. namd: | pgcpp |
Fortran benchmarks (except as noted below):
pathf95 | |
410.bwaves: | pgf95 |
434.zeusmp: | pgf95 |
437.leslie3d: | pgf95 |
Benchmarks using both Fortran and C (except as noted below):
pgcc pgf95 |
|
435.gromacs: |
pathcc pathf95 |
481.wrf: |
pathcc pathf95 |
410.bwaves: | -DSPEC_CPU_LP64 |
416.gamess: | -DSPEC_CPU_LP64 |
433.milc: | -DSPEC_CPU_LP64 |
434.zeusmp: | -DSPEC_CPU_LP64 |
435.gromacs: | -DSPEC_CPU_LP64 |
436. cactusADM: |
-DSPEC_CPU_LP64 -Mnomain |
437.leslie3d: | -DSPEC_CPU_LP64 |
444.namd: | -DSPEC_CPU_LP64 |
453.povray: | -DSPEC_CPU_LP64 |
454.calculix: |
-DSPEC_CPU_LP64 -Mnomain |
459.GemsFDTD: | -DSPEC_CPU_LP64 |
465.tonto: | -DSPEC_CPU_LP64 |
470.lbm: | -DSPEC_CPU_LP64 |
481.wrf: |
-DSPEC_CPU_LP64 -DSPEC_CPU_LINUX -fno-second-underscore |
482.sphinx3: | -DSPEC_CPU_LP64 |
C benchmarks:
433.milc: | basepeak = yes |
470.lbm: |
-Mvect=cachesize:6291456 -fastsse -Msmartalloc=huge -Mprefetch=t0 -Mloop32 -Mfprelaxed -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi |
482. sphinx3: |
-Mpfi=indirect(pass 1) -Mpfo=indirect(pass 2) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mvect=cachesize:6291456 -fastsse -Mfprelaxed -Msmartalloc -tp barcelona-64 -Bstatic_pgi |
C++ benchmarks:
444.namd: |
-Mpfi(pass 1) -Mpfo(pass 2) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mvect=cachesize:6291456 -fastsse -Munroll=n:4 -Munroll=m:8 -Msmartalloc=huge -Mnodepchk -Mfprelaxed —zc_eh -tp barcelona-64 -Bstatic_pgi |
447.dealII: |
-march=barcelona -Ofast -static -INLINE:aggressive=on -fno-exceptions -m32 |
450.soplex: |
-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -L/usr/lib -lhugetlbfs(pass 2) -O3 -INLINE:aggressive=on -OPT:IEEE_arith=3 -OPT:IEEE_NaN_Inf=off -OPT:fold_unsigned_relops=on -OPT:malloc_alg=1 -CG:load_exe=0 -fno-exceptions -m32 |
453. povray: |
-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Ofast -INLINE:aggressive=on |
Fortran benchmarks:
410.bwaves: |
-Mvect=cachesize:6291456 -fastsse -Msmartalloc -Mprefetch=nta -Mfprelaxed -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi |
416.gamess: |
-march=barcelona -fb_create fbdata(pass 1) -fb_opt fbdata(pass 2) -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT(pass 2) -L/usr/lib64 -lhugetlbfs(pass 2) -O2 -OPT:Ofast -OPT:ro=3 -OPT:unroll_size=256 |
434.zeusmp: |
-Mvect=cachesize:6291456 -fastsse -Mfprelaxed -Mprefetch=distance:8 -Mprefetch=t0 -Msmartalloc=huge -Msmartalloc=hugebss -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi |
437. leslie3d: |
-Mpfi=indirect(pass 1) -Mpfo=indirect(pass 2) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mvect=cachesize:6291456 -fastsse -Mvect=fuse -Msmartalloc=huge -Mprefetch=distance:8 -Mprefetch=t0 -Mfprelaxed -tp barcelona-64 -Bstatic_pgi |
459.GemsFDTD: |
-march=barcelona -Ofast -LNO:fission=2 -LNO:simd=2 -LNO:prefetch_ahead=1 -CG:load_exe=0 -CG:prefer_lru_reg=off -OPT:malloc_alg=1 -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT -L/usr/lib64 -lhugetlbfs |
465.tonto: |
-march=barcelona -Ofast -OPT:alias=no_f90_pointer_alias -LNO:blocking=off -CG:load_exe=1 -IPA:plimit=525 -OPT:malloc_alg=1 -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT -L/usr/lib64 -lhugetlbfs |
Benchmarks using both Fortran and C:
435. gromacs: |
-march=barcelona -Ofast -OPT:rsqrt=2 -OPT:malloc_alg=1 -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64.xBDT -L/usr/lib64 -lhugetlbfs |
436.cactusADM: |
-Mvect=cachesize:6291456 -fastsse -Mconcur -Msmartalloc=huge -Mfprelaxed -Mipa=fast -Mipa=inline -tp barcelona-64 -Bstatic_pgi |
454.calculix: |
-Mpfi=indirect(pass 1) -Mpfo=indirect(pass 2) -Mipa=fast(pass 2) -Mipa=inline(pass 2) -Mvect=cachesize:6291456 -fastsse -Msmartalloc=huge -Mprefetch=t0 -Mpre -Mfprelaxed -tp barcelona-64 -Bstatic_pgi |
481.wrf: |
-march=barcelona -Ofast -LNO:blocking=off -LNO:prefetch_ahead=10 -LANG:copyinout=off -IPA:callee_limit=5000 -GRA:prioritize_by_density=on -OPT:malloc_alg=1 -m3dnow -Wl,-T/usr/share/libhugetlbfs/ldscripts/elf_x86_64. xBDT -L/usr/lib64 -lhugetlbfs |
C benchmarks:
-Mipa=jobs:4(pass 2) |
C++ benchmarks:
444.namd: | -Mipa=jobs:4(pass 2) |
Fortran benchmarks (except as noted below):
-Mipa=jobs:4(pass 2) | |
416.gamess: | No flags used |
459.GemsFDTD: | No flags used |
465.tonto: | No flags used |
Benchmarks using both Fortran and C (except as noted below):
-Mipa=jobs:4(pass 2) | |
435.gromacs: | No flags used |
481.wrf: | No flags used |
AMD’s ‘Shanghai’ 45nm Opterons — The Tech Report
AMD’s quad-core Opterons have certainly had a rough life to this point. The original “Barcelona” Opterons were hamstrung by delays, unable to meet clock frequency and performance expectations, and plagued by a show-stopper bug that forced AMD largely to stop shipments of the chips for months while waiting for a new revision, as we first reported. Once the revised Opterons made it into the market, they faced formidable competition from Intel’s 45nm “Harpertown” Xeons, whose best-in-class performance and much-improved power efficiency have stolen quite of a bit of the Opteron’s luster.
AMD is looking to reverse its fortunes with the introduction of a brand-new version of the quad-core Opteron, code-named Shanghai, which has been manufactured using a new, smaller 45-nanometer fabrication process that should bring gains in power efficiency and clock speeds. Shanghai also has the considerable benefit of being the second generation of a new processor design, and AMD has taken the opportunity to tweak this design in innumerable ways, large and small, in order to improve its performance and, one would hope, allow it more fully to meet its potential. The result is an Opteron processor with higher clock speeds, improved performance per clock, and lower power consumptiona better proposition in almost every way than Barcelona.
Will it be enough to make the Opteron truly competitive with Intel’s latest Xeons? We’ve been testing systems for the past couple of weeks in Damage Labs in order to find out.
The Opteron gets Shanghaied
In spite of the troubles “Barcelona” Opterons have faced, AMD got quite a bit right in designing themor so it would seem when peering down at the basic layout from high altitude. Barcelona was the first native quad-core x86-compatible processor, with four cores sharing a single piece of silicon. Each of those cores had its own 512KB L2 cache, and the four cores then shared a larger, on-chip 2MB L3 cache. Barcelona’s cores could also, of course, share data via this cache, making inter-core communication quick and relatively straightforward. In order to manage power consumption, Barcelona could modify the clock speed of each core independently in response to demand. In addition, the chip had dual power planes, one for the CPU cores and a second for the chip’s other elementsspecifically, its L3 cache, integrated memory controller, and HyperTransport links. Voltage to either plane could be reduced independently, again in response to activity. All of these provisions seemed to make Barcelona an ideal candidate for servers and workstations based on AMD’s Socket F infrastructure, which in itself was a strength, thanks to a topology based on high-speed, point-to-point interconnects and CPUs with integrated memory controllers.
Few will argue these basic concepts aren’t sound, especially now that Intel has adopted a very similar architecture for its Nehalem processors, which are already available on the desktop in the form of the staggeringly fast Core i7 and will be headed to servers in the first half of next year.
Shanghai retains Barcelona’s strengths and looks to better capitalize on them. To that end, AMD has outfitted Shanghai with a larger, 6MB L3 cache and a host of tweaks aimed at bringing higher performance per clock and increased power efficiency.
Like the city for which it’s named, Shanghai is about growth: it’s comprised of an estimated 758 million transistors, up from 463 million in Barcelona. Despite this growth, though, the smaller fabrication process means Shanghai has a smaller die area, at 258 mm², than Barcelona’s 283 mm².
AMD’s 45-nm fabrication process combines strained silicon and silicon-on-insulator techniques to achieve higher switching speeds at lower power levels, as did the past two generations of its fabrication technology. This time around, though, the firm has incorporated immersion lithography in order to reach smaller geometries. The use of a liquid medium between the lens and the wafer, as shown in the diagram on the right, offers improved focus and resolution versus the usual air gap in this space. AMD claims immersion lithography will be essential for the 32nm process node, even for Intel, and proudly notes that it has made the transition first.
Most of Shanghai’s additional transistors (versus Barcelona) come from its expanded L3 cache, whose performance benefits for many server-class workloads should be fairly obvious. A number of logic changes, many of them cache-related, consume fewer transistors but promise additional benefits. For example, along with the larger cache comes an enhanced data pre-fetch mechanism. This logic attempts to recognize data access patterns and speculatively loads likely-to-be-needed data into cache ahead of time. As caches grow, pre-fetch algorithms often become more aggressive. Shanghai can also probe the L1 and L2 caches in its cores for coherency information twice as often as Barcelona, which gives it double the probe bandwidth. This provision should be particularly helpful when a core has lowered its clock speed to conserve power while idle.
In order to make sure its larger caches don’t cause data integrity problems, AMD has built in a new feature it calls L3 Cache Index Disable. This feature allows the CPU to turn off parts of the L3 cache if too many machine-check errors occur. This capability will apparently require OS-level support, and that’s not here quite yet. AMD expects “select operating systems” to bring support for this feature next year.
By contrast, the somewhat confusingly named Smart Fetch should have immediate benefits. Despite the name, Smart Fetch is primarily a power-saving feature intended to work around the fact that AMD’s caches are exclusive in naturethat is, the lower-level caches don’t replicate the entire contents of the higher-level caches. Exclusive caches have the simple benefit of extending the total effective size of the cache hierarchyAMD justifiably bills Shanghai as having 8MB of cachebut they can present conflicts with dynamic power saving schemes. In Barcelona, for instance, a completely idle core would have to continue operating, though at a lower frequency, in order to keep its caches active and their contents available. Shanghai, by contrast, will dump the contents of that core’s L1 and L2 caches into the L3 cache and put the core entirely to sleep, essentially reducing its clock speed to zero. AMD claims this provision can reduce idle power draw by up to 21%. One core in the system must remain active at all times, but in a four-socket system, only a single core in one socket must keep ticking. Smart Fetch isn’t quite as impressive as the core-level power switching Intel built into Nehalem because it doesn’t eliminate leakage power, but it’s still a nice improvement over Barcelona.
One tweak in Shanghai that affects not just the cache but the entire memory hierarchy has to do with the chip’s support for nested page tables, a feature that accelerates memory address translation with system virtualization software. Shanghai maintains the same basic feature set as Barcelona here, but AMD claims a reduction in “world switch time” of up to 25% for Shanghai. That means the system should be able to transition from guest mode to hypervisor mode and then back to guest mode much more quickly. Since we’ve only had a couple of weeks following the release of the Core i7 to test Shanghai, we weren’t able to test this improvement ourselves, unfortunately. (Proper, publishable virtualization benchmarking is a non-trivial undertaking.) AMD says it tested the time required to make these two transitions (guest-to-hypervisor and hypervisor-to-guest) itself and measured a latency of 1360 cycles on Barcelona versus 900 cycles on Shanghai. Hypervisors that support the AMD-V feature set could thus see a marked improvement in performance in cases where virtual server performance is hampered by world-switch latency. Indeed, VMware has published some Shanghai performance numbers with VMware ESX 3.5 that show dramatic performance advantages over software-based shadow page tables.
Our 2P Opteron test system with 16GB of DDR2-800 memory
A couple of other changes ought to bring more general performance gains. Shanghai’s memory controller bumps up officially supported memory frequencies from 667MHz to 800MHz, for one. Also, HyperTransport 3 support is finally imminent. The first Shanghai processors don’t support it, mainly because AMD didn’t want to hold up these products’ introduction while waiting for full validation of HT3 solutions. Instead, the firm plans
to introduce HT3-ready Opterons next spring. When those arrive, they’ll double the available bandwidth for CPU-to-CPU communication in Opteron systems. With HyperTransport clock speeds up to 2.2GHz, HT3 will allow for up to 17.6 GB/s of bandwidth (the bidirectional total) per link. Only with the introduction of the Fiorano platform later in 2009 will the CPU-to-chipset interconnect transition to HT3.
Pricing and availability
Even with all of these chip-level changes, the biggest news of the day may be the advent of Opterons with higher clock speeds and lower prices. The refreshed Shanghai lineup now looks like so:
Model | Clock speed | North bridge
speed |
ACP | Price |
Opteron 2384 | 2. 7GHz | 2.2GHz | 75W | $989 |
Opteron 2382 | 2.6GHz | 2.2GHz | 75W | $873 |
Opteron 2380 | 2.5GHz | 2.0GHz | 75W | $698 |
Opteron 2378 | 2.4GHz | 2.0GHz | 75W | $523 |
Opteron 2376 | 2. 3GHz | 2.0GHz | 75W | $377 |
Opteron 8384 | 2.7GHz | 2.2GHz | 75W | $2,149 |
Opteron 8382 | 2.6GHz | 2.2GHz | 75W | $1,865 |
Opteron 8380 | 2.5GHz | 2.0GHz | 75W | $1,514 |
Opteron 8378 | 2. 4GHz | 2.0GHz | 75W | $1,165 |
All of the new Opterons, ranging from 2.3 to 2.7GHz, fit into the same 75W thermal envelope, according to AMD’s “ACP” rating method (which it insists is the best analog to Intel’s TDP numbers, though Intel would disagree.) Clock speeds overall are up, and notably, north bridge clocks participate in that advance. I say that’s notable because the north bridge clock governs the L3 cache, as well, which has a pretty direct impact on overall Opteron performance.
