BM Seer Facts & Questions from an Anonymous Sun Source

Sun Fire X4450 SPECjbb World Records

Friday May 09, 2008

Dave Dagastine's Blog covers Sun's two new SPECjbb2005 World Records on Sun's X64 systems. The Sun Fire X4450, 4-chip Xeon QC CPUs and Java SE 6 Update 6-P, now hold the 4-chip Multi-JVM World Record and the single-JVM x86 world record. see: http://blogs.sun.com/dagastine/entry/sun_java_on_intel_delivers1

Now one of the things I don't know is if my Sun colleages used a non-standard BIOS on this benchmark. I imagine my colleages did the same thing as the other vendors who benchmark Xeons on SPECjbb, so at least everyone is playing the same field. My personal opinion is that the BIOS should not be tuned differently for different benchmarks. But no one listens to me :)

Disclosure Statement

SPEC, SPECjbb reg tm of Standard Performance Evaluation Corporation. Sun Fire X4450 results submitted to SPEC. Other results as of 05/6/08 on www.spec.org. Sun Fire X4450 (4 chips, 16 cores, Sun JDK 6u6-p) SPECjbb2005 bops = 464355, SPECjbb2005 bops/JVM = 58044. Sun Fire X4450 (4 chips, 16 cores, Sun JDK 6u6-p) SPECjbb2005 bops = 464355, SPECjbb2005 bops/JVM = 58044. SPECjbb2005 bops = 389208, SPECjbb2005 bops/JVM = 389208.

[5] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 05:00AM May 09, 2008 by BM Seer in Benchmark Issues
Tags:

Configs used for SPECpower_ssj

Thursday May 08, 2008

Yet another SPECpower_ssj of a "different" configuration:

  • tiny memory: ONLY 4GB!
  • low GHZ CPU: only 2.83GHz QC
  • tiny config: only 1 chip!
Why do the servers that vendors publish on SPECpower_ssj2008 look so different from servers used on other benchmarks? See, this is the problem with NOT adding perf/watt on every benchmark as published. What can the industry learn from low-GHz small-memory configurations?

I a previous posting I mentioned that HP configurations used in other benchmarks have reasonable-sized memory and high-GHz CPUs, I'll dig up the same on IBM, or you can just look at the www.spec.org website yourself:
64GB: HP DL580 G5 (4 quad-core Xeon 2.933GHz)
64GB: HP DL585 G2 (4 dual-core Opteron 3GHz)
32GB: HP DL380 G5 (2 quad-core Xeon 2.66GHz)
32GB: HP DL380 (2 quad-core Xeon 3GHz)
32GB: HP BL685c (4 dual-core Opteron 3GHz)
32GB: HP BL460c (2 quad-core Xeon 3GHz)
for more see: http://blogs.sun.com/bmseer/entry/hp_dl580_g5_4_qc

It is so easy to measure watts on benchmarks that one publishes, Sun does it all of the time. Why other vendors not disclose their measured system wattages" Sun has shown them on UltraSPARC for YEARS!:
2008: UltraSPARC T2+
2007: UltraSPARC T2
2005: UltraSPARC T1 & T2000 blogs with power-performance
...and Sun is starting to show them on X64.

Disclosure statement:

IBM System x3200 M2 server achieved a Performance to Power Ratio of 1,054 overall ssj_ops/watt (one-chip quad-core Intel Xeon Processor X3360 (2.83GHz, 1 chip, 4 cores, 4 cores per chip, 2x6MB L2 cache, and 1333 MHz front-side bus), 4GB of DDR2 PC2-5300 FBD memory, IBM JavaTM 6 Runtime Environment, Microsoft Windows Server 2003 R2 Enterprise x64 Edition SP1. SPEC and the SPECpower are registered trademarks of the Standard Performance Evaluation Corporation. All results from www.spec.org as of 5/08/08.

Note: I got this info from the IBM website, as the report isn't up on SPEC.org yet. We'll all have to wait to find out measured watts @100% util on the 1-chip with only 4GB (!) configuration mentioned above. IBM didn't mention this in any of the press info or blogs.

Also how come no one jumps on IBM for lack of proper SPEC copyright information? IBM bloggers write:

    SPEC and the SPEC benchmark names are registered trademarks of the Standard Performance Evaluation Corporation.

