GeForce RTX 3060 vs Radeon HD 2900 XT
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 3060 and 512MB VRAM Radeon HD 2900 XT to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3060 's Advantages
Released 13 years and 8 months late
Boost Clock1777MHz
More VRAM (12GB vs 512GB)
Larger VRAM bandwidth (360.0GB/s vs 106.0GB/s)
3264 additional rendering cores
Lower TDP (170W vs 215W)
Score
Benchmark
FP32 (float)
GeForce RTX 3060
+2576%
12740
Radeon HD 2900 XT
476
Graphics Card
Jan 2021
Release Date
May 2007
GeForce 30
Generation
Radeon R600
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
1320 MHz
Base Clock
-
1777 MHz
Boost Clock
-
1875 MHz
Memory Clock
828 MHz
Memory
12GB
Memory Size
512MB
GDDR6
Memory Type
GDDR3
192bit
Memory Bus
512bit
360.0GB/s
Bandwidth
106.0GB/s
Render Config
-
Compute Units
4
28
SM Count
-
3584
Shading Units
320
112
TMUs
16
48
ROPs
16
112
Tensor Cores
-
28
RT Cores
-
128 KB (per SM)
L1 Cache
-
3 MB
L2 Cache
256 KB
Theoretical Performance
85.30 GPixel/s
Pixel Rate
11.89 GPixel/s
199.0 GTexel/s
Texture Rate
11.89 GTexel/s
12.74 TFLOPS
FP16 (half)
-
12.74 TFLOPS
FP32 (float)
475.5 GFLOPS
199.0 GFLOPS
FP64 (double)
-
Board Design
170W
TDP
215W
450 W
Suggested PSU
550 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
2x DVI
1x S-Video
1x 12-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
GA106
GPU Name
R600
GA106-300-A1
GPU Variant
R600 XT
(215RGMDKA13FG)
Ampere
Architecture
TeraScale
Samsung
Foundry
TSMC
8 nm
Process Size
80 nm
12 billion
Transistors
0.72 billion
276 mm²
Die Size
420 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
10.0 (10_0)
4.6
OpenGL
3.3 (full)
4.0 (partial)
3.0
OpenCL
N/A
1.3
Vulkan
N/A
8.6
CUDA
-
6.6
Shader Model
4.0