GPU Comparison
GEFORCE
NVIDIA CMP 30HX
CORE STATE
TU116
VRAM
6 GB
CLOCK SPEED
1785 MHz
TDP
125 W
BUS WIDTH
192 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2021
VS
GEFORCE
P106-090
CORE STATE
GP106
VRAM
3 GB
CLOCK SPEED
1531 MHz
TDP
75 W
BUS WIDTH
192 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
3dmark_3dmark_steel_nomad_dx12
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 30HX
P106-090
Core Specs
Shading Units
1,408
768
-45.5%
Shaders
1,408
768
-45.5%
TMUs
88
48
-45.5%
ROPs
48
48
0.0%
SM Count
22
6
-72.7%
Clocks
Base Clock
1530 MHz
1354 MHz
Boost Clock
1785 MHz
1531 MHz
Memory Clock
1750 MHz
14 Gbps effective
2002 MHz
8 Gbps effective
Memory
Memory Size
6 GB
3 GB
VRAM (MB)
6,144
3,072
-50.0%
Memory Type
GDDR6
GDDR5
Memory Bus
192 bit
192 bit
Bandwidth
336.0 GB/s
192.2 GB/s
Cache
L1 Cache
64 KB (per SM)
48 KB (per SM)
L2 Cache
1536 KB
1536 KB
Performance
Pixel Rate
85.68 GPixel/s
73.49 GPixel/s
Texture Rate
157.1 GTexel/s
73.49 GTexel/s
FP32 (TFLOPS)
5.027 TFLOPS
2.352 TFLOPS
FP64 (TFLOPS)
157.1 GFLOPS (1:32)
73.49 GFLOPS (1:32)
FP16 (TFLOPS)
10.05 TFLOPS (2:1)
36.74 GFLOPS (1:64)
Power
TDP
125 W
75 W
TDP (W)
125
75
-40.0%
Suggested PSU
300 W
250 W
Power Connectors
1x 8-pin
1x 6-pin
Architecture
Architecture
Turing
Pascal
GPU Name
TU116
GP106
Generation
Mining GPUs
Mining GPUs
Process Size
12 nm
16 nm
Transistors
6,600 million
4,400 million
Die Size
284 mm²
200 mm²
Foundry
TSMC
TSMC
Density
23.2M / mm²
22.0M / mm²
API Support
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
7.5
6.1
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
229 mm
9 inches
250 mm
9.8 inches
Height
111 mm
4.4 inches
—
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 1.0 x1
Other
Launch Price
799 USD
—
Production
End-of-life
End-of-life