[4] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 01:48PM May 08, 2008 by BM Seer in Benchmark Issues
Tags:

Single system world record TPC-H Sun SPARC Enterprise M9000 Sun and StorageTek 2540

Thursday May 08, 2008

The Sun SPARC Enterprise M9000 configured with SPARC VI processors, Sun StorEdge 2540 Arrays, and running Solaris 10 combined with Oracle 11g achieved World Record TPC-H performance of 118,573.3 QphH@1000GB for non-clustered systems.

The TPC-H result demonstrates that the Sun SPARC Enterprise M9000 can handle the increasingly large databases required of DSS systems. Oracle delivered 13 GB/sec during the benchmark. editorial note: IBM has never proven delivered IO rates? Why does IBM only resort to quoting un-obtainable peaks?

  • Why no single-system 4.7GHz or 5.0GHz Power6 on TPC-H? IBM has cluster results, this allows IBM to avoid comparisons to a single system.
  • The Sun SPARC Enterprise M9000 outperformed the next best competitor non-clustered system, the HP Integrity Superdome by 69%.
  • The Sun SPARC Enterprise M9000 outperformed the next best competitor non-cluster system, the HP Integrity Superdome by 18% on price/performance.
  • The Sun SPARC Enterprise M9000 outperformed the clustered IBM xSeries 346 by 122%.
  • The Sun SPARC Enterprise M9000 outperformed the clustered IBM xSeries 346 by 29% on price/performance.
  • Sun StorageTek 2540 Array disk configuration - the 20x ST2540 configuration in this benchmark delivered sustained rates of 13.7 GB/sec and showed linear scaling from 1 to 20 arrays.
  • This result demonstrates the effectiveness of Solaris 10 running Oracle 11g.
TPC-H @1000GB Single-system (non-cluster) Performance Chart

QphH = the Composite Metric (bigger is better), $/QphH = the Price/Performance metric (smaller is better)

System Metric
QphH		 3 Year
Total
Sys $		 $/QphH QppH QthH  
CPUs		 Storage
Amount
Sun SPARC Enterprise M9000 118,573.3 $2,772,675 $23.38 114,725.4 122,550.2 32 34.8 TB
HP Superdome 69,999.0 $2,008,168 $28.69 90,909.1 53,898.5 32 39.7 TB
HP Superdome 68,100.6 $4,008,065 $59.00 83,041.7 55,847.7 64 40.6 TB


System  
CPU		  
Cluster		 CPU
MHz		 CPU Operating System Database RDBMS+HW
Avail
date
Sun SPARC Enterprise M9000 32 N 2400 SPARC64 VI Solaris 10 Oracle 11g 09/10/2008
HP Superdome 32 N 1600 Itanium2 Windows Server 2003 SQL Server 2005 06/18/2007
HP Superdome 64 N 1600 Itanium2 HP-UX 11.i V2 Oracle 10gR2 01/18/2006

Benchmark Description

The TPC-H benchmark is a performance benchmark established by the Transaction Processing Council (TPC) to demonstrate Data Warehousing/Decision Support Systems (DSS). TPC-H measurements are produced for customers to evaluate the performance of various DSS systems. These queries and updates are executed against a standard database under controlled conditions. Performance projections and comparisons between different TPC-H Database sizes (100GB, 300GB, 1000GB, 3000GB and 10000GB) are not allowed by the TPC.

TPC-H is a data warehousing-oriented, non-industry-specific benchmark that consists of a large number of complex queries typical of decision support applications. It also includes some insert and delete activity that is intended to simulate loading and purging data from a warehouse. TPC-H measures the combined performance of a particular database manager on a specific computer system.

The main performance metric reported by TPC-H is called the TPC-H Composite Query-per-Hour Performance Metric (QphH@SF, where SF is the number of GB of raw data, referred to as the scale factor). QphH@SF is intended to summarize the ability of the system to process queries in both single and multi user modes. The benchmark requires reporting of price/performance, which is the ratio of QphH to total HW/SW cost plus 3 years maintenance. A secondary metric is the storage efficiency, which is the ratio of total configured disk space in GB to the scale factor.

