NVIDIA CMP 50HX vs NVIDIA GeForce GT 1030 DDR4
We compared two Desktop platform GPUs: 10GB VRAM CMP 50HX and 2GB VRAM GeForce GT 1030 DDR4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 50HX 's Advantages
Released 3 years and 3 months late
Boost Clock has increased by 12% (1545MHz vs 1379MHz)
More VRAM (10GB vs 2GB)
Larger VRAM bandwidth (560.0GB/s vs 16.80GB/s)
3200 additional rendering cores
NVIDIA GeForce GT 1030 DDR4 's Advantages
Lower TDP (20W vs 250W)
Score
Benchmark
FP32 (float)
CMP 50HX
+945%
11.07 TFLOPS
GeForce GT 1030 DDR4
1.059 TFLOPS
Blender
CMP 50HX
+1341%
1384
GeForce GT 1030 DDR4
96
Graphics Card
Jun 2021
Release Date
Mar 2018
Mining GPUs
Generation
GeForce 10
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 3.0 x4
Clock Speeds
1350 MHz
Base Clock
1152 MHz
1545 MHz
Boost Clock
1379 MHz
1750 MHz
Memory Clock
1050 MHz
Memory
10GB
Memory Size
2GB
GDDR6
Memory Type
DDR4
320bit
Memory Bus
64bit
560.0GB/s
Bandwidth
16.80GB/s
Render Config
-
-
-
56
SM Count
3
3584
Shading Units
384
192
TMUs
24
80
ROPs
16
448
Tensor Cores
-
56
RT Cores
-
64 KB (per SM)
L1 Cache
48 KB (per SM)
5 MB
L2 Cache
512 KB
-
-
-
Theoretical Performance
123.6 GPixel/s
Pixel Rate
22.06 GPixel/s
296.6 GTexel/s
Texture Rate
33.10 GTexel/s
22.15 TFLOPS
FP16 (half)
16.55 GFLOPS
11.07 TFLOPS
FP32 (float)
1059 GFLOPS
346.1 GFLOPS
FP64 (double)
33.10 GFLOPS
Board Design
250W
TDP
20W
600 W
Suggested PSU
200 W
No outputs
Outputs
1x DVI
1x HDMI 2.0
2x 8-pin
Power Connectors
None
Graphics Processor
TU102
GPU Name
GP108
TU102-100-A1
GPU Variant
GP108-310-A1
Turing
Architecture
Pascal
TSMC
Foundry
Samsung
12 nm
Process Size
14 nm
18.6 billion
Transistors
1.8 billion
754 mm²
Die Size
74 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.5
CUDA
6.1
6.8
Shader Model
6.4
