GeForce GTX 1050 vs Radeon HD 3870
We compared two Desktop platform GPUs: 2GB VRAM GeForce GTX 1050 and 512MB VRAM Radeon HD 3870 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX 1050 's Advantages
Released 8 years and 11 months late
Boost Clock1455MHz
More VRAM (2GB vs 512GB)
Larger VRAM bandwidth (112.1GB/s vs 72.06GB/s)
320 additional rendering cores
Lower TDP (75W vs 106W)
Score
Benchmark
FP32 (float)
GeForce GTX 1050
+274%
1862
Radeon HD 3870
497
Graphics Card
Oct 2016
Release Date
Nov 2007
GeForce 10
Generation
Radeon R600
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1354 MHz
Base Clock
-
1455 MHz
Boost Clock
-
1752 MHz
Memory Clock
1126 MHz
Memory
2GB
Memory Size
512MB
GDDR5
Memory Type
GDDR4
128bit
Memory Bus
256bit
112.1GB/s
Bandwidth
72.06GB/s
Render Config
-
Compute Units
4
5
SM Count
-
640
Shading Units
320
40
TMUs
16
32
ROPs
16
48 KB (per SM)
L1 Cache
-
1024 KB
L2 Cache
256 KB
Theoretical Performance
46.56 GPixel/s
Pixel Rate
12.43 GPixel/s
58.20 GTexel/s
Texture Rate
12.43 GTexel/s
29.10 GFLOPS
FP16 (half)
-
1.862 TFLOPS
FP32 (float)
497.3 GFLOPS
58.20 GFLOPS
FP64 (double)
99.46 GFLOPS
Board Design
75W
TDP
106W
250 W
Suggested PSU
300 W
1x DVI
1x HDMI 2.0
1x DisplayPort 1.4a
Outputs
2x DVI
1x S-Video
None
Power Connectors
1x 6-pin
Graphics Processor
GP107
GPU Name
RV670
GP107-300-A1
GPU Variant
RV670 XT
(215-0708005)
Pascal
Architecture
TeraScale
Samsung
Foundry
TSMC
14 nm
Process Size
55 nm
3.3 billion
Transistors
0.666 billion
132 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