AMD expects all of the products above to be available now. Conspicuous by their absence are low-power HE and higher-speed SE derivatives of Shanghai. AMD intends for these HE and SE parts to fit into their traditional 55W and 105W thermal envelopes, respectively, when they arrive in the first quarter of next year. With the additional power headroom, the SE parts could quite possibly reach 3GHz, although only time will tell.
The Opteron’s next steps
The improvements in Shanghai sound pretty good, but many folks are still asking exactly what AMD will do in order to counter Intel’s Nehalem, which promises a similar system architecture andby all current indications, at leasthigher performance per core and per socket. Interestingly enough, AMD does have some credible answers to such questions, and it has disclosed quite a bit of its future Opteron roadmap in response. Here’s a quick overview of the basic plan:
AMD’s Opteron roadmap into 2011. Source: AMD.
Not noted above is the planned release of HyperTransport 3-enabled Opterons next spring. After that, the next big change will be the introduction of the Fiorano platform in mid-2009. Fiorano will be the first Opteron chipset based on the core-logic technology AMD acquired when it purchased ATI. That chipset will be comprised of the SR5690 I/O hub and the SP5100 south bridge. Fiorano will retain compatibility with Socket F-type CPUs, but will add several noteworthy enhancements, including full HyperTransport 3 and (at last) PCI Express 2. 0, complete with support for device hot-plugging. As one would expect, Fiorano will support AMD’s IOMMU technology for fast and secure hardware-assisted virtualization of I/O devices.
A simple block diagram of the Fiorano platform. Source: AMD.
Fiorano will be scalable from 2P to 4P and 8P systems. As you can see in the diagram above, 4P Opteron systems will not be fully connectedthere will still be two “hops” from one corner of a 4P system to the opposing corner. Also notable by its absence is support for DDR3 memory. Although the desktop Phenom II is expected to make the move to DDR3 in early 2009, the Opteron won’t follow until it makes a socket transition in 2010.
Before that happens, some time in late 2009, the Opteron lineup will get a boost with the release of a six-core processor code-named Istanbul. This 45-nm chip should look very much like Shanghai, but with two additional cores onboardsame 6MB L3 cache, same DDR2 memory controller, still HyperTransport 3. For certain applications, a six-core Opteron could conceivably be a nice alternative to Intel’s quad-core, eight-thread Nehalem-based Xeons, although by the time Istanbul arrives, Intel may be reaching new milestones in its own roadmap.
Istanbul looks like Shanghai plus two cores. Source: AMD.
Then comes the transition to the new G34 socketthe funky elongated, rectangular socket you may have seen in some reportsin 2010. This socket will bring a major infrastructure refresh for the Opteron. DDR3 support will come in with a bang; each socket is expected to support four channels of DDR3 memory. Also, the maximum number of HyperTransport 3 links per chip will rise from three to four, potentially enabling fully connected 4P systems.
Interestingly enough, all of the changes here will apparently be the result of modifications to the physical socket and to Opteron processors. Although AMD has given the new platform a code name, Maranello, it uses the same two core-logic chips as Fiorano.
The new processors will come in two distinct flavors: Sao Paulo, with six cores and 6MB of L3 cache, and the oh-so-cleverly named Magny-Cours, with a whopping 12 cores and 12MB of L3 cache. We don’t yet know whether or how these cores will be enhanced compared to Shanghai Opterons. Both chips will be manufactured with 45nm process tech, and the basic cache hierarchy on the Opteron will remain the same, with an exclusive L3. AMD will add additional smarts to these chips, though, in the form of a probe filter (or snoop filter) that will reduce cache coherency management traffic. Also, much like Nehalem, these processors will feature on-chip power management and thermal control capabilities, including the ability to raise and lower clock speeds based on thermal control points.
Beyond that, things become foggy. We know that AMD’s spun-off manufacturing arm, temporarily dubbed “the foundry company,” has plans to introduce two advanced 32-nm fabrication technologies in the first half of 2010, a high-performance process using SOI and a low-power process using high-k metal gates. Meanwhile, AMD is working on a next-generation CPU microarchitecture code-named “Bulldozer,” about which we know very little. Early information on Bulldozer suggested it would initially tape out on a 45nm process, but more recent rumblings from AMD suggest Bulldozer has been pushed backthe desktop variant to 2011and may be a 32nm part.
Sizing up the Xeons and Opterons in our test
Intel, of course, hasn’t been sitting still since we last looked at its server/workstation-class processors. The firm is now shipping a new E stepping of its 45nm Xeons that reduces power draw and allows for slightly higher clock frequencies. All of the Xeons we tested for this review are based on E-stepping silicon. We had intended to review these Xeons in a separate article but weren’t able to complete it before this one, so we have a range of new-to-us products to test, based on multiple different Intel server- and workstation-class platforms.
The most direct competition for the Shanghai Opterons we’ve tested is the Xeon E5450, a 3GHz quad-core part with a 1333MHz front-side bus. We’ve tested the E5450 on Intel’s highest-volume server platform, known as Bensley. This platform, based on the Intel 5000P chipset, is getting a little long in the tooth and lacks a few features, like support for a 1600MHz FSB, 800MHz FB-DIMMs, and a full-coverage snoop filter. However, it is still the predominant Xeon server platform, and is thus the best basis of comparison versus the Opteron systems we’re testing. The Xeon E5450 is priced at $915 in volume, quite close to the $989 price tag of the Shanghai Opteron 2384. The two chips also share similar thermal envelopes; the Xeon E5450 is rated at an 80W TDP and the Opteron 2384 has a 75W ACP. (Assuming you buy AMD’s arguments about its ACP ratings, at least, the two should be similar. We will test power consumption ourselves, regardless.)
We have also, of course, included AMD’s best 65nm Opteron within this same thermal envelope, the 2356, to see how it compares to Shanghai.
Intel’s 45nm Xeons extend into higher-performance and lower-power territory in some interesting ways, as well. The low-voltage Xeon L5430, for instance, has specs very similar to the E5450quad cores, 2.66GHz core clock, 1333MHz bus, 12MB total L2 cachebut comes with a TDP rating of just 50W. For our testing, we’ve mated it with a very intriguing low-power server platform from Intel, known as San Clemente.
This is our first look at San Clemente, which Intel hasn’t pushed especially hard in the mainstream server or workstation spaces. Instead, Intel has aimed it primarily at dense blade servers and embedded systems like routers, SANs, and NAS boxes. That’s kind of a shame, since the Intel 5100 MCH at the heart of San Clemente makes a key power-saving move, shunning Fully Buffered DIMMs for registered DDR2 memory modules just like Opterons use. FB-DIMMs allow for higher total system memory capacities, but they exact notable penalties in terms of both memory access latencies and power consumption. San Clemente’s power consumption could be quite a bit lower than Bensley’s, as could its memory access latencies. Like Bensley, San Clemente has dual, independent front-side bus connections to each socket in a 2P system, as well.
The tradeoffs are several. The 5100 MCH is limited to a maximum of six DIMMs per system and 48GB of total memory, versus 16 FB-DIMMs and 64GB total memory for Bensley. Also, the 5100 MCH’s two channels of DDR2-667 memory yield a peak of 10.6 GB/s of bandwidth, compared to Bensley’s 21 GB/s max.
The guts of our San Clemente test rig, fully populated with six DIMMs
Our San Clemente test system underscored its memory capacity limitations by proving to be incompatible with our 2GB DDR2 DIMMs, for whatever reason. We were limited to testing with only 6GB of total memory by populating each of its DIMM slots with 1GB modules.
Since AMD’s 45nm Opteron HE products aren’t out yet, the closest competition we have to the Xeon L5430/San Clemente combo is the Opteron 2347 HE, a 65nm part with a 55W ACP (68W TDP), a 1.9GHz core clock, and a 1. 6GHz north bridge/L3 cache. That’s a rough comparison for AMD, but things should change once the 45nm Opteron HE parts arrive next quarter.
At the other end of the spectrum entirely is the Xeon X5492, an ultra-high-end processor (nearly $1,500 list) that tests the outer limits of Intel’s 45nm process tech with a 3.4GHz core clock, a 1600MHz FSB, and a 150W TDP rating. We’ve tested a pair of these babies on the Stoakley platform. Stoakley is essentially an updated version of the Bensley platform with higher bandwidth, but it’s been targeted largely at workstations and HPC systems.
There really is no Opteron analog to the Xeon X5492. The closest comparison might be to the 65nm Opteron 2360 SE, which has a 105W ACP (and 119W TDP), but Shanghai has higher clock frequencies and a larger cache in a much smaller power budget, so the 2360 SE is essentially obsolete. Again, we may have to wait for the introduction of 45nm Opteron SE models before we have a truly comparable product from AMDand even then, AMD may choose not to produce an Opteron with a 150W thermal envelope.
Our testing methods
As ever, we did our best to deliver clean benchmark numbers. Tests were run at least three times, and the results were averaged.
Our test systems were configured like so:
Processors | Dual Xeon E5450 3.0GHz | Dual Xeon X5492 3.4GHz | Dual Xeon L5430 2.66GHz |
Dual Opteron 2347 HE 1.9GHz Dual |
Dual Opteron 2384 2.7GHz |
System bus |
1333MHz (333MHz quad-pumped) | 1600MHz (400MHz quad-pumped) | 1333MHz (333MHz quad-pumped) | 1GHz HyperTransport |
1GHz HyperTransport |
Motherboard | SuperMicro X7DB8+ |
SuperMicro X7DWA |
Asus RS160-E5 |
SuperMicro H8DMU+ |
SuperMicro H8DMU+ |
BIOS revision |
6/23/2008 | 8/04/2008 | 8/08/2008 | 3/25/08 | 10/15/08 |
North bridge |
Intel 5000P MCH |
Intel 5400 MCH |
Intel 5100 MCH |
Nvidia nForce Pro 3600 |
Nvidia nForce Pro 3600 |
South bridge |
Intel 6321 ESB ICH |
Intel 6321 ESB ICH |
Intel ICH9R |
Nvidia nForce Pro 3600 |
Nvidia nForce Pro 3600 |
Chipset drivers |
INF Update 9. 0.0.1008 |
INF Update 9.0.0.1008 |
INF Update 9.0.0.1008 |
– | – |
Memory size |
16GB (8 DIMMs) |
16GB (8 DIMMs) |
6GB (6 DIMMs) | 16GB (8 DIMMs) |
16GB (8 DIMMs) |
Memory type |
2048MB DDR2-800 FB-DIMMs |
2048MB DDR2-800 FB-DIMMs |
1024MB registered ECC DDR2-667 DIMMs |
2048MB registered ECC DDR2-800 DIMMs |
2048MB registered ECC DDR2-800 DIMMs |
Memory speed (Effective) |
667MHz | 800MHz | 667MHz | 667MHz | 800MHz |
CAS latency (CL) |
5 | 5 | 5 | 5 | 6 |
RAS to CAS delay (tRCD) |
5 | 5 | 5 | 5 | 5 |
RAS precharge (tRP) |
5 | 5 | 5 | 5 | 5 |
Storage controller |
Intel 6321 ESB ICH with Matrix Storage Manager 8. 6 |
Intel 6321 ESB ICH with Matrix Storage Manager 8.6 |
Intel ICH9R with
Matrix Storage Manager 8.6 |
Nvidia nForce Pro 3600 |
LSI Logic Embedded MegaRAID with 8.9.518.2007 drivers |
Power supply |
Ablecom PWS-702A-1R 700W |
Ablecom PWS-702A-1R 700W |
FSP Group FSP460-701UG 460W |
Ablecom PWS-702A-1R 700W |
Ablecom PWS-702A-1R 700W |
Graphics |
Integrated ATI ES1000 with 8.240.50.3000 drivers |
Integrated ATI ES1000 with 8. 240.50.3000 drivers |
Integrated XGI Volari Z9s with 1.09.10_ASUS drivers |
Integrated ATI ES1000 with 8.240.50.3000 drivers |
Integrated ATI ES1000 with 8.240.50.3000 drivers |
Hard drive |
WD Caviar WD1600YD 160GB |
||||
OS | Windows Server 2008 Enterprise x64 Edition with Service Pack 1 |
We used the following versions of our test applications:
- SPECjbb 2005 1.07 with Oracle JRockIt JRE R27.6 Windows 64-bit
- SiSoft Sandra 2009.1.15.42
- CPU-Z 1.48
- Valve VRAD map build benchmark
- Cinebench R10 64-bit Edition
- POV-Ray for Windows 3.7 beta 29 64-bit
- CASE Lab Euler3d CFD benchmark multithreaded edition
- MyriMatch proteomics benchmark
- notfred’s Folding benchmark CD 9/28/08 revision
- x264 HD benchmark 2. 0 with x264 version 0.59.819
- TR XML benchmark
The tests and methods we employ are usually publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.
Memory subsystem performance
This test shows us a nice visual picture of the memory bandwidth available at the different levels of the memory hierarchy. One can see the impact of the Opteron 2384’s larger L3 cache at the 16MB test block size, where it’s much faster than the older quad-core Opterons. Still, the Xeons’ caches typically achieve quite a bit higher throughput than the Opterons’.
Our graph is tough to read at the largest test block sizes where main memory comes into play. Here’s a closer look at the 256MB block size, which should be a good indicator of main memory bandwidth.
These results are consistent with what we’ve seen in the past from most of these platforms. I believe these results only show the bandwidth available to a single CPU core, so they’re substantially less than the peak available in the entire system. The Opterons appear to benefit greatly from their integrated memory controllers here, and the Shanghai Opteron 2384 takes advantage of its faster 800MHz memory, as well.
The Opteron 2384’s revamped cache and TLB hierarchy, along with faster memory, delivers major reductions in memory access latency. With the 65nm Barcelona Opterons, we’ve found that the L3 cache tends to contribute quite a bit of latency to the overall picture. Yet with three times the L3 cache of the Opteron 2356, the 2384 is still faster to main memory. Let’s have a closer look at the cache picture and see why that is.
