NVIDIA CMP 170HX vs NVIDIA P102 101
We compared two Desktop platform GPUs: 16GB VRAM CMP 170HX and 10GB VRAM P102 101 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 170HX 's Advantages
Released 3 years and 8 months late
More VRAM (16GB vs 10GB)
Larger VRAM bandwidth (1493GB/s vs 320.3GB/s)
1280 additional rendering cores
NVIDIA P102 101 's Advantages
Boost Clock has increased by 18% (1670MHz vs 1410MHz)
Score
Benchmark
FP32 (float)
CMP 170HX
+18%
12.63 TFLOPS
P102 101
10.69 TFLOPS
Graphics Card
Sep 2021
Release Date
Jan 2018
Mining GPUs
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 4.0 x4
Bus Interface
PCIe 3.0 x4
Clock Speeds
1140 MHz
Base Clock
1557 MHz
1410 MHz
Boost Clock
1670 MHz
1458 MHz
Memory Clock
2002 MHz
Memory
16GB
Memory Size
10GB
HBM2e
Memory Type
GDDR5
4096bit
Memory Bus
320bit
1493GB/s
Bandwidth
320.3GB/s
Render Config
-
-
-
70
SM Count
25
4480
Shading Units
3200
280
TMUs
200
128
ROPs
80
280
Tensor Cores
-
-
-
-
192 KB (per SM)
L1 Cache
48 KB (per SM)
8 MB
L2 Cache
0 MB
-
-
-
Theoretical Performance
180.5 GPixel/s
Pixel Rate
133.6 GPixel/s
394.8 GTexel/s
Texture Rate
334.0 GTexel/s
50.53 TFLOPS
FP16 (half)
167.0 GFLOPS
12.63 TFLOPS
FP32 (float)
10.69 TFLOPS
6.317 TFLOPS
FP64 (double)
334.0 GFLOPS
Board Design
250W
TDP
250W
600 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
2x 8-pin
Power Connectors
2x 8-pin
Graphics Processor
GA100
GPU Name
GP102
GA100-105F-A1
GPU Variant
GP102-101-A1
Ampere
Architecture
Pascal
TSMC
Foundry
TSMC
7 nm
Process Size
16 nm
54.2 billion
Transistors
11.8 billion
826 mm²
Die Size
471 mm²
Graphics Features
N/A
DirectX
12 (12_1)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
8.0
CUDA
6.1
N/A
Shader Model
6.4
