GeForce GTX TITAN X vs Radeon HD 3870 AGP
We compared two Desktop platform GPUs: 12GB VRAM GeForce GTX TITAN X and 512MB VRAM Radeon HD 3870 AGP to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX TITAN X 's Advantages
Boost Clock1089MHz
More VRAM (12GB vs 512GB)
Larger VRAM bandwidth (336.6GB/s vs 72.06GB/s)
2752 additional rendering cores
Radeon HD 3870 AGP 's Advantages
Lower TDP (106W vs 250W)
Score
Benchmark
FP32 (float)
GeForce GTX TITAN X
+1246%
6691
Radeon HD 3870 AGP
497
Graphics Card
Mar 2015
Release Date
Unknown
GeForce 900
Generation
Radeon R600
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
AGP 8x
Clock Speeds
1000 MHz
Base Clock
-
1089 MHz
Boost Clock
-
1753 MHz
Memory Clock
1126 MHz
Memory
12GB
Memory Size
512MB
GDDR5
Memory Type
GDDR4
384bit
Memory Bus
256bit
336.6GB/s
Bandwidth
72.06GB/s
Render Config
-
Compute Units
4
3072
Shading Units
320
192
TMUs
16
96
ROPs
16
48 KB (per SMM)
L1 Cache
-
3 MB
L2 Cache
256 KB
Theoretical Performance
104.5 GPixel/s
Pixel Rate
12.43 GPixel/s
209.1 GTexel/s
Texture Rate
12.43 GTexel/s
6.691 TFLOPS
FP32 (float)
497.3 GFLOPS
209.1 GFLOPS
FP64 (double)
99.46 GFLOPS
Board Design
250W
TDP
106W
600 W
Suggested PSU
300 W
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
Outputs
2x DVI
1x S-Video
1x 6-pin + 1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
GM200
GPU Name
RV670
GM200-400-A1
GPU Variant
RV670 XT
(215-0708005)
Maxwell 2.0
Architecture
TeraScale
TSMC
Foundry
TSMC
28 nm
Process Size
55 nm
8 billion
Transistors
0.666 billion
601 mm²
Die Size
192 mm²
Graphics Features
12 (12_1)
DirectX
10.1 (10_1)
4.6
OpenGL
3.3 (full)
4.0 (partial)
3.0
OpenCL
N/A
1.3
Vulkan
N/A
5.2
CUDA
-
6.4
Shader Model
4.1