AMD Radeon RX 5700 vs NVIDIA GeForce GTX 1070
We compared two Desktop platform GPUs: 8GB VRAM Radeon RX 5700 and 8GB VRAM GeForce GTX 1070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon RX 5700 's Advantages
Released 3 years and 1 months late
Boost Clock has increased by 2% (1725MHz vs 1683MHz)
Larger VRAM bandwidth (448.0GB/s vs 256.3GB/s)
384 additional rendering cores
NVIDIA GeForce GTX 1070 's Advantages
Lower TDP (150W vs 180W)
Score
Benchmark
FP32 (float)
Radeon RX 5700
+22%
7.949 TFLOPS
GeForce GTX 1070
6.463 TFLOPS
3DMark Time Spy
Radeon RX 5700
+37%
8374
GeForce GTX 1070
6078
3DMark Time Spy Extreme
Radeon RX 5700
+40%
3956
GeForce GTX 1070
2825
Shadow of the Tomb Raider 2160p
Radeon RX 5700
+34%
35
GeForce GTX 1070
26
Shadow of the Tomb Raider 1440p
Radeon RX 5700
+36%
68
GeForce GTX 1070
50
Shadow of the Tomb Raider 1080p
Radeon RX 5700
+36%
105
GeForce GTX 1070
77
Battlefield 5 2160p
Radeon RX 5700
+18%
51
GeForce GTX 1070
43
Battlefield 5 1440p
Radeon RX 5700
+22%
97
GeForce GTX 1070
79
Battlefield 5 1080p
Radeon RX 5700
+35%
135
GeForce GTX 1070
100
GTA 5 2160p
Radeon RX 5700
+33%
64
GeForce GTX 1070
48
GTA 5 1440p
Radeon RX 5700
74
GeForce GTX 1070
+13%
84
GTA 5 1080p
Radeon RX 5700
+21%
180
GeForce GTX 1070
148
Graphics Card
Jul 2019
Release Date
Jun 2016
Navi
Generation
GeForce 10
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1465 MHz
Base Clock
1506 MHz
1725 MHz
Boost Clock
1683 MHz
1750 MHz
Memory Clock
2002 MHz
Memory
8GB
Memory Size
8GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
256.3GB/s
Render Config
36
Compute Units
-
-
SM Count
15
2304
Shading Units
1920
144
TMUs
120
64
ROPs
64
-
-
-
-
-
-
-
L1 Cache
48 KB (per SM)
4 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
110.4 GPixel/s
Pixel Rate
107.7 GPixel/s
248.4 GTexel/s
Texture Rate
202.0 GTexel/s
15.90 TFLOPS
FP16 (half)
101.0 GFLOPS
7.949 TFLOPS
FP32 (float)
6.463 TFLOPS
496.8 GFLOPS
FP64 (double)
202.0 GFLOPS
Board Design
180W
TDP
150W
450 W
Suggested PSU
450 W
1x HDMI 2.0b
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
Navi 10
GPU Name
GP104
Navi 10 XL
(215-0917220)
GPU Variant
GP104-200-A1
RDNA 1.0
Architecture
Pascal
TSMC
Foundry
TSMC
7 nm
Process Size
16 nm
10.3 billion
Transistors
7.2 billion
251 mm²
Die Size
314 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_1)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
6.1
6.8
Shader Model
6.4
