BM Seer Unofficial thoughts from an anonymous Sun employee

SPEC CPU2006 UltraSPARC T2 exactly real just like we said

Tuesday Oct 09, 2007

Today, Sun submitted the SPECint_rate2006 and SPECfp_rate2006 Single-Chip World Records on the Sun SPARC Enterprise T5120/T5220. What are these servers? UltraSPARC T2 1.4GHz servers that you will hear loads more on today.

The Sun SPARC Enterprise T5120 is the 1RU version, and the Sun SPARC Enterprise T5220 is the 2RU version, both of these servers are electronically equivalent with the 2RU having a bit more connectivity and storage if you need.

The Sun SPARC Enterprise T5220 server, running at 1.4 GHz, beat all single-chip results running SPECint_rate2006 with a result of 78.5.

The Sun SPARC Enterprise T5220 server beats the best single IBM 4.7 GHz dual-core POWER6 processor result by 29% and beat the best published single 3 GHz Xeon quad-core by 28% on SPECint_rate2006. There are no single quad-core Opteron results published for SPECint_rate2006.

"but I've heard there is no floating point on Niagara processors :) Nay, the 1.4GHz UltraSPARC T2 in the Sun SPARC Enterprise T5220 server, beat all single-chip results running SPECfp_rate2006 with a result of 62.3.

The Sun SPARC Enterprise T5220 server beat the best single IBM 4.7 GHz POWER6 processor based system result by 7% and beats the best published single 3 GHz quad-core Intel Xeon by 61% for SPECfp_rate2006.

There are no single quad-core Opteron results published for SPECfp_rate2006.

SPEC CPU2006 Performance Charts - bigger is better, selected recent results, please see www.spec.org for complete results.

SPECint_rate2006

System Procs Perf Results
Type GHz Chips
Cores		 Threads Peak Base
T5120/T5220 UltraSPARC T2 1.4 1, 8 64 78.5 73.0
HP DL380 G5 Intel X5365 3.0 1, 4 4 61.3 53.8
IBM p 570 Power6 4.7 1, 2 4 60.9 53.2
Fujitsu RX300 Intel X5355 2.66 1,4 4 52.8 50.5

SPECfp_rate2006

System Processors Performance Results
Type GHz Chips, Cores Threads Peak Base
T5120/T5220 UltraSPARC T2 1.4 1, 8 64 62.3 57.9
IBM p 570 Power6 4.7 1, 2 4 58.0 51.5
HP DL380 G5 Intel X5365 3.0 1, 4 4 38.8 36.4
Fujitsu RX300 Intel X5355 2.66 1, 4 4 37.5 36.2

Results as of 27 Sep 2007 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 9/27/07. Sun SPARC Enterprise T5220/T5120 (UltraSPARC T2, 1 chip, 8 cores), 78.5 SPECint_rate2006, IBM p570 (POWER6, 1 chip, 2 cores), 60.9 SPECint_rate2006, HP DL380 G5 (X5365, 1 chip, 4 cores), 61.3 SPECint_rate2006, Sun SPARC Enterprise T5220 (UltraSPARC T2, 1 chip, 8 cores), 62.3 SPECfp_rate2006.

SPEC, SPECfp reg tm of Standard Performance Evaluation Corporation. Sun result submitted to SPEC, other results from www.spec.org as of 9/27/07. Sun SPARC Enterprise T5220/T5120 (UltraSPARC T2, 1 chip, 8 cores), 62.3 SPECfp_rate2006. IBM p570 (POWER6, 1 chip, 2 cores), 58.0 SPECfp_rate2006, Sun SPARC Enterprise T5220 (UltraSPARC T2, 1 chip, 8 cores), 62.3 SPECfp_rate2006. HP DL380 G5 (X5365, 1 chip, 4 cores), 38.8 SPECfp_rate2006.

System Configuration

Results
Reference Date: Oct 09, 2007
System: Sun SPARC Enterprise T5120/T5220
Processor: Sun UltraSPARC T2, 1.4 GHz
  78.5 SPECint_rate2006
  62.3 SPECfp_rate2006
Software: Solaris 10, Sun Studio 12 Compiler

[6] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 08:47AM Oct 09, 2007 in Benchmarks
Tags:
Comments:

Nice results!
I think your second table is messed up a bit.

Dmitri

Posted by Dmitri Trembovetski on October 09, 2007 at 08:56 AM PDT #

Great (technically) product at absolutely ridiculous price.
I can buy 2 CPU quad-core Intel or AMD x64 server that'll be both faster (in most apps) and at least 5 TIMES (!!!) cheaper that Sun's list price.
How can I possibly justify buying it???

Posted by I on October 09, 2007 at 09:34 AM PDT #

In terms of pricing, take those X64 boxes get the latest prices and 32GB or 64GB of memory and recheck pricing and watch it rise by 5x. My boss just bought a competitive server for a project I need to start, with full memory and latest processors it cost a LOT of money.

Whoops, I'll fix the table.

Posted by BM Seer on October 09, 2007 at 09:57 AM PDT #

>get the latest prices and 32GB or 64GB of memory and recheck pricing

Is it joke ?

Sun Fire X4450 (4 Quad-Core Intel Xeon X7350, 2.93 GHz, 1066 MHz FSB, 130W) 64Gb RAM less than $50K

Sun Fire T5220 (1 CPU, 64Gb RAM) $60K

4 CPU, 16-cores XEON cores VS 8-cores SPARC

Posted by Triffids on October 09, 2007 at 12:49 PM PDT #

Base 2 x Xeon E5355 server + 2 hd etc but no RAM cost about $3,500-4,000.
Extra FBDIMMs (brand name high quality) 667MHz ECC cost about $2,500-3,000 for 16x2GB modules and about $7,500-8,000 for 16x4GB modules.
So we have 6-7K $ for 32GB config and 11-12K $ for 64GB config.
Your boss apparently has too much money for hw purchases.

Posted by I on October 09, 2007 at 05:07 PM PDT #

I'll let you and Tiffids fight it out. You guys play fast and lose with pricing, it seems to me.

Posted by BM Seer on October 09, 2007 at 05:15 PM PDT #

Post a Comment:
Comments are closed for this entry.