NVIDIA CMP 40HX vs ATI FireGL V5600
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 512MB VRAM FireGL V5600 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 6 months late
Boost Clock1650MHz
More VRAM (8GB vs 512GB)
Larger VRAM bandwidth (448.0GB/s vs 35.20GB/s)
2184 additional rendering cores
ATI FireGL V5600 's Advantages
Lower TDP (89W vs 185W)
Score
Benchmark
FP32 (float)
CMP 40HX
+3859%
7.603 TFLOPS
FireGL V5600
0.192 TFLOPS
Graphics Card
Feb 2021
Release Date
Aug 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
1100 MHz
Memory
8GB
Memory Size
512MB
GDDR6
Memory Type
GDDR4
256bit
Memory Bus
128bit
448.0GB/s
Bandwidth
35.20GB/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
3.200 GPixel/s
237.6 GTexel/s
Texture Rate
6.400 GTexel/s
15.21 TFLOPS
FP16 (half)
-
7.603 TFLOPS
FP32 (float)
192.0 GFLOPS
237.6 GFLOPS
FP64 (double)
-
Board Design
185W
TDP
89W
450 W
Suggested PSU
250 W
No outputs
Outputs
2x DVI
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
