If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below. |
|
|
|
Thread Tools | Display Modes |
#1
|
|||
|
|||
VIA C3 cpu benchmark
Could anyone compare the speed of a VIA CPU (1GHz) comparing with
Celeron 1GHz and PIII-1GHz for database applications? Is it PIIIVIACeleron or PIII about equal to VIA? Thanks! |
#2
|
|||
|
|||
|
#3
|
|||
|
|||
z wrote:
(terry) wrote in m: Could anyone compare the speed of a VIA CPU (1GHz) comparing with Celeron 1GHz and PIII-1GHz for database applications? Is it PIIIVIACeleron or PIII about equal to VIA? Thanks! dono if this will help but my c3 866 is pretty dog slow for FPU intensive stuff. -- makes a nice little linux box and is uber quiet (and small mini- atx). If you need speed pIII is probably best of those choices I've set a few dozen people up with C3 systems over the last couple of years. If you want a fanless system or a PSU-fan only system that is good enough to run XP, web browser, word processor, play DVD's, etc, then a 1 GHz C3 is more than good enough for most people. Other than that - forget it, a C3 is almost undoubtedly not for you. Once you get outside of the basic tasks I outlined above, a pre-Nehemiah C3 is like a Celeron or Duron at 1/3 the clock speed, while a Nehemiah does a little better. If you think a 500 MHz Celery or Duron would be good enough for your database app, then I suppose a 1 GHz Nehemiah would be good enough as well. I suppose it all depends on how big the database is, how many C3 systems you are prepared to cluster together, how many users, ... Also be sure to use avoid VIA's PLE133 chipset. Their CLE266 chipset, however, is quite a big improvement and I would recommend it. -- Reply to newsgroup only please. This e-mail account is real but effectively abandoned because of excessive spamming. |
#4
|
|||
|
|||
On Mon, 01 Dec 2003 16:36:55 -0600, z wrote:
(terry) wrote in om: Could anyone compare the speed of a VIA CPU (1GHz) comparing with Celeron 1GHz and PIII-1GHz for database applications? Is it PIIIVIACeleron or PIII about equal to VIA? Thanks! dono if this will help but my c3 866 is pretty dog slow for FPU intensive stuff. Yeah, and databases applications are real FPU intensive (in a not-at-all kind of way). Database applications tend to require three things, cache, low latency/high bandwidth memory (whether latency or bandwidth is more important usually depends on what sort of operations you do mostly) and the speed of I/O and storage. Assuming that the last is equal between systems, you see that the VIA C3 has a larger L1 cache (64K instruction + 64K data) but smaller L2 cache (64K) as compared to a Celeron (16K/16K L1 + 128K L2). In total the VIA C3 can cache up to 128K of data though (it uses a victim cache design for the L2, unlike the Celeron), essentially the same as the Celeron. The larger 256K cache of the PIII tends to make it a noticeably quicker on database apps when compared to the Celeron. Both chips use the same GTL bus, though the VIA C3 uses a 133MHz bus speed vs. the 100MHz bus speed of the Celeron, so this should give an edge to the C3. The PIII also uses a 133MHz bus. For the actual processor itself, this usually doesn't factor into databases TOO much, though it will have an effect. Here the Celeron will probably be a bit faster, the C3 was really designed with low-cost/low power in mind, so some ops are slower. For databases though, most of the ops used will tend to be fairly standard load/stores, maybe a few adds, multiplies, etc. and branches. None of these are very slow on the C3, so it should be pretty competitive with the Celeron. In total, I would through out a guesstimate that the VIA C3 will probably be about 5-10% slower than a similarly clocked Celeron for database stuff, and the PIII being 10-15% quicker than the Celeron. Of course, I'd give my estimate at least a 25% margin of error! : If anyone has some real-world numbers, please feel free to share! ------------- Tony Hill hilla underscore 20 at yahoo dot ca |
#5
|
|||
|
|||
(terry) wrote in
m: Could anyone compare the speed of a VIA CPU (1GHz) comparing with Celeron 1GHz and PIII-1GHz for database applications? Is it PIIIVIACeleron or PIII about equal to VIA? its semi equal to celeron mendocino 300MHz in FPU, same celeron overclocked to 450MHz at integers, its fanless but its terribly slow Pozdrawiam. -- RusH // http://kiti.pulse.pdi.net/qv30/ -- heckme Pent-up passive-aggressive dork alert! Whoop! Whoop! Whoop! Whoop! Boy, you're really lighting up this alarm here! |
#6
|
|||
|
|||
Tony Hill wrote in
.com: On Mon, 01 Dec 2003 16:36:55 -0600, z wrote: (terry) wrote in . com: Could anyone compare the speed of a VIA CPU (1GHz) comparing with Celeron 1GHz and PIII-1GHz for database applications? Is it PIIIVIACeleron or PIII about equal to VIA? Thanks! dono if this will help but my c3 866 is pretty dog slow for FPU intensive stuff. Yeah, and databases applications are real FPU intensive (in a not-at-all kind of way). right. the FPU being slow is the only thing i've noticed as a negative of this chip in using it for the last year or so is all. |
