Intel UHD Graphics 620 vs NVIDIA GeForce GTX 650 Ti
We compared a Integrated graphics card GPU: 0System Shared VRAM UHD Graphics 620 and a Desktop platform GPU: 1024MB VRAM GeForce GTX 650 Ti to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel UHD Graphics 620 's Advantages
Released 5 years and 10 months late
Boost Clock1000MHz
Lower TDP (15W vs 110W)
NVIDIA GeForce GTX 650 Ti 's Advantages
576 additional rendering cores
Score
Benchmark
FP32 (float)
UHD Graphics 620
0.384 TFLOPS
GeForce GTX 650 Ti
+271%
1.425 TFLOPS
Graphics Card
Aug 2018
Release Date
Oct 2012
HD Graphics-M
Generation
GeForce 600
Integrated
Type
Desktop
Ring Bus
Bus Interface
PCIe 3.0 x16
Clock Speeds
300 MHz
Base Clock
-
1000 MHz
Boost Clock
-
System Shared
Memory Clock
1350 MHz
Memory
System Shared
Memory Size
1024MB
System Shared
Memory Type
GDDR5
System Shared
Memory Bus
128bit
System Dependent
Bandwidth
86.40GB/s
Render Config
-
-
-
-
-
-
192
Shading Units
768
24
TMUs
64
3
ROPs
16
-
-
-
-
-
-
-
L1 Cache
16 KB (per SMX)
-
L2 Cache
256 KB
-
-
-
Theoretical Performance
3.000 GPixel/s
Pixel Rate
14.85 GPixel/s
24.00 GTexel/s
Texture Rate
59.39 GTexel/s
768.0 GFLOPS
FP16 (half)
-
384.0 GFLOPS
FP32 (float)
1425 GFLOPS
96.00 GFLOPS
FP64 (double)
59.39 GFLOPS
Board Design
15W
TDP
110W
-
Suggested PSU
300 W
No outputs
Outputs
2x DVI
1x mini-HDMI 1.4a
-
Power Connectors
1x 6-pin
Graphics Processor
Whiskey Lake GT2
GPU Name
GK106
-
GPU Variant
GK106-220-A1
Generation 9.5
Architecture
Kepler
Intel
Foundry
TSMC
14 nm
Process Size
28 nm
Unknown
Transistors
2.54 billion
Unknown
Die Size
221 mm²
Graphics Features
12 (12_1)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
-
CUDA
3.0
6.4
Shader Model
5.1
