NVIDIA CMP 40HX vs ATI FirePro V3700
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 256MB VRAM FirePro V3700 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Released 12 years and 6 months late
Boost Clock1650MHz
More VRAM (8GB vs 256GB)
Larger VRAM bandwidth (448.0GB/s vs 15.20GB/s)
2264 additional rendering cores
ATI FirePro V3700 's Advantages
Lower TDP (32W vs 185W)
Score
Benchmark
FP32 (float)
CMP 40HX
+11779%
7.603 TFLOPS
FirePro V3700
0.064 TFLOPS
Graphics Card
Feb 2021
Release Date
Aug 2008
Mining GPUs
Generation
FirePro
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 2.0 x16
Clock Speeds
1470 MHz
Base Clock
-
1650 MHz
Boost Clock
-
1750 MHz
Memory Clock
950 MHz
Memory
8GB
Memory Size
256MB
GDDR6
Memory Type
GDDR3
256bit
Memory Bus
64bit
448.0GB/s
Bandwidth
15.20GB/s
Render Config
-
Compute Units
2
36
SM Count
-
2304
Shading Units
40
144
TMUs
4
64
ROPs
4
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
-
4 MB
L2 Cache
64 KB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
3.200 GPixel/s
237.6 GTexel/s
Texture Rate
3.200 GTexel/s
15.21 TFLOPS
FP16 (half)
-
7.603 TFLOPS
FP32 (float)
64.00 GFLOPS
237.6 GFLOPS
FP64 (double)
-
Board Design
185W
TDP
32W
450 W
Suggested PSU
200 W
No outputs
Outputs
2x DVI
1x 8-pin
Power Connectors
None
Graphics Processor
TU106
GPU Name
RV620
TU106-100-A1
GPU Variant
RV620 GL
(215-0670004)
Turing
Architecture
TeraScale
TSMC
Foundry
TSMC
12 nm
Process Size
55 nm
10.8 billion
Transistors
0.181 billion
445 mm²
Die Size
67 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
10.1 (10_1)
4.6
OpenGL
3.3
3.0
OpenCL
N/A
1.3
Vulkan
N/A
7.5
CUDA
-
6.8
Shader Model
4.1