Disclosure Statement:

Sun SPARC Enterprise M9000 118,573.3 QphH@1000GB, $23.38/QphH@1000GB, avail 09/10/08, HP Integrity Superdome 69,999.0 QphH@1000GB, $28.69/QphH@1000GB avail 06/18/07, HP Integrity Superdome 68,100.6 QphH@1000GB, $59.00/QphH@1000GB avail 01/18/06, IBM xSeries 346 QphH@1000GB, $32.80/QphH@1000GB, avail 02/14/05, TPC-H, QphH, $/QphH tm of Transaction Processing Performance Council (TPC). More info www.tpc.org.

A 128-core (32-node 4-core) IBM Power 570 cluster (4.7 GHz, 64 chips, 256 threads) with DB2 is the best overall system at 10TB (343,551 QphH@10000GB, 32.89$/QphH, configuration available 04/15/08, Results as of 5/07/08). Note: Do not divide this result by 32 to guess at single node performance, do not compare $/perf between different GB tests, these are not permitted by TPC rules!

Results Summary

  • Audited Results
    		•
  • Database Size:
    		•  1000 GB (Scale Factor 1000)
  • TPC-H Composite:
    		•  118,573.3 QphH@1000GB
  • Price/performance:
    		•  $23.38/QphH@1000GB
  • Available:
    		•  09/10/2008 for Oracle (Sun HW/SW available 05/02/2008)
  • Number of Systems:
    		•  One Sun SPARC Enterprise M9000
  • Total Number Processors:
    		•  32
  • Processor/MHz of Server:
    		•  SPARC VI 2400 MHz / 6MB L2 Cache
  • Storage:
    		•  34.8 Terabytes of disk
  • Database:
    		•  Oracle 11g
  • Operating System:
    		•  Solaris 10 Update 4
  • Total 3 year Cost:
    		•  $2,772,675
  • Other Performance Metrics
    		•
  • TPC-H Power:
    		•  114,725.4
  • TPC-H Throughput:
    		•  122,550.2
  • Database Load Time:
    		•  1:35:27

[0] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 06:17AM May 08, 2008 by BM Seer in Benchmark Issues
Tags:

Easy Google date range search with dropdown

Tuesday May 06, 2008

Want more from google like an easy date-range search dropdown on the main window? Check out this link: http://www.google.com/search?hl=en&q=HP+benchmark+watts&as_qdr=w&btnG=Search

To make this happen for any search term, first go to you normal www.Google.com. Then type search term in the normal box, then add
&as_qdr=d
to the end of the URL and press enter. The nice dropdown box appears.

[0] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 09:07AM May 06, 2008 by BM Seer in Misc
Tags:

VMmark performance & watt/performance

Wednesday Apr 30, 2008

Sun continues to show watts on a wide variety of benchmarks, first on UltraSPARC T1, T2, T2 Plus benchmarks on all kinds of SPEC benchmarks that don't require it! ...and Sun extends this to X64 on VMmark benchmark. Other vendors need to do the same!

I didn't know about this benchmark until I saw it here (personally I hope Sun continues to show Watt/performance data on everything, hint hint for the internal people): http://blogs.sun.com/ontherecord/entry/ibm_sun_fire_x4450_tops

4-chip 2.93GHz Quad-Core Intel Xeon, 64GB, standard BIOS: VMmark = 830watts

The Sun Fire X4450 server, running VMware Virtual Infrastructure 3 software, posted one of the best scores among all 16 core results – 12.23 @ 8 tiles, with an average power consumption of only 830W measured during the steady state of the benchmark.

Sun used a 64GB configuration, which makes sense because virtualisation is driving up memory sizes. Table with the current 4-socket 16-core results which all use 64GB of memory (4/28/08)

System Sk/Cr/Th Clock/CPU ESX watts Tiles Score
IBM x3850 M2 4/16/16 2.93 Xeon7350 3.5.0 ? 9 13.16
Sun Fire X4450 4/16/16 2.93 Xeon7350 3.5.0 830w 8 12.23
Dell PE R900 4/16/16 2.93 Xeon7350 3.5.0 1325w
watt calc		 8 12.23
HP DL580 G5 4/16/16 2.93 Xeon7350 3.0.2 1086w
watt calc		 8 11.54
More details and results at: http://www.vmware.com/products/vmmark/results.html

The Sun wattage measured on 2 hours benchmark steady state: Watts: min=788watt, max=850watts, avg=830watts.

