NVIDIA CMP 40HX vs NVIDIA CMP 90HX
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 10GB VRAM CMP 90HX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Lower TDP (185W vs 320W)
NVIDIA CMP 90HX 's Advantages
Boost Clock has increased by 4% (1710MHz vs 1650MHz)
More VRAM (10GB vs 8GB)
Larger VRAM bandwidth (760.3GB/s vs 448.0GB/s)
4096 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 40HX
7.603 TFLOPS
CMP 90HX
+187%
21.89 TFLOPS
Graphics Card
Feb 2021
Release Date
Jul 2021
Mining GPUs
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 1.0 x4
Clock Speeds
1470 MHz
Base Clock
1500 MHz
1650 MHz
Boost Clock
1710 MHz
1750 MHz
Memory Clock
1188 MHz
Memory
8GB
Memory Size
10GB
GDDR6
Memory Type
GDDR6X
256bit
Memory Bus
320bit
448.0GB/s
Bandwidth
760.3GB/s
Render Config
-
-
-
36
SM Count
50
2304
Shading Units
6400
144
TMUs
200
64
ROPs
80
288
Tensor Cores
200
36
RT Cores
50
64 KB (per SM)
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
5 MB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
136.8 GPixel/s
237.6 GTexel/s
Texture Rate
342.0 GTexel/s
15.21 TFLOPS
FP16 (half)
21.89 TFLOPS
7.603 TFLOPS
FP32 (float)
21.89 TFLOPS
237.6 GFLOPS
FP64 (double)
342.0 GFLOPS
Board Design
185W
TDP
320W
450 W
Suggested PSU
700 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
TU106
GPU Name
GA102
TU106-100-A1
GPU Variant
GA102-100-A1
Turing
Architecture
Ampere
TSMC
Foundry
Samsung
12 nm
Process Size
8 nm
10.8 billion
Transistors
28.3 billion
445 mm²
Die Size
628 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.5
CUDA
8.6
6.8
Shader Model
6.8