#7
|
|||
|
|||
z wrote:
Tony Hill wrote in .com: On Mon, 01 Dec 2003 16:36:55 -0600, z wrote: (terry) wrote in .com: Could anyone compare the speed of a VIA CPU (1GHz) comparing with Celeron 1GHz and PIII-1GHz for database applications? Is it PIIIVIACeleron or PIII about equal to VIA? Thanks! dono if this will help but my c3 866 is pretty dog slow for FPU intensive stuff. Yeah, and databases applications are real FPU intensive (in a not-at-all kind of way). right. the FPU being slow is the only thing i've noticed as a negative of this chip in using it for the last year or so is all. The FPU situation is much improved with the Nehemiah C3's compared to the pre-Nehemiah versions, but still not on a par with the Celery or Duron. -- Reply to newsgroup only please. This e-mail account is real but effectively abandoned because of excessive spamming. |
#8
|
|||
|
|||
Tony Hill wrote:
On Mon, 01 Dec 2003 16:36:55 -0600, z wrote: (terry) wrote in om: Could anyone compare the speed of a VIA CPU (1GHz) comparing with Celeron 1GHz and PIII-1GHz for database applications? Is it PIIIVIACeleron or PIII about equal to VIA? Thanks! dono if this will help but my c3 866 is pretty dog slow for FPU intensive stuff. Yeah, and databases applications are real FPU intensive (in a not-at-all kind of way). Database applications tend to require three things, cache, low latency/high bandwidth memory (whether latency or bandwidth is more important usually depends on what sort of operations you do mostly) and the speed of I/O and storage. Assuming that the last is equal between systems, you see that the VIA C3 has a larger L1 cache (64K instruction + 64K data) but smaller L2 cache (64K) as compared to a Celeron (16K/16K L1 + 128K L2). In total the VIA C3 can cache up to 128K of data though (it uses a victim cache design for the L2, unlike the Celeron), essentially the same as the Celeron. The larger 256K cache of the PIII tends to make it a noticeably quicker on database apps when compared to the Celeron. Both chips use the same GTL bus, though the VIA C3 uses a 133MHz bus speed vs. the 100MHz bus speed of the Celeron, so this should give an edge to the C3. The PIII also uses a 133MHz bus. For the actual processor itself, this usually doesn't factor into databases TOO much, though it will have an effect. Here the Celeron will probably be a bit faster, the C3 was really designed with low-cost/low power in mind, so some ops are slower. For databases though, most of the ops used will tend to be fairly standard load/stores, maybe a few adds, multiplies, etc. and branches. None of these are very slow on the C3, so it should be pretty competitive with the Celeron. In total, I would through out a guesstimate that the VIA C3 will probably be about 5-10% slower than a similarly clocked Celeron for database stuff, and the PIII being 10-15% quicker than the Celeron. Of course, I'd give my estimate at least a 25% margin of error! : If anyone has some real-world numbers, please feel free to share! Here goes: http://www6.tomshardware.com/cpu/20020605/ Basic idea is - Via C3 1GHz is slower then Celeron 800 in most tests, but considering how chip and heat-saving it is, still a good deal. Regards, Yevge -- __________________________________________________ *science&fiction*free programs*fine art*phylosophy: http://sudy_zhenja.tripod.com ----------remove hate_spam to answer-------------- |
#9
|
|||
|
|||
Evgenij Barsukov wrote:
Tony Hill wrote: On Mon, 01 Dec 2003 16:36:55 -0600, z wrote: (terry) wrote in .com: Could anyone compare the speed of a VIA CPU (1GHz) comparing with Celeron 1GHz and PIII-1GHz for database applications? Is it PIIIVIACeleron or PIII about equal to VIA? Thanks! dono if this will help but my c3 866 is pretty dog slow for FPU intensive stuff. Yeah, and databases applications are real FPU intensive (in a not-at-all kind of way). Database applications tend to require three things, cache, low latency/high bandwidth memory (whether latency or bandwidth is more important usually depends on what sort of operations you do mostly) and the speed of I/O and storage. Assuming that the last is equal between systems, you see that the VIA C3 has a larger L1 cache (64K instruction + 64K data) but smaller L2 cache (64K) as compared to a Celeron (16K/16K L1 + 128K L2). In total the VIA C3 can cache up to 128K of data though (it uses a victim cache design for the L2, unlike the Celeron), essentially the same as the Celeron. The larger 256K cache of the PIII tends to make it a noticeably quicker on database apps when compared to the Celeron. Both chips use the same GTL bus, though the VIA C3 uses a 133MHz bus speed vs. the 100MHz bus speed of the Celeron, so this should give an edge to the C3. The PIII also uses a 133MHz bus. For the actual processor itself, this