NVIDIA CMP 40HX vs AMD FireStream 9170
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 2GB VRAM FireStream 9170 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Released 13 years and 3 months late
Boost Clock1650MHz
More VRAM (8GB vs 2GB)
Larger VRAM bandwidth (448.0GB/s vs 51.33GB/s)
1984 additional rendering cores
AMD FireStream 9170 's Advantages
Lower TDP (105W vs 185W)
Score
Benchmark
FP32 (float)
CMP 40HX
+1429%
7.603 TFLOPS
FireStream 9170
0.497 TFLOPS
Graphics Card
Feb 2021
Release Date
Nov 2007
Mining GPUs
Generation
FireStream
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 2.0 x16
Clock Speeds
1470 MHz
Base Clock
-
1650 MHz
Boost Clock
-
1750 MHz
Memory Clock
802 MHz
Memory
8GB
Memory Size
2GB
GDDR6
Memory Type
GDDR3
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
51.33GB/s
Render Config
-
Compute Units
4
36
SM Count
-
2304
Shading Units
320
144
TMUs
16
64
ROPs
16
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
-
4 MB
L2 Cache
256 KB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
12.43 GPixel/s
237.6 GTexel/s
Texture Rate
12.43 GTexel/s
15.21 TFLOPS
FP16 (half)
-
7.603 TFLOPS
FP32 (float)
497.3 GFLOPS
237.6 GFLOPS
FP64 (double)
99.46 GFLOPS
Board Design
185W
TDP
105W
450 W
Suggested PSU
300 W
No outputs
Outputs
2x DVI
1x S-Video
1x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
TU106
GPU Name
RV670
TU106-100-A1
GPU Variant
-
Turing
Architecture
TeraScale
TSMC
Foundry
TSMC
12 nm
Process Size
55 nm
10.8 billion
Transistors
0.666 billion
445 mm²
Die Size
192 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
10.1 (10_1)
4.6
OpenGL
3.3 (full)
4.0 (partial)
3.0
OpenCL
N/A
1.3
Vulkan
N/A
7.5
CUDA
-
6.8
Shader Model
4.1
