Author: Aaron Gordon
Date: 19:25:47 04/26/03
Go up one level in this thread
On April 26, 2003 at 21:11:59, Tom Kerrigan wrote: >I checked Aaron's story with his contact at AMD. The guy said that AMD didn't >allow performance testing with the memory _overclocked_, but it certainly isn't >underclocked. This makes perfect sense to me. (If you allow overclocking memory, >why wouldn't you also overclock the processor? Then all your benchmarks are >worthless.) > >So SPEC is comparing non-overclocked Intel to non-overclocked AMD and Intel >wins. > >-Tom When I ran the tests I recalled seeing some information where the P4 was running CAS2 and the like. The settings I was told to use put me at CAS 2.5. How would this be 'fair'? Same thing happens on some review pages, but to a much larger degree. As I have proven in the past tomshardware has actually run the memory lower than the bus on the athlons tested, put the AGP to 1x, etc. Also, running CAS2 with all tweaks enabled isn't "overclocking". Especially when you are running 133fsb with 150mhz rated memory (PC2400). Nothing wrong with running tight memory timings. If the platform supports it, so be it. Both systems should be running as fast as possible. This weekend I tested a P4-2.53 vs my Athlon XP system. I also overclocked the P4 to 3.32GHz/175(700)fsb. All memory timings were as fast as possible on both systems, AGP was 4x, identical drivers, windows versions, etc. Here are a few test results. While I appreciated the testing Matt Taylor let me do I didn't think the P4 was going to be THAT slow. I went and 'rented' one myself. I compared a few clock speeds, I'll post what I have so far but the most for now will be just the max both systems could do. GCC (Linux kernel compile times) XP-2.50GHz: 119.5 seconds P4-3.32GHz: 126.87 seconds Gzip: P4-3.32GHz: 25.340 seconds XP-2.50GHz: 26.060 seconds XP-2.00GHz: 32.420 seconds P4-2.53GHz: 33.270 seconds Bzip2: XP-2.50GHz: 63.450 seconds P4-3.32GHz: 65.020 seconds 3DMark 2001se: XP-2.50GHz: 15135 3DMarks P4-3.32GHz: 13836 3DMarks Shredder 7.04: XP-2.50GHz: 449.2kn/s P4-3.32GHz: 412.2kn/s XP-2.00GHz: 357.5kn/s XP-1.80GHz: 327.5kn/s P4-2.53GHz: 317.2kn/s Fritz 8: XP-2.50GHz: 1191.1kn/s P4-3.32GHz: 1160.8kn/s XP-2.00GHz: 947.5kn/s P4-2.53GHz: 885.9kn/s XP-1.80GHz: 862.9kn/s I haven't tested my regular 2507/218fsb yet, and for Quake3 it should be quite a bit faster than 2500/200 due to Quake3 being extremely memory bandwidth reliant. 2507/218 fps estimation is around 440fps. Quake3 v3.20 - Demo 'four' @ Normal Detail CPU Type FPS Pentium 4 2.53GHz/133 = 284.7 Athlon XP 2100+/133 = 285.5 Athlon XP 2200+/133 = 289.7 Athlon XP 2400+/133 = 303.8 Athlon XP 2600+/133 = 311.6 Athlon XP 2600+/166 = 348.5 Pentium 4 3.32GHz/175 = 350.9 Athlon XP 2700+/166 = 355.5 Athlon XP 2800+/166 = 360.1 Athlon XP 2GHz/200 = 373.4 Athlon XP 2.1GHz/200 = 381.8 Athlon XP 2.2GHz/200 = 391.1 Athlon XP 2.3GHz/200 = 398.2 Athlon XP 2.4GHz/200 = 405.8 Athlon XP 2.5GHz/200 = 412.4 OGR (www.distributed.net): XP-2.50GHz: 19,445,807 nodes/second XP-2.00GHz: 15,499,359 nodes/second XP-1.80GHz: 13,946,532 nodes/second P4-3.32GHz: 12,725,272 nodes/second P4-2.53GHz: 9,681,306 nodes/second RC5 (www.distributed.net): XP-2.50GHz: 7,676,643 keys/second XP-2.00GHz: 6,109,325 keys/second XP-1.80GHz: 5,533,416 keys/second P4-3.32GHz: 4,726,698 keys/second P4-2.53GHz: 3,599,431 keys/second AES (Rijndael) encryption: XP-2.5GHz: 122.38mb/s P4-3.32GHz: 98.77mb/s XP-2.00GHz: 95.83mb/s XP-1.80GHz: 86.14mb/s P4-2.53GHz: 74.19mb/s ScienceMark 1.0: XP-2.50GHz: 233.24 Sciencemarks P4-3.32GHz: 193.46 XP-2.00GHz: 184.08 XP-1.80GHz: 166.63 P4-2.53GHz: 150.18 Athlon XP is definitely faster.. then if you throw price into the equasion it's an even more simple choice. You can get a JIUHB DLT3C Athlon XP 1700+ for $49 that does 2.4GHz easily. Motherboard for $70-80. The P4 system I got was $209 for the CPU, $119 for the motherboard.
This page took 0.01 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.