NVIDIA CMP 40HX vs ATI FireGL V3600
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 256MB VRAM FireGL V3600 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Released 13 years and 8 months late
Boost Clock1650MHz
More VRAM (8GB vs 256GB)
Larger VRAM bandwidth (448.0GB/s vs 16.00GB/s)
2184 additional rendering cores
ATI FireGL V3600 's Advantages
Lower TDP (73W vs 185W)
Score
Benchmark
FP32 (float)
CMP 40HX
+5179%
7.603 TFLOPS
FireGL V3600
0.144 TFLOPS
Graphics Card
Feb 2021
Release Date
Jun 2007
Mining GPUs
Generation
FireGL
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 1.0 x16
Clock Speeds
1470 MHz
Base Clock
-
1650 MHz
Boost Clock
-
1750 MHz
Memory Clock
500 MHz
Memory
8GB
Memory Size
256MB
GDDR6
Memory Type
DDR2
256bit
Memory Bus
128bit
448.0GB/s
Bandwidth
16.00GB/s
Render Config
-
Compute Units
3
36
SM Count
-
2304
Shading Units
120
144
TMUs
8
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
2.400 GPixel/s
237.6 GTexel/s
Texture Rate
4.800 GTexel/s
15.21 TFLOPS
FP16 (half)
-
7.603 TFLOPS
FP32 (float)
144.0 GFLOPS
237.6 GFLOPS
FP64 (double)
-
Board Design
185W
TDP
73W
450 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
None
Graphics Processor
TU106
GPU Name
RV630
TU106-100-A1
GPU Variant
RV630 GL
Turing
Architecture
TeraScale
TSMC
Foundry
TSMC
12 nm
Process Size
65 nm
10.8 billion
Transistors
0.39 billion
445 mm²
Die Size
153 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
10.0 (10_0)
4.6
OpenGL
3.3
3.0
OpenCL
N/A
1.3
Vulkan
N/A
7.5
CUDA
-
6.8
Shader Model
4.0