usually doesn't factor into databases TOO much, though it will have an effect. Here the Celeron will probably be a bit faster, the C3 was really designed with low-cost/low power in mind, so some ops are slower. For databases though, most of the ops used will tend to be fairly standard load/stores, maybe a few adds, multiplies, etc. and branches. None of these are very slow on the C3, so it should be pretty competitive with the Celeron. In total, I would through out a guesstimate that the VIA C3 will probably be about 5-10% slower than a similarly clocked Celeron for database stuff, and the PIII being 10-15% quicker than the Celeron. Of course, I'd give my estimate at least a 25% margin of error! : If anyone has some real-world numbers, please feel free to share! Here goes: http://www6.tomshardware.com/cpu/20020605/ Basic idea is - Via C3 1GHz is slower then Celeron 800 in most tests, but considering how chip and heat-saving it is, still a good deal. Those THG numbers are out of date and totally irrelevant - they predate the C3-Nehemiah. If you buy a 1 GHz C3 today it will probably be a Nehemiah and a Nehemiah is a good improvement over the pre-Nehemiah C3's. Just found this review: http://www.digit-life.com/articles2/...-nehemiah.html It compares - 1 GHz Nehemiah, VIA CLE266 chipset - 1 GHz Nehemiah, Intel i815P chipset - 1.3 GHz Celery/Tualatin Which makes me reconsider my recommendation of the CLE266 chipset unless you intend to play DVDs a lot: the i815P beats the CLE266 in everything else, often by very large margins. And I believe "Whining Dog" compared a C3-Nehemiah and a pre-Nehemiah against a 2.x GHz P4. Note also that the 1.3 GHz Nehemiah should be available now or very soon. There are also rumours that a C3 version that is pin-compatible with a P4 is under development - which would mean you will no longer have to settle for a Socket 370 motherboard. -- Reply to newsgroup only please. This e-mail account is real but effectively abandoned because of excessive spamming. |
#10
|
|||
|
|||
On Wed, 03 Dec 2003 13:37:20 -0600, Rob Stow
wrote: In total, I would through out a guesstimate that the VIA C3 will probably be about 5-10% slower than a similarly clocked Celeron for database stuff, and the PIII being 10-15% quicker than the Celeron. Of course, I'd give my estimate at least a 25% margin of error! : If anyone has some real-world numbers, please feel free to share! Here goes: http://www6.tomshardware.com/cpu/20020605/ Basic idea is - Via C3 1GHz is slower then Celeron 800 in most tests, but considering how chip and heat-saving it is, still a good deal. Those THG numbers are out of date and totally irrelevant - they predate the C3-Nehemiah. If you buy a 1 GHz C3 today it will probably be a Nehemiah and a Nehemiah is a good improvement over the pre-Nehemiah C3's. Just found this review: http://www.digit-life.com/articles2/...-nehemiah.html Actually the numbers on this test are every bit as irrelevant as the THG numbers for the original poster. Let's see, they have: CPU RightMark: FPU/SSE test MP3 encoding: FPU/memory test MPEG encoding: FPU/memory test ACE archiving: ??? I'd have thought it's a disk-intensive test 3DMax Rendering: FPU test Sysmark: System wide test with no way to get individual scores 3DMark: Mainly a video card test Games: FPU/video card test So how, exactly do any of these tests remotely demonstrate how the chip will perform on database applications? It's a well established fact that the chip isn't so hot at FPU stuff, but database use basically ZERO floating point instructions. Reviews that are full of FPU tests aren't overly useful to the original poster. It compares - 1 GHz Nehemiah, VIA CLE266 chipset - 1 GHz Nehemiah, Intel i815P chipset - 1.3 GHz Celery/Tualatin Which makes me reconsider my recommendation of the CLE266 chipset unless you intend to play DVDs a lot: the i815P beats the CLE266 in everything else, often by very large margins. That's mainly due to the integrated video. The video for this chipset doesn't contain any of the bandwidth-saving technologies of Intel's chipset, and performance of integrated video is 99% determined by memory bandwidth. ------------- Tony Hill hilla underscore 20 at yahoo dot ca |
|
Thread Tools | |
Display Modes | |
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
Suggestions for planned bonnie++ benchmark | Jochen Kaiser | Storage & Hardrives | 0 | April 13th 04 02:01 PM |
REQ: benchmark help | H.W. Stockman | Overclocking AMD Processors | 0 | April 12th 04 07:07 PM |
Athlon 64 Vs. Pentium 4 article: On the Justification for Quake3 as a CPU Benchmark | rms | Overclocking AMD Processors | 7 | October 5th 03 10:05 PM |
Athlon 64 Vs. Pentium 4 article: On the Justification for Quake3 as a CPU Benchmark | rms | Overclocking | 6 | October 2nd 03 05:16 PM |
Athlon 64 Vs. Pentium 4 article: On the Justification for Quake3 as a CPU Benchmark | rms | General | 6 | October 2nd 03 05:16 PM |