GeForce GTX 470 and P106-090 - video card comparison
Passmark - benchmark score GeForce GTX 470 vs P106-090
GeForce GTX 470
3199
P106-090
2412
GeForce GTX 470
P106-090
Architecture
Fermi (2010−2014)
Pascal (2016−2021)
GPU code name
GF100
GP106
Market segment
Desktop
Desktop
Release date
April 2010
July 2017
Bus support
16x PCI-E 2.0
-
Interface
PCIe 2.0 x16
PCIe 3.0 x16
Supplementary power connectors
Two 6-pins
1x 6-pin
SLI options
+
-
Boost clock speed
-
1531 MHz
Core clock speed
607 MHz
1354 MHz
CUDA cores
448
-
Floating-point performance
1,088.6 gflops
2,352 gflops
Manufacturing process technology
40 nm
16 nm
Number of transistors
3,100 million
4,400 million
Pipelines / CUDA cores
448
768
Power consumption (TDP)
225 Watt
75 Watt
Maximum GPU temperature
105 °C
-
Texture fill rate
34.0 billion/sec
73.49
Memory type
GDDR5
GDDR5
Maximum RAM amount
1280 MB
3 GB
Memory bus width
320 Bit
192 Bit
Memory clock speed
1674 MHz (3348 data rate)
8008 MHz
Memory bandwidth
133.9 GB/s
192.2 GB/s
Shared memory
-
-
Display Connectors
Two Dual Link DVIMini HDMI
No outputs
Multi monitor support
+
-
HDMI
+
-
Maximum VGA resolution
2048x1536
-
Audio input for HDMI
Internal
-
DirectX
12 (11_0)
12 (12_1)
CUDA
+
6.1
OpenCL
1.1
1.2
OpenGL
4.2
4.6
Shader Model
5.1
6.4
Vulkan
N/A
1.2.131