NVIDIA CMP 40HX vs NVIDIA CMP 170HX
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 16GB VRAM CMP 170HX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Boost Clock has increased by 17% (1650MHz vs 1410MHz)
Lower TDP (185W vs 250W)
NVIDIA CMP 170HX 's Advantages
Released 7 months late
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (1493GB/s vs 448.0GB/s)
2176 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 40HX
7.603 TFLOPS
CMP 170HX
+66%
12.63 TFLOPS
Graphics Card
Feb 2021
Release Date
Sep 2021
Mining GPUs
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 4.0 x4
Clock Speeds
1470 MHz
Base Clock
1140 MHz
1650 MHz
Boost Clock
1410 MHz
1750 MHz
Memory Clock
1458 MHz
Memory
8GB
Memory Size
16GB
GDDR6
Memory Type
HBM2e
256bit
Memory Bus
4096bit
448.0GB/s
Bandwidth
1493GB/s
Render Config
-
-
-
36
SM Count
70
2304
Shading Units
4480
144
TMUs
280
64
ROPs
128
288
Tensor Cores
280
36
RT Cores
-
64 KB (per SM)
L1 Cache
192 KB (per SM)
4 MB
L2 Cache
8 MB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
180.5 GPixel/s
237.6 GTexel/s
Texture Rate
394.8 GTexel/s
15.21 TFLOPS
FP16 (half)
50.53 TFLOPS
7.603 TFLOPS
FP32 (float)
12.63 TFLOPS
237.6 GFLOPS
FP64 (double)
6.317 TFLOPS
Board Design
185W
TDP
250W
450 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
TU106
GPU Name
GA100
TU106-100-A1
GPU Variant
GA100-105F-A1
Turing
Architecture
Ampere
TSMC
Foundry
TSMC
12 nm
Process Size
7 nm
10.8 billion
Transistors
54.2 billion
445 mm²
Die Size
826 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
7.5
CUDA
8.0
6.8
Shader Model
N/A
