GPU Comparison
RADEON
AMD FireStream 9170
CORE STATE
RV670
VRAM
2 GB
CLOCK SPEED
—
TDP
105 W
BUS WIDTH
256 bit
ARCHITECTURE
TeraScale
PROCESS
55 nm
LAUNCH DATE
2007
VS
GEFORCE
GeForce RTX 2060 Max-Q Refresh
CORE STATE
TU106B
VRAM
6 GB
CLOCK SPEED
1200 MHz
TDP
115 W
BUS WIDTH
192 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2019
DETAILED SPECIFICATIONS
SPECIFICATION
FireStream 9170
RTX 2060 Max-Q Refresh
Core Specs
Shading Units
320
1,920
+500.0%
Shaders
320
1,920
+500.0%
TMUs
16
120
+650.0%
ROPs
16
48
+200.0%
Compute Units
4
—
SM Count
—
30
Clocks
Base Clock
—
960 MHz
Boost Clock
—
1200 MHz
GPU Clock
777 MHz
—
Memory Clock
802 MHz
1604 Mbps effective
1353 MHz
10.8 Gbps effective
Memory
Memory Size
2 GB
6 GB
VRAM (MB)
2,048
6,144
+200.0%
Memory Type
GDDR3
GDDR6
Memory Bus
256 bit
192 bit
Bandwidth
51.33 GB/s
259.8 GB/s
Cache
L1 Cache
—
64 KB (per SM)
L2 Cache
256 KB
3 MB
Performance
Pixel Rate
12.43 GPixel/s
57.60 GPixel/s
Texture Rate
12.43 GTexel/s
144.0 GTexel/s
FP32 (TFLOPS)
497.3 GFLOPS
4.608 TFLOPS
FP64 (TFLOPS)
99.46 GFLOPS (1:5)
144.0 GFLOPS (1:32)
FP16 (TFLOPS)
—
9.216 TFLOPS (2:1)
AI/RT
RT Cores
—
30
Tensor Cores
—
240
Power
TDP
105 W
115 W
TDP (W)
105
115
+9.5%
Suggested PSU
300 W
—
Power Connectors
1x 6-pin
None
Architecture
Architecture
TeraScale
Turing
GPU Name
RV670
TU106B
Generation
FireStream
GeForce 20 Mobile
Process Size
55 nm
12 nm
Transistors
666 million
10,800 million
Die Size
192 mm²
445 mm²
Foundry
TSMC
TSMC
Density
3.5M / mm²
24.3M / mm²
API Support
DirectX
10.1 (10_1)
12 Ultimate (12_2)
OpenGL
3.3 (full)
4.0 (partial)
4.6
Vulkan
—
1.4
OpenCL
—
3.0
CUDA
—
7.5
Shader Model
4.1
6.8
Physical
Slot Width
Dual-slot
MXM Module
Length
241 mm
9.5 inches
—
Height
111 mm
4.4 inches
—
Outputs
2x DVI1x S-Video
Portable Device Dependent
Bus Interface
PCIe 2.0 x16
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Rage GL
GeForce 10 Mobile
Successor
FireGL
GeForce 30 Mobile