P102-100 and GeForce GTX 1650 - video card comparison
P102-100
GeForce GTX 1650
Architecture
Pascal (2016−2021)
Turing (2018−2021)
GPU code name
GP102
TU117
Market segment
Desktop
Desktop
Release date
February 2018
April 2019
Interface
PCIe 3.0 x4
PCIe 3.0 x16
Supplementary power connectors
2x 8-pin
None
Boost clock speed
1683 MHz
1665 MHz
Core clock speed
1582 MHz
1485 MHz
Floating-point performance
10,125 gflops
-
Manufacturing process technology
16 nm
12 nm
Number of transistors
11,800 million
4,700 million
Pipelines / CUDA cores
3200
896
Power consumption (TDP)
250 Watt
75 Watt
Texture fill rate
336.6
93.24
Memory type
GDDR5X
GDDR5
Maximum RAM amount
5 GB
4 GB
Memory bus width
320 Bit
128 Bit
Memory clock speed
11008 MHz
8000 MHz
Memory bandwidth
440.3 GB/s
128.0 GB/s
Shared memory
-
-
Display Connectors
No outputs
1x DVI, 1x HDMI, 1x DisplayPort
HDMI
-
+
DirectX
12 (12_1)
12 (12_1)
CUDA
6.1
7.5
OpenCL
1.2
1.2
OpenGL
4.6
4.6
Shader Model
6.4
6.5
Vulkan
1.2.131
1.2.131