AMD FireStream 9170 vs NVIDIA CMP 170HX
We compared two Desktop platform GPUs: 2GB VRAM FireStream 9170 and 16GB VRAM CMP 170HX 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 170HX 's Advantages
Released 13 years and 10 months late
Boost Clock1410MHz
More VRAM (16GB vs 2GB)
Larger VRAM bandwidth (1493GB/s vs 51.33GB/s)
4160 additional rendering cores
Score
Benchmark
FP32 (float)
FireStream 9170
0.497 TFLOPS
CMP 170HX
+2441%
12.63 TFLOPS
Graphics Card
Nov 2007
Release Date
Sep 2021
FireStream
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x4
Clock Speeds
-
Base Clock
1140 MHz
-
Boost Clock
1410 MHz
802 MHz
Memory Clock
1458 MHz
Memory
2GB
Memory Size
16GB
GDDR3
Memory Type
HBM2e
256bit
Memory Bus
4096bit
51.33GB/s
Bandwidth
1493GB/s
Render Config
4
Compute Units
-
-
SM Count
70
320
Shading Units
4480
16
TMUs
280
16
ROPs
128
-
Tensor Cores
280
-
-
-
-
L1 Cache
192 KB (per SM)
256 KB
L2 Cache
8 MB
-
-
-
Theoretical Performance
12.43 GPixel/s
Pixel Rate
180.5 GPixel/s
12.43 GTexel/s
Texture Rate
394.8 GTexel/s
-
FP16 (half)
50.53 TFLOPS
497.3 GFLOPS
FP32 (float)
12.63 TFLOPS
99.46 GFLOPS
FP64 (double)
6.317 TFLOPS
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
GA100
-
GPU Variant
GA100-105F-A1
TeraScale
Architecture
Ampere
TSMC
Foundry
TSMC
55 nm
Process Size
7 nm
0.666 billion
Transistors
54.2 billion
192 mm²
Die Size
826 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
8.0
4.1
Shader Model
N/A
