CMP 170HX vs GeForce GT 640 Rev. 2
We compared two Desktop platform GPUs: 16GB VRAM CMP 170HX and 1024MB VRAM GeForce GT 640 Rev. 2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
CMP 170HX 's Advantages
Released 8 years and 4 months late
Boost Clock1410MHz
More VRAM (16GB vs 1024GB)
Larger VRAM bandwidth (1493GB/s vs 40.06GB/s)
4096 additional rendering cores
GeForce GT 640 Rev. 2 's Advantages
Lower TDP (49W vs 250W)
Score
Benchmark
FP32 (float)
CMP 170HX
+1472%
12630
GeForce GT 640 Rev. 2
803
Graphics Card
Sep 2021
Release Date
May 2013
Mining GPUs
Generation
GeForce 600
Desktop
Type
Desktop
PCIe 4.0 x4
Bus Interface
PCIe 2.0 x8
Clock Speeds
1140 MHz
Base Clock
-
1410 MHz
Boost Clock
-
1458 MHz
Memory Clock
1252 MHz
Memory
16GB
Memory Size
1024MB
HBM2e
Memory Type
GDDR5
4096bit
Memory Bus
64bit
1493GB/s
Bandwidth
40.06GB/s
Render Config
70
SM Count
-
4480
Shading Units
384
280
TMUs
32
128
ROPs
8
280
Tensor Cores
-
192 KB (per SM)
L1 Cache
16 KB (per SMX)
8 MB
L2 Cache
512 KB
Theoretical Performance
180.5 GPixel/s
Pixel Rate
8.368 GPixel/s
394.8 GTexel/s
Texture Rate
33.47 GTexel/s
50.53 TFLOPS
FP16 (half)
-
12.63 TFLOPS
FP32 (float)
803.3 GFLOPS
6.317 TFLOPS
FP64 (double)
33.47 GFLOPS
Board Design
250W
TDP
49W
600 W
Suggested PSU
200 W
No outputs
Outputs
1x DVI
1x HDMI 1.4a
1x VGA
2x 8-pin
Power Connectors
None
Graphics Processor
GA100
GPU Name
GK208
GA100-105F-A1
GPU Variant
GK208-400-A1
Ampere
Architecture
Kepler 2.0
TSMC
Foundry
TSMC
7 nm
Process Size
28 nm
54.2 billion
Transistors
1.02 billion
826 mm²
Die Size
87 mm²
Graphics Features
N/A
DirectX
12 (11_0)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.1
8.0
CUDA
3.5
N/A
Shader Model
5.1