Before we do, though, we should also point out that the Xeon L5430 on the San Clemente platform has much lower access latencies than the E5450 on the Bensley platform, although they share the same bus frequency and topology. Assuming there aren’t any other major contributing factors, FB-DIMMs would appear to add about 14ns of delay versus DDR2 modules at the same 667MHz clock speed. The Stoakley platform essentially makes up that deficit by using higher bus and memory frequencies.
Note that, below, I’ve color-coded the block sizes that roughly correspond to the different caches on each of the processors. L1 data cache is yellow, L2 is light orange, L3’s darker orange, and main memory is brown.
These graphs offer a good visual representation of the data, but perhaps some numbers would illuminate things further. Because the Opteron’s L3 cache is clocked independently from the CPU cores, it doesn’t make sense to quantify that cache’s latency in terms of CPU clock cycles. In this case, the Opteron 2356’s L3 cache runs at 2GHz, while the 2384’s runs at 2.2GHza 10% increase. Despite the fact that the 2384’s L3 cache is three times the size, though, its latencies are considerably lower. At the 2048KB block size and step size of 256, the 2356’s latency is 23ns, while the 2384’s is only 16nsa reduction of nearly a third.
SPECjbb 2005
SPECjbb 2005 simulates the role a server would play executing the “business logic” in the middle of a three-tier system with clients at the front-end and a database server at the back-end. The logic executed by the test is written in Java and runs in a JVM. This benchmark tests scaling with one to many threads, although its main score is largely a measure of peak throughput.
As you may know, system vendors spend tremendous effort attempting to achieve peak scores in benchmarks like this one, which they then publish via SPEC. We did not intend to challenge the best published scores with our results, but we did hope to achieve reasonably optimal tuning for our test systems. To that end, we used a fast JVMthe 64-bit version of Oracle’s JRockIt JRE R27.6and picked up some tweaks for tuning from recently published results. We used two JVM instances with the following command line options:
start /AFFINITY [0F, F0] java -Xms3700m -Xmx3700m -XXaggressive -XXlazyunlocking -Xlargepages:exitOnFailure=true -Xgc:genpar -XXgcthreads=4 -Xns3200m -XXcallprofiling -XXtlasize:min=4k,preferred=512k -XXthroughputcompaction
Notice that we used the Windows “start” command to affinitize our threads on a per-socket basis. We also tried affinitizing on a per-chip basis for the Xeon systems, but didn’t see any performance benefit from doing so. The one exception to the command line options above was our Xeon L5430/San Clemente system. Since it had only 6GB of memory, we had to back the heap size down to 2200MB for it.
The Opteron 2384’s performance here is undeniably impressivea massive leap from the performance of the Opteron 2356, and substantially higher than its most direct competitor, the Xeon E5450. In fact, at just 2.7GHz, the Shanghai Opteron performs nearly as well as the exotic of the group, the 3.4GHz Xeon X5492, remarkably enough. Shanghai’s larger L3 cache and other tweaks, combined with the Opteron’s native quad-core design and strong system architecture, yield big returns in this server-class workload.
Not only that, but Oracle has hinted to us that even higher performance is possible when using a version of JRockIt optimized for Shanghai. That version of JRockIt hasn’t yet been released, but we understand it’s on the way.
Before we move on, let’s take a quick look at power consumption during this test. SPECjbb 2005 is the basis for SPEC’s own power benchmark, which we had initially hoped to use in this review, but time constraints made that impractical. Nevertheless, we did capture power consumption for each system during a test run using our Extech 380803 power meter. All of the systems used the same model of Ablecom 700W power supply unit, with the exception of the Xeon L5430 server, which used an FPS Group 460W unit. Power management features (such as SpeedStep and Cool’n’Quiet) were enabled via Windows Server’s “Balanced” power policy.
Although it has the same 75W ACP rating as the Opteron 2356, the Opteron 2384 draws substantially less power at every step of the way. The Xeon E5450 system is practically a power hog by comparison, with much higher peak power draw. The bright spot for Intel here is the Xeon L5430/San Clemente system with DDR2 memory, whose power consumption is admirably lowalmost 60W less than the Opteron 2384 system.
Have a look at what happens when we consider performance per watt.
Our Opteron 2384 system combines higher performance with lower power draw than the Xeon E5450 system, so its “bops per watt” lead is predictably large. Shanghai certainly looks good in this light.
Meanwhile, the Xeon L5430 aims to steal the limelight. It’s a bit of a wild card, with less total memory, only six DIMMs to eight for the other systems, and a much lower wattage PSU (which may be more efficient at these load levels). Still, one can’t deny the efficiency of its 50W quad-core Xeonsand one can’t help but wonder whether Intel made the right call in choosing FB-DIMMs for its mainstream server platform just as performance per watt was becoming perhaps the key metric for server evaluations.
Cinebench rendering
We can take a closer look at power consumption and energy-efficient performance by using a test whose time to completion varies with performance. In this case, we’re using Cinebench, a 3D rendering benchmark based on Maxon’s Cinema 4D rendering engine.
This is a very different sort of application, in which the Shanghai Opterons’ larger cache and faster memory don’t bring the sort of performance gains we saw in SPECjbb. Here, the Xeon E5450 is faster. In fact, the Xeons are faster clock for clockthe Xeon L5430 at 2.66GHz outperforms the Opteron 2384 at 2.7GHz.
As we did with SPECjbb, we measured power draw at the wall socket for each of our test systems across a set time period, during which we ran Cinebench’s multithreaded rendering test.
Some of the outcomes are obvious immediately, like the fact that the Xeon E5450 and X5492 systems have much higher overall power draw. Still, we can quantify these things with more precision. We’ll start with a look at idle power, taken from the trailing edge of our test period, after all CPUs have completed the render.
The Opteron 2384 system’s idle power draw is just over 10W less than that of the system based on its 65nm predecessor, the 2356, in spite of the fact that its L3 cache is larger and runs at a higher clock speed. Shanghai’s ability to flush its L1 and L2 caches into the L3 and shut down its cores does appear to pay dividends. Even so, those incremental gains seem small in light of the considerably higher idle power draw of the FB-DIMM-equipped Xeon systems.
Meanwhile, the low-voltage Xeons and San Clemente continue to impress.
Next, we can look at peak power draw by taking an average from the ten-second span from 15 to 25 seconds into our test period, during which the processors were rendering.
Peak power draw with Cinebench isn’t quite as high as it is with SPECjbb, but the trends remain the same. The Shanghai Opterons draw less power, at a higher clock speed, than their 65nm counterparts.
Another way to gauge power efficiency is to look at total energy use over our time span. This method takes into account power use both during the render and during the idle time. We can express the result in terms of watt-seconds, also known as joules.
We can quantify efficiency even better by considering specifically the amount of energy used to render the scene. Since the different systems completed the render at different speeds, we’ve isolated the render period for each system. We’ve then computed the amount of energy used by each system to render the scene. This method should account for both power use and, to some degree, performance, because shorter render times may lead to less energy consumption.
Even though the Opteron 2384 isn’t as fast as the Xeon E5450 in this application, the Opteron system still requires less energy to render the scene than the Xeon E5450-based one. The Opteron 2356 isn’t nearly as efficient as either, but the Shanghai Opterons more than restore AMD’s competitiveness in power-efficient performance.
With that said, the biggest winner here, obviously, is the Xeon L5430 system, which is simply in a class by itself.
XML handling
We are working, bit by bit, to add additional pieces to our server/workstation CPU benchmark suite over time. As part of that effort, our web developer and sysadmin, Stephen Roylance, has put together an XML handling benchmark for us. He based some elements of this test on parts of the open-source XML Benchmark project, but Steve ported everything to Microsoft’s C# language and .NET runtime environment. Here’s how he describes the program:
The program runs four different XML related tests for a configurable number of cycles, across a configurable number of threads.
The four operations are:
- Read a test XML file and parse it.
- Generate a randomized XML tree and write it into memory as a document.
- Transform an XML tree with XSLT, writing the resulting document into memory.
- Attach a cryptographic signature to a parsed XML tree, write it back to memory as an XML document in a string, parse it and verify the signature.
In contrast to SPECjbb, this test is written in C# and runs under Microsoft’s .NET common language runtime. It should be a reasonable simulation of real-world CPU workloads on servers running ASP.NET web applications.
The results you see below show the total time required to execute 100 iterations of an interleaved mix of the four thread types across eight concurrent threads. We tested using the benchmark’s “medium” file size option, so the data files involved were around 256KB in size.
Curiously enough, the Opteron 2384 is no faster than the 2356 here. This data point, plus a couple of others, points to a possible cause. The Opterons struggle versus the Xeons overall, which suggests that the NUMA memory subsystem of the Opteron systems may be causing problems. In other words, we may have threads ping-ponging between cores on different sockets, forcing them to access memory associated with the non-local CPU socket, draining performance. Also, notice how much quicker the Xeon L5430 is in this test than the E5450. That fact heightens my suspicion that this test is particularly sensitive to memory access latencies. In SPECjbb, where the Shanghai Opterons were much more effective, we explicitly affinitized threads with CPU sockets.
Of course, performance bottlenecks like this one are a day-to-day reality of living with the Opteron’s NUMA architecture, and many off-the-shelf applications aren’t NUMA-aware. This issue will probably get quite a bit more attention soon, since Intel will be making the move to a very similar NUMA arrangement with 2P Nehalem systems.
Our next steps in the development of this benchmark will have to include affinitizing threads with sockets, if at all possible. Also, we’d like to report execution times for individual thread types, and I believe Steve plans to write up a blog post about this benchmark and release the source code. If any of our readers have suggestions for improvement, he’ll be taking them at that time.
MyriMatch proteomics
Our benchmarks sometimes come from unexpected places, and such is the case with this one. David Tabb is a friend of mine from high school and a long-time TR reader. He has provided us with an intriguing new benchmark based on an application he’s developed for use in his research work. The application is called MyriMatch, and it’s intended for use in proteomics, or the large-scale study of proteins. I’ll stop right here and let him explain what MyriMatch does:
In shotgun proteomics, researchers digest complex mixtures of proteins into peptides, separate them by liquid chromatography, and analyze them by tandem mass spectrometers. This creates data sets containing tens of thousands of spectra that can be identified to peptide sequences drawn from the known genomes for most lab organisms. The first software for this purpose was Sequest, created by John Yates and Jimmy Eng at the University of Washington. Recently, David Tabb and Matthew Chambers at Vanderbilt University developed MyriMatch, an algorithm that can exploit multiple cores and multiple computers for this matching. Source code and binaries of MyriMatch are publicly available.
In this test, 5555 tandem mass spectra from a Thermo LTQ mass spectrometer are identified to peptides generated from the 6714 proteins of S. cerevisiae (baker’s yeast). The data set was provided by Andy Link at Vanderbilt University. The FASTA protein sequence database was provided by the Saccharomyces Genome Database.MyriMatch uses threading to accelerate the handling of protein sequences. The database (read into memory) is separated into a number of jobs, typically the number of threads multiplied by 10. If four threads are used in the above database, for example, each job consists of 168 protein sequences (1/40th of the database). When a thread finishes handling all proteins in the current job, it accepts another job from the queue. This technique is intended to minimize synchronization overhead between threads and minimize CPU idle time.
The most important news for us is that MyriMatch is a widely multithreaded real-world application that we can use with a relevant data set. MyriMatch also offers control over the number of threads used, so we’ve tested with one to eight threads.
I should mention that performance scaling in MyriMatch tends to be limited by several factors, including memory bandwidth, as David explains:
Inefficiencies in scaling occur from a variety of sources. First, each thread is comparing to a common collection of tandem mass spectra in memory. Although most peptides will be compared to different spectra within the collection, sometimes multiple threads attempt to compare to the same spectra simultaneously, necessitating a mutex mechanism for each spectrum. Second, the number of spectra in memory far exceeds the capacity of processor caches, and so the memory controller gets a fair workout during execution.
Here’s how the processors performed.
The Opteron 2384 finishes ahead of the Xeon E5450, with a best time two seconds faster than the Xeon. What’s more interesting is how it gets there: the Xeon is faster at every thread count from one to six, but the Opteron scales better when taking that last step to an optimal thread count, likely thanks to its native quad-core layout and integrated memory controller.
Another intriguing development is the fact that the Xeon L5430/San Clemente system is nearly as fast as the Xeon E5450 on the Bensley platformfaster at low thread counts, in factin spite of the L5430’s clock speed deficit.
And, well, there’s a storm brewing on the horizon. A single-socket desktop version of Nehalem, the Core i7-965 Extreme, completed this same test in only 60 seconds, 10 seconds ahead of even our dual-socket Xeon X5492 system. Granted, that’s with a different OS with possible kernel tuning advantages and exotic 1600MHz RAM, but one can’t help but wonder how a dual-socket Nehalem system might perform.
STARS Euler3d computational fluid dynamics
Charles O’Neill works in the Computational Aeroservoelasticity Laboratory at Oklahoma State University, and he contacted us to suggest we try the computational fluid dynamics (CFD) benchmark based on the STARS Euler3D structural analysis routines developed at CASELab. This benchmark has been available to the public for some time in single-threaded form, but Charles was kind enough to put together a multithreaded version of the benchmark for us with a larger data set. He has also put a web page online with a downloadable version of the multithreaded benchmark, a description, and some results here.
In this test, the application is basically doing analysis of airflow over an aircraft wing. I will step out of the way and let Charles explain the rest:
The benchmark testcase is the AGARD 445.6 aeroelastic test wing. The wing uses a NACA 65A004 airfoil section and has a panel aspect ratio of 1.65, taper ratio of 0.66, and a quarter-chord sweep angle of 45º. This AGARD wing was tested at the NASA Langley Research Center in the 16-foot Transonic Dynamics Tunnel and is a standard aeroelastic test case used for validation of unsteady, compressible CFD codes.
The CFD grid contains 1.23 million tetrahedral elements and 223 thousand nodes . . . . The benchmark executable advances the Mach 0.50 AGARD flow solution. A benchmark score is reported as a CFD cycle frequency in Hertz.
So the higher the score, the faster the computer. Charles tells me these CFD solvers are very floating-point intensive, but oftentimes limited primarily by memory bandwidth. He has modified the benchmark for us in order to enable control over the number of threads used. Here’s how our contenders handled the test with different thread counts.
