NVIDIA GeForce 8800 Ultra

Graphics Processor

G80

Cores

128

TMUs

ROPs

Memory Size

768 MB

Memory Type

GDDR3

Bus Width

384 bit

GPU

I/O

Back

Recommended Gaming Resolutions:

1366x768
1600x900
1920x1080

The GeForce 8800 Ultra was an enthusiast-class graphics card by NVIDIA, launched on May 2nd, 2007. Built on the 90 nm process, and based on the G80 graphics processor, in its G80-450-A3 variant, the card supports DirectX 11.1. Even though it supports DirectX 11, the feature level is only 10_0, which can be problematic with many DirectX 11 & DirectX 12 titles. The G80 graphics processor is a large chip with a die area of 484 mm² and 681 million transistors. It features 128 shading units, 32 texture mapping units, and 24 ROPs. NVIDIA has paired 768 MB GDDR3 memory with the GeForce 8800 Ultra, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 612 MHz, memory is running at 1080 MHz.
Being a dual-slot card, the NVIDIA GeForce 8800 Ultra draws power from 2x 6-pin power connectors, with power draw rated at 171 W maximum. Display outputs include: 2x DVI, 1x S-Video. GeForce 8800 Ultra is connected to the rest of the system using a PCI-Express 1.0 x16 interface. The card measures 270 mm in length, and features a dual-slot cooling solution. Its price at launch was 829 US Dollars.

Graphics Processor

GPU Name: G80

GPU Variant: G80-450-A3

Architecture: Tesla

Foundry: TSMC

Process Size: 90 nm

Transistors: 681 million

Die Size: 484 mm²

Graphics Card

Release Date: May 2nd, 2007

Generation: GeForce 8
(8800)

Predecessor: GeForce 7 PCIe

Successor: GeForce 9

Production: End-of-life

Launch Price: 829 USD

Bus Interface: PCIe 1.0 x16

Reviews: 403 in our database

Relative Performance

Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.

Performance estimated based on architecture, shader count and clocks.

Board Design

Slot Width: Dual-slot

Length: 270 mm
10.6 inches

TDP: 171 W

Suggested PSU: 450 W

Outputs: 2x DVI
1x S-Video

Power Connectors: 2x 6-pin

Board Number: P355

G80 GPU Notes

Each Streaming Multiprocessor(SM) in the chip architecture contains 8 SPs and 2 SFUs.

Each SP can fulfill up to two single precision operations MAD per clock.

Each SFU can fulfill up to four operations SF per clock (these units can also handle single-precision floating-point multiplications per clock).

The approximate ratio of operations MAD to operations SF is equal 2:1.

The theoretical SP + SFU performance in single-precision floating point operations
[FLOPSsp + sfu, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following formula: FLOPSsp+sfu; f × n × 3.

Alternative formula: FLOPSsp+sfu; f × m × ( 8 SPs * 2 (MAD) + 4 * 2 SFUs ). [m] - SM count.

SP - Shader Processor (Unified Shader, CUDA Core)
SFU - Special Function Unit
SM - Streaming Multiprocessor
MAD - ADD+MUL

Retail boards based on this design (11)

Name	GPU Clock	Memory Clock	Other Changes
ASUS ROG 8800 Ultra	612 MHz	1080 MHz
EVGA 8800 Ultra	612 MHz	1080 MHz	267 mm/10.5 inches
EVGA 8800 Ultra Black Pearl	655 MHz	1125 MHz	Single-slot
EVGA 8800 Ultra KO	638 MHz	1125 MHz
EVGA 8800 Ultra Special Edition	630 MHz	1100 MHz
EVGA 8800 Ultra Superclocked	655 MHz	1125 MHz
GIGABYTE 8800 Ultra	612 MHz	1080 MHz
PNY XLR8 8800 Ultra Overclocked	648 MHz	1116 MHz
XFX 8800 Ultra Extreme	650 MHz	1110 MHz
XFX 8800 Ultra XXX	675 MHz	1150 MHz
XFX 8800 Ultra XXX V2	685 MHz	1150 MHz

Name

GPU Clock

Memory Clock

Other Changes

ASUS ROG 8800 Ultra