GPU Comparison
RADEON
AMD FirePro V3900
CORE STATE
Turks
VRAM
1024 MB
CLOCK SPEED
—
TDP
50 W
BUS WIDTH
128 bit
ARCHITECTURE
TeraScale 2
PROCESS
40 nm
LAUNCH DATE
2012
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
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
FirePro V3900
RTX 2060 Max-Q Refresh
Core Specs
Shading Units
480
1,920
+300.0%
Shaders
480
1,920
+300.0%
TMUs
24
120
+400.0%
ROPs
8
48
+500.0%
Compute Units
6
—
SM Count
—
30
Clocks
Base Clock
—
960 MHz
Boost Clock
—
1200 MHz
GPU Clock
650 MHz
—
Memory Clock
900 MHz
1800 Mbps effective
1353 MHz
10.8 Gbps effective
Memory
Memory Size
1024 MB
6 GB
VRAM (MB)
1,024
6,144
+500.0%
Memory Type
GDDR3
GDDR6
Memory Bus
128 bit
192 bit
Bandwidth
28.80 GB/s
259.8 GB/s
Cache
L1 Cache
8 KB (per CU)
64 KB (per SM)
L2 Cache
256 KB
3 MB
Performance
Pixel Rate
5.200 GPixel/s
57.60 GPixel/s
Texture Rate
15.60 GTexel/s
144.0 GTexel/s
FP32 (TFLOPS)
624.0 GFLOPS
4.608 TFLOPS
FP64 (TFLOPS)
—
144.0 GFLOPS (1:32)
FP16 (TFLOPS)
—
9.216 TFLOPS (2:1)
AI/RT
RT Cores
—
30
Tensor Cores
—
240
Power
TDP
50 W
115 W
TDP (W)
50
115
+130.0%
Suggested PSU
250 W
—
Power Connectors
None
None
Architecture
Architecture
TeraScale 2
Turing
GPU Name
Turks
TU106B
Generation
FirePro Terascale
(Vx900)
GeForce 20 Mobile
Process Size
40 nm
12 nm
Transistors
716 million
10,800 million
Die Size
118 mm²
445 mm²
Foundry
TSMC
TSMC
Density
6.1M / mm²
24.3M / mm²
API Support
DirectX
11.2 (11_0)
12 Ultimate (12_2)
OpenGL
4.4
4.6
Vulkan
—
1.4
OpenCL
1.2
3.0
CUDA
—
7.5
Shader Model
5.0
6.8
Physical
Slot Width
Single-slot
MXM Module
Length
168 mm
6.6 inches
—
Height
69 mm
2.7 inches
—
Outputs
1x DVI1x DisplayPort 1.1
Portable Device Dependent
Bus Interface
PCIe 2.0 x16
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
FireGL
GeForce 10 Mobile
Successor
Radeon Pro GCN
GeForce 30 Mobile