AMD Radeon HD 6970 vs NVIDIA GeForce GTX 1070 GDDR5X
We compared two Desktop platform GPUs: 2GB VRAM Radeon HD 6970 and 8GB VRAM GeForce GTX 1070 GDDR5X 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 8 years late
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 250W)
Score
Benchmark
FP32 (float)
Radeon HD 6970
2.703 TFLOPS
GeForce GTX 1070 GDDR5X
+139%
6.463 TFLOPS
Graphics Card
Dec 2010
Release Date
Dec 2018
Northern Islands
Generation
GeForce 10
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
-
Base Clock
1506 MHz
-
Boost Clock
1683 MHz
1375 MHz
Memory Clock
1001 MHz
Memory
2GB
Memory Size
8GB
GDDR5
Memory Type
GDDR5X
256bit
Memory Bus
256bit
176.0GB/s
Bandwidth
256.3GB/s
Render Config
24
Compute Units
-
-
SM Count
15
1536
Shading Units
1920
96
TMUs
120
32
ROPs
64
-
-
-
-
-
-
8 KB (per CU)
L1 Cache
48 KB (per SM)
512 KB
L2 Cache
2 MB
-
-
-
Theoretical Performance
28.16 GPixel/s
Pixel Rate
107.7 GPixel/s
84.48 GTexel/s
Texture Rate
202.0 GTexel/s
-
FP16 (half)
101.0 GFLOPS
2.703 TFLOPS
FP32 (float)
6.463 TFLOPS
675.8 GFLOPS
FP64 (double)
202.0 GFLOPS
Board Design
250W
TDP
150W
600 W
Suggested PSU
450 W
2x DVI
1x HDMI 1.4a
2x mini-DisplayPort 1.2
Outputs
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
Cayman
GPU Name
GP104
Cayman XT
(215-0807007)
GPU Variant
GP104-200-A1
TeraScale 3
Architecture
Pascal
TSMC
Foundry
TSMC
40 nm
Process Size
16 nm
2.64 billion
Transistors
7.2 billion
389 mm²
Die Size
314 mm²
Graphics Features
11.2 (11_0)
DirectX
12 (12_1)
4.4
OpenGL
4.6
1.2
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
6.1
5.0
Shader Model
6.4
