AMD Radeon HD 6990 vs NVIDIA GeForce GTX 260
We compared two Desktop platform GPUs: 2GB VRAM Radeon HD 6990 and 896MB VRAM GeForce GTX 260 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon HD 6990 's Advantages
Released 2 years and 9 months late
More VRAM (2GB vs 896GB)
Larger VRAM bandwidth (160.0GB/s vs 111.9GB/s)
1344 additional rendering cores
NVIDIA GeForce GTX 260 's Advantages
Lower TDP (182W vs 375W)
Score
Benchmark
FP32 (float)
Radeon HD 6990
+434%
2.55 TFLOPS
GeForce GTX 260
0.477 TFLOPS
Graphics Card
Mar 2011
Release Date
Jun 2008
Northern Islands
Generation
GeForce 200
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
-
-
-
-
-
1250 MHz
Memory Clock
999 MHz
Memory
2GB
Memory Size
896MB
GDDR5
Memory Type
GDDR3
256bit
Memory Bus
448bit
160.0GB/s
Bandwidth
111.9GB/s
Render Config
24
Compute Units
-
-
SM Count
24
1536
Shading Units
192
96
TMUs
64
32
ROPs
28
-
-
-
-
-
-
8 KB (per CU)
L1 Cache
-
512 KB
L2 Cache
224 KB
-
-
-
Theoretical Performance
26.56 GPixel/s
Pixel Rate
16.13 GPixel/s
79.68 GTexel/s
Texture Rate
36.86 GTexel/s
-
-
-
2.550 TFLOPS
FP32 (float)
476.9 GFLOPS
637.4 GFLOPS
FP64 (double)
59.62 GFLOPS
Board Design
375W
TDP
182W
750 W
Suggested PSU
450 W
1x DVI
4x mini-DisplayPort 1.2
Outputs
2x DVI
1x S-Video
2x 8-pin
Power Connectors
2x 6-pin
Graphics Processor
Antilles
GPU Name
GT200
Antilles XT
(215-0807027)
GPU Variant
G200-100-A2
TeraScale 3
Architecture
Tesla 2.0
TSMC
Foundry
TSMC
40 nm
Process Size
65 nm
2.64 billion
Transistors
1.4 billion
389 mm²
Die Size
576 mm²
Graphics Features
11.2 (11_0)
DirectX
11.1 (10_0)
4.4
OpenGL
3.3
1.2
OpenCL
1.1
N/A
Vulkan
N/A
-
CUDA
1.3
5.0
Shader Model
4.0
