Home GPU Comparison NVIDIA GeForce GT 640 OEM Rebrand vs NVIDIA CMP 70HX

NVIDIA GeForce GT 640 OEM Rebrand vs NVIDIA CMP 70HX

We compared two Desktop platform GPUs: 1536MB VRAM GeForce GT 640 OEM Rebrand and 8GB VRAM CMP 70HX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA CMP 70HX 's Advantages
Released 8 years and 9 months late
Boost Clock1395MHz
More VRAM (8GB vs 1536GB)
Larger VRAM bandwidth (608.3GB/s vs 38.40GB/s)
3696 additional rendering cores

Score

Benchmark

FP32 (float)
GeForce GT 640 OEM Rebrand
0.415 TFLOPS
CMP 70HX +2480%
10.71 TFLOPS
VS

Graphics Card

Apr 2012
Release Date
Jan 2021
GeForce 600
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

-
Base Clock
1365 MHz
-
Boost Clock
1395 MHz
800 MHz
Memory Clock
1188 MHz

Memory

1536MB
Memory Size
8GB
DDR3
Memory Type
GDDR6X
192bit
Memory Bus
256bit
38.40GB/s
Bandwidth
608.3GB/s

Render Config

-
-
-
3
SM Count
30
144
Shading Units
3840
24
TMUs
120
24
ROPs
64
-
Tensor Cores
120
-
RT Cores
30
64 KB (per SM)
L1 Cache
128 KB (per SM)
384 KB
L2 Cache
4 MB
-
-
-

Theoretical Performance

4.320 GPixel/s
Pixel Rate
89.28 GPixel/s
17.28 GTexel/s
Texture Rate
167.4 GTexel/s
-
FP16 (half)
10.71 TFLOPS
414.7 GFLOPS
FP32 (float)
10.71 TFLOPS
34.56 GFLOPS
FP64 (double)
167.4 GFLOPS

Board Design

75W
TDP
Unknown
250 W
Suggested PSU
200 W
2x DVI 1x mini-HDMI 1.3a
Outputs
No outputs
None
Power Connectors
1x 12-pin

Graphics Processor

GF116
GPU Name
GA104
GF116-150-A1
GPU Variant
GA104-100-A1
Fermi 2.0
Architecture
Ampere
TSMC
Foundry
Samsung
40 nm
Process Size
8 nm
1.17 billion
Transistors
17.4 billion
238 mm²
Die Size
392 mm²

Graphics Features

12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
1.1
OpenCL
3.0
N/A
Vulkan
1.3
2.1
CUDA
8.6
5.1
Shader Model
6.8

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy