Tom's Hardware > All Reviews > Special > Miscellaneous > Gigabit Ethernet: On-Board Chips Reviewed

Test System

07:00 - Friday 30 April 2004 by Patrick Schmid

Test System

Processor
Socket 478	Intel Pentium 4 Northwood, 3.2 GHz, 512 kB Cache, FSB800
Socket 604	Dual Intel Pentium 4 Xeon, 2.8 GHz, 512 kB Cache, FSB533
System Memory
DDR-SDRAM	2x 512 MB PC3700 OCZ Gold Edition Rev. 2 (2.5-3-3-7)
Network/Motherboard
3COM / Marvell 940	Asus P4C800, Rev. 1.03 Intel 875P chipset & ICH5-R
Broadcom BCM5705	Epox EP-4PCA3+, Rev. 1.0 Intel 875P chipset & ICH5-R
Intel 82547EI (CSA)	DFI LanParty PRO875, Rev. A Intel 875P chipset & ICH5-R
3COM 3C996B-T Broadcom BCM5701	Asus PP-DLW, Rev. 1.03 Intel E7505 chipset
Realtek RTL8100S	Gigabyte GA-8S655TX Ultra, Rev. 1.0 SiS655TX & SiS964
Other Hardware
Graphics card	nVIDIA GeForce FX 5900, 128 MB
Controller	Client systems : ICH5-R or SiS964 for RAID 0 Host system : Raidcore RC4000 für RAID 0
Hard drives (client systems)	System drive : Western Digital WD800JB Test drive : RAID-0 array consisting of 2x Hitachi Deskstar 7K250, HDS722580VLSA80, 80 GB, 7,200 rpm, 8 MB Cache
Hard drives (server system)	System drive : Western Digital WD1000BB Test drive : RAID-0 array consisting of 4x Western Digital WD360 Raptor, 36 GB, 10,000 rpm, 8 MB Cache
Software
Intel Chipset	Intel Chipset Installation Utility 5.1.1.1002 Intel Application Accelerator RAID Edition Ver. 3.53
Network drivers	3COM / Marvel 940 Broadcom BCM5705 & BCM5701 : Ver. 6.34.0.0 Intel Pro/1000 CT&MT (82547EI & 82541GI) : Ver. 7.3.13.0 Realtek : Ver. 5.611.1231.2003
DirectX	9.0b
OS	Windows XP Professional Build 2600 Service Pack 1

Tests : A Detailed Look

Synthetic Benchmarks
TCP Transfer performance	NetIO Ver. 1.23 from Kai Uwe Rommel
TCP Transfer performance	Netperf Ver. 2.1
TCP Transfer performance	NetIQ Chariot 5.0
Application Benchmarks
Real Life Transfer Performance	xxcopy 2.85.3 von Pixelab, Inc. idf2002_master.avi - 1.17 GB
Real Life Windows File Copy Performance	Windows Explorer Drag&Drop Test idf2002_master.avi - 1.17 GB

During our benchmarks under real-life conditions, we copied the said file five times, doing so back to back. All tests were conducted five times in order to compensate for data dispersion while determining the mean.

To avoid a slowdown of the network adapter through an unnecessary bottleneck, we added a RAID 0 array (consisting of two current hard drives) to each system for this test. As a result, transfer rates von 110 MB/s were, therefore, no problem - that’s more than most adapters manage as a net output.