BM Seer Unofficial thoughts from an anonymous Sun employee

2-chip SPEC CPU2006 Rate World Records: Sun SPARC Enterprise T5240

Thursday Apr 10, 2008

Sun has announced two-chip world record results for SPECint_rate2006 and SPECfp_rate2006. These results were run on the Sun SPARC Enterprise T5240 server which uses the UltraSPARC T2 Plus processor running at 1.4 GHz.

The Sun SPARC Enterprise T5240 server, powered by two UltraSPARC T2 Plus processors, delivered a World Record 2-chip "peak" result of 157 on the SPECint_rate2006 benchmark.

The Sun SPARC Enterprise T5240 server, powered by two UltraSPARC T2 Plus processors, delivered a World Record 2-chip "base" result of 142 on the SPECint_rate_base2006 benchmark.

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 p 570 by 29% on the SPECint_rate2006 benchmark.

The Sun SPARC Enterprise T5240 server delivers 1.9X the throughput performance of the Sun SPARC Enterprise T5220 server as measured by SPECint_rate2006 in the same amount of space.

The Sun SPARC Enterprise T5240 server, powered by two UltraSPARC T2 Plus processors, delivered a World Record 2-chip "peak" result of 119 on the SPECfp_rate2006 benchmark.

The Sun SPARC Enterprise T5240 server, powered by two UltraSPARC T2 Plus processors, delivered a World Record 2-chip "base" result of 111 on the SPECfp_rate_base2006 benchmark.

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 p 570 by 3% on the SPECfp_rate2006 benchmark.

The Sun SPARC Enterprise T5240 server delivers 1.9X the throughput performance of the Sun SPARC Enterprise T5220 server as measured by SPECfp_rate2006 in the same amount of space.

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 SE T5240 UltraSPARC T2 Plus 1.4 2 16 128 157 142
Supermicro X7DWA-N Xeon X5482 3.2 2 8 8 147 121
SGI Altix XE 250 Xeon X5472 3.0 2 8 8 143 119
HP DL160 G5 Xeon X5472 3.0 2 8 8 140 115
IBM p 570 Power6 4.7 2 4 8 122 108

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

SPECfp_rate2006

Please see www.spec.org for complete results

System Processors Performance
Results
Type GHz Chips Cores Threads Peak Base
Sun SE T5240 UltraSPARC T2 Plus 1.4 2 16 128 119 111
IBM p 570 POWER6 4.7 2 4 8 116 98.8
IBM i 570 POWER6 4.7 2 4 8 115 102
HP BL685c G5 Opteron 8356 2.3 2 8 8 89.8 82.0
HP DL385 G5 Opteron 2356 2.3 2 8 8 89.3 81.1

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 SPARC Enterprise T5240 (UltraSPARC T2 Plus, 2 chips, 16 cores), 157 SPECint_rate2006, 142 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 SPARC Enterprise T5240 (UltraSPARC T2 Plus, 2 chips, 16 cores), 157 SPECint_rate2006; IBM p 570 (POWER6, 2 chips, 4 cores), 122 SPECint_rate2006.

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; Sun SPARC Enterprise T5220 (UltraSPARC T2, 1 chip, 8 cores), 83.2 SPECint_rate2006.

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 SPARC Enterprise T5240 (UltraSPARC T2 Plus, 2 chips, 16 cores), 119 SPECfp_rate2006, 111 SPECfp_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 SPARC Enterprise T5240 (UltraSPARC T2 Plus, 2 chips, 16 cores), 119 SPECfp_rate2006; IBM p 570 (POWER6, 2 chips, 4 cores), 116 SPECfp_rate2006.

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 SPARC Enterprise T5240 (UltraSPARC T2 Plus, 2 chips, 16 cores), 119 SPECfp_rate2006; Sun SPARC Enterprise T5220 (UltraSPARC T2, 1 chip, 8 cores), 62.3 SPECfp_rate2006.

Results Summary

Results
Reference Date: Apr 9, 2008
System: Sun SPARC Enterprise T5240
Processor: Sun UltraSPARC T2 Plus, 1.4 GHz
  157 SPECint_rate2006
  142 SPECint_rate_base2006
  119 SPECfp_rate2006
  111 SPECfp_rate_base2006
Software: Solaris 10, Sun Studio 12 Compiler

[2] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Comments:

Yes, this is all great and I'm a real fan of these system. Can't wait for the 4-way and see what it can do with our databases. However, one problem is the price/performance... I don't have the exact numbers in front of me, but I can get a number (more than 2) X86 systems for the same price as a Sparc system, and I think this difference needs to come down for sparc to survive as a viable alternative.

Posted by Mike on April 11, 2008 at 12:43 PM PDT #

There is public data on HP DL580 G5, when configured reasonably with memory the prices quickly add up...
http://blogs.sun.com/ritu/entry/mysql_benchmark_us_t2_beats

HP 4S QC with 64GB are NOT cheap (with 2.96GHz and full speed dimms) and I just saw data showing that system drawing 900+watts. The other thing happening is virtualization is driving up memory requirements on X86 so system prices can be high.

Posted by BM Seer on April 11, 2008 at 01:09 PM PDT #

Post a Comment:
Comments are closed for this entry.