NVIDIA GeForce GTX 1070 GDDR5X vs AMD Radeon HD 6970 X2
We compared two Desktop platform GPUs: 8GB VRAM GeForce GTX 1070 GDDR5X and 2GB VRAM Radeon HD 6970 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
Boost Clock1683MHz
More VRAM (8GB vs 2GB)
Larger VRAM bandwidth (256.3GB/s vs 176.0GB/s)
384 additional rendering cores
Lower TDP (150W vs 375W)
Score
Benchmark
FP32 (float)
GeForce GTX 1070 GDDR5X
+139%
6.463 TFLOPS
Radeon HD 6970 X2
2.703 TFLOPS
Graphics Card
Dec 2018
Release Date
Unknown
GeForce 10
Generation
Northern Islands
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
1375 MHz
Memory
8GB
Memory Size
2GB
GDDR5X
Memory Type
GDDR5
256bit
Memory Bus
256bit
256.3GB/s
Bandwidth
176.0GB/s
Render Config
-
Compute Units
24
15
SM Count
-
1920
Shading Units
1536
120
TMUs
96
64
ROPs
32
-
-
-
-
-
-
48 KB (per SM)
L1 Cache
8 KB (per CU)
2 MB
L2 Cache
512 KB
-
-
-
Theoretical Performance
107.7 GPixel/s
Pixel Rate
28.16 GPixel/s
202.0 GTexel/s
Texture Rate
84.48 GTexel/s
101.0 GFLOPS
FP16 (half)
-
6.463 TFLOPS
FP32 (float)
2.703 TFLOPS
202.0 GFLOPS
FP64 (double)
-
Board Design
150W
TDP
375W
450 W
Suggested PSU
750 W
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
Outputs
2x DVI
1x HDMI 1.4a
2x mini-DisplayPort 1.2
1x 8-pin
Power Connectors
3x 8-pin
Graphics Processor
GP104
GPU Name
Antilles
GP104-200-A1
GPU Variant
Antilles XT
(215-0807027)
Pascal
Architecture
TeraScale 3
TSMC
Foundry
TSMC
16 nm
Process Size
40 nm
7.2 billion
Transistors
2.64 billion
314 mm²
Die Size
389 mm²
Graphics Features
12 (12_1)
DirectX
11.2 (11_0)
4.6
OpenGL
4.4
3.0
OpenCL
1.2
1.3
Vulkan
N/A
6.1
CUDA
-
6.4
Shader Model
5.0
