NVIDIA PG506 232 vs ATI FireGL V7700
We compared two Desktop platform GPUs: 24GB VRAM PG506 232 and 512MB VRAM FireGL V7700 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA PG506 232 's Advantages
Released 13 years and 5 months late
Boost Clock1440MHz
More VRAM (24GB vs 512GB)
Larger VRAM bandwidth (933.1GB/s vs 72.06GB/s)
3264 additional rendering cores
Score
Benchmark
FP32 (float)
PG506 232
+1976%
10.32 TFLOPS
FireGL V7700
0.497 TFLOPS
Graphics Card
Apr 2021
Release Date
Nov 2007
Tesla
Generation
FireGL
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
930 MHz
Base Clock
-
1440 MHz
Boost Clock
-
1215 MHz
Memory Clock
1126 MHz
Memory
24GB
Memory Size
512MB
HBM2
Memory Type
GDDR4
3072bit
Memory Bus
256bit
933.1GB/s
Bandwidth
72.06GB/s
Render Config
-
Compute Units
4
56
SM Count
-
3584
Shading Units
320
224
TMUs
16
96
ROPs
16
224
Tensor Cores
-
-
-
-
192 KB (per SM)
L1 Cache
-
24 MB
L2 Cache
256 KB
-
-
-
Theoretical Performance
138.2 GPixel/s
Pixel Rate
12.43 GPixel/s
322.6 GTexel/s
Texture Rate
12.43 GTexel/s
10.32 TFLOPS
FP16 (half)
-
10.32 TFLOPS
FP32 (float)
497.3 GFLOPS
5.161 TFLOPS
FP64 (double)
99.46 GFLOPS
Board Design
165W
TDP
Unknown
450 W
Suggested PSU
200 W
No outputs
Outputs
1x DVI
1x DisplayPort
1x S-Video
8-pin EPS
Power Connectors
1x 6-pin
Graphics Processor
GA100
GPU Name
RV670
-
GPU Variant
RV670 GL
Ampere
Architecture
TeraScale
TSMC
Foundry
TSMC
7 nm
Process Size
55 nm
54.2 billion
Transistors
0.666 billion
826 mm²
Die Size
192 mm²
Graphics Features
N/A
DirectX
10.1 (10_1)
N/A
OpenGL
3.3 (full)
4.0 (partial)
3.0
OpenCL
N/A
N/A
Vulkan
N/A
8.0
CUDA
-
N/A
Shader Model
4.1