In reality with the same CPU, and memory configuration, I really don't expect actual measured to be much different, but it would help if HP and Dell actually published measured watts.

Watt calc:
Dell's public power information on CPU & memory configurations used in their VMmark submission is from the Dell's Datacenter Capacity Planner found on this web site http://www.dell.com/content/topics/topic.aspx/global/products/pedge/topics/en/config_calculator?c=us&cs=555&l=en&s=biz) This shows a power consumption estimate of 1325watts using "Typical SPEC workload" (it is even higher with "Scientific" workload).

Watt calc:
HP's only public power information on CPU & memory configurations used in their VMmark submission is from the HP power calculator (http://h30099.www3.hp.com/configurator/powercalcs.asp). The tool produced power requirement of 1086watts at 115V with 95% CPU utilisation.

...but you get very different watts when you change the frequency, memory-size, and an very different power benchmark (can't compare SPEC to non-SPEC benchmarks).

4-chip 1.86GHz Quad-Core Intel Xeon, 16GB hacked BIOS: SPECpower_ssj2008 = 387 watts at 100% target load

Reading "HP ProLiant DL580 G5 server posts highest 4P result on the new SPECpower_ssj2008(TM) benchmark" brochure leaves one quite confused. HP does not specify processor GHz, Memory size, or the use of non-standard BIOS - why?. Take note SPEC members: you guys need to force that be clearly specified in the future, or you will just encourage confusion.

Also why doesn't HP benchmark four 2.93GHz QC with 64GB of memory with default (normal) BIOS settings? So the industry can see the wattage difference vs 1.86GHz QC with 16GB memory. The 2.93GHz QC 4-chip results (with 32GB to 64GB with normal BIOS) exist on performance benchmarks they should also exist on power-performance benchmarks.

I'd suggest SPEC require better disclosure of information and clearly show effects of CPU GHz and memory size. MEMORY SIZE makes a HUGE difference in watts. Again I plea to add power measurements and power-performance metrics to all performance benchmarks at full utilisation.

SPEC Disclosure statement

SPECpower_ssj2008: HP Proliant DL580 G5 (4-chip QC Xeon L7345 1.86GHz, 16GB), 546 overall ssj_ops/watt, 359523 ssj_ops and 387 watt at 100% target load, 255512 ssj_ops and 359 watt at 70% target load, and 71409 ssj_ops and 294 watt at 20% target load. SPEC, SPECpower reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org as of 12/11/07.

Issues?
http://blogs.sun.com/bmseer/entry/specpower_ssj2008_power_benchmark_needs
http://blogs.sun.com/bmseer/entry/hp_dl580_g5_4_qc

[1] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 12:16PM Apr 30, 2008 by BM Seer in Benchmark Issues
Tags:

MySQL article in Computer World

Monday Apr 28, 2008

New article: "Will Sun rise higher after MySQL deal?" by Cath Jennings
http://www.computerweekly.com/Articles/2008/04/25/230456/will-sun-rise-higher-after-mysql-deal.htm

Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 02:13PM Apr 28, 2008 by BM Seer in Misc
Tags:

IBM Power6 pricing - cores configured in systems are very expensive

Friday Apr 25, 2008

IBM finally let the truth out about their $70K/core pricing - and it is just as I said. Now you can do your own $/perf analysis. IBM has posted real prices publicly on the web. I've included those links and a summary of the cost breakdown for those expensive cores.

IBM p570 4-core 64GB Memory(667MHz) = $287K or $71K/core

  • $50.9K for base system (chassis, 2-sas disks, two 1600w power supplies, IO, ethernet, etc.) = $50.9K
  • $115.0K for 4-core of 4.7GHz CPUs (note: you have to buy the CPUs and then pay for activation: part#7380 4.7GHZ POWER6-2/0CORE 12 DDR2 2x$11,500, part#5403 ONE PROC (1-core) Activation fee FOR FC#7380 is 4x$23,000)
  • $121.2 for 64GB of 667MHz memory (note: you have to buy the memory and then pay for activation: part#5694 0/8GB DDR2 Memory(4X2GB) DIMMs - 8*$3,035, part#5680 Activation of 1GB DDR2 POWER6 64*$1,515)

