Intel defaults and judging performance

Tuesday Sep 18, 2007

Intel non-default BIOS change results by 25%? Sure turning off prefetch is a technique but if you don't know if a priori if you should, then should you use it to judge performance?

Always interesting when you have more information. I guess our friends at AMD wanted everyone to see what our friends at Intel were doing so they submitted two SPEC results for them.

Case in point on Clovertown there are two AMD results on the same hardware that gives 25% difference.

Point: Normal mode = prefetch on
Gives 163,080 SPECjbb2005 bops
www.spec.org/jbb2005/results/res2007q2/jbb2005-20070326-00276.txt

Counter-point: Disable HW prefetcher in BIOS for benchmark imprv
Gives 203,754 SPECjbb2005 bops
www.spec.org/jbb2005/results/res2007q2/jbb2005-20070326-00275.txt

...both on the same hardware:
same: 2-socket SuperMicro X7DBE (Intel 2.66GHz Xeon quad-core X5355), 16 GB

Disclosure statement

SPECjbb2005 SuperMicro X7DBE (2 chips, 8 cores, 2.66 GHz) SPECjbb2005 bops=163080, SPECjbb2005 bops/JVM=81540 submitted by AMD; SuperMicro X7DBE (2 chips, 8 cores, 2.66 GHz) SPECjbb2005 bops=203754, SPECjbb2005 bops/JVM=101877 submitted by AMD; SPEC, SPECjbb are registered trademarks of Standard Performance Evaluation Corporation. Results 3/7/07 on www.spec.org.

Like this post? | | | |

Posted at 07:50AM Sep 18, 2007 in Benchmark Issues
Tags: amd clovertown intel performance specjbb2005 x64

Sun Fire X2200 M2 running Fluent CFD Beats Woodcrest & Clovertown

Friday Mar 30, 2007

The Sun Fire X2200 M2 server beats Woodcrest on large CFD models. The X2200 M2 Cluster beats all currently posted Opteron cluster results (dual core HP XC4000 2.2GHz, HP DL145 G2 2.2GHz, HP XW9300 2.4GHz, and HP DL585 2.6GHz) for all "cpu" levels and for all test cases. All clusters had the high performance Infiniband interconnects.

The X2200 M2 beats the IBM X3650 2.66GHz quad core Clovertown across the board at all cpu levels and for all test cases.

Tests were run on the official version of Fluent (lnxamd64 V6.3.26 build). The Sun Opteron server numbers were generated under 64-bit SUSE SLES 9 SP 3. Sun many customers that use Solaris, Linux, and windows so we show benchmarks on all of these.

Although the X2200 M2 cluster has the best performance on the larger and more complex tests, "FL5L3". It is most closely representative of actual customer benchmarks (requires over 9GB of memory, best run using several cpu's). FL5L3 simulates turbulent flow through a transition duct.

Note that the X2200 M2 cluster results shown in following table are consistently better than those obtained on the two Woodcrest cluster systems at the same "cpu" levels and for all indicated "cpu" levels (4 to 32).

The efficiency of the Sun X2200 M2 cluster is superb at well above 90% up to 32 cores. This essentially perfect scalability is contrasted with the Woodcrest clusters where scalability has dropped off and efficiency is below 70% at and above 4 cores.

Scaling Performance : Results in "Ratings" (# runs/day, bigger is better)

System	4 Cores	8 Cores	16 Cores	32 Cores
Sun X2200 M2 2.8GHz Operton	89.9	174.4	341.5	664.4
HP BL460C 3.0GHz Woodcrest	80.3	155.4	299.0	576.0
HP DL140 3.0GHz Woodcrest	N/A	160.7	320.5	620.1
Bull NovaScale 3.0GHz Woodcrest	78.9	157.8	313.2	619.0

Fluent Performance : Results in "Ratings" (# runs/day, bigger is better)

System	Interconnect/MPI	cores	FL5L1	FL5L2	FL5L3
X2200 2.8GHz DC 2220 SLES 9 SP 3	IB(V)/HP-MPI	8	1219.5	952.1	174.4
X2100 3.0GHz SC 156 SLES 9 SP3	IB(V)/MVAPICH	8	1148.2	1063.4	184.6
HPDL140 3.0GHz DC WC EM64T Linux	IB/HP-MPI	8	1378.0	915.0	160.7
Bull Nova 3.0 GHz DC WC EM64T RHEL4	IB	8	1323.6	884.1	157.8
HP BL460C 3.0GHz WC EM64T WinCCS	IB(V)	8	1289.6	881.6	155.4
Intel White 3.0GHz WC EM64T DC RHAS4	IB(Mellanox)	8	---	828.0	137.8
Tyan Typh. 630 2.3GHz WC SLES 10	GbE	8	1011.7	692.4	122.7
Tyan Typh. 630 2.3GHz WC WinCCS	GbE	8	981.8	635.3	---
HPDL140 3.6GHz EM64T WINCCS	IB	8	970.8	675.0	120.0
HPDL585 2.6GHz DC 152 RHEL4	IB(V)/HP-MPI	8	966.2	723.2	119.2
HPXC4000 2.2GHz DC 148 Linux	IB(V)/HP-MPI	8	951.0	680.4	102.7
HPDL145 G2 Opteron 2.2GHz DC WinCCS	IB(V)	8	847.1	654.5	119.2
IBMX3650 2.66GHz 4C Clovert. EM64T RHEL4	?	8	953.6	551.2	93.3

Benchmark Description

Nine industrial CFD applications ranging in size from 32,000 to 10,000,000 cells have been selected to demonstrate the performance of FLUENT on a variety of hardware platforms. The performance of a CFD code will depend on several factors including size and topology of the mesh, physical models, numerics and parallelization, compilers and optimization, in addition to performance characteristics of the hardware where the simulation is performed. The problems selected represent a range of simulations typical of those which might be found in industry. The principal objective of this benchmark suite is to provide comprehensive and fair comparative information of the performance of FLUENT on available hardware platforms.

System Configuration

Hardware Configuration:

Sun Fire X2200 M2
2-socket 2x2.8 GHz dual core Opteron 2220 processors
4x1GB + 4x2GB (12GB) DDR2 667 MHz dimms
IB(Voltaire)/PCI-Express (interconnect)

Software Configuration:

64-bit SuSE SLES 9 SP 3
Fluent V6.3.26
Voltaire Infiniband Software Stack: 3.5.5_16-S2sles9.k2.6.5_7.244_smp.x86_64
Message Passing Interface: HP-MPI V hpmpi-2.02.05.00-20061003r.x86_64

See Also

Current V6.2(.16) results at:
http://www.fluent.com/software/fluent/fl5bench/flbench_6.3/fullres.htm

Like this post? | | | |

Posted at 11:04AM Mar 30, 2007 in Benchmarks
Tags: cfd clovertown fire fluent m2 opteron sun woodcrest x2200