Friday Dec 08, 2006
Here is a processor wattage chart, but notice that Intel has the memory controller off chip so you need to add 30-35 watts to this figures
(opteron includes this on chip)
http://www.intel.com/products/processor_number/chart/xeon.htm
For more details on power budget breakdown I got pointed to these
two pages for an AMD comparison (looks like it is part of a bigger preso?, no confidential statement):
http://www.amd.com/us-en/assets/content_type/DownloadableAssets/opt_vs_wc_8_dimms.pps
http://www.amd.com/us-en/assets/content_type/DownloadableAssets/4_opt_vs_4_pax.pps
Thursday Dec 07, 2006
More details on power budget differences that give Opteron at least a 34% lead
over Woodcrest.
I gave some basics of this in this posting:
http://blogs.sun.com/bmseer/entry/design_strategies%3A_wattage_advantage_of
Woodcrest power budget: Dual-core Xeon's : 160 watts per socket (80w each) PLUS 44.8 watts for chipset (incl memory controllers) PLUS 66.4 watts
166.4 watts FBDIMM (16 DIMMs).
{{typo corrected: yes FB-DIMMs suck an amazing 170 watts for 16 DIMMs -- that's nearly 100watts more than DDR2. That is why Intel-based systems only report wattage on small memory configs, but still use the same large memory configs for various benchmarks.}}
Opteron power budget: Dual-core Opteron's: 190 watts socket (95w max each) PLUS 16 watts for chipset PLUS 70.4 watts for DDR2 (16 DIMMs).
...and this is just looking at just the chips -- and not adding the typical
controllers you'd have for a functioning system like disk , network, etc...
Tuesday Dec 05, 2006
Some things to look at when you seen marketing around wattage. You
can avoid errors by really looking at total measured wattage when systems
running and doing real work. I've seen a lot of Intel marketing about
wattage of Woodcrest being 65 watts. But that really doesn't show the
whole picture. I'll break it down a bit...
What GHz at what wattage?:First recognize that Woodcrest
2.66 GHz & 2.33 GHz is 65 watts for chip only, but Woodcrest at 3.0 GHz
is 80 watts. ...and all benchmarks I've seen is on the 80 watt 3.0 GHz
systems.
What about the memory controller?: The CPU isn't everything.
Woodcrest designs have an external memory controller. Opteron designs have
an integrated memory controller. So you need to add another 30 watts (or more)
for the pair of Woodcrest CPUs.
What about the memory technology differences?: The CPU+Memory_controller
isn't everything. Woodcrest designs use FB-DIMMs. Opteron designs use the
more power efficient DDR2. FB-DIMMS draw a lot more power. In fact, as
I've blogged about before, 32GB 2-socket Woodcrest system draws 500 watts!
Measured when the CPU is busy. Sun's Opteron systems is way over 100 watts less.
Every IT department I talk to really wants to cut cost out -- power consumption
is a growing a major factor in IT costs.
...this just in...
Sun is now shipping a wattage meter with the "Try-and-buy" program for
Sun Fire T2000. More details at:
http://blogs.sun.com/cohen/entry/kill_a_watt_--_power
Thursday Nov 16, 2006
The Sun Ultra 40 M2 Workstation demonstrates a new World Record integer throughput
performance for all x86 systems, sets a new world record on the
new and improved SPEC cpu benchmark called "SPECint_rate2006." It fixes
things like SPECint_rate2000 has/had floating-point applications in the integer suite, whaaaat? yes
strange but true.
The Sun Ultra 40 M2 delivered the SPECint_rate2006 score of 48.8, using
Solaris 10 and Studio 11 combination. Sun's Opteron beats Woodcrest by 7%.
As you can see below 'Peak' means
you add a few more compiler flags. I guess Woodcrest didn't have any
others to try on Woodcrest or maybe they saw no improvement so they avoided
publishing? Anyone know?
Competitive Landscape
Selected SPEC CPU2006 (SPECint_rate2006) Performance Results -
bigger is better, see
www.spec.org for complete results.
| System |
Processors |
Performance Results |
| Type |
GHz |
Chips |
Cores |
Threads |
Peak |
Base |
| Sun Ultra 40 M2 |
AMD Opteron 2220SE |
2.8 |
2 |
4 |
4 |
48.4 |
41.9 |
| HP DL585 |
Opteron 854 |
2.8 |
4 |
4 |
4 |
46.9 |
41.4 |
| Supermicro X7DBE |
Woodcrest, Xeon 5160 |
3.0 |
2 |
4 |
4 |
--- |
45.2 |
| Sun Fire X4200 |
Opteron 285 |
2.6 |
2 |
4 |
4 |
42.8 |
37.8 |
| Fujjitsu RX220 |
Opteron 280 |
2.4 |
2 |
4 |
4 |
40.0 |
35.7 |
| Sun Fire X4200 |
Opteron 256 |
3.0 |
2 |
2 |
2 |
26.4 |
23.1 |
| HP DL585 |
Opteron 854 |
2.8 |
2 |
2 |
2 |
25.2 |
22.3 |
| Dell PrecWork 380 |
Pentium EE |
3.73 |
1 |
2 |
2 |
-- |
23.1 |
| HP DL380 G4 |
Pentium 4 |
3.8 |
2 |
2 |
2 |
-- |
20.9 |
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 www.spec.org.