IBM p570 8-core 128GB Memory(667MHz) = $553.8K or $69k/core

  • $81.4K base system (chassis, 2-sas disks, two 1600w power supplies, IO, ethernet, etc.)
  • $230.0K for 8-core of 4.7GHz CPUs (note: you have to buy the CPUs and then pay for activation: part#7380 4.7GHZ POWER6-2/0CORE 12 DDR2 4x$11,500, part#5403 1-core Activation fee FOR FC#7380 is 8x$23,000)
  • $242.4k for 128GB of 667MHz memory (note: you have to buy the memory and then pay for activation: part#5694 0/8GB DDR2 Memory(4X2GB) DIMMs - 16*$3,035, part#5680 Activation of 1GB DDR2 POWER6 128*$1,515)

IBM's official public links, found by Googling:

IBM p570 power6 4.7GHz pricing:
http://www-01.ibm.com/common/ssi/rep_ca/8/897/ENUS107-288/ENUS107288.PDF

IBM p595 power6 5.0GHz pricing:
http://www-01.ibm.com/common/ssi/rep_ca/7/897/ENUS108-257/index.html

OK, Its very very late now, so I don't have time to post the 4.2GHz and slower memory, but it really doesn't change the price story that much, anyway you can go to the links and find it yourself.

[5] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 05:04PM Apr 25, 2008 by BM Seer in Competitor Follies
Tags:

IBM funny comparisons...

Wednesday Apr 23, 2008

Just saw this posting on c0t0d0s0:

    IBM understands the art of nonsensical comparision to perfection. IBM Germany tries to convince the customers, that Sun is extremly expensive. Okay, at first: They use the oldest trick in their portfolio again. Comparing a new system with an old system. The p570 is a system introduced last year. The UltraSPARC IV+ with 1.8 GHz was introduced in August 2006. We´ve introduced the UltraSPARC T2 and the SPARC64-based system since.
Read the complete at:
http://www.c0t0d0s0.org/archives/4203-Benchmark-games-today-The-german-Power6-brings-the-truth-to-daylight-campaign.html

[30] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 04:00PM Apr 23, 2008 by BM Seer in Competitor Follies
Tags:

Uptime Institute has a whitepaper on Sun MD (Project Blackbox)

Friday Apr 18, 2008

The Uptime Institute has a whitepaper called "New Product Review: Self-Contained Computer Room in a Shipping Container from Sun Microsystems". You can find a link to this whitepaper at: http://uptimeinstitute.org/wp_pdf/(TUI3023)SunModularDataCenterOp_weblock.pdf

It talks about the design, their review, and the efficiency of the design.

Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 06:41AM Apr 18, 2008 by BM Seer in Wattage-Power
Tags:

HP's real story about power6

Thursday Apr 17, 2008

HP puts out various "real stories" about competitors. They have an updated one about the new IBM power6 systems. http://h71028.www7.hp.com/ERC/cache/107848-0-0-0-121.aspx

I'll try to comment on some of them:

    Fact 1 they state:
      IBM software experts have admitted that software already tuned for out-of-order version of POWER is, “no [sic] so good for in-order power6 processor.” “Maximizing Application Performance on POWER” IBM Linux on POWER GCC Team Lead, April 19, 2007, page 8, SW_Summit_gcc_and_tool_chain_Peter.pdf
    If you don't understand the issues with"out-of-order", what you can take away is that not every technology that you hear hyped by vendors will give you a true advantage when you look at whole system performance on real applications.

    Fact 2 & 3: shows that adding GHz doesn't add delivered performance but it does add a disproportionate number of watts. IBM p 595 (POWER6) 27,500 watts max for 64 cores. 27500w/64-core = 430watts/power6-core

      The max rated system electrical load for the POWER6-595 server has increased nearly 5000 watts over the POWER5-p595 for the same number of processors.(ENUS108-257)
    Then they go on to compare multi-threaded server chips with a 1-job benchmark. I don't know why they didn't compare on server benchmark SPECrate_int2006, maybe when you test these as servers you see real differences. Let's look at the latest 2-chip results for Itanium2, power6, and UltraSPARC T2 Plus:

    A 2-chip Sun SPARC Enterprise T5240 server, running the UltraSPARC T2 Plus processor at 1.4 GHz, beat the 2-chip IBM 4.7GHz POWER6-based p570 by 29% on the SPECint_rate2006 benchmark, and also beat the 2-chip HP 1.66GHz Itanium-based Integrity rx2660 by 2.5 times on the SPECint_rate2006 benchmark.

