AMD FirePro S9170 vs NVIDIA GeForce RTX 3060 Ti GA103
We compared two Desktop platform GPUs: 32GB VRAM FirePro S9170 and 8GB VRAM GeForce RTX 3060 Ti GA103 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD FirePro S9170 's Advantages
More VRAM (32GB vs 8GB)
NVIDIA GeForce RTX 3060 Ti GA103 's Advantages
Released 6 years and 7 months late
Boost Clock1665MHz
Larger VRAM bandwidth (448.0GB/s vs 320.0GB/s)
2048 additional rendering cores
Lower TDP (200W vs 275W)
Score
Benchmark
FP32 (float)
FirePro S9170
5.238 TFLOPS
GeForce RTX 3060 Ti GA103
+209%
16.2 TFLOPS
Graphics Card
Jul 2015
Release Date
Feb 2022
FirePro
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1410 MHz
-
Boost Clock
1665 MHz
1250 MHz
Memory Clock
1750 MHz
Memory
32GB
Memory Size
8GB
GDDR5
Memory Type
GDDR6
512bit
Memory Bus
256bit
320.0GB/s
Bandwidth
448.0GB/s
Render Config
44
Compute Units
-
-
SM Count
38
2816
Shading Units
4864
176
TMUs
152
64
ROPs
80
-
Tensor Cores
152
-
RT Cores
38
16 KB (per CU)
L1 Cache
128 KB (per SM)
1024 KB
L2 Cache
4 MB
-
-
-
Theoretical Performance
59.52 GPixel/s
Pixel Rate
133.2 GPixel/s
163.7 GTexel/s
Texture Rate
253.1 GTexel/s
-
FP16 (half)
16.20 TFLOPS
5.238 TFLOPS
FP32 (float)
16.20 TFLOPS
2.619 TFLOPS
FP64 (double)
253.1 GFLOPS
Board Design
275W
TDP
200W
600 W
Suggested PSU
550 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 6-pin + 1x 8-pin
Power Connectors
1x 12-pin
Graphics Processor
Hawaii
GPU Name
GA103S
Hawaii XT GL
GPU Variant
GA103-200-A1
GCN 2.0
Architecture
Ampere
TSMC
Foundry
Samsung
28 nm
Process Size
8 nm
6.2 billion
Transistors
Unknown
438 mm²
Die Size
496 mm²
Graphics Features
12 (12_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.0
OpenCL
3.0
1.2
Vulkan
1.3
-
CUDA
8.6
6.3
Shader Model
6.5
