AMD FireStream 9170 vs NVIDIA H200 NVL
We compared two Desktop platform GPUs: 2GB VRAM FireStream 9170 and 141GB VRAM H200 NVL to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD FireStream 9170 's Advantages
Lower TDP (105W vs 600W)
NVIDIA H200 NVL 's Advantages
Released 17 years late
Boost Clock1785MHz
More VRAM (141GB vs 2GB)
Larger VRAM bandwidth (4.89TB/s vs 51.33GB/s)
16576 additional rendering cores
Score
Benchmark
FP32 (float)
FireStream 9170
0.497 TFLOPS
H200 NVL
+12036%
60.32 TFLOPS
Graphics Card
Nov 2007
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
802 MHz
Memory Clock
1593 MHz
Memory
2GB
Memory Size
141GB
GDDR3
Memory Type
HBM3e
256bit
Memory Bus
6144bit
51.33GB/s
Bandwidth
4.89TB/s
Render Config
4
Compute Units
-
-
SM Count
132
320
Shading Units
16896
16
TMUs
528
16
ROPs
24
-
Tensor Cores
528
-
-
-
-
L1 Cache
256 KB (per SM)
256 KB
L2 Cache
50 MB
-
-
-
Theoretical Performance
12.43 GPixel/s
Pixel Rate
42.84 GPixel/s
12.43 GTexel/s
Texture Rate
942.5 GTexel/s
-
FP16 (half)
241.3 TFLOPS
497.3 GFLOPS
FP32 (float)
60.32 TFLOPS
99.46 GFLOPS
FP64 (double)
30.16 TFLOPS
Board Design
105W
TDP
600W
300 W
Suggested PSU
1000 W
2x DVI
1x S-Video
Outputs
No outputs
1x 6-pin
Power Connectors
8-pin EPS
Graphics Processor
RV670
GPU Name
GH100
-
-
-
TeraScale
Architecture
Hopper
TSMC
Foundry
TSMC
55 nm
Process Size
5 nm
0.666 billion
Transistors
80 billion
192 mm²
Die Size
814 mm²
Graphics Features
10.1 (10_1)
DirectX
N/A
3.3 (full)
4.0 (partial)
OpenGL
N/A
N/A
OpenCL
3.0
N/A
Vulkan
N/A
-
CUDA
9.0
4.1
Shader Model
N/A
