NVIDIA GeForce GTX 1070 GDDR5X vs ATI Radeon HD 3870 X2
We compared two Desktop platform GPUs: 8GB VRAM GeForce GTX 1070 GDDR5X and 512MB VRAM Radeon HD 3870 X2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GTX 1070 GDDR5X 's Advantages
Released 10 years and 11 months late
Boost Clock1683MHz
More VRAM (8GB vs 512GB)
Larger VRAM bandwidth (256.3GB/s vs 57.66GB/s)
1600 additional rendering cores
Lower TDP (150W vs 165W)
Score
Benchmark
FP32 (float)
GeForce GTX 1070 GDDR5X
+1124%
6.463 TFLOPS
Radeon HD 3870 X2
0.528 TFLOPS
Graphics Card
Dec 2018
Release Date
Jan 2008
GeForce 10
Generation
Radeon R600
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1506 MHz
Base Clock
-
1683 MHz
Boost Clock
-
1001 MHz
Memory Clock
901 MHz
Memory
8GB
Memory Size
512MB
GDDR5X
Memory Type
GDDR3
256bit
Memory Bus
256bit
256.3GB/s
Bandwidth
57.66GB/s
Render Config
-
Compute Units
4
15
SM Count
-
1920
Shading Units
320
120
TMUs
16
64
ROPs
16
-
-
-
-
-
-
48 KB (per SM)
L1 Cache
-
2 MB
L2 Cache
256 KB
-
-
-
Theoretical Performance
107.7 GPixel/s
Pixel Rate
13.20 GPixel/s
202.0 GTexel/s
Texture Rate
13.20 GTexel/s
101.0 GFLOPS
FP16 (half)
-
6.463 TFLOPS
FP32 (float)
528.0 GFLOPS
202.0 GFLOPS
FP64 (double)
105.6 GFLOPS
Board Design
150W
TDP
165W
450 W
Suggested PSU
450 W
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
Outputs
2x DVI
1x S-Video
1x 8-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
GP104
GPU Name
R680
GP104-200-A1
GPU Variant
R680 XT
(215-0708017)
Pascal
Architecture
TeraScale
TSMC
Foundry
TSMC
16 nm
Process Size
55 nm
7.2 billion
Transistors
0.666 billion
314 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
6.1
CUDA
-
6.4
Shader Model
4.1
