Author Topic: GPU Power & Naming System  (Read 3054 times)

0 Members and 1 Guest are viewing this topic.

KoRo

  • Fat, Emo Robot
  • Centurian Lord
  • ********
  • Posts: 3,437
  • Reputation: +14/-6
GPU Power & Naming System
« on: October 30, 2009 10:51 pm CDT »
I'm not too familiar with nVidia's system for naming and rating video cards. It's not hard to figure out that a higher number tends to mean a more powerful card, but I know that can't be entirely correct because I've seen 7 series cards costing more than 8 series cards in the past. I'm particularly interested in comparing two cards for personal reasons.

GeForce 7800 GT vs GeForce 7950

Does anyone have in-depth knowledge on this naming system, and could you explain to me how it works (or if I'm even correct in assuming that higher doesn't always = better?) Also, is a truly 7950 better than a 7800?

Rinluyen

  • Goblin Pup
  • *
  • Posts: 6
  • Reputation: +0/-0
Re: GPU Power & Naming System
« Reply #1 on: October 31, 2009 07:28 am CDT »
GeForce 7800 GTX 512
The 512 MB version of the GeForce 7800 GTX was released on November 14, 2005. The card features more than simply an increased frame buffer from 256 MB to 512 MB. The card features a much improved core clock speed of 550 MHz vs. 430 MHz (27.9% increase) and fast 1.1 ns GDDR3 memory clocked at 1.7 GHz vs. 1.2 GHz (41.7% increase), when compared to the original version. Like ATI's X1800 XT, the addition of another 256 MB of memory, and to a lesser extent, the increased clock speeds, have raised the heat and power output significantly. To combat this, the GeForce 7800 GTX 512 sports a much larger yet quieter dual slot cooling solution when compared to the original 256 MB version.[15]

Performance Specs
Core Clock Speed: 550 MHz
Memory Interface: 256-bits
Memory Bandwidth: 54.4 GB/s
Fill Rate: 8.8 billion pixel/s, 13.2 billion texel/s
Vertex/s: 1100 millions
Shader Power: 24 pixels per clock
Memory Type: GDDR3



GeForce 7950 GT
On 14 September 2006 Nvidia released the 7950GT. Announced with a 550 MHz core clock, 700 MHz (1400 MHz effective) memory clock, 24 pixel shader units, standard configurations come equipped with both 512 MB GDDR3 memory and HDCP support. At an introductory price of US$300, the GeForce 7950 GT replaces the older GeForce 7900 GT and improves performance: the GeForce 7950 GT has a fillrate of 13,200 Megatexels/s and a memory bandwidth of 44.8 GB/s (versus 10800 Megatexels/s and 940 Megavertices/s for the 7900 GT).

Performance Specs
Memory Interface: 256-bits
Memory Bandwidth: 44.8 GB/s memory bandwidth
Fill Rate: 13.2 Billion pixel/s
Vertex/s: 1.1 Billion
Shader Power: 24 pixels per clock
SLI Support (PCI-E model only)
Memory Type: GDDR3
NOTE: XFX has developed and released AGP versions of this card. [24]


i use the 9800 myself:

On April 1, 2008 the GeForce 9800 GTX was officially launched. It was basically an 8800 GTS 512MB with two SLI connectors, higher clock speeds, and support for Nvidia Hybrid Power, a technology that allows the discrete GPU to shut off during non resource intensive applications, and instead use the integrated GPU. With these extra features though, a high price came too.

Taken from an eVGA specification sheet:[21]

128 Stream Processors.
Clocks (Core/Shader/Memory): 675 MHz/1688 MHz/2200 MHz
256-bit memory interface.
512 MB of GDDR3 memory.
70.4 GB/s memory bandwidth
Texture Fill Rate of 43.2 (billion/s).
DirectX 10, Shader Model 4.0, OpenGL 3.2, and PCI-Express 2.0.
Outputs include two DVI ports, an HDMI output(Using nVidia DVI to HDMI adapter(included)), and S/PDIF in connector on-board for routing audio through the HDMI cable

KoRo

  • Fat, Emo Robot
  • Centurian Lord
  • ********
  • Posts: 3,437
  • Reputation: +14/-6
Re: GPU Power & Naming System
« Reply #2 on: October 31, 2009 04:05 pm CDT »
It seems as though the 7800 GT and 7950 are nearly identical, with the 7800 GT actually having the advantage in memory bandwidth and effective memory clock speed. So then why is the 7950 given a higher number than the 7800 GT?

Kyrie

  • Orb Member
  • Uber Menace
  • ***
  • Posts: 1,014
  • Reputation: +5/-4
Re: GPU Power & Naming System
« Reply #3 on: November 4, 2009 12:59 pm CST »
NVIDIA really twisted up their naming conventions.

The first number represents the series, so a 7000 is the 7th series. The higher that number is, the newer the card. Though low end cards from a newer series will be slower than high end cards from an older series.

Then the last three numbers, if I recall, were generall related to the pricing point for that card. Low end cards had lower numbers, so starting at the second digit, a *800 card would be better than a *600 card, depending on the generation difference.

Then, of course, they put in their post-fixes.
GS
GT
GTS
GTX
Ultra
GX2
I think that's the order of bad to good. And the postfix designation will generally offer an advantage that wipes out the advantage of a higher "numbered" card. As is the case between your 7800GT and 7950.

There isn't really any good way to just say X card is better than Y card, based on the name. Your best bet is just to compare the specs and read reviews for any technical issues people might have encountered with a particular card.

Newegg is great for both of those tasks.







KoRo

  • Fat, Emo Robot
  • Centurian Lord
  • ********
  • Posts: 3,437
  • Reputation: +14/-6
Re: GPU Power & Naming System
« Reply #4 on: November 6, 2009 11:08 am CST »
Got it, thanks Kyrie. That helped a lot.

Lidge Farkley

  • Uber Menace
  • *******
  • Posts: 1,357
  • Reputation: +2/-3
    • http://www.angelfire.com/ca2/psychosworld2/
Re: GPU Power & Naming System
« Reply #5 on: November 9, 2009 02:43 am CST »
I go look at the VGA charts on tomshardware.com when malarkey get's confusing.
Lend your heart unto the divine mineral TOPAZ;
from which our reverent hearts and minds sprang.
Also Known As:  Alcoholic 007
My Page of tribes Tools and Helpful "FAQ" Stuff