NVIDIA B100 vs AMD FireStream 9370
We compared two Desktop platform GPUs: 96GB VRAM B100 and 4GB VRAM FireStream 9370 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA B100 's Advantages
Released 14 years and 5 months late
Boost Clock1837MHz
More VRAM (96GB vs 4GB)
Larger VRAM bandwidth (4.10TB/s vs 147.2GB/s)
15296 additional rendering cores
AMD FireStream 9370 's Advantages
Lower TDP (225W vs 1000W)
Score
Benchmark
FP32 (float)
B100
+2251%
62.08 TFLOPS
FireStream 9370
2.64 TFLOPS
Graphics Card
Nov 2024
Release Date
Jun 2010
Server Blackwell
Generation
FireStream
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1665 MHz
Base Clock
-
1837 MHz
Boost Clock
-
2000 MHz
Memory Clock
1150 MHz
Memory
96GB
Memory Size
4GB
HBM3e
Memory Type
GDDR5
4096bit
Memory Bus
256bit
4.10TB/s
Bandwidth
147.2GB/s
Render Config
-
Compute Units
20
132
SM Count
-
16896
Shading Units
1600
528
TMUs
80
24
ROPs
32
528
Tensor Cores
-
-
-
-
256 KB (per SM)
L1 Cache
8 KB (per CU)
50 MB
L2 Cache
512 KB
-
-
-
Theoretical Performance
44.09 GPixel/s
Pixel Rate
26.40 GPixel/s
969.9 GTexel/s
Texture Rate
66.00 GTexel/s
248.3 TFLOPS
FP16 (half)
-
62.08 TFLOPS
FP32 (float)
2.640 TFLOPS
31.04 TFLOPS
FP64 (double)
528.0 GFLOPS
Board Design
1000W
TDP
225W
1400 W
Suggested PSU
550 W
No outputs
Outputs
1x DisplayPort 1.1
-
Power Connectors
1x 8-pin
Graphics Processor
GB102
GPU Name
Cypress
-
GPU Variant
Cypress XT GL
Blackwell
Architecture
TeraScale 2
TSMC
Foundry
TSMC
5 nm
Process Size
40 nm
104 billion
Transistors
2.154 billion
Unknown
Die Size
334 mm²
Graphics Features
N/A
DirectX
11.2 (11_0)
N/A
OpenGL
4.4
3.0
OpenCL
1.2
N/A
Vulkan
N/A
10.1
CUDA
-
N/A
Shader Model
5.0