    Fact 4: shows IBM is raising its software prices.

    Fact 5: HP states that AIX 6.1 will be needed to more fully exploit POWER6, and then asks: how many ISV applications are certified for AIX 6.1?

For more on the latest SPECint_rate 2006 results see: http://blogs.sun.com/bmseer/entry/2_chip_spec_cpu2006_rate

For more on prices on small 4-core IBM: http://blogs.sun.com/bmseer/entry/some_ibm_power6_actual_prices

I haven't seen anything on IBM p 595 power6 prices 64-core 5GHz, if you have any pointers please post in the comments.

Disclosure statement:
SPEC, SPECint reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC, other results from www.spec.org as of 4/7/08. Sun SPARC Enterprise T5240 (UltraSPARC T2 Plus, 2 chips, 16 cores), 157 SPECint_rate2006; IBM p 570 (POWER6, 2 chips, 4 cores), 122 SPECint_rate2006, HP Integrity rx2660 (Itanium2, 2-chip, 1.66GHz/18MB), 62.8 SPECint_rate2006.

[11] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 07:37AM Apr 17, 2008 by BM Seer in Competitor Follies
Tags:

UltraSPARC T2 Plus: try it yourself on Web, Appl, & Database

Monday Apr 14, 2008

In the last week this blog had talked a lot about the great performance of the SPARC Enterprise T5140 and T5240 servers.

But forget the leading performance, price/performance, watt/perf results, if you want to try it for yourself you can. Sun continues its try-and-buy program and extends it to the new Sun SPARC Enterprise T5140 and T5240 servers.

Free 60-day trial program. You pay nothing (Sun even pays the shipping), for details see: http://www.sun.com/tryandbuy/index.jsp (scroll down to find T5240/T5140)

Reminder: Summary of technical index of CMT blogs @ Allan Packer's blog:
http://blogs.sun.com/allanp/entry/sun_s_cmt_goes_multi

I've had several talks with friends at different competitors, and they said they didn't think Sun had it in it to really make a breakthrough in performance, price, and power -- but now they all talk about high-level meetings in their companies (competitors) who are frantically trying to figure out how to counter Sun's offering.

[1] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 12:18PM Apr 14, 2008 by BM Seer in Benchmarks
Tags:

Summary of new CMT

Monday Apr 14, 2008

For a survey of the wide variety of blogs with good technical data on the new UltraSPARC T2 Plus servers (Sun SPARC Enterprise T5240, Sun SPARC Enterprise T5140,...), please look at Allan Packer's blog index at:
http://blogs.sun.com/allanp/entry/sun_s_cmt_goes_multi

Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 08:25AM Apr 14, 2008 by BM Seer in Benchmark Issues
Tags:

Datacenter Throughput is King: SPEC CPU2006 Rate Blade System World Record: Sun Blade 6000 w/T6320

Friday Apr 11, 2008

What most people forget, is that datacenters are really throughput engines. I don't know any datacenter (besides home ones) that only use one thread or one core. When you look at racks of servers in a datacenter, you are looking at thousands of threads! Which means 10,000 to 100,000 or more in a complete datacenter. Lots of work to be done, lots of threads doing it!

Sun has announced blade system world record results for SPECint_rate2006 and SPECfp_rate2006. These results were run on the Sun Blade 6000 system with 10 Sun Blade T6320 server modules which use the 1.4 GHz UltraSPARC T2 processor.

The Sun Blade 6000 system fully populated with 10 T6320 server modules delivered a SPECint_rate2006 score of 838, a world record result for blade systems.

The Sun Blade 6000 system (10 RUs) powered by 10 Sun UltraSPARC T2 1.4 GHz processors provides 73% more integer throughput than the IBM p 570 (16 RUs) equipped with 8 POWER6 4.7 GHz processors, as measured by SPECint_rate2006.

The Sun Blade 6000 system fully populated with 10 T6320 server modules delivered a blade system world record SPECfp_rate2006 score of 571.