The Opteron 2384 can’t quite catch the Xeons here, but consider the match-up against the Xeon L5430. The L5430 reaches a much higher frequency with a single thread, but its advantage gradually erodes as the number of threads climbs. At eight threads, the L5430 is only ahead by a fraction.
For comparison’s sake, by the way, the single-socket Core i7-965 Extreme broke the 5Hz barrier on this testagain, well ahead of our Xeon X5492 system.
[email protected]
Next, we have a slick little [email protected] benchmark CD created by notfred, one of the members of Team TR, our excellent Folding team. For the unfamiliar, [email protected] is a distributed computing project created by folks at Stanford University that investigates how proteins work in the human body, in an attempt to better understand diseases like Parkinson’s, Alzheimer’s, and cystic fibrosis. It’s a great way to use your PC’s spare CPU cycles to help advance medical research. I’d encourage you to visit our distributed computing forum and consider joining our team if you haven’t already joined one.
The [email protected] project uses a number of highly optimized routines to process different types of work units from Stanford’s research projects. The Gromacs core, for instance, uses SSE on Intel processors, 3DNow! on AMD processors, and Altivec on PowerPCs. Overall, [email protected] should be a great example of real-world scientific computing.
notfred’s Folding Benchmark CD tests the most common work unit types and estimates performance in terms of the points per day that a CPU could earn for a Folding team member. The CD itself is a bootable ISO. The CD boots into Linux, detects the system’s processors and Ethernet adapters, picks up an IP address, and downloads the latest versions of the Folding execution cores from Stanford. It then processes a sample work unit of each type.
On a system with two CPU cores, for instance, the CD spins off a Tinker WU on core 1 and an Amber WU on core 2. When either of those WUs are finished, the benchmark moves on to additional WU types, always keeping both cores occupied with some sort of calculation. Should the benchmark run out of new WUs to test, it simply processes another WU in order to prevent any of the cores from going idle as the others finish. Once all four of the WU types have been tested, the benchmark averages the points per day among them. That points-per-day average is then multiplied by the number of cores on the CPU in order to estimate the total number of points per day that CPU might achieve.
This may be a somewhat quirky method of estimating overall performance, but my sense is that it generally ought to work. We’ve discussed some potential reservations about how it works here, for those who are interested. I have included results for each of the individual WU types below, so you can see how the different CPUs perform on each.
The Xeons are plainly faster here, and the scores for both the AMD and Intel processors appear to scale rather linearly with clock speed improvements.
3D modeling and rendering
POV-Ray rendering
We’re using the latest beta version of POV-Ray 3.7 that includes native multithreading and 64-bit support. Some of the beta 64-bit executables have been quite a bit slower than the 3.6 release, but this should give us a decent look at comparative performance, regardless.
Shanghai’s performance gains here aren’t quite sufficient to allow the Opteron 2384 to catch the Xeon E5450, but they are remarkably solid improvements, especially in the benchmark scene. The question is: why? POV-Ray hasn’t been particularly sensitive to cache sizes or memory bandwidth in recent years. During my recent visit to AMD’s Austin, Texas campus, one of AMD’s engineers told me that Shanghai’s branch prediction algorithm had been tweaked to improve its accuracy in certain cases, and one of the applications that should benefit from that tweak is POV-Ray. Looks like it helped.
Valve VRAD map compilation
This next test processes a map from Half-Life 2 using Valve’s VRAD lighting tool. Valve uses VRAD to pre-compute lighting that goes into its games.
This is our final lighting/rendering-type test, and the results are what we’ve come to expect, more or less.
x264 HD video encoding
This benchmark tests performance with one of the most popular H.264 video encoders, the open-source x264. The results come in two parts, for the two passes the encoder makes through the video file. I’ve chosen to report them separately, since that’s typically how the results are reported in the public database of results for this benchmark. These scores come from the newer, faster version 0.59.819 of the x264 executable.
For more workstation-oriented applications like this one, the Xeons have a consistent edge over the Opterons, and Shanghai doesn’t really change that.
Sandra Mandelbrot
We’ve included this final test largely just to satisfy our own curiosity about how the different CPU architectures handle from SSE extensions and the like. SiSoft Sandra’s “multimedia” benchmark is intended to show off the benefits of “multimedia” extensions like MMX, SSE, and SSE2. According to SiSoft’s FAQ, the benchmark actually does a fractal computation:
This benchmark generates a picture (640×480) of the well-known Mandelbrot fractal, using 255 iterations for each data pixel, in 32 colours. It is a real-life benchmark rather than a synthetic benchmark, designed to show the improvements MMX/Enhanced, 3DNow!/Enhanced, SSE(2) bring to such an algorithm.
The benchmark is multi-threaded for up to 64 CPUs maximum on SMP systems. This works by interlacing, i.e. each thread computes the next column not being worked on by other threads. Sandra creates as many threads as there are CPUs in the system and assignes [sic] each thread to a different CPU.
The benchmark contains many versions (ALU, MMX, (Wireless) MMX, SSE, SSE2, SSSE3) that use integers to simulate floating point numbers, as well as many versions that use floating point numbers (FPU, SSE, SSE2, SSSE3). This illustrates the difference between ALU and FPU power.
The SIMD versions compute 2/4/8 Mandelbrot point iterations at once – rather than one at a time – thus taking advantage of the SIMD instructions. Even so, 2/4/8x improvement cannot be expected (due to other overheads), generally a 2.5-3x improvement has been achieved. The ALU & FPU of 6/7 generation of processors are very advanced (e.g. 2+ execution units) thus bridging the gap as well.
We’re using the 64-bit version of the Sandra executable, as well.
Shanghai is nearly as fast, clock for clock, as the Xeon in both the integer x8 and FP double tests. The Opteron 2384 runs neck and neck with the 2.66GHz Xeon L5430.
Conclusions
The Shanghai Opterons’ higher clock speeds, larger and quicker L3 cache, and improved memory subsystem are just what the doctor ordered for AMD’s quad-core CPU architecture. These changes, along with lower power consumption both at idle and while loaded, go a long way toward alleviating the weaknesses of the 65nm Barcelona Opterons. The Opteron 2384’s ability to outperform the Xeon E5450 in SPECjbb is dramatic proof of Shanghai’s potency. Similar server-class workloads are likely to benefit with Shanghai, as well, so long as they are properly NUMA-aware. Both in SPECjbb and in the more difficult case (for the Opteron) of the Cinema 4D renderer, we found our Opteron 2384-based system to be quantifiably superior in terms of power-efficient performance than Xeon systems that employ FB-DIMMs.
The new Opterons are clearly more competitive now, but they were still somewhat slower overall in the HPC- and workstation-oriented applications we tested, with the lone exception of MyriMatch. In many cases, Shanghai at 2.7GHz was slightly behind the Xeon L5430 at 2.66GHz. The Opteron does best when it’s able to take advantage of its superior system architecture and native quad-core design, and it suffers most by comparison in applications that are more purely compute-bound, where the Xeons generally have both the IPC and clock frequency edge.
We should say a word here about Intel’s San Clemente platform, which we paired with its low-voltage Xeons. It’s a shame this platform isn’t more of a mainstream affair, and it’s a shame the memory controller is limited to only six DIMMs. Even with that limitation, San Clemente may be Intel’s best 2P server platform. In concert with the Xeon L5430, it’s even more power efficient than this first wave of Shanghai Opterons, and in several cases, the lower latency of DDR2 memory seemed to translate into a performance advantage over the Bensley platform in our tests. For servers that don’t require large amounts of RAM, there’s no better choice.
AMD argues that it has a window of opportunity at present, while its Shanghai Opterons are facing off in mainstream servers versus current Xeons. I would tentatively agree. For the right sort of application, an Opteron 2384-based system offers competitive performance and lower power draw than a Xeon E5450 system based on the Bensley platform. The Xeon lineup has other options with consistently higher performance or lower power consumption, but the Shanghai Opterons match up well against Intel’s mainstream server offerings. (Workstations and HPC, of course, are another story.) If AMD can deliver on its plans for HyperTransport 3-enabled Opterons early next year, along with low-power HE and high-performance SE models, it may have a little time to regain lost ground in the server space before 2P versions of Nehalem arrive and the window slams shut.
Alle produkter og priser på ett sted
Prisjakt — Alle produkter og priser på ett sted
-18%
Magnor Rocks (Ø280)Hengelamper
3 073 ,-
-11%
WMF Perfect Plus Trykkoker 22cm 6,5LGryter & kasseroller
1 490 ,-
-9%
Apple iPhone 14 Pro 5G Dual SIM 6GB RAM 256GBMobiltelefoner
13 990 ,-
-25%
FIFA 23 (PS5)PlayStation 5-spill
499 ,-
- Dagens beste tilbud
- Sko, klær & accessories
- Løpesko
- Jakker
- Ryggsekker
- Fjellstøvler & tursko
- Mellomlag
- Se alle
- Hjem & Husholdning
- Vedovner og peiser
- Robotstøvsugere
- Støvsugere
- Kontrollenheter for hjemmeautomatisering
- Hundemat
- Se alle
- Telefon & GPS
- Mobiltelefoner
- Smartklokker
- Pulsklokker og sportsklokker
- Deksel for mobiler
- Portable batterier
- Se alle
- Datamaskiner & tilbehør
- PC-skjermer
- Bærbare datamaskiner
- Tastatur
- Nettbrett
- Routere
- Se alle
- Lyd & bilde
- Hodetelefoner
- TV
- Mobilhøyttalere
- Mediesenter
- Mikrofoner
- Se alle
- Skjønnhet & helse
- Parfymer
- Linser
- Ansiktskrem
- Sexleketøy
- Hårklippere & trimmer
- Se alle
- Spill & underholdning
- Spillkonsoller
- Nintendo Switch-spill
- Håndkontroller
- PlayStation 5-spill
- PlayStation 4-spill
- Se alle
- Sport & Friluftsliv
- Elsykler
- Telt
- Stormkjøkken
- Sykkelhjelmer
- Termoser
- Se alle
- Renovering og bygg
- Boremaskiner og skrumaskiner
- Hørselsvern
- Sirkelsager
- Kjøkkenbatterier
- Skrumaskiner og spikerpistoler
- Se alle
- Barn og Familie
- LEGO
- Bilseter
- Barnevogner
- Droner
- Vognposer
- Se alle
- Hage
- Griller
- Vedkløyv og sager
- Hagestoler og hagebenker
- Motorsager
- Pizzaovner
- Se alle
- Kjøretøy og tilbehør
- Vinterdekk
- Takbokser & lastekurver
- Sommerdekk
- Bilkameraer
- Bilstereo hovedenheter
- Se alle
- Foto & video
- Digitale systemkamera
- Videokameraer
- Objektiver
- Digitale kompaktkameraer
- Kamerastativ
- Se alle
- Husholdningsapparater & Hvitevarer
- Griller
- Grilltilbehør
- Hvitevarer
- Kaffemaskiner
- Kjøkkenmaskiner
- Se alle
Alt nytt fra Apples store Far out-event
Apples Far out-event bød på flere heftige lanseringer med iPhone 14-telefonene som stjernene. Her er alt som ble vist i løpet av kvelden.
Les mer
Ut på tur aldri sur, eller sulten!
Ta deg en tur ut og nyt de spiselige vekstene rundt deg. Du kan (nesten) plukke rett fra fortauskanten – sier forfatteren av boken Håndplukk, Kristin H. R. Nielsen. Her er hennes beste tips.
Les mer
5 praktiske ting til en liten studenthybel
Skal du flytte inn i en liten hybel eller leilighet er dette noen smarte dingser til deg!
Les mer
Apple Watch Series 8 45mm Aluminium with Sport BandSmartklokker
5 390 ,-
Sony SRS-XE300 Bluetooth HøyttalerMobilhøyttalere
1 957 ,-
Shelly Plug SSendere & mottakere for hjemmeautomatisering
224 ,-
Sensibo AirKontrollenheter for hjemmeautomatisering
1 389 ,-
Apple AirPods Pro Wireless In-ear
2 229 ,-
Apple AirPods Max Wireless Over-ear Headset
4 890 ,-
Apple AirPods (2nd Generation) Wireless In-ear med trådløst ladeetui
1 439 ,-
Apple AirPods Pro (2nd generation) 2022
2 990 ,-
Aduro Asgård 2
5 990 ,-
Aduro 9
11 990 ,-
Jøtul F 162
19 400 ,-
Jøtul F 136
25 690 ,-
Mitsubishi Electric Hero MSZ-LN25VG* / MUZ-LN25VG
15 990 ,-
Mitsubishi Electric Hero MSZ-LN35VG* / MUZ-LN35VG
17 099 ,-
Wilfa Svalbard Extreme
19 990 ,-
Panasonic CS-HZ25XKE / CU-HZ25XKE
19 788 ,-
Liebherr KB 4330 (Hvit)
16 999 ,-
Liebherr Kef 4330 (Rustfritt)
12 999 ,-
Gorenje ORB153BK-L (Sort)
7 995 ,-
Gorenje ORB153BK (Sort)
7 995 ,-
Philips Hue Play Gradient Light Tube
1 535 ,-
Philips Hue White and Colour Ambiance E27 Starter Kit 3-pack
999 ,-
Philips Hue White Ambiance LED Starter Pack E27 A60 2200-6500K 806lm 8,5W 3-pack
777 ,-
Philips Hue White And Color LED E14 B39 2000K-6500K +16 million colors 470lm 4W
637 ,-
Apple iPhone 14 5G Dual SIM 4GB RAM 128GB
10 990 ,-
Apple iPhone 13 Pro 5G Dual SIM 6GB RAM 128GB
10 990 ,-
Apple iPhone 14 Pro 5G Dual SIM 6GB RAM 128GB
13 990 ,-
Apple iPhone 13 5G Dual SIM 4GB RAM 128GB
8 890 ,-
Fubuki Niseko 2. 0 (Unisex)
995 ,-
Viking Footwear Trophy 4.0 (Unisex)
924 ,-
Muckboot Arctic Sport Mid (Herre)
1 099 ,-
Hunter Boots Original Tall (Dame)
999 ,-
Miele Triflex HX1 Pro Trådløs
4 990 ,-
Philips SpeedPro Max Aqua 8000 XC8349 Trådløs
5 999 ,-
Bissell 2602C Trådløs
1 525 ,-
Dyson V15 Detect Absolute Trådløs
7 990 ,-
Makita LXT DUB185Z (Uten Batteri)
499 ,-
Gardena ErgoJet 3000
1 218 ,-
Makita DUB362Z (Uten Batteri)
1 990 ,-
Dewalt DCV100 (Uten Batteri)
1 140 ,-
MSR Hubba Hubba NX (2)
4 798 ,-
High Peak Siskin (2)
4 525 ,-
Rab Ridge Raider Bivi (1)
3 879 ,-
Bergans Super Light (2)
5 922 ,-
Didriksons Boardman Set (Jr)
400 ,-
Didriksons Waterman Set (Jr)
200 ,-
Helly Hansen Bergen Set (Jr)
299 ,-
Reima Lampi Jacket (Jr)
289 ,-
Db The Strøm 30L Backpack
1 679 ,-
Db The Strøm 20L Backpack
1 274 ,-
Db The Hugger 30L
1 549 ,-
Db The Ramverk 21L
1 709 ,-
Processor AMD Opteron 2380 — specifications, prices, tests » BNAME.
