FireGL V8650 vs A40 PCIe
We compared two Desktop platform GPUs: 2GB VRAM FireGL V8650 and 48GB VRAM A40 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
A40 PCIe 's Advantages
Released 13 years and 2 months late
Boost Clock1740MHz
More VRAM (48GB vs 2GB)
Larger VRAM bandwidth (695.8GB/s vs 111.1GB/s)
10432 additional rendering cores
Score
Benchmark
FP32 (float)
FireGL V8650
440
A40 PCIe
+8404%
37420
Graphics Card
Aug 2007
Release Date
Oct 2020
FireGL
Generation
Tesla
Desktop
Type
Desktop
PCIe 1.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1305 MHz
-
Boost Clock
1740 MHz
868 MHz
Memory Clock
1812 MHz
Memory
2GB
Memory Size
48GB
GDDR4
Memory Type
GDDR6
512bit
Memory Bus
384bit
111.1GB/s
Bandwidth
695.8GB/s
Render Config
4
Compute Units
-
-
SM Count
84
320
Shading Units
10752
16
TMUs
336
16
ROPs
112
-
Tensor Cores
336
-
RT Cores
84
-
L1 Cache
128 KB (per SM)
256 KB
L2 Cache
6 MB
Theoretical Performance
11.01 GPixel/s
Pixel Rate
194.9 GPixel/s
11.01 GTexel/s
Texture Rate
584.6 GTexel/s
-
FP16 (half)
37.42 TFLOPS
440.3 GFLOPS
FP32 (float)
37.42 TFLOPS
-
FP64 (double)
584.6 GFLOPS
Board Design
Unknown
TDP
300W
200 W
Suggested PSU
700 W
2x DVI
1x S-Video
Outputs
3x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
R600
GPU Name
GA102
R600 V8650
(215RGIDKA13FG)
GPU Variant
-
TeraScale
Architecture
Ampere
TSMC
Foundry
Samsung
80 nm
Process Size
8 nm
0.72 billion
Transistors
28.3 billion
420 mm²
Die Size
628 mm²
Graphics Features
10.0 (10_0)
DirectX
12 Ultimate (12_2)
3.3 (full)
4.0 (partial)
OpenGL
4.6
N/A
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
8.6
4.0
Shader Model
6.6