Sun has chosen to submit a single run as both SPECfp_rate_base2006 and SPECfp_rate2006, (which is allowed under the run rules), in order to emphasize that even without aggressive tuning, the score of 571 is a record for both base and peak.

The Sun Blade 6000 system powered by 10 Sun UltraSPARC T2 1.4 GHz processors provides 73% more floating-point throughput than the IBM p 570 equipped with 8 POWER6 4.7 GHz processors, as measured by SPECfp_rate_base2006.

The IBM p 570 system (16RU) uses 1.6x times more rack units than the 10RU Sun Blade 6000 system(16 RU vs. 10 RU).

SPEC CPU2006 Performance Charts - bigger is better, selected recent results

SPECint_rate2006

Please see www.spec.org for complete results

System Processors Performance Results
Type GHz Chips Cores Threads Peak Base
Sun B6000 w/10 x T6320 UltraSPARC T2 1.4 10 80 640 838 752
HP Superdome Itanium 2 1.6 32 64 64 824 770
Sun M9000 SPARC VI 2.4 32 64 64 650 553
IBM p 570 POWER6 4.7 8 16 32 484 420

Results as of 7 Apr 2008 from www.spec.org.

SPECfp_rate2006

Please see www.spec.org for complete results or for just SPECfp_rate2006 results ordered by peak score.

System Processors Performance Results
Type GHz Chips Cores Threads Peak Base
Sun M9000 SPARC VI 2.4 32 64 64 600 556
Sun B6000 w/10 x T6320 UltraSPARC T2 1.4 10 80 640 571 571
IBM p 570 POWER6 4.7 8 16 32 430 369
HP rx8640 Itanium 2 1.6 16 32 32 371 357

Results as of 7 Apr 2008 from www.spec.org.

Benchmark Description<

SPEC CPU2006 is made up of two suites of benchmarks, CFP2006 and CINT2006. CFP2006 targets floating-point performance, while CINT2006 targets integer performance.

Each suite has two different measures. First is the CPU measure, which is the performance on the suite as a single stream. This can be either a single thread or automatic compiled parallel run. This measure is further defined by base and optimized runs. Base uses the same compiler flags for all kernels, where optimized is allowed to use different compiler flags for each kernel. Results are compared against a baseline system run that was standardized by SPEC.

The second measure is Rate. It is a measure of how many CPU measures can be run at a time. Typically, it is run as n processes on n processors. It shows how well the same job mix can run on a system under some load. It also is run as a base and optimized set of results.

Disclosure Statement:

SPEC, SPECint reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC, other results from www.spec.org as of 4/7/08. Sun Blade T6320 (UltraSPARC T2, 10 chips, 80 cores), 838 SPECint_rate2006, 752 SPECint_rate_base2006.

SPEC, SPECint reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC, other results from www.spec.org as of 4/7/08. Sun Blade T6320 (UltraSPARC T2, 10 chips, 80 cores), 838 SPECint_rate2006, 752 SPECint_rate_base2006. IBM p 570 (POWER6, 8 chips, 16 cores), 484 SPECint_rate2006, 420 SPECint_rate_base2006.

SPEC, SPECfp reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC, other results from www.spec.org as of 4/7/08. Sun Blade T6320 (UltraSPARC T2, 10 chips, 80 cores), 571 SPECfp_rate2006, 571 SPECfp_rate_base2006.

SPEC, SPECint reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC, other results from www.spec.org as of 4/7/08. Sun Blade T6320 (UltraSPARC T2, 10 chips, 80 cores), 571 SPECfp_rate_base2006. IBM p 570 (POWER6, 8 chips, 16 cores), 369 SPECfp_rate_base2006.