RU
Processor search
Opteron 2380
Compare Opteron 2380
Main information
Brand
AMD
Family Family
9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000
2008
Main Harcatericism
Number
4 Nuclei
Flows
4 Streams
SOCKET (connector)
SOCKET F
9000
Free Processor Multiplier
None
Processor
Process
45nm
Transistors (millions)
758 million
TDP
115 W
Maximum temperature
77 ° C
Shina
1000 MHZ HYPERTRANSPORT
CESH L1
4X64 + 4X64 of KB 9000 Kesh 2l L2
512×4 KB
L3 cache
6144 KB
RAM
RAM controller
Present
RAM types
0005
Memory channels
2
Opteron performance rating 2380
Attention! The general rating calculation method is chosen, which means that the rating percentage is calculated relative to the most powerful processor participating on our site.
Rating calculation method:
Overall ratingBy architecture ShanghaiBy Socket FAmong Intel processorsAmong AMD processorsAmong server processorsAmong Opteron family processorsAmong 4-core processorsAmong 2008 processors
General performance rating
1981.04
(1.87%)
Passmark CPU Mark
1659
(1.89%)
Cinebench 11.5 (64-bit) Multipolate test
9000 1.9
( 1.8%)
Cinebench 11.5 (64-bit) Single-threaded test
0.39
(4.51%)
Cinebench 15 (64-bit) Multi-threaded test
163.91
4 ( 163.91
%)
Cinebench 15 (64-bit) Single threaded test
41.7
(12.44%)
Geekbench 4.0 (64-bit) Multipotive test
3515.12
(1.9%)
Geekbench 4.0 (64-bit) Single-test test
1166.56
(7 42%)
x264 HD 4.0 Pass 1
44.39
(1.72%)
x264 HD 4.0 Pass 2
10.34
(1. 67%)
3DMARK06 CPU
9000 1.89%)
WinRAR 4.0
1121.76
(1.88%)
Positions in the rating
Attention! The general rating calculation method is chosen, which means that the rating percentage is calculated relative to the most powerful processor participating on our site.
Rating calculation method:
Overall ratingBy architecture ShanghaiBy Socket FAmong Intel processorsAmong AMD processorsAmong server processorsAmong Opteron family processorsAmong 4-core processorsAmong 2008 processors
The total performance rating
The ranking is participated in the rating 3291 processor
1383 place
(out of 3291)
Passmark CPU MARK
in the ranking 3279 processors
1392 9000
(of 32779)
(of 3277) bit) Multi-threaded test
3221 processors
1289 place
(out of 3221)
Cinebench 11.5 (64-bit) Single-threaded test
3215 processors participate in the rating
616 place
(out of 3215)
Cinebench 15 (64-bit) Multipotive test
in the ranking 3218 processors
1252 place
(out of 3218)
Cinebench 15 (64-bit) single-circuit vehicle
VN The rating is participated in 3217 processors
752 place
(out of 3217)
Geekbench 4. 0 (64-bit) multipropoped test
in the ranking is participated in the rating
1161 place
(out of 3209)
Geekbench 4.0 (64-Best) Single thread test
The ranking is involved in 3209 processors
737 place
(out of 3209)
x264 HD 4.0 Pass 1
The ranking is involved in 3211 processors
1200
(out of 3211)
x264 hd 4.0 PASS 2
3211 processors
1260 place
(out of 3211)
3DMark06 CPU
The ranking is participated in the ranking 3242 processors
1399 place
(out of 3242)
Winrar 4.0
in the ranking. 3212 processors 9 processors are participated in the ranking0005
1169 place
(out of 3212)
Technology or instruction name | Meaning | Short description |
---|---|---|
Enhanced PowerNow! | PowerNow! advanced idle frequency drooping technology. | |
CoolCore Technology | Complements Cool’n’Quiet. Temporarily disable unused processor blocks. | |
DPM (Dynamic Power management) | Dynamic Power Management. |
Technology or instruction name | Meaning | Short description |
---|---|---|
MMX (Multimedia Extensions) | Multimedia extensions. | |
SSE (Streaming SIMD Extensions) | Streaming SIMD processor extension. | |
SSE2 (Streaming SIMD Extensions 2) | Processor Streaming SIMD Extension 2. | |
SSE3 (Streaming SIMD Extensions 3) | Processor Streaming SIMD Extension 3. | |
AMD64 | 64-bit microprocessor architecture developed by AMD. | |
3DNow! | Optional MMX extension for AMD processors. |
Technology or instruction name | Meaning | Short description |
---|---|---|
EVP (Enhanced Virus Protection) | Improved virus protection. |
Name of technology or instruction | Meaning | Short description |
---|---|---|
AMD-V | AMD-V Virtualization Technology. |
Overview of AMD Opteron 2380 processor
The Opteron 2380 processor model, developed on the Shanghai microarchitecture, is designed for assembling server computers. Produced since 2008.
The bus speed will be 1000 MHz HyperTransport. The processor is designed for motherboards on Socket F connectors. With a 45 nanometer process, the total number of transistors reaches 758 million. The temperature in the load will be 77°C. The processor requires an efficient cooling system because the calculated thermal power reaches 115 watts.
Good server processor made in 2008. It is used to build servers.
Competitors and analogues
AMD models on socket F stand out among rivals: model 2427 on socket F from the Opteron line, model SE among the line of Opteron processors, model SE on socket F from the Opteron family, Opteron 2431, released 1 year later, Shanghai-based Opteron 2384, model 2378 from the Opteron processor family. Competitors from Intel include the slightly later Xeon X3430, the X6550 socket LGA1567 model of the Xeon X processor series, the X3220 model of the Xeon X processor family, the 2010 Xeon E5507, the 2006 Xeon X5355, and the earlier Xeon E5410.
If we compare the entire Core family, then it confidently holds the 60th place in the table. The most similar models from AMD are Opteron 2384, Opteron 2386 SE, Opteron 2393 SE, Opteron 2374 HE, Opteron 2373 EE, Opteron 2378, Opteron 2376. They work on the same Socket F socket and the same Shanghai microarchitecture.
Technology and instructions
The processor supports many top technologies and instructions.
This model has integrated energy saving technologies such as CoolCore Technology, DPM (Dynamic Power management), Enhanced PowerNow!. Instruction sets SSE2, AMD64, SSE3, MMX, SSE (Streaming SIMD Extensions), 3DNow! are used.
Similar processors
Opteron 2373EE
Opteron 1354
Atom C3538
Opteron 3320 EE
Xeon E5335
Xeon L5320
Xeon X5270
Xeon X5260
Xeon E5504
Opteron 1352
Xeon Silver 4116T
Opteron 2354
If you like our site — you can support our project .
AMD Opteron 2380 processor — specifications, tests, reviews
- Edelmark rating — 4.7 out of 10;
- Release date: November, 2008;
- Number of cores: 4;
- Frequency: 2. 5 GHz;
- Power consumption (TDP): 75W;
AMD Opteron 2380 Specifications
General Specifications
Clock frequency | 2.5 GHz |
---|---|
Cores | 4 |
Socket | F |
Unlock cores | No |
Functions
NX-bit (XD-bit) available | Yes |
---|---|
Virtualization support | Yes |
Instructions supported | MMX SSE SSE2 3DNow! SSE4a SSE3 |
Support for dynamic frequency scaling (CPU Throttling) | Yes |
Power consumption
Power consumption | 75W |
---|---|
Annual cost of electricity (NON-commercial use) | 18.07 $/year |
Annual cost of electricity (commercial use) | 65. 7 $/year |
Capacity per W | 1.44pt/W |
Average energy consumption | 60.94W |
Bus
Clock frequency | 2.000 MHz |
---|
Parts and Features
Threads | 4 |
---|---|
Second level cache (L2) | 2MB |
Second level cache per core (L2) | 0.5 MB/core |
L3 cache | 6MB |
Level 3 cache per core (L3) | 1.5 MB/core |
Process | 45 nm |
Maximum processors | 2 |
Processor multiplier | 12 |
Voltage range | 1.3 — Unknown V |
Operating temperature | 0 — 55°C |
Overclocking Opteron 2380
Overclocking Clock | 2. 51 GHz |
---|---|
Water-cooled boost clock | 2.5 GHz |
Air cooled boost clock | 2.51 GHz |
Integrated (integrated) graphics
Graphics core | No |
---|---|
Grade | No |
Latest DirectX | No |
Number of displays supported | No |
Graphics core clock speed | No |
Maximum clock frequency | No |
3DMark06 | No |
Comparison of Opteron 2380 with similar processors
Performance
Performance using all cores.
Opteron 2380 | 5.5 out of 10 |
---|---|
Core i7 975 | 5.8 out of 10 |
Opteron 2425 HE | no data |
Performance per core
Base performance per processor core.
Opteron 2380 | no data |
---|---|
Core i7 975 | 6.6 out of 10 |
Opteron 2425 HE | no data |
Integrated Graphics
Integrated GPU performance for graphics tasks.
Opteron 2380 | 0.0 out of 10 |
---|---|
Core i7 975 | 0.0 out of 10 |
Opteron 2425 HE | 0.0 out of 10 |
Integrated graphics (OpenCL)
Embedded GPU performance for parallel computing.
Opteron 2380 | 0.0 out of 10 |
---|---|
Core i7 975 | 0.0 out of 10 |
Opteron 2425 HE | 0. 0 out of 10 |
Performance per Watt
How efficiently the processor uses electricity.
Opteron 2380 | 5.0 out of 10 |
---|---|
Core i7 975 | 5.0 out of 10 |
Opteron 2425 HE | no data |
Price-performance ratio
How much you overpay for performance.
Opteron 2380 | 5.1 out of 10 |
---|---|
Core i7 975 | 5.1 out of 10 |
Opteron 2425 HE | no data |
Total Edelmark rating
Total processor rating.
Opteron 2380 | 4.7 out of 10 |
---|---|
Core i7 975 | 5.2 out of 10 |
Opteron 2425 HE | no data |
Benchmarks Opteron 2380
PassMark
Opteron 2380 | 2.640 |
---|---|
Core i7 975 | 6.173 |
Opteron 2425 HE | no data |
Video reviews
Game 12 core processor for $3. AMD Opteron 6172 review and benchmarks. Reupload.
Dual AMD Opteron 2427 Workstation — Brief Overview
Opteron reviews in builds just in 2016, such a trouble was nya …)
inaccurate assembly on a shiper stump and it will be cheaper
Tags:2. 5 GHz, 75W, AMD, CPU, Opteron 2380
90,000 AMD Opteron-2380 Shanghai (2500MHz, S1207, L3 6144 KB, L2 2048 KB)
You are here
Home
Processor brand:
Model of the processor:
Processor number:
PROCESSION NACKS
Number of cores:
Processor clock speed:
Socket type:
Process technology:
L1 cache size:
L2 cache size:
L3 cache size:
Maximum memory bandwidth0453
Processor type:
Release date:
Processor Description:
AMD brand processor with Opteron line (model range) and processor number: 2380. This processor works on the Shanghai Core, the CPU itself is designed according to the technological process (lithography) of 45 nm. The number of cores in the processor is 4, and the total clock frequency is 2500MHz . This AMD brand CPU has a socket (connector) for connecting to the S1207 motherboard. The third level cache (L3) is 6144 KB, and the second level cache (L2) is 2048 KB. Information about maximum memory bandwidth: -. This processor is positioned by the manufacturer as a CPU for systems of the type: Server. Known start date for the release (production) of this processor: 11/13/2008.
Information about the technical characteristics of the goods listed on the pages of the site is for reference only and does not mean that the goods are available from sellers on the radio market.
Specify the availability of goods directly from sellers of , contacting them using the contacts listed in the catalog of radio market companies.
CPUs most unlike this CPU
0115 Pentium 4 part number — . This processor uses the Willamette Core , and the processor itself is made according to the 180 nm manufacturing process. The number of cores in it is 1 , and the total clock frequency of this processor is 1700MHz . This Intel product connects to the computer motherboard using a connector (socket) S478 . The memory of the third level is — , and the memory capacity is of the second level is equal to 256 KB . Maximum memory bandwidth found on the manufacturer’s website: — . This processor is presented by the company as a CPU for systems: Desktop PCs . Start date of production (release) of this processor: — .
The company’s Intel CPU is represented by the Xeon E3 model line with the number 1285LV3 . This processor uses Haswell Core , and the processor itself is made according to process 22 nm . The number of cores in it is 4 , and the total clock frequency of this processor is 3100MHz . This Intel product connects to the computer motherboard using the LGA1150 connector (socket). The memory of the third level is 8192 KB , and the amount of memory of the second level is 1024 KB . Maximum memory bandwidth found on the manufacturer’s website: 25.6 Gb/s . This processor is presented by the company as a CPU for systems: Desktop PCs . Start date of production (release) of this processor: Q2 2013 .
CPU company Intel represented by the model range Celeron D with the number 335J . This processor uses the Prescott Core , and the processor itself is made according to the 90 nm manufacturing process . The number of cores in it is 1 , and the total clock speed of this processor is 2800MHz . This Intel product connects to the computer motherboard using the LGA775 connector (socket). The third level memory is — , and the second level memory is 256 KB . Maximum memory bandwidth found on the manufacturer’s website: — . This processor is presented by the company as a CPU for systems: Desktop PCs . Start date of production (release) of this processor: Q4 2004 .
