AMD FireStream 9350 vs NVIDIA H200 NVL
We compared two Desktop platform GPUs: 2GB VRAM FireStream 9350 and 141GB VRAM H200 NVL to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD FireStream 9350 's Advantages
Lower TDP (150W vs 600W)
NVIDIA H200 NVL 's Advantages
Released 14 years and 5 months late
Boost Clock1785MHz
More VRAM (141GB vs 2GB)
Larger VRAM bandwidth (4.89TB/s vs 128.0GB/s)
15456 additional rendering cores
Score
Benchmark
FP32 (float)
FireStream 9350
2.016 TFLOPS
H200 NVL
+2892%
60.32 TFLOPS
Graphics Card
Jun 2010
Release Date
Nov 2024
FireStream
Generation
Server Hopper
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
-
Base Clock
1365 MHz
-
Boost Clock
1785 MHz
1000 MHz
Memory Clock
1593 MHz
Memory
2GB
Memory Size
141GB
GDDR5
Memory Type
HBM3e
256bit
Memory Bus
6144bit
128.0GB/s
Bandwidth
4.89TB/s
Render Config
18
Compute Units
-
-
SM Count
132
1440
Shading Units
16896
72
TMUs
528
32
ROPs
24
-
Tensor Cores
528
-
-
-
8 KB (per CU)
L1 Cache
256 KB (per SM)
512 KB
L2 Cache
50 MB
-
-
-
Theoretical Performance
22.40 GPixel/s
Pixel Rate
42.84 GPixel/s
50.40 GTexel/s
Texture Rate
942.5 GTexel/s
-
FP16 (half)
241.3 TFLOPS
2.016 TFLOPS
FP32 (float)
60.32 TFLOPS
403.2 GFLOPS
FP64 (double)
30.16 TFLOPS
Board Design
150W
TDP
600W
450 W
Suggested PSU
1000 W
1x DisplayPort 1.1
Outputs
No outputs
1x 6-pin
Power Connectors
8-pin EPS
Graphics Processor
Cypress
GPU Name
GH100
Cypress PRO GL
GPU Variant
-
TeraScale 2
Architecture
Hopper
TSMC
Foundry
TSMC
40 nm
Process Size
5 nm
2.154 billion
Transistors
80 billion
334 mm²
Die Size
814 mm²
Graphics Features
11.2 (11_0)
DirectX
N/A
4.4
OpenGL
N/A
1.2
OpenCL
3.0
N/A
Vulkan
N/A
-
CUDA
9.0
5.0
Shader Model
N/A
