NVIDIA B100 vs ATI FireGL V3600
We compared two Desktop platform GPUs: 96GB VRAM B100 and 256MB VRAM FireGL V3600 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA B100 's Advantages
Released 17 years and 5 months late
Boost Clock1837MHz
More VRAM (96GB vs 256GB)
Larger VRAM bandwidth (4.10TB/s vs 16.00GB/s)
16776 additional rendering cores
ATI FireGL V3600 's Advantages
Lower TDP (73W vs 1000W)
Score
Benchmark
FP32 (float)
B100
+43011%
62.08 TFLOPS
FireGL V3600
0.144 TFLOPS
Graphics Card
Nov 2024
Release Date
Jun 2007
Server Blackwell
Generation
FireGL
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
1665 MHz
Base Clock
-
1837 MHz
Boost Clock
-
2000 MHz
Memory Clock
500 MHz
Memory
96GB
Memory Size
256MB
HBM3e
Memory Type
DDR2
4096bit
Memory Bus
128bit
4.10TB/s
Bandwidth
16.00GB/s
Render Config
-
Compute Units
3
132
SM Count
-
16896
Shading Units
120
528
TMUs
8
24
ROPs
4
528
Tensor Cores
-
-
-
-
256 KB (per SM)
L1 Cache
-
50 MB
L2 Cache
64 KB
-
-
-
Theoretical Performance
44.09 GPixel/s
Pixel Rate
2.400 GPixel/s
969.9 GTexel/s
Texture Rate
4.800 GTexel/s
248.3 TFLOPS
FP16 (half)
-
62.08 TFLOPS
FP32 (float)
144.0 GFLOPS
31.04 TFLOPS
FP64 (double)
-
Board Design
1000W
TDP
73W
1400 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
-
Power Connectors
None
Graphics Processor
GB102
GPU Name
RV630
-
GPU Variant
RV630 GL
Blackwell
Architecture
TeraScale
TSMC
Foundry
TSMC
5 nm
Process Size
65 nm
104 billion
Transistors
0.39 billion
Unknown
Die Size
153 mm²
Graphics Features
N/A
DirectX
10.0 (10_0)
N/A
OpenGL
3.3
3.0
OpenCL
N/A
N/A
Vulkan
N/A
10.1
CUDA
-
N/A
Shader Model
4.0