You were watching
Processor AMD Opteron-2380 Shanghai (2500MHz, S1207, L3 6144 Kb, L2 2048 Kb)
Similar processors:
Processor AMD Opteron-8380 Shanghai (2500MHz, S1207, L3 6144 KB, L2 2048 KB)
Processor AMD Opteron-8378 Shanghai (2400MHz, S1207, L3 6144 KB, L2 2048 KB)
Processor AMD Opteron-2384 Shanghai (2700MHz, S1207, L3 6144 KB, L2 2048 KB)
Processor AMD Opteron-2382 Shanghai (2600MHz, S1207, L3 6144 KB, L2 2048 KB)
Processor AMD Opteron-2378 Shanghai (2400MHz, S1207, L3 6144 KB, L2 2048 KB)
Moscow, Kostromskaya str. , 17
In the price of prices and similar goods
10 796
Processor AMD Socket AM4, Ryzen 5 PRO 4650G, 6 -core, 3700 MHz, Turbo: 4200 Renoir, Cache L2 — 3 MB, l3 8 MB, l3 Radeon Vega 7, 7 Nm, 65 W, OEM (100-000000143)
More prices and similar goods
13 269
Processor AMD Ryzen 5 5600x (3700MHZ/ AM4/ L2 L3 L3) 100-000000065 OEM
DETAILSMore prices and similar items
47 257
Processor AMD Socket AM4, Ryzen 9 5950X, 16-core, 3400 MHz, Turbo: 4900 Vermeer, L2 cache — 8 MB, L3 614 without cooler, BOX 5 (100-0000059wof)
More prices and similar goods
116 633
Processor Server AMD SOCKET SP3, EPYC 7313, 16-core, 3000 MHz, Milan, Cache L2 -8 MB, L3 128 7nm, 180W, OEM (100-000000329)
DETAILSMore prices and similar items
1 840
2055
Processor AMD A6 9500E PRO AD950BAHM23AB BRISTOL RIDGE PRO, 2C/2T, 3-3. 4GHZ (AM4, L2 9016 1MB, 28NM, RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON, RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEON RADEN and similar goods
RM697AA Processor HP AMD Opteron Processor Model 2222 / 3.0 GHZ, 1 MB L2 Cache perver
9,000 9000 9000 9000 9000 9000 9000 9000 9000 9000 9000
115 AMD
Socket SP3, EPYC 7543, 32-core, 2800 MHz, Milan, Cache L2 — 16 MB, L3 256 7nm, 240W, OEM (100-000000345)
DETAILSMore prices and similar products
156
Processor Server AMD Socket SP3, EPYC 7542, 32-core, 2900 MHz, Rome, Cache L2 -16 MB, L3 128 7 W, OEM (100-000000075)
9000 9000
more prices and similar items
634956-001 Processor HP AMD Cache, AM4555SHE44HJ)
In the price of prices and similar products
169 541
Processor AMD SOCKET SP3, Epyc 7502P, 32 -Jailed, 2500 MHz, Rome, Kesh, Kesh, Kesh, Kesh 128 nm, 180 watts, OEM (100-000000045)
More prices and similar goods
1 807
2048
Processor AMD 85858BAGM23AB BRISTOL RIDGE, 2T, 3,3,3. -4GHz (AM4, L2 1MB, 28NM, Radeon R5, 65W)
More prices and similar goods
12 130
Processor AMD SOCKET AM4, Ryzen 5 Pro 4650G, 6-Jewish, 3700 MHz, Turbo: 4200 RENIIII. L2 — 3 MB, L3 8 Radeon Vega 7, 7 Nm, 65 W, OEM + Coler (100-100000143MPK)
More prices and similar goods
402 214
Server AMD SOCKET SP3, EPYC 7742, 64-core, 2250 MHz, Rome, Cache L2 — 32 MB, L3 256 7nm, 225W, OEM (100-000000053)
DETAILSMore prices and similar items , Cache L2 — 1 MB, L3 4 Radeon Vega 3, 14 Nm, 35 W, OEM (YD3000C6M2OFH)
More prices and similar goods
20,0005
processor AMD SOCKET AM4, RYZEN 4750G, 8-core, 3600 MHz, Turbo: 4400 Renoir, Cache L2 -4 MB, L3 8 Radeon Vega 8, 7 Nm, 65 W, OEM + Coler (100-100000145MPK)
More prices and similar goods
126 723
397819-L21 Processor HP Genuine AMD O254 Opteron 2. 8GHZ 1MB L2 CPU
In the price of prices and similar goods
18 025
Processor AMD SOCKET AM4, RYZEN 7 5700 MGC, 3800 MHPS, TRAB, TRAB, TREB L2 — 4MB, L3 16 Radeon Vega 8, 7nm, 65W, OEM (100-000000263)
More prices and similar goods
10 041
Processor AMD SOKKET AM4, Ryzen 3 3200G, 3600 MHz, TURBO: 4000 Picasso, Cache — 2 MB, L3 4 RADON. 8, 12 Nm, 65 V, OEM + cooler (YD320GC5Fimpk)
More prices and similar goods
14 540
Processor AMD SOCKET AM4, RYZEN 5 5600X, 6-nuclear, 3700 MMs, TURBO, TURBO, TURBO, TURBO: Vermeer, Cache L2 — 3MB, L3 32 7nm, 65W, OEM (100-000000065)
More prices and similar goods
12 940
Processor AMD SOKKET AM4, ATHLON GOLD 3150GE, 4 -core, 3300 MHz, TURBO, TURBO, 3800 Picasso, Cache L2 — 2 CEF 12 Nm, 35 W, OEM (YD3150C6M4MFH)
More prices and similar goods
57 623
NH356AA
HP QUAD-Core
OPTERON 2387/ 2. 8 GHZ, 512 Kb, 512 Kb / 2.8 GHA 6MB shared L3
In the price of prices and similar goods
18 626
Processor AMD SOKKET AM4, Ryzen 7 5700G, 3800 MHz, Turbo: 4600 Cezanne, Cache L2 — 4 MB, L3 16 RADEN VEGA 8, 7 Nm, 65 W, BOX (100-100000263BOX)
More prices and similar goods
209 909
Server AMD SOCKET SP3, Epyc 7501, 32-nuclear, 2000 MHz, Naples, Naples Cache L2 — 16MB, L3 64 14nm, 170W, OEM (PS7501BEVIHAF)
More prices and similar goods
1 793
1965
Processor AMD A6 8570E PRO AD857BAHM23AB CARRIZO PRO, 2C/2T, 3-3.4GHZ (AM4, L2 1MB (AM4, L2 1MB 35W)
DETAILSMore prices and similar items
Processor AMD Socket AM3+, FX-4300, Quad Core, 3800 MHz, Turbo: 4000 Vishera, L2 Cache — 4 MB W, BOX (FD4300WMHKBOX/FD4300WMHKSBX)
14 540
Processor AMD Socket AM4, Ryzen 5 5600G, 6-core, 3900 MHz, Turbo: 4400 Cezanne, L2 cache — 3 MB, L3 16 7nm, 6. 5 watts Vega BOX (100-100000252BOX)
More prices and similar goods
34 132
Processor AMD SOCKET AM4, Ryzen 9 5900x, 12-core, 3700 MHz, Turbo: 4800 VERMEER, Kesh 9015, Kesh 9015 Mb, L3 64 7nm, 105W, OEM (100-000000061)
DETAILSMore prices and similar items
115 756
CPU Server AMD Socket SP3, EPYC 7502, 32-core, 2500 MHz, Rome, L2 Cache — 16 MB, L3-010 0.5 nm
More prices and similar goods
206 528
Processor Server AMD Socket SP3, Epyc 7601, 32 -nuclear, 2200 MHz, CASh L2 — 16 MB, 180 NM, 18 NM, 18 NM, 18 NM, 18 NM, 18 NM, 18 NM, 18 NM, 18 NM. , OEM (PS7601BDVIHAF)
DETAILSMore prices and similar items
10 063
Processor AMD Socket AM4, Athlon Gold 3150G, 4-core, 3500 MHz, Turbo: 3900 Picasso, L2 Cache — 2 MB, L3 2 nm, Radeon Graphics OEM (YD3150C5M4MFH)
More prices and similar goods
12 433
Processor AMD SOCKET AM4, Ryzen 5 5600G, 3900 MHz, Turbo: 4400 Cezanne, Kesh , Kesh, Kesh . L3 16 Radeon Vega 7, 7nm, 65W, OEM (100-000000252)
DETAILSMore prices and similar products
2 page of 3
Comparison of Intel Core i5-2380P and AMD Opteron 248
Comparative analysis of Intel Core i5-2380P and AMD Opteron 248 processors by all known characteristics in the categories: General Information, Performance, Memory, Graphics, Graphical Interfaces, Compatibility, Peripherals, Security and Reliability, Technology, Virtualization.
Analysis of processor performance by benchmarks: PassMark — Single thread mark, PassMark — CPU mark, Geekbench 4 — Single Core, Geekbench 4 — Multi-Core, CompuBench 1.5 Desktop — Face Detection (mPixels/s), CompuBench 1.5 Desktop — Ocean Surface Simulation ( Frames/s), CompuBench 1.5 Desktop — T-Rex (Frames/s), CompuBench 1.5 Desktop — Video Composition (Frames/s), CompuBench 1.5 Desktop — Bitcoin Mining (mHash/s).Intel Core i5-2380P
versus
AMD Opteron 248
Benefits
Reasons to choose Intel Core i5-2380P
- Newer processor, release date difference 8 year(s) 2 month(s)
- more, run more cores, run more 30505
applications simultaneously: 4 vs 1
- Approximately 55% more clock speed: 3. 40 GHz vs 2.2 GHz
- A newer technological process of manufacturing the processor allows it to be more powerful, but with lower power consumption: 32 nm vs 130 nm
- L1 cache is 2x larger, which means more data can be stored in it for quick access
- Performance in the PassMark — CPU mark benchmark is 8x larger: 3797 vs 476
Release date January 2012 vs November 2003 Number of cores 4 vs 1 Maximum frequency 3.40 GHz vs 2.2 GHz Process 32 nm vs 130 nm Level 1 cache 64 KB (per core) vs 128 KB PassMark — CPU mark 3797 vs 476 89 Watt vs 95 Watt
89 Watt vs 95 Watt Benchmark comparison
CPU 1: Intel Core i5-2380P
CPU 2: AMD Opteron 248
PassMark — CPU mark
CPU 1 CPU 2
Name Intel Core i5-2380P AMD Opteron 248 PassMark — Single thread mark 1607 0 PassMark — CPU mark 3797 476 Geekbench 4 — Single Core 681 Geekbench 4 — Multi-Core 2289 CompuBench 1. 5 Desktop — Face Detection (mPixels/s) 9.004 CompuBench 1.5 Desktop — Ocean Surface Simulation (Frames/s) 63.404 CompuBench 1.5 Desktop — T-Rex (Frames/s) 0.409 CompuBench 1.5 Desktop — Video Composition (Frames/s) 2.63 CompuBench 1.5 Desktop — Bitcoin Mining (mHash/s) 9.134 Performance comparison
Intel Core i5-2380P AMD Opteron 248 Architecture name Sandy Bridge SledgeHammer Production date January 2012 November 2003 Price at first issue date $180 $12 Place in the ranking 1705 2751 Price now $89. 99 $99.95 Processor Number i5-2380P Series Legacy Intel® Core™ Processors Status Discontinued Price/performance ratio (0-100) 18.59 1.40 Applicability Desktop Server Support 64 bit Base frequency 3. 10 GHz Bus Speed 5 GT/s DMI Crystal area 216 mm 193 mm Level 1 cache 64 KB (per core) 128KB Level 2 cache 256 KB (per core) 1024KB Level 3 cache 6144 KB (shared) Process 32nm 130nm Maximum core temperature 72. 6°C Maximum frequency 3.40 GHz 2.2 GHz Number of cores 4 1 Number of threads 4 Number of transistors 1160 million 106 million Maximum number of memory channels 2 Maximum memory bandwidth 21 GB/s Maximum memory size 32GB Supported memory types DDR3 1066/1333 Intel® Clear Video Technology HD Intel® Flexible Display Interface (Intel® FDI) Intel® InTru™ 3D Technology Intel® Quick Sync Video WiDi support Low Halogen Options Available Maximum number of processors in configuration
1 1 Package Size 37. 5mm x 37.5mm Supported sockets LGA1155 940 Power consumption (TDP) 95 Watt 89 Watt Number of PCI Express lanes 16 PCI Express revision 2.0 Execute Disable Bit (EDB) Intel® Identity Protection Technology Intel® Trusted Execution Technology (TXT) Enhanced Intel SpeedStep® Technology Flexible Display interface (FDI) Idle States Extended instructions Intel® SSE4. 1, Intel® SSE4.2, Intel® AVX Intel 64 Intel® Advanced Vector Extensions (AVX) Intel® AES New Instructions Intel® Fast Memory Access Intel® Flex Memory Access Intel® Hyper-Threading Technology Intel® Turbo Boost Technology Intel® vPro™ Platform Eligibility Thermal Monitoring Intel® Virtualization Technology (VT-x) Intel® Virtualization Technology for Directed I/O (VT-d) Intel® VT-x with Extended Page Tables (EPT) Opteron — Wikipedia (with comments)
The Opteron (codenamed Sledgehammer or K8 ) is AMD’s first microprocessor based on AMD64 64-bit technology (also referred to as x86-64 ). AMD designed this processor primarily for use in the server market, so there are Opteron variants for use in systems with 1-8 processors.
In June 2004, the Dawning 4000A, a Chinese supercomputer built on Opteron processors, ranked tenth in the Top500 supercomputers. In November 2005, it dropped to 42nd place due to the emergence of more productive competitors. Then in the November Top500, 10% of supercomputers were built on the basis of AMD64 Opteron processors. For comparison, 16.2% of supercomputers were built based on the Intel EM64T Xeon processors.
