Report an Error

NVIDIA GeForce 8800 Ultra

Graphics Processor
G80
Cores
128
TMUs
32
ROPs
24
Memory Size
768 MB
Memory Type
GDDR3
Bus Width
384 bit
GPU Chip
GPU
I/O
I/O
Back
Back
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
Density
1.4M / mm²
Die Size
484 mm²
Chip Package
BGA-1449

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

GeForce 210
12%
GeForce 9400 GT
16%
Radeon HD 4550
20%
Radeon HD 5450
25%
Radeon HD 6450
30%
GeForce GT 520
31%
GeForce GT 220
39%
GeForce GT 430
50%
Radeon HD 5570
51%
Radeon HD 4670
56%
GeForce GT 440
59%
GeForce GT 240
60%
GeForce 9600 GT
69%
Radeon HD 5670
73%
GeForce GT 640
78%
GeForce 9800 GT
81%
Radeon HD 6670
84%
Radeon HD 4830
87%
Radeon HD 4770
93%
Radeon HD 4850
98%
GeForce GTS 250
100%
GeForce 8800 Ultra
100%
GeForce GTS 450
103%
Radeon HD 5750
107%
Radeon HD 7750
122%
Radeon HD 5770
123%
GeForce GTX 260
125%
Radeon HD 4870
126%
Radeon Vega 8
127%
GeForce GTX 550 Ti
128%
GeForce GTX 650
129%
Radeon HD 5830
137%
Radeon HD 6790
144%
Radeon HD 4890
146%
GeForce GTX 460
151%
Radeon RX Vega 11
153%
GeForce GT 1030
154%
GeForce GTX 275
155%
Radeon HD 7770 GHz Edition
156%
GeForce GTX 280
156%
GeForce GTX 465
159%
Radeon HD 6850
167%
GeForce GTX 285
170%
Radeon HD 5850
183%
GeForce GTX 650 Ti
186%
Radeon HD 7790
186%
Radeon RX 550
194%
GeForce GTX 470
194%
Radeon HD 6870
201%
Radeon HD 5870
215%
GeForce GTX 560 Ti
222%
Radeon HD 4870 X2
223%
GeForce GTX 750 Ti
227%
Radeon HD 6950
228%
GeForce GTX 295
236%
GeForce GTX 650 Ti Boost
239%
Radeon HD 7850
240%
GeForce GTX 480
245%
Radeon HD 6970
256%
Radeon R7 265
261%
Radeon RX 460
265%
Radeon R7 370
265%
GeForce GTX 660
266%
GeForce GTX 570
267%
Radeon RX 560
271%
GeForce GTX 950
288%
Radeon HD 7870 GHz Edition
291%
Radeon R9 270X
298%
GeForce GTX 660 Ti
301%
GeForce GTX 580
303%
GeForce GTX 1050
305%
Radeon HD 7950
306%
GeForce GTX 1630
312%
Radeon HD 5970
312%
GeForce GTX 760
321%
GeForce GTX 670
345%
GeForce GTX 960
354%
Radeon R9 380
363%
Radeon R9 285
365%
Radeon HD 7970
369%
GeForce GTX 680
373%
GeForce GTX 1050 Ti
381%
GeForce GTX 770
391%
Radeon HD 6990
400%
Radeon R9 280X
410%
GeForce GTX 590
416%
Radeon HD 7970 GHz Edition
416%
GeForce GTX 780
461%
Arc A380
462%
Radeon RX 6400
468%
GeForce GTX 1650
477%
Radeon RX 470
507%
Radeon R9 290
514%
Radeon RX 570
542%
Radeon R9 390
549%
Radeon R9 290X
552%
GeForce GTX 970
559%
GeForce GTX TITAN
566%
GeForce GTX 780 Ti
574%
Radeon R9 390X
582%
Radeon HD 7990
585%
Radeon RX 480
588%
GeForce GTX 690
593%
GeForce GTX 1060 6 GB
609%
Radeon RX 5500 OEM
617%
Radeon RX 580
624%
Radeon RX 5500 XT
629%
Radeon RX 6500 XT
635%
GeForce GTX 980
637%
GeForce GTX 1650 SUPER
643%
Radeon R9 FURY
646%
Radeon RX 590
674%
Radeon R9 295X2
710%
GeForce GTX 1660
714%
Radeon R9 FURY X
722%
GeForce GTX 980 Ti
735%
GeForce GTX TITAN X
754%
GeForce GTX 1660 SUPER
776%
GeForce GTX 1070
820%
GeForce GTX 1660 Ti
820%
GeForce RTX 3050 8 GB
833%
Radeon RX Vega 56
873%
GeForce GTX 1070 Ti
926%
Radeon RX 5600 XT
939%
Radeon RX Vega 64
952%
GeForce GTX 1080
965%
GeForce RTX 2060
965%
Radeon RX 5700
1005%
Arc A580
1007%
Radeon RX 6600
1049%
GeForce RTX 2060 SUPER
1084%
GeForce RTX 2070
1098%
Radeon RX 5700 XT
1099%
GeForce RTX 3060 12 GB
1121%
Arc A750
1157%
Radeon VII
1163%
TITAN X Pascal
1194%
Radeon RX 6600 XT
1206%
GeForce GTX 1080 Ti
1230%
Arc A770
1242%
GeForce RTX 2070 SUPER
1243%
Radeon RX 6650 XT
1307%
Radeon RX 7600
1322%
GeForce RTX 4060
1328%
GeForce RTX 2080
1337%
Radeon RX 7600 XT
1364%
GeForce RTX 2080 SUPER
1402%
GeForce RTX 3060 Ti
1436%
Radeon RX 6700 XT
1486%
Radeon RX 6750 XT
1578%
GeForce RTX 4060 Ti 8 GB
1595%
GeForce RTX 2080 Ti
1607%
GeForce RTX 3070
1681%
GeForce RTX 3070 Ti
1799%
Radeon RX 7700 XT
1818%
Radeon RX 6800
1853%
GeForce RTX 4070
2054%
Radeon RX 6800 XT
2105%
GeForce RTX 3080
2185%
Radeon RX 7800 XT
2207%
Radeon RX 6900 XT
2268%
GeForce RTX 4070 SUPER
2382%
Radeon RX 7900 GRE
2428%
GeForce RTX 3080 Ti
2448%
Radeon RX 6950 XT
2451%
GeForce RTX 3090
2494%
GeForce RTX 4070 Ti
2557%
GeForce RTX 4070 Ti SUPER
2793%
Radeon RX 7900 XT
2868%
GeForce RTX 3090 Ti
2893%
GeForce RTX 4080
3248%
GeForce RTX 4080 SUPER
3296%
Radeon RX 7900 XTX
3328%
GeForce RTX 4090
4080%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
612 MHz
Shader Clock
1512 MHz
Memory Clock
1080 MHz
2.2 Gbps effective

Memory

Memory Size
768 MB
Memory Type
GDDR3
Memory Bus
384 bit
Bandwidth
103.7 GB/s

Render Config

Shading Units
128
TMUs
32
ROPs
24
SM Count
16
L2 Cache
96 KB

Theoretical Performance

Pixel Rate
14.69 GPixel/s
Texture Rate
39.17 GTexel/s
FP32 (float)
387.1 GFLOPS

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 SKU 2

Graphics Features

DirectX
11.1 (10_0)
OpenGL
3.3
OpenCL
1.1 (1.0)
Vulkan
N/A
CUDA
1.0
Shader Model
4.0

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

Latest Drivers:
Windows 2000:
Quadro Release 261.19

Windows XP / Server 2003 x64:
GeForce Release 340.52
Quadro Release R319 U2 (321.01)
Tesla Release 258.96

Windows Vista / 7 / 8 / 8.1 / 10 32-bit:
GeForce Release 342.01
Quadro Release R340 U15 (342.01)
Tesla Release 258.96

Retail boards based on this design (11)

Name GPU Clock Memory Clock Other Changes
612 MHz 1080 MHz
612 MHz 1080 MHz 267 mm/10.5 inches
655 MHz 1125 MHz Single-slot
638 MHz 1125 MHz
630 MHz 1100 MHz
655 MHz 1125 MHz
612 MHz 1080 MHz
648 MHz 1116 MHz
650 MHz 1110 MHz
675 MHz 1150 MHz
685 MHz 1150 MHz
Nov 24th, 2024 19:18 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts