ATI FireGL V3600 vs NVIDIA CMP 70HX
We compared two Desktop platform GPUs: 256MB VRAM FireGL V3600 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 13 years and 7 months late
Boost Clock1395MHz
More VRAM (8GB vs 256GB)
Larger VRAM bandwidth (608.3GB/s vs 16.00GB/s)
3720 additional rendering cores
Score
Benchmark
FP32 (float)
FireGL V3600
0.144 TFLOPS
CMP 70HX
+7337%
10.71 TFLOPS
Graphics Card
Jun 2007
Release Date
Jan 2021
FireGL
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 1.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
-
Base Clock
1365 MHz
-
Boost Clock
1395 MHz
500 MHz
Memory Clock
1188 MHz
Memory
256MB
Memory Size
8GB
DDR2
Memory Type
GDDR6X
128bit
Memory Bus
256bit
16.00GB/s
Bandwidth
608.3GB/s
Render Config
3
Compute Units
-
-
SM Count
30
120
Shading Units
3840
8
TMUs
120
4
ROPs
64
-
Tensor Cores
120
-
RT Cores
30
-
L1 Cache
128 KB (per SM)
64 KB
L2 Cache
4 MB
-
-
-
Theoretical Performance
2.400 GPixel/s
Pixel Rate
89.28 GPixel/s
4.800 GTexel/s
Texture Rate
167.4 GTexel/s
-
FP16 (half)
10.71 TFLOPS
144.0 GFLOPS
FP32 (float)
10.71 TFLOPS
-
FP64 (double)
167.4 GFLOPS
Board Design
73W
TDP
Unknown
250 W
Suggested PSU
200 W
No outputs
Outputs
No outputs
None
Power Connectors
1x 12-pin
Graphics Processor
RV630
GPU Name
GA104
RV630 GL
GPU Variant
GA104-100-A1
TeraScale
Architecture
Ampere
TSMC
Foundry
Samsung
65 nm
Process Size
8 nm
0.39 billion
Transistors
17.4 billion
153 mm²
Die Size
392 mm²
Graphics Features
10.0 (10_0)
DirectX
12 Ultimate (12_2)
3.3
OpenGL
4.6
N/A
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
8.6
4.0
Shader Model
6.8