The second measure is Rate. I think this one is a LOT more important. 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 or threads. 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. "Rate" is what you use for any mult-threaded workstation and
all servers.
Disclosure Statement:
SPEC, SPECint reg tm of Standard Performance Evaluation Corporation.
Results from www.spec.org as of 11/14/06. Sun Ultra 40 M2, 48.8 SPECint_rate2006.
System Configuration
- Sun Ultra 40 M2
- 2 x 2.8 GHz Opteron 2220SE
- 16GB memory
- Solaris 10
- Sun Studio 11
- 48.8 SPECint_rate2006
Wednesday Nov 15, 2006
As mentioned in the posting earlier today, scalability is important factor in system performance. Woodcrest's poor scaling may not bode well for
Cloverton. Sure you can package for threads onto a module, but unless you design for them you'll just have more threads not delivering performance but just burning more watts.
Wattage: I'll get detailed wattage results posted soon, but it looks like
as we mentioned Opteron performance is about 20% more than Woodcrest. The
wattage for both configurations looks the same. Therefore expect Sun's
Opteron to have about 20% perf/watt advantage.
Sun's Fluent results will be posted shortly on the website, it is a busy
week with Supercomputing conference and lots of busy people. So keep
checking back. A few of the smaller gave Woodcrest a small percent advantage, but most were significantly faster on Sun's Opteron.
...maybe Woodcrest will have better idle power, but why in the world would
you buy the latest server and leave it idle?
Wednesday Nov 15, 2006
Woodcrest scaling issues? Yes, remember scaling is critical for
system performance, so don't look too much at single core performance or single job performance as it can lead to the wrong conclusions. In fact Sun's Opteron scaling means that the Sun systems can outperform Woodcrest by 18% to 22% as shown below.
On a 4 core/2chip
Intel Woodcrest systems they are only seeing 2.8x to 2.9x on 4 cores -- this doesn't bode well for quad-core or larger systems made out of these. Sun sees 3.6x to 4.1x scaling in the table below. Couple this with the high-wattage of these Woodcrest (31-Oct posting) and Woodcrest may have issues?
Opteron leads poor Woodcrest scaling & performance on Fluent 6 Benchmark (Both systems 2 sockets and using dual-core)
| System |
GHz/Chip |
#cores |
FL5M3 (scaling) |
FL5L2 (scaling) |
| INTEL S5000XAL |
3.0GHz Xeon Woodcrest 5160 |
4-core |
827.0 (2.8x) |
400.0 (2.9x) |
| INTEL S5000XAL |
3.0GHz Xeon Woodcrest 5160 |
2-core |
553.7 (1.9x) |
226.0 (1.6x) |
| INTEL S5000XAL |
3.0GHz Xeon Woodcrest 5160 |
1-core |
297.3 (1.0x) |
138.0 (1.0x) |
| Sun |
| Sun X4100 M2 |
2.8GHz Opteron DC 2200 |
4-core |
979.9 (3.6x) |
486.6 (4.1x) |
| Sun X4100 M2 |
2.8GHz Opteron DC 2200 |
2-core |
516.1 (1.9x) |
241.8 (2.1x) |
| Sun X4100 M2 |
2.8GHz Opteron DC 2200 |
1-core |
273.5 (1.0x) |
117.6 (1.0x) |
Rating = No. of sequential runs of test case possible in 1 day,
86,400/(Total Elapsed Run Time in Seconds)
Fluent results at:
http://www.fluent.com/software/fluent/fl5bench/flbench_6.2/fullres.htm
...I suspect even better performance and scaling on Sun Fire X4100 M2
with Solaris...
Tuesday Nov 14, 2006
Sun Ultra 40 M2 w/2xFX 5500 nVidia Framebuffers (SLI)
World Record Performance SPECapc Unigraphics UGS-NX3
The Sun Ultra 40 M2 with dual nVidia Quadro FX 5500s
in SLI mode sets a world record running the SPEC APC
UGS-NX3 graphics oriented MCAD benchmark beating all desktop platforms, including the Woodcrest and Intel Core2 "Extreme Processor" X6800 cpu's.
The SPEC APC MCAD benchmarks consist of tasks
representative of what a designer would do in a typical
session. This consists of "Graphics", "CPU", and "I/O" activities.
- In dual framebuffer SLI mode the Ultra 40 M2 with 2.8GHz
2220SE dual core Opteron processors outperforms a
Dell 690 (3.0 GHz Woodcrest) by 14% overall and by 37% in
the graphics test components.
- In addition, in dual framebuffer SLI mode the existing
Ultra 40 outperforms the Dell 690 (Woocrest 3.0 GHz)
by 16% overall and by 61% in the graphics component.
