AMD FireStream 9170 vs NVIDIA CMP 30HX
We compared two Desktop platform GPUs: 2GB VRAM FireStream 9170 and 6GB VRAM CMP 30HX 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 125W)
NVIDIA CMP 30HX 's Advantages
Released 13 years and 3 months late
Boost Clock1785MHz
More VRAM (6GB vs 2GB)
Larger VRAM bandwidth (336.0GB/s vs 51.33GB/s)
1088 additional rendering cores
Score
Benchmark
FP32 (float)
FireStream 9170
0.497 TFLOPS
CMP 30HX
+911%
5.027 TFLOPS
Graphics Card
Nov 2007
Release Date
Feb 2021
FireStream
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
-
Base Clock
1530 MHz
-
Boost Clock
1785 MHz
802 MHz
Memory Clock
1750 MHz
Memory
2GB
Memory Size
6GB
GDDR3
Memory Type
GDDR6
256bit
Memory Bus
192bit
51.33GB/s
Bandwidth
336.0GB/s
Render Config
4
Compute Units
-
-
SM Count
22
320
Shading Units
1408
16
TMUs
88
16
ROPs
48
-
-
-
-
-
-
-
L1 Cache
64 KB (per SM)
256 KB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
12.43 GPixel/s
Pixel Rate
85.68 GPixel/s
12.43 GTexel/s
Texture Rate
157.1 GTexel/s
-
FP16 (half)
10.05 TFLOPS
497.3 GFLOPS
FP32 (float)
5.027 TFLOPS
99.46 GFLOPS
FP64 (double)
157.1 GFLOPS
Board Design
105W
TDP
125W
300 W
Suggested PSU
300 W
2x DVI
1x S-Video
Outputs
No outputs
1x 6-pin
Power Connectors
1x 8-pin
Graphics Processor
RV670
GPU Name
TU116
-
GPU Variant
TU116-100-A1
TeraScale
Architecture
Turing
TSMC
Foundry
TSMC
55 nm
Process Size
12 nm
0.666 billion
Transistors
6.6 billion
192 mm²
Die Size
284 mm²
Graphics Features
10.1 (10_1)
DirectX
12 (12_1)
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
