AMD FireStream 9170 vs NVIDIA CMP 50HX
We compared two Desktop platform GPUs: 2GB VRAM FireStream 9170 and 10GB VRAM CMP 50HX 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 250W)
NVIDIA CMP 50HX 's Advantages
Released 13 years and 7 months late
Boost Clock1545MHz
More VRAM (10GB vs 2GB)
Larger VRAM bandwidth (560.0GB/s vs 51.33GB/s)
3264 additional rendering cores
Score
Benchmark
FP32 (float)
FireStream 9170
0.497 TFLOPS
CMP 50HX
+2127%
11.07 TFLOPS
Graphics Card
Nov 2007
Release Date
Jun 2021
FireStream
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
-
Base Clock
1350 MHz
-
Boost Clock
1545 MHz
802 MHz
Memory Clock
1750 MHz
Memory
2GB
Memory Size
10GB
GDDR3
Memory Type
GDDR6
256bit
Memory Bus
320bit
51.33GB/s
Bandwidth
560.0GB/s
Render Config
4
Compute Units
-
-
SM Count
56
320
Shading Units
3584
16
TMUs
192
16
ROPs
80
-
Tensor Cores
448
-
RT Cores
56
-
L1 Cache
64 KB (per SM)
256 KB
L2 Cache
5 MB
-
-
-
Theoretical Performance
12.43 GPixel/s
Pixel Rate
123.6 GPixel/s
12.43 GTexel/s
Texture Rate
296.6 GTexel/s
-
FP16 (half)
22.15 TFLOPS
497.3 GFLOPS
FP32 (float)
11.07 TFLOPS
99.46 GFLOPS
FP64 (double)
346.1 GFLOPS
Board Design
105W
TDP
250W
300 W
Suggested PSU
600 W
2x DVI
1x S-Video
Outputs
No outputs
1x 6-pin
Power Connectors
2x 8-pin
Graphics Processor
RV670
GPU Name
TU102
-
GPU Variant
TU102-100-A1
TeraScale
Architecture
Turing
TSMC
Foundry
TSMC
55 nm
Process Size
12 nm
0.666 billion
Transistors
18.6 billion
192 mm²
Die Size
754 mm²
Graphics Features
10.1 (10_1)
DirectX
12 Ultimate (12_2)
3.3 (full)
4.0 (partial)
OpenGL
4.6
N/A
OpenCL
3.0
N/A
Vulkan
1.3
-
CUDA
7.5
4.1
Shader Model
6.8