The Ultra 40 with 3.0 GHz single core
Opteron 256 processors (400 MHz DDR1 dimms) versus
the 2.8 GHz dual core Opteron 2220SE processors
(667 MHz DDR2 dimms), edging the
Ultra 40 M2 by about 1%.
The Sun Ultra 40 with a single nVidia Quadro FX 5500
outperforms most other high end desktops equipped with
a single framebuffer with currently posted results
obtained running the SPEC APC UGS-NX3 benchmark.
- The Sun Ultra 40 with FX 5500 framebuffer
outperforms (is faster than) Woodcrest desktops.
H-P XW 6400 (4% overall, 39% on graphics);
Dell Precision 690 (9% overall, 52% on graphics);
IBM Intellistation Z Pro 9228 (14% overall, 62% on graphics)
- The Sun Ultra 40 with FX 5500 framebuffer also outperforms
all desktops equipped with the Intel 2.93 GHz X6800
"Extreme Processors".
H-P XW 4400 (6% overall, 47% on graphics);
Dell Precision 390 (10% overall, 47% on graphics)
Sun Opteron desktops have dominated with leading
MCAD benchmark results dating back to the introduction
of the Sun W1100 and W2100.
Sun desktops continue to exhibit excellent MCAD performance
as demonstrated by the world record results here for this
SPEC APC UGS-NX3 benchmark.
SPECapc Unigraphics NX 3 Benchmark Competitive Landscape (larger is faster):
| System |
Overall
Composite |
CPU
Composite |
File I/0
Composite |
Graphics
Composite |
Sun Ultra 40
3.0GHz Opteron 256
2x FX 5500 (SLI) |
7.28 |
2.94 |
2.85 |
19.81 |
Sun Ultra 40 M2
2.8GHz Opteron 2220SE
2x FX 5500 (SLI) |
7.19 |
3.08 |
3.00 |
16.85 |
Fujitsu Siemens CELSIUS
3.0GHz Intel 5150
FX 5500 |
6.42 |
3.67 |
2.28 |
10.17 |
Dell Precision 690
3.0GHz Woodcrest
2x FX 4500 (SLI) |
6.30 |
3.25 |
1.64 |
12.29 |
Sun Ultra 40
3.0GHz Opteron 256
FX 5500 |
5.66 |
2.94 |
1.96 |
10.11 |
HP xw6400 WS
3.0GHz Woodcrest
FX 4500 |
5.42 |
3.39 |
3.51 |
7.26 |
HP xw4400
2.93GHz X6800
FX 3500 |
5.33 |
3.40 |
4.52 |
6.87 |
Dell Precision 690
3.00 GHz Woodcrest
FX 3500 |
5.17 |
3.38 |
3.69 |
6.64 |
Dell Precision 390
2.93 GHz X6800
FX 3500 |
5.16 |
3.46 |
2.18 |
6.87 |
IBM Intellistation Z Pro 9228
3.0GHz Woodcrest
FX 3500 |
4.96 |
3.43 |
2.84 |
6.23 |
Results Summary for the SPECapc Unigraphics NX 3 benchmark:
| Results |
|
|
|
Dual
FX 5500 |
|
Dual
FX 5500 |
|
Overall Composite: |
|
7.19 |
|
7.28 |
|
CPU Composite: |
|
3.08 |
|
2.94 |
|
File I/O Composite: |
|
3.00 |
|
2.85 |
|
Graphics Composite: |
|
16.85 |
|
19.81 |
| Reference Date: |
|
11/10/06 |
|
10/12/06 |
| System: |
|
Sun Ultra U40 M2 |
|
Sun Ultra U40 |
| Processor/GHz: |
|
Opteron 2220SE/2.8 |
|
Opteron 256/3.0 |
Disclosure Statement:
SPEC reg tm, SPECapc server mark of Standard Performance
Evaluation Corporation.
Results from www.spec.org as of Oct 12, 2006:
Sun Ultra 40, 2xFX 5500, overall composite 7.28;
Dell Precision 690, 2xFX 4500, overall composite 6.30.
Results from www.spec.org as of Oct 12, 2006:
Sun Ultra 40, FX 5500, overall composite 5.66;
HP xw6400, FX 4500, overall composite 5.42;
Dell Precision 690, FX 3500, overall composite 5.17;
IBM Intellistation Z Pro 9228, FX 3500, overall composite 4.96.
Results from www.spec.org as of Nov. 8, 2006:
Fujitsu Siemens CELSIUS, FX 5500, overall composite 6.42.
Results from www.spec.org as of Nov 10, 2006:
Sun Ultra 40 M2, 2xFX 5500, overall composite 7.19.
Results from www.spec.org as of Oct 12, 2006:
Sun Ultra 40, FX 5500, overall composite 5.66;
HP xw4400, FX 3500, overall composite 5.33;
Dell Precision 390, FX 3500, overall composite 5.16.
|
|
|
|
Do you notice on the Xeon 7000 series (NetBurst ba...