A New Battle Front: Athlon XP 1900+
AMD has opened up a new front in its war with Intel by introducing the Athlon XP 1900+. This time, AMD attempts to entrench its position in the performance-oriented high-end segment. For a while there last week, the Athlon XP 1800+ with a Palomino core was the crиme de la crиme. But what your average user won’t know is that, as is the case with the other XP models, “1900+” doesn’t indicate the processor’s clock speed, but rather its AMD performance class. In fact, the new Athlon XP 1900+ is clocked at 1600 MHz – that’s exactly 66 MHz more than the 1533 MHz the Athlon XP 1800+ offers. The next performance class is called, logically enough, “2000+”, and is almost certain to remain under wraps until the beginning of 2002. AMD’s arch-rival is thinking along similar lines – Intel is intending to wait until January of next year, if not longer, to present its first Pentium 4 clocked at 2200 MHz and based on the Northwood core. Until then, there are enough processors of all different performance classes out there on the market to secure a good starting position for the Christmas season.
After all, PC manufacturers have already had their systems configured for quite a while so that potential customers can get them from retailers in time for Christmas. AMD will be represented with its “mid-range” Athlon XP models “1700+” and “1800+”, while Intel will be hawking the Pentium 4/1700 and Pentium 4/1800 in complete systems. In terms of price, customers will hardly notice any difference between the AMD and the Intel systems. While PCs based on AMD processors often use slow DDR-SDRAM with CL2.5 (CAS Latency time 2.5 ns), PC assemblers scrimp on Intel computers by installing slow SDRAM on an 845 motherboard. By and large, however, PC systems with AMD processors generally perform better than comparable Intel systems.
The Nitty Gritty On The Athlon XP 1900+
The new Athlon XP 1900+, clocked at 1600 MHz.
There’s not much new to say, really. The most important things were already said in our last article, “Athlon XP Meets P4: A Comparison of All CPUs”. The new top-of-the-range model runs around 250 dollars. To get the biggest bang for your buck, you have to install your AMD Athlon XP 1900+ on a perfect platform. Currently available motherboards furnished with a VIA KT266 chipset are incapable of milking the full performance potential from an Athlon processor. Instead, you not only need a VIA KT266A chipset, but fast DDR-SDRAM, which also helps ensure that your Athlon performs at its best. More detailed information is provided in our test “Accelerating Athlon: VIA Releases KT266A Chipset”.
All the important technical data from the AMD Athlon XP 1900+.
Testing Procedure: A Comparison Of 13 Processors
Test Setup
Intel Hardware Socket 478 |
|
Processor | Intel Pentium 4/2000 MHz (400 MHz QDR FSB) Intel Pentium 4/1900 MHz (400 MHz QDR FSB) Intel Pentium 4/1800 MHz (400 MHz QDR FSB) Intel Pentium 4/1700 MHz (400 MHz QDR FSB) Intel Pentium 4/1600 MHz (400 MHz QDR FSB) Intel Pentium 4/1500 MHz (400 MHz QDR FSB) Intel Pentium 4/1400 MHz (400 MHz QDR FSB) |
Motherboard | ASUS P4T-E (I850) Revision: 1.00 |
Memory | 2 x 128 MB, RDRAM, 400 MHz, Viking |
AMD Hardware Socket 462 |
|
Processor | AMD Athlon XP 1900+ MHz (1600/266 MHZ DDR) AMD Athlon XP 1800+ MHz (1533/266 MHZ DDR) AMD Athlon XP 1700+ MHz (1467/266 MHZ DDR) AMD Athlon XP 1600+ MHz (1400/266 MHZ DDR) AMD Athlon XP 1500+ MHz (1333/266 MHZ DDR) AMD Athlon 1400 MHz (1400/266 MHZ DDR) |
Motherboard | Soltek (VIA KT266 A) SL75-DRV2 |
Memory | 256 MB DDR-SDRAM, CL2, PC2100, Micron |
General Hardware | |
Graphics card | GeForce 3 Memory: 64 MB DDR-SDRAM Memory clock: 400 MHz Chip speed: 250 MHz |
Hard drive | 40 GB, 5T040H4, Maxtor UDMA100 7200 rpm 2 MB Cache |
Drivers & Software | |
Graphics card driver | Detonator 4 Serie V21.85 |
DirectX version | 8.1 |
Operating system | Windows XP Final, Build 2600 (Englisch) |
Benchmarks & Settings | |
Quake III Arena | Retail Version 1.16 command line = +set cd_nocd 1 +set s_initsound 0 Graphics detail set to ‘Normal’ Benchmark using ‘Q3DEMO1’ |
3DMark2000 | Version 1.1 Build 340 – default Benchmark |
3DMark2001 | Build 200 – default Benchmark |
SiSoft Sandra 2001 | Professional Version 2001.3.7.50 |
CINEMA 4D | CineBench 6.103 |
mpeg4 encoding | Flask V0.6 (MPEG 3) DivX codec 4.02b codec Compression: 100 Data Rate: 1500 Kbit 720×480 Pixel, 25 fps no Audio |
Studio 7 | Version 7.02.7 (MPEG 2) |
Sysmark 2001 | Patch 3 |
Lame | Lame 3.89 MMX, SSE, SSE 2, 3DNow |
WinACE | 2.04, 178 MB Wave file, best compression, Dictonary 4096 KB |
Newtek Lightwave | Rendering Bench SKULL_HEAD_NEWEST.LWS |
Suse Linux 7.3 | Kernel 2.4.13 Compiling |
The picture shows the test system set-up for the AMD Athlon XP 1900+ processor. We’ve taken a different motherboard from the one we used in our last test, “Athlon XP Meets P4: A Comparison of All CPUs”. This new board is the Soltek SL75-DRV2, which proved to be slightly faster than the Epox board in some benchmark disciplines during our preparatory tests. It took some doing, but we worked out the benchmarks for all 13 processors again from scratch.
Benchmarks: 18 Rigorous Tests
OpenGL Performance | Quake 3 Arena “Demo 1” and “NV15 Demo” |
Direct3D Performance | 3D Mark 2000 and 3D Mark 2001 |
3D Rendering | Newtek Lightwave 7b |
3D Rendering | SPECviewperf “Lightscape” |
MP3 Audio Encoding | Lame MP3 Encoder |
MPEG-2 Video Encoding | Pinnacle Studio 7 |
MPEG-4 Video Encoding | Flask Mpeg 0.6 and DivX codec 4.02 |
Office Performance | Sysmark 2001 |
Archiving | WinACE 2.04 |
Compiling Linux Kernel | Suse Linux 7.3 (Kernel 2.4.13) |
SiSoft Sandra 2001 | CPU and Multimedia Bench |
We performed a total of 18 different benchmark tests (the same used in the last comparison) in order to obtain the most complete, the most well-balanced view of how the processors perform, only this time the focus was on the Athlon XP 1900+. We continued to determine OpenGL performance using four different Quake tests – Direct3D performance from the DirectX package is determined using the 3D Mark 2000 (based on DirectX 7) and the 3D Mark 2001 (based on DirectX 8).
The different MPEG-encoding benchmarks represent a comprehensive testing scenario – the Lame MP3 Encoder was used to encode a 178 MB WAV file into “MPEG-1 Layer 3 Format.” Still a classic, our MPEG-4 test converts a file from a commercial DVD-ROM into MPEG-4 format using Flask Mpeg and DivX.
A new addition to our benchmark suite is encoding an MPEG-2 file within a project by using “Pinnacle Studio 7” video editing software.
OpenGL-Performance: Quake 3 Arena
In both time-demo runs of Quake 3 Arena, the Intel Pentium 4 processors clocked at 1900 MHz and 2000 MHz stole the show from the AMD Athlon XP 1900+. The Athlon XP 1900+ had to wait until the NV15 demos to show its true capabilities.
Direct3D Performance – DirectX 7: 3D Mark 2000
The 3D Mark 2000 determines DirectX 7’s Direct3D performance under Windows XP. The diagram shows that the Athlon XP 1900+ has quite a lead over the other processors. It even scores 1000 points higher than the Intel Pentium 4/2000.
Direct3D Performance – DirectX 8: 3D Mark 2001
The 3D Mark 2001 determines DirectX 8’s Direct3D performance under Windows XP. The Athlon XP 1900+’s edge over the fastest Intel Pentium 4 isn’t as great as it was in the 3D Mark 2000 and DirectX 7.
MP3 Audio Encoding: Lame MP3
The Lame MP3 Encoder under Windows XP is used to convert a 178 MB sound file from WAV format to “MPEG-1 Layer 3” format. While the Pentium 4/2000 was the fastest CPU at encoding and MP3 in our last test, in this round the Athlon XP 1900+ takes the gold.
