FireGL V8650 vs PG506 232
We compared two Desktop platform GPUs: 2GB VRAM FireGL V8650 and 24GB VRAM PG506 232 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
PG506 232 's Advantages
Released 13 years and 8 months late
Boost Clock1440MHz
More VRAM (24GB vs 2GB)
Larger VRAM bandwidth (933.1GB/s vs 111.1GB/s)
3264 additional rendering cores
Score
Benchmark
FP32 (float)
FireGL V8650
440
PG506 232
+2245%
10320
Graphics Card
Aug 2007
Release Date
Apr 2021
FireGL
Generation
Tesla
Desktop
Type
Desktop
PCIe 1.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
930 MHz
-
Boost Clock
1440 MHz
868 MHz
Memory Clock
1215 MHz
Memory
2GB
Memory Size
24GB
GDDR4
Memory Type
HBM2
512bit
Memory Bus
3072bit
111.1GB/s
Bandwidth
933.1GB/s
Render Config
4
Compute Units
-
-
SM Count
56
320
Shading Units
3584
16
TMUs
224
16
ROPs
96
-
Tensor Cores
224
-
L1 Cache
192 KB (per SM)
256 KB
L2 Cache
24 MB
Theoretical Performance
11.01 GPixel/s
Pixel Rate
138.2 GPixel/s
11.01 GTexel/s
Texture Rate
322.6 GTexel/s
-
FP16 (half)
10.32 TFLOPS
440.3 GFLOPS
FP32 (float)
10.32 TFLOPS
-
FP64 (double)
5.161 TFLOPS
Board Design
Unknown
TDP
165W
200 W
Suggested PSU
450 W
2x DVI
1x S-Video
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
R600
GPU Name
GA100
R600 V8650
(215RGIDKA13FG)
GPU Variant
-
TeraScale
Architecture
Ampere
TSMC
Foundry
TSMC
80 nm
Process Size
7 nm
0.72 billion
Transistors
54.2 billion
420 mm²
Die Size
826 mm²
Graphics Features
10.0 (10_0)
DirectX
N/A
3.3 (full)
4.0 (partial)
OpenGL
N/A
N/A
OpenCL
3.0
N/A
Vulkan
N/A
-
CUDA
8.0
4.0
Shader Model
N/A
