NVIDIA A40 PCIe vs ATI FireGL V5600
We compared two Desktop platform GPUs: 48GB VRAM A40 PCIe and 512MB VRAM FireGL V5600 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A40 PCIe 's Advantages
Released 13 years and 2 months late
Boost Clock1740MHz
More VRAM (48GB vs 512GB)
Larger VRAM bandwidth (695.8GB/s vs 35.20GB/s)
10632 additional rendering cores
ATI FireGL V5600 's Advantages
Lower TDP (89W vs 300W)
Score
Benchmark
FP32 (float)
A40 PCIe
+19389%
37.42 TFLOPS
FireGL V5600
0.192 TFLOPS
Graphics Card
Oct 2020
Release Date
Aug 2007
Tesla
Generation
FireGL
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
1305 MHz
Base Clock
-
1740 MHz
Boost Clock
-
1812 MHz
Memory Clock
1100 MHz
Memory
48GB
Memory Size
512MB
GDDR6
Memory Type
GDDR4
384bit
Memory Bus
128bit
695.8GB/s
Bandwidth
35.20GB/s
Render Config
-
Compute Units
3
84
SM Count
-
10752
Shading Units
120
336
TMUs
8
112
ROPs
4
336
Tensor Cores
-
84
RT Cores
-
128 KB (per SM)
L1 Cache
-
6 MB
L2 Cache
64 KB
-
-
-
Theoretical Performance
194.9 GPixel/s
Pixel Rate
3.200 GPixel/s
584.6 GTexel/s
Texture Rate
6.400 GTexel/s
37.42 TFLOPS
FP16 (half)
-
37.42 TFLOPS
FP32 (float)
192.0 GFLOPS
584.6 GFLOPS
FP64 (double)
-
Board Design
300W
TDP
89W
700 W
Suggested PSU
250 W
3x DisplayPort 1.4a
Outputs
2x DVI
8-pin EPS
Power Connectors
None
Graphics Processor
GA102
GPU Name
RV630
-
GPU Variant
RV630 GL
Ampere
Architecture
TeraScale
Samsung
Foundry
TSMC
8 nm
Process Size
65 nm
28.3 billion
Transistors
0.39 billion
628 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
8.6
CUDA
-
6.6
Shader Model
4.0