Contents
- 1 Technical description
- 1.1 Key features of
- 1.2 Multiprocessing Features
- 1.3 Opteron
multi-core processors
- 1.4 Socket 939 and AM2
- 1.5 1974-pin Socket G34
- 2 models
- 2.1 Opteron 1G (130nm SOI)
- 2.2 Opteron 1G (90nm SOI)
- 2.3 Opteron 1G (90nm SOI)
- 2. 4 Opteron 1G (90nm SOI)
- 2.5 Opteron 1G (90nm SOI)
- 2.6 Opteron 2G (90nm SOI)
- 2.7 Opteron 2G (90nm SOI)
- 2.8 Opteron 2G (90nm SOI)
- 2.9 Opteron 3G (65nm SOI)
- 2.10 Opteron 3G (65nm SOI)
- 2.11 Opteron 3G (65nm SOI)
- 2.12 Opteron 3G (45nm SOI)
- 2.13 Opteron 3G (45nm SOI)
- 3 See also
- 4 Links
- 5 Notes
Datasheet
Key Features
Two important technologies implemented in the Opteron processor are:
- Direct (no emulation) support for 32-bit x86 applications without speed loss
- Direct (without emulation) support for 64-bit x86-64 applications (linear addressing more than 4 GB of RAM)
applications was Intel Itanium (emulation of 32-bit code using a decoder [www.3dnews.ru/cpu/amd-opteron]). But Itanium ran 32-bit applications with a significant loss of speed.
The second technology in itself is not so remarkable, since the main manufacturers of RISC processors (SPARC, DEC, HP, IBM, MIPS and others) have had 64-bit solutions for many years. But the combination of these 2 properties in one product, on the contrary, brought recognition to the Opteron , as it offered an affordable and cost-effective solution for running existing x86 applications with a subsequent transition to more promising 64-bit computing.
The Opteron processors have an integrated DDR SDRAM memory controller. This made it possible to significantly reduce delays in memory access and eliminate the need for a separate northbridge chip on the motherboard.
Multiprocessor features
In multiprocessor systems (more than one Opteron processor per motherboard), the CPUs communicate with each other using the Direct Connect Architecture via the high-speed Hyper-Transport bus. Each processor can access the memory of another processor transparently to the programmer. Unlike conventional symmetric multiprocessing, Opterons use NUMA (Non-Uniform Memory Access) technology, when instead of allocating one memory bank for all CPUs, each processor has its own memory. Processors 9The 1044 Opteron directly support 8 processor configurations commonly found in midrange servers. More powerful servers use additional costly routing chips to support more than 8 CPUs per board.
In many computer tests, the Opteron architecture demonstrates better multiprocessor system scalability than the Intel Xeon . [1] In systems based on the Xeon , the total processing power is often less than the sum of the individual CPUs. For example, a system based on 9The 1044 Xeon can run two parallel tasks at 90% throughput, or four parallel tasks at 80% throughput. Systems based on the Opteron are significantly less affected by this effect, justifying AMD’s choice of the architectural solution applied. In addition, the Opteron has a processor-integrated memory controller that allows each CPU to access its own memory without using the HyperTransport bus. If it is necessary to access the memory of another processor or during interprocessor interactions, only the initiator and its counterpart are involved, which reduces the use of the bus to a minimum. On multiprocessor systems based on Xeon , on the other hand, uses one common bus for processor-to-processor and processor-to-memory data exchange. As the number of processors used in a single Xeon based system increases, the load on this common bus from competing requests from different processors increases. This leads to a drop in the efficiency of the system as a whole.
Multi-core Opteron
In May 2005, AMD introduced the first «multi-core» Opteron processor. AMD currently uses the term «multi-core» to refer to «dual-core» processors; in each processor 9The 1044 Opteron hosts 2 separate processor cores. This effectively doubles the processing power available to each processor socket on motherboards that support these processors. One processor socket can now provide the performance of two processors, two processor sockets — four, and so on. The cost of motherboards increases significantly with the increase in the number of processor sockets installed on them, so new multi-core processors now allow building high-performance systems on the basis of relatively cheap motherboards with fewer sockets that were previously unavailable.
The processor model numbering system used by AMD has changed slightly in light of the new multi-core product lineup. During the official release, AMD introduced the fastest multi-core Opteron , model 875 with two cores running at 2.2 GHz. The fastest single-core processor Opteron at that time was the «model 252», operating at 2.6 GHz. For multi-threaded applications, the 875 performs better than the 252, but in single-threaded applications, the 252 outperforms the 875.
In September 2007, quad-core Opteron 3G models based on the Barcelona core were introduced. But due to an error in revision B2 (BA), their deliveries were suspended. In April 2008, with the announcement of new B3 revision models, deliveries were resumed.
Socket 939 and AM2
AMD also introduced the Socket 939 Opteron to reduce the cost of motherboards in low-end servers and workstations. Opteron s for Socket 939 processors are identical to the San Diego-based Athlon 64 processors, while running at much lower clock speeds than their maximum, providing extremely reliable performance. Because this under-clocked design means a lot of overclocking potential, these processors are in high demand among enthusiasts. With the transition of desktop processors to Socket AM2, the Opteron 1xxx series processors also switched to it.
1974-pin Socket G34
In March 2010, AMD released the world’s first 12-core x86 architecture Opteron 6100 server processors for the 1974-pin Socket G34. There are currently 16-core versions of Opteron processors, and in this indicator, AMD processors outperform similar server versions of Intel [2] processors.
Models
All Opteron 1G chips have a three-digit model number, in the form «Opteron xyy «. First digit ( x ) shows the maximum number of processors in the system:
- 1 — Designed for use in
single processor systems
- 2 — Designed for use in dual processor systems
- 8 — Designed for use in multiprocessor systems (4 or 8 processor systems)
The last two numbers in the model number ( yy ) indicate the speed of the processor. Meanings yy more than 60 are used in dual core models.
Opteron 2G and 3G chips have a four-digit model number, in the form «Opteron xzyy «.
x denotes belonging to the series:
- 1 — Designed for use in
single processor systems
- 2 — Designed for use in dual processor systems
- 8 — Designed for use in multiprocessor systems (4 or 8 processor systems)
z stands for Opteron processor generation.
- 2 — for Opteron 2G
- 3 — for Opteron 3G
The last two numbers in the model number ( yy ) indicate the speed of the processor.
Opteron 1G (130 nm SOI)
- Single core — SledgeHammer (1yy, 2yy, 8yy)
- processor steppings: B3, C0, CG
- First level cache: 64 + 64 KB (data + instructions)
- Second level cache: 1024 KB running at
core speed
- Support for MMX, Extended 3DNow!, SSE, SSE2, AMD64
- Socket: Socket 940, 800 MHz HyperTransport
- NOT required to use registered DDR SDRAM, ECC memory supported
- Core voltage: 1. 50 — 1.55 V
- First introduced: April 22, 2003 [www.amd.com/us-en/Corporate/VirtualPressRoom/0,51_104_543_13302~69678,00.html]
- Clock speeds: 1400 — 2400 MHz (x40 — x50)
Opteron 1G (90nm SOI)
- Single core — Venus (1yy), Troy (2yy), Athens (8yy) 92:445
stepping processors
- First level cache: 64 + 64 KB (data + instructions)
- Second level cache: 1024 KB running at
core speed
- MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64
- Socket: Socket 939/Socket 940, 1000 MHz HyperTransport
- Requires registered DDR SDRAM for Socket 9 variant40, memory with ECC
supported
- Core voltage: 1.35 — 1.4 V
- NX Bit Support
- Optimized Power Management (OPM)
- First introduced: February 14, 2005
- Clocks: 1600 — 3000 MHz (x42 — x56)
Opteron 1G (90nm SOI)
- Dual Core — Denmark (1yy).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, OPM, NX-Bit.
- Connector: Socket 939.
- Core voltage: 1.10 V — 1.35 V, power: 110 W (TDP), technology: 90 nm (SOI).
- Clock rates: 1.8 GHz — 2.6 GHz
- Models: 165: 1.8 GHz, 170: 2 GHz, 175: 2.2 GHz, 180: 2.4 GHz, 185: 2.6 GHz.
Opteron 1G (90nm SOI)
- Dual Core — Italy (2yy).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, OPM, NX-Bit.
- Connector: Socket 940.
- Core voltage: ? — 1.35V, power: 55W — 95W (TDP), technology: 90nm (SOI).
- Clock speeds: 1.6 GHz — 2.8 GHz
- Model HE (TDP: 55 W): 260: 1.6 GHz, 265: 1.8 GHz, 270: 2.0 GHz, 275: 2.2 GHz.
- Standard model (TDP: 95 W): 260: 1.6 GHz, 265: 1.8 GHz, 270: 2. 0 GHz, 275: 2.2 GHz, 280: 2.4 GHz, 285: 2.6 GHz, 290: 2.8 GHz.
Opteron 1G (90nm SOI)
- Dual Core — Egypt (8yy).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, OPM, NX-Bit.
- Socket: Socket 940.
- Core voltage: ? — 1.35V, power: 55W — 95W (TDP), technology: 90nm (SOI).
- Clock speeds: 1.6 GHz — 2.8 GHz
- Model HE (TDP: 55 W): 860: 1.6 GHz, 865: 1.8 GHz, 870: 2.0 GHz, 875: 2.2 GHz.
- Standard model (TDP: 95 W): 860: 1.6 GHz, 865: 1.8 GHz, 870: 2.0 GHz, 875: 2.2 GHz, 880: 2.4 GHz, 885: 2.6 GHz, 890: 2.8 GHz.
Opteron 2G (90nm SOI)
- Dual Core — Santa Ana (1000 Series).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool’n’Quiet, NX-Bit, AMD Virtualization.
- Connector: Socket AM2.
- Core voltage: 1.3 — 1.4V, power: 103W — 125W (TDP), technology: 90nm (SOI).
- Clock speeds: 1.8 GHz — 3.0 GHz
- Standard Model (TDP: 103 W): 1210: 1.8 GHz, 1212: 2.0 GHz, 1214: 2.2 GHz, 1216: 2.4 GHz, 1218: 2.6 GHz, 1220: 2.8 GHz, 1222: 3.0 GHz.
- HE Model (TDP: 68W): 1210HE: 1.8GHz, 1212HE: 2.0GHz, 1214HE: 2.2GHz, 1216HE: 2.4GHz, 1218HE: 2.6GHz.
- SE Model (TDP: 125W): 1220SE: 2.8GHz, 1222SE: 3.0GHz.
Opteron 2G (90nm SOI)
- Dual Core — Santa Roza (2000 Series).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool’n’Quiet, NX-Bit, AMD Virtualization.
- Connector: Socket F.
- Core Voltage: 1.2V — 1.375V, Power: 68W — 120W (TDP), Technology: 90nm (SOI).
- Clock speeds: 1.8 GHz — 2.8 GHz
- Standard Model (TDP: 95 W): 2210: 1. 8 GHz, 2212: 2.0 GHz, 2214: 2.2 GHz, 2216: 2.4 GHz, 2218: 2.6 GHz, 2220: 2.8 GHz, 2222: 3.0 GHz.
- HE Model (TDP: 68W): 2210HE: 1.8GHz, 2212HE: 2.0GHz, 2214HE: 2.2GHz, 2216HE: 2.4GHz, 2218HE: 2.6GHz.
- SE model (TDP: 120W): 2220SE: 2.8GHz, 2222SE: 3.0GHz, 2224SE: 3.2GHz.
Opteron 2G (90nm SOI)
- Dual Core — Santa Roza (8000 Series).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool’n’Quiet, NX-Bit, AMD Virtualization.
- Connector: Socket F.
- Core Voltage: 1.2V — 1.375V, Power: 68W — 120W (TDP), Technology: 90nm (SOI).
- Clock rates: 2.0 GHz — 3.2 GHz
- Standard model (TDP: 95 W): 8212: 2.0 GHz, 8214: 2.2 GHz, 8216: 2.4 GHz, 8218: 2.6 GHz, 8220: 2.8 GHz, 8222: 3.0 GHz.
- HE model (TDP 68W): 8212HE: 2.0 GHz, 8214HE: 2.2 GHz, 8216HE: 2. 4 GHz, 8218HE: 2.6 GHz.
- SE Model (TDP: 120W): 8220SE: 2.8GHz, 8222SE: 3.0GHz, 8224SE: 3.2GHz.
Opteron 3G (65nm SOI)
- Quad Core — Barcelona (AMD) (1000 Series).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 512 KB.
- Level 3 cache (L3): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool’n’Quiet 2.0, NX-Bit, AMD Virtualization.
- Connector: AM2+.
- Core voltage: 1.2 — 1.375V, power: 75W (ACP), technology: 65nm (SOI).
- Clock rates: 2.1 GHz — 2.3 GHz
- Standard model (ACP: 75W): 1356 2.3GHz, 1354 2.2GHz, 1352 2.1GHz.
Opteron 3G (65nm SOI)
- Quad Core — Barcelona (AMD) (2000 Series).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 512 KB.
- Level 3 cache (L3): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool’n’Quiet 2. 0, NX-Bit, AMD Virtualization.
- Connector: Socket F.
- Core voltage: 1.2 — 1.375 V, power: 68 W — 120 W (TDP), 55 W — 95 W (ACP), technology: 65 nm (SOI).
- Clock speeds: 1.7 GHz — 2.5 GHz
- Standard Model (ACP: 75W): 2356 2.3GHz, 2354 2.2GHz, 2352 2.1GHz, 2350 2.0GHz, 2347: 1.9GHz.
- HE model (ACP: 55 W): 2347HE: 1.6 GHz, 2346HE: 1.9 GHz, 2344HE: 1.7 GHz.
- SE model (ACP: 95 W): 2360SE: 2.5 GHz, 2358SE: 2.4 GHz.
Opteron 3G (65nm SOI)
- Quad Core — Barcelona (AMD) (8000 Series).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 512 KB.
- Level 3 cache (L3): 2048 KB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool’n’Quiet 2.0, NX-Bit, AMD Virtualization.
- Connector: Socket F.
- Core voltage: 1.2V — 1.375V, Wattage: 68W — 120W (TDP), 55W — 95W (ACP), Technology: 65nm (SOI).
- Clock rates: 1.8 GHz — 2.5 GHz
- Standard model (ACP: 75W): 8356 2.3GHz, 8354 2.2GHz, 8350 2.0GHz, 8347: 1.9GHz.
- HE model (ACP: 55 W): 8347HE: 1.6 GHz, 8346HE: 1.9 GHz.
- SE model (ACP: 95 W): 8360SE: 2.5 GHz, 8358SE: 2.4 GHz.
Opteron 3G (45nm SOI)
- Quad Core — Shanghai (AMD) (2000 Series).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 512 KB.
- Level 3 cache (L3): 6 MB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool’n’Quiet 2.0, NX-Bit, AMD Virtualization.
- Connector: Socket F.