MPEG-4 Video Encoding: Flask Mpeg and DivX
Our last comparison was the ultimate sensation – the AMD Athlon XP 1800+ beat the Intel Pentium 4/2000. With the Athlon XP 1900+, Athlon has just widened its lead. But it remains to be seen how both run once the new DivX codec with an enhanced Flask Mpeg comes out – the tables might just turn then.
SiSoft Sandra Benchmarks: CPU, Multimedia and Memory
In the SiSoft Sandra Benchmark 2001, we see that, with the exception of the memory benchmark, where the Intel Pentium 4/2000 takes the lead, the AMD Athlon XP 1900+ is the overall winner. A small glitch continues to crop up, making the AMD Athlon 1400 look better than the new XP processors.
3D-Rendering: Lightwave 7b
Rendering Bench SKULL_HEAD_NEWEST.LWS.
In view of the current situation, we felt that the Cinema 4D benchmark for 3D rendering is outdated, so we replaced this with the newest version of Lightwave (ver. 7b) from Newtek, which also provides information on rendering performance and is an application used specifically by game developers. This was the software used to create the cult game Diabolo 2, for example.
Scene from Diablo 2.
Office Performance: Sysmark 2001
The Athlon XP 1900+ takes first place in the overall score category. Athlon’s lead is even wider in the office test – all Athlon processors come out ahead of the Intel CPUs. Intriguingly, the Athlon XP 1900+ is the clear winner even without the patch for Media Encoder 7.1 distributed by AMD.
Compiling Linux: Suse Linux 7.3 / Kernel 2.4.13
When it comes to compiling the latest Linux kernel, the AMD Athlon XP 1900+ is the fastest CPU. It needs a mere 217 seconds – whereas the Intel Pentium 4/2000 needs 264 seconds to compile the same kernel.
Archiving: WinACE 2.04
Archiving is a very practical application. WinACE 2.04 was used under Windows XP to archive a 178 MB WAV file while the clock was running. In this discipline, the Intel Pentium 4/2000 continues to be head and shoulders above the rest. The Athlon XP 1900+ takes second place.
3D Rendering Performance: SPECviewperf “Lightscape”
In the Lightscape benchmark, the Intel Pentium 4/2000 continues to be a nose ahead of the competition – the fastest Athlon XP 1900+ takes fifth place.
MPEG-2 Video Encoding: Pinnacle Studio 7
The Intel Pentium 4/2000 was still the fastest at creating an MPEG-2 film using Pinnacle Studio 7. However, the difference between it and the fastest AMD processor – the Athlon XP 1900+ – is minimal.
Conclusion: AMD Widens Its Lead
With its new Athlon XP 1900+, AMD has widened its lead in performance even more. In virtually all the benchmark disciplines we re-selected, the Athlon XP 1900+ takes the gold. The Athlon XP 1900+ is especially effective in CPU-intensive situations, for example audio/video encoding or classic 3D rendering. However, we have observed an important trend in this area: the frequent appearance of application patches and updates that increase performance of the Pentium 4 via SSE2.
Intel’s efforts to gain a foothold for SSE2 in the market are beginning to show results, although it still cannot be claimed that SSE2 has really established itself at wider level. For the typical office user or gamer, the extra performance offered by Intel’s fastest processor (Pentium 4/2000) makes only a marginal difference when it comes to practical applications.
However, the difference between Athlon XP 1900+ and the fastest Intel processor – the Pentium 4/2000 – is, realistically speaking, minimal in most cases. There is still a clear argument in favor of purchasing the Athlon XP 1900+ speed-demon – its price: AMD is launching this processor at a price of 265 dollars. The fastest Intel processor costs 400 dollars with fan (boxed version).
We’d like to round off this article with a meaningful price comparison for users interested in building their own high-end PC system themselves. Those of you in the market for complete systems are in a different situation, since OEM manufacturers acquire processors for substantially cheaper prices than customers can at their neighborhood computer store.
AMD System With Athlon XP 1900+
Processor 265 dollars, fan with thermal paste 45 dollars, motherboard with VIA KT266A 85 dollars, 256 MB DDR-SDRAM (Micron – CL2) 35 dollars, graphics card GeForce 3 (Asus V8200 Deluxe) 280 dollars = Total price 710 dollars
Intel System With Pentium 4/2000
Processor with fan and thermal paste 400 dollars, motherboard 100 dollars, 2x 128 MB RDRAM (Samsung 400 MHz) 70 dollars, graphics card GeForce 3 (Asus V8200 Deluxe) 280 dollars = Total price 850 dollars
The result from both configurations shows that there is a difference in price of 140 dollars between the two systems. With these figures, it’s really up to the buyer to make the right decision.