FireStream 9250 vs PG506 232
We compared two Desktop platform GPUs: 1024MB VRAM FireStream 9250 and 24GB VRAM PG506 232 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
FireStream 9250 's Advantages
Lower TDP (150W vs 165W)
PG506 232 's Advantages
Released 12 years and 10 months late
Boost Clock1440MHz
More VRAM (24GB vs 1024GB)
Larger VRAM bandwidth (933.1GB/s vs 63.55GB/s)
2784 additional rendering cores
Score
Benchmark
FP32 (float)
FireStream 9250
1000
PG506 232
+932%
10320
Graphics Card
Jun 2008
Release Date
Apr 2021
FireStream
Generation
Tesla
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
930 MHz
-
Boost Clock
1440 MHz
993 MHz
Memory Clock
1215 MHz
Memory
1024MB
Memory Size
24GB
GDDR3
Memory Type
HBM2
256bit
Memory Bus
3072bit
63.55GB/s
Bandwidth
933.1GB/s
Render Config
10
Compute Units
-
-
SM Count
56
800
Shading Units
3584
40
TMUs
224
16
ROPs
96
-
Tensor Cores
224
16 KB (per CU)
L1 Cache
192 KB (per SM)
256 KB
L2 Cache
24 MB
Theoretical Performance
10.00 GPixel/s
Pixel Rate
138.2 GPixel/s
25.00 GTexel/s
Texture Rate
322.6 GTexel/s
-
FP16 (half)
10.32 TFLOPS
1000 GFLOPS
FP32 (float)
10.32 TFLOPS
200.0 GFLOPS
FP64 (double)
5.161 TFLOPS
Board Design
150W
TDP
165W
450 W
Suggested PSU
450 W
1x DVI
Outputs
No outputs
1x 6-pin
Power Connectors
8-pin EPS
Graphics Processor
RV770
GPU Name
GA100
RV770 PRO
GPU Variant
-
TeraScale
Architecture
Ampere
TSMC
Foundry
TSMC
55 nm
Process Size
7 nm
0.956 billion
Transistors
54.2 billion
256 mm²
Die Size
826 mm²
Graphics Features
10.1 (10_1)
DirectX
N/A
3.3
OpenGL
N/A
1.1
OpenCL
3.0
N/A
Vulkan
N/A
-
CUDA
8.0
4.1
Shader Model
N/A