- Core voltage: 1.2V — 1.375V, Wattage: 68W — 120W (TDP), 55W — 105W (ACP), Technology: 45nm (SOI).
- Clock rates: 2.3 GHz — 2.7 GHz
- Standard Model (ACP: 75W): 2384 2.7GHz, 2382 2.6GHz, 2380 2.5GHz, 2378 2.4GHz, 2376: 2.3GHz.
- Model HE (ACP: 55W): no (11/15/08)
- SE Model (ACP: 95 W): no (11/15/08)
Opteron 3G (45nm SOI)
- Quad Core — Shanghai (AMD) (8000 Series).
- First level cache (L1): 64 KB + 64 KB (data + instructions).
- Second level cache (L2): 512 KB.
- Level 3 cache (L3): 6 MB.
- Flags: MMX, Extended 3DNow!, SSE, SSE2, SSE3, AMD64, Cool’n’Quiet 2.0, NX-Bit, AMD Virtualization.
- Connector: Socket F.
- Core voltage: 1.2V — 1.375V, Wattage: 68W — 120W (TDP), 55W — 105W (ACP), Technology: 45nm (SOI).
- Clock rates: 2.5 GHz — 2.7 GHz
- Standard model (ACP: 75W): 8384 2.7GHz, 8382 2.6GHz, 8380 2.5GHz
- Model HE (ACP: 55W): no (11/15/08)
- SE model (ACP: 95 W): no (11/15/08)
See also
- AMD
microprocessor list
- List of Intel microprocessors
Write a Review on Opteron
Links
- [www.amd.com/us-en/Processors/ProductInformation/0,30_118_8825,00.html
- ↑ [europa.eu/rapid/pressReleasesAction.do?reference=MEMO/09/400&format=HTML&aged=0&language=EN&guiLanguage=en EUROPA — Press Releases — Antitrust: Commission publishes decision concerning Intel’s abuse of dominant position]
- ↑ Website overclockers. ua: [www.overclockers.ua/news/hardware/2010-03-29/105401/ «AMD greenlights 8- and 12-core Opteron 6100 series processors»].
Excerpt characterizing the Opteron
For the first time, as a young foreign person allowed herself to reproach her, she, proudly raising her beautiful head and turning to him in a half turn, said firmly:
— Voila l’egoisme et la cruaute des hommes! Je ne m’attendais pas a autre chose. Za femme se sacrifie pour vous, elle souffre, et voila sa recompense. Quel droit avez vous, Monseigneur, de me demander compte de mes amities, de mes affections? C’est un homme qui a ete plus qu’un pere pour moi. [Here is the selfishness and cruelty of men! I didn’t expect anything better. The woman sacrifices herself to you; she suffers, and here is her reward. Your highness, what right have you to demand from me an account of my affections and friendships? This is a man who was more than a father to me.]
The face wanted to say something. Helen interrupted him.
“Eh bien, oui,” she said, “peut etre qu’il a pour moi d’autres sentiments que ceux d’un pere, mais ce n’est; pas une raison pour que je lui ferme ma porte. Je ne suis pas un homme pour etre ingrate. Sachez, Monseigneur, pour tout ce qui a rapport a mes sentiments intimes, je ne rends compte qu’a Dieu et a ma conscience, [Well, yes, maybe the feelings he has for me are not entirely paternal; but that is not why I should refuse him my house. I’m not a man to pay with ingratitude. Let it be known to your highness that in my innermost feelings I give account only to God and my conscience.] — she finished, touching her hand to her beautiful chest that rose high and looking at the sky.
Mais ecoutez moi, au nom de Dieu. [But hear me out, for God’s sake.]
— Epousez moi, et je serai votre esclave. [Marry me and I will be your work.]
Mais c’est impossible. [But that’s impossible.]
— Vous ne daignez pas descende jusqu’a moi, vous … [You do not condescend to marry me, you . ..] — Helen said, crying.
The face began to console her; Helen, through tears, said (as if forgetting) that nothing could prevent her from getting married, that there were examples (there were still few examples then, but she named Napoleon and other high persons), that she had never been the wife of her husband, that she was sacrificed.
“But laws, religion…” the face was already giving up.
— Laws, religion … What would they have been invented if they could not do this! Ellen said.
The important person was surprised that such a simple reasoning could not occur to him, and he turned for advice to the holy brothers of the Society of Jesus, with whom he was in close relations.
A few days after that, at one of the charming holidays that Helen gave at her dacha on Kamenny Island, she was introduced to a middle-aged, with snow-white hair and black sparkling eyes, charming m r de Jobert, un jesuite a robe courte, [r Jaubert, a Jesuit in a short dress,] who for a long time in the garden, in the light of illumination and the sounds of music, talked with Helen about love for God, for Christ, for the heart of the mother of God and about the consolations delivered in this and in the future life by the only true the Catholic religion. Helen was touched, and several times she and Mr. Jobert had tears in their eyes and their voices trembled. The dance, to which the gentleman came to call Helen, upset her conversation with her future directeur de conscience [guardian of conscience]; but the next day mr de Jobert came alone in the evening to Helene, and from that time began to visit her often.
One day he took the countess to a Catholic church, where she knelt before the altar, to which she was led. A middle-aged charming Frenchman put his hands on her head, and, as she herself later told, she felt something like a breath of fresh wind that descended into her soul. It was explained to her that it was la grace [grace].
Then the abbot was brought to her a robe longue [in a long dress], he confessed her and remitted her sins to her. The next day, a box containing the sacrament was brought to her and left at home for her to use. After a few days, Helen learned to her pleasure that she had now entered the true Catholic Church, and that in a few days the pope himself would find out about her and send her some kind of paper.
Everything that was done during this time around her and with her, all this attention paid to her by so many intelligent people and expressed in such pleasant, refined forms, and the pigeon purity in which she now found herself (she wore all this time white dresses with white ribbons) — all this gave her pleasure; but because of this pleasure, she did not miss her goal for a moment. And as always happens that in a matter of cunning, a stupid person leads smarter ones, she, realizing that the purpose of all these words and troubles was mainly to convert her to Catholicism, to take money from her in favor of the Jesuit institutions (about which she hinted), Helen, before giving money, insisted that she be subjected to those various operations that would free her from her husband. In her conception, the significance of any religion consisted only in the fact that, in satisfying human desires, to observe certain decorum. And for this purpose, in one of her conversations with her confessor, she urgently demanded from him an answer to the question of the extent to which her marriage binds her.
They sat in the living room by the window. There were dusk. Flowers smelled from the window. Helen was wearing a white dress that showed through her shoulders and chest. The abbot, well-fed, but with a plump, smoothly shaven beard, a pleasant strong mouth and white hands folded meekly on his knees, sat close to Helen and with a thin smile on his lips, peacefully — admiring her beauty with a look from time to time looked at her face and expounded his opinion to their question. Helen smiled uneasily, looked at his curly hair, smooth-shaven, blackening, full cheeks, and waited every minute for a new turn in the conversation. But the abbe, although obviously enjoying the beauty and intimacy of his companion, was carried away by the skill of his craft.
The reasoning of the leader of conscience was as follows. In ignorance of the significance of what you were undertaking, you took a vow of marriage fidelity to a man who, on his part, having entered into marriage and not believing in the religious significance of marriage, committed blasphemy. This marriage did not have the double meaning it should have. But in spite of that, your vow bound you. You backed off from him. What did you do with it? Peche veniel or peche mortel? [A venial sin or a mortal sin?] Peche veniel, because you did an act without ill intent. If you now, in order to have children, would enter into a new marriage, then your sin could be forgiven. But the question again splits in two: the first …
“But I think,” said Helen, suddenly bored, with her charming smile, “that I, having entered into the true religion, cannot be bound by what the false religion has imposed on me.
The directeur de conscience [Guardian of conscience] was amazed at this Columbus egg set before him with such simplicity. He admired the unexpected speed of his student’s progress, but he could not give up his labors of intellectually constructed edifice of arguments.
— Entendons nous, comtesse, [Let’s look at the matter, countess,] — he said with a smile and began to refute the reasoning of his spiritual daughter.Helen understood that the matter was very simple and easy from a spiritual point of view, but that her leaders were only making difficulties because they were afraid of how the secular authorities would look at this matter.
And as a result of this, Helen decided that it was necessary to prepare this matter in society. She aroused the jealousy of the old nobleman and told him the same thing as the first seeker, that is, she put the question in such a way that the only way to get rights to her was to marry her. The old important person was for the first minute as struck by this proposal to marry a living husband as the first young person; but Helen’s unshakable conviction that it was as simple and natural as the marriage of a girl had an effect on him. If even the slightest sign of hesitation, shame or secrecy in Helen herself were noticeable, then her case would undoubtedly have been lost; but not only were there no signs of secrecy and shame, but, on the contrary, she with simplicity and good-natured naivety told her close friends (and this was the whole of Petersburg) that both the prince and the nobleman had made an offer to her and that she loved both and was afraid to upset him. and another.
A rumor instantly spread throughout Petersburg not that Helen wanted to divorce her husband (if this rumor spread, very many would rebel against such an illegal intention), but a rumor spread directly that the unfortunate, interesting Helen was at a loss about which of the two she should marry. The question was no longer to what extent this was possible, but only which party was more profitable and how the court would look at it. There were indeed some inveterate people who did not know how to rise to the height of the question and saw in this plan a desecration of the sacrament of marriage; but there were few of them, and they were silent, while most were interested in questions about the happiness that befell Helen, and what choice is better. They didn’t talk about whether it’s good or bad to marry a living husband, because this question, obviously, had already been resolved for people smarter than you and me (as they said) and to doubt the correctness of the solution of the issue meant to risk showing their stupidity and inability live in the light.
Only Marya Dmitrievna Akhrosimova, who came to St. Petersburg that summer to meet with one of her sons, allowed herself to express her opinion, contrary to public opinion, directly. Meeting Helen at the ball, Marya Dmitrievna stopped her in the middle of the hall and, in the general silence, in her rough voice said to her:
— You have started getting married from a living husband. Do you think you’ve come up with something new? Beware, mother. It’s been invented for a long time. In all … … they do it that way. — And with these words, Marya Dmitrievna, with her usual formidable gesture, rolling up her wide sleeves and looking around sternly, passed through the room.
Although they were afraid of her, they looked at Marya Dmitrievna in Petersburg as a cracker, and therefore, from the words spoken by her, they noticed only a rude word and repeated it in a whisper to each other, assuming that this word contained all the salt of what was said.
Prince Vasily, who lately had especially often forgotten what he said, and repeated the same thing a hundred times, said every time he happened to see his daughter.
«Helene, j’ai un mot a vous dire,» he told her, pulling her aside and jerking her arm down. – J’ai eu vent de certains projets relatifs a… Vous savez. Eh bien, ma chere enfant, vous savez que mon c?ur de pere se rejouit do vous savoir… Vous avez tant souffert… Mais, chere enfant… ne consultez que votre c?ur. C’est tout ce que je vous dis. [Ellen, I need to tell you something. I’ve heard about some of the species regarding… you know. Well, my dear child, you know that your father’s heart rejoices that you … You endured so much … But, dear child … Do as your heart tells you. That’s my whole advice.] — And, always hiding the same excitement, he pressed his cheek to his daughter’s cheek and walked away.
Bilibin, who has not lost his reputation as the smartest person and was a disinterested friend of Helen, one of those friends that brilliant women always have, friends of men who can never turn into the role of lovers, Bilibin once in a petit comite [small intimate circle] said to his friend Helen view of the whole thing.
— Ecoutez, Bilibine (Helen always called friends like Bilibin by their last names), — and she touched his white ringed hand to the sleeve of his tailcoat. — Dites moi comme vous diriez a une s?ur, que dois je faire? Lequel des deux? [Listen, Bilibin: tell me, how would you tell your sister, what should I do? Which of the two?]
Bilibin gathered the skin over his eyebrows and thought about it with a smile on his lips.
“Vous ne me prenez pas en by surprise, vous savez,” he said. — Comme veritable ami j’ai pense et repense a votre affaire. Voyez vous. Si vous epousez le prince (it was a young man) — he bent his finger — vous perdez pour toujours la chance d’epouser l’autre, et puis vous mecontentez la Cour. (Comme vous savez, il y a une espece de parente.) Mais si vous epousez le vieux comte, vous faites le bonheur de ses derniers jours, et puis comme veuve du grand… le prince ne fait plus de mesalliance en vous epousant, [You don’t take me by surprise, you know. As a true friend, I have considered your case for a long time. You see: if you marry a prince, then you forever lose the opportunity to be the wife of another, and in addition, the court will be dissatisfied. (You know, kinship is involved here.) And if you marry the old count, then you will make up the happiness of his last days, and then … it will no longer be humiliating for the prince to marry the widow of a nobleman.] — and Bilibin loosened his skin.
– Voila un veritable ami! said Helen, beaming, once more touching Bilibip’s sleeve with her hand. Mais c’est que j’aime l’un et l’autre, je ne voudrais pas leur faire de chagrin. Je donnerais ma vie pour leur bonheur a tous deux, [Here is a true friend! But I love both and would not want to upset anyone. For the happiness of both, I would be ready to sacrifice my life.] — she said.
Bilibin shrugged his shoulders, expressing that even he could no longer help such grief.
«Une maitresse femme! Voila ce qui s’appelle poser carrement la question. Elle voudrait epouser tous les trois a la fois», [«Well done woman! That’s what is called firmly asking a question. She would like to be the wife of all three at the same time.] thought Bilibin.
“But tell me, how does your husband look at this matter?” he said, owing to the firmness of his reputation, not afraid to drop himself with such a naive question. Will he agree?
— Ah! Il m’aime tant! — said Helen, who for some reason thought that Pierre also loved her. – Il fera tout pour moi. [Oh! he loves me so much! He is ready for anything for me.]
Bilibin picked up the skin to indicate the forthcoming mot.
– Meme le divorce, [Even for a divorce.] – he said.
Ellen laughed.
Among the people who allowed themselves to doubt the legality of the proposed marriage was Helen’s mother, Princess Kuragina. She was constantly tormented by envy of her daughter, and now, when the object of envy was the closest to the heart of the princess, she could not come to terms with this thought. She consulted with a Russian priest about the extent to which divorce and marriage were possible with a living husband, and the priest told her that this was impossible, and, to her joy, pointed out to her the Gospel text, which (it seemed to the priest) directly rejected the possibility of marriage from a living husband.