Results Summary

Results
Reference Date: Apr 7, 2008
System: Sun Blade 6000 with 10 T6320 Modules
Processor: 10 Sun UltraSPARC T2, 1.4 GHz
  838 SPECint_rate2006
  752 SPECint_rate_base2006
  571 SPECfp_rate2006
  571 SPECfp_rate_base2006
Software: Solaris 10, Sun Studio 12 Compiler gccfss

[2] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 08:24AM Apr 11, 2008 by BM Seer in Benchmarks
Tags:

UltraSPARC T2 Plus: Designed for Web, App, & Database

Friday Apr 11, 2008

To see under the covers and the design of the amazing UltraSPARC T2 Plus based systems check out this great blog: http://blogs.sun.com/deniss/date/20080410. More postings to come on this great product. Remember it is delivered-system-performance that is key. A couple of warnings about the results of others:

  • Check the prices for the configs as benchmarked (especially watch up out for entry level pricing as realistic configs on competitors can cost 2x to 10x more when configured with the fastest processors and full fast memory)
  • Watch out for performance per widget metrics. Some things you can see (servers) some things you can't see (cores). Especially as some cores are extremely expensive and this totally throws of any advantage of per-core performance.
  • Watch for benchmarks that aren't published (I'm still waiting for IBM p570 4-core & 8-core stream performance or LMbench.
  • Watch out for 1.xGhz published on one benchmark and 2.xGHz published for performance.

Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 06:46AM Apr 11, 2008 by BM Seer in Benchmarks
Tags:

Dual Chip World Record, SPEC OMP2001: Sun SPARC Enterprise T5240

Thursday Apr 10, 2008

The Sun SPARC Enterprise T5240 server delivers the best performance on the SPEC OMPM2001 benchmark for two chips. These results were run on the Sun SPARC Enterprise T5240 server using the UltraSPARC T2 Plus processor running at 1.4 GHz.

The Sun SPARC Enterprise T5240 server running the UltraSPARC T2 Plus processor at 1.4 GHz, beat all dual chip scores running SPECompM2001 with a score of 25488.

The Sun SPARC Enterprise T5240 server running the UltraSPARC T2 Plus processor at 1.4 GHz, beat all dual chip scores running SPECompM_base2001 with a score of 21145.

The Sun SPARC Enterprise T5240 server running at 1.4 GHz beat the best IBM dual chip result (POWER6) by 25% on the SPECompM2001 benchmark.

SPEComp2001 Performance Chart - SPECompM2001 (bigger is better)

Select 2 chip or less results ordered by peak metric.

Result Chips Cores OpenMP
Thrds		 System
Peak Base
25488 21145 2 8 128 Sun SPARC Enterprise T5240, UltraSPARC T2 Plus, 1.4GHz
20443 18950 2 4 8 IBM p 520, POWER6, 4.2 GHz
19983 15355 2 4 8 IBM p5 550, POWER5+, 2.1 GHz
19688 17980 2 4 8 IBM JS22, POWER6, 4.0 GHz
19568 18218 2 4 8 IBM JS22, POWER6, 4.0 GHz
16208 14399 1 8 63 Sun SE T5120/T5220, US T2, 1.4 GHz

Benchmark Description

The SPEC OMPM2001 Benchmark Suite was released in June 2001 and tests HPC performance using OpenMP for parallelism.

  • 11 programs (3 in C and 8 in Fortran) parallelized using OpenMP API
Goals of suite:
  • Targeted to mid-range (4-32 processor) parallel systems
  • Run rules, tools and reporting similar to SPEC CPU2000
  • Programs representative of HPC and Scientific Applications

Disclosure Statement:

SPEC, SPEComp reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC. Other results from www.spec.org as of 4/6/08. Sun SPARC Enterprise T5240 (2 chips, 16 cores, 128 threads, 1.4GHz) 25488 SPECompM2001.

SPEC, SPEComp reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC. Other results from www.spec.org as of 4/6/08. Sun SPARC Enterprise T5240 (2 chips, 16 cores, 128 threads, 1.4GHz) 21145 SPECompM_base2001.

SPEC, SPEComp reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC. Other results from www.spec.org as of 4/6/08. Sun SPARC Enterprise T5240 (2 chips, 16 cores, 128 threads, 1.4GHz) 25294 SPECompM2001. IBM p 520 (2 chips, 4 cores, 8 threads, 4.2GHz) 20443 SPECompM2001.

Results Summary

Result
Sun SPARC Enterprise T5240: 25488 SPECompM2001
  21145 SPECompM_base2001
Reference Date: Apr 09, 2008
Operating System: Solaris 10 8/07
Compiler: Sun Studio 12

[2] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 09:54AM Apr 10, 2008 by BM Seer in Benchmarks
Tags: