GPU Comparison
GPU
3dfx Voodoo4 4500 AGP
CORE STATE
VSA-100
VRAM
32 MB
CLOCK SPEED
—
TDP
15 W
BUS WIDTH
128 bit
ARCHITECTURE
Voodoo Scalable
PROCESS
250 nm
LAUNCH DATE
2000
VS
GEFORCE
GeForce RTX 2070 Max-Q
CORE STATE
TU106
VRAM
8 GB
CLOCK SPEED
1185 MHz
TDP
90 W
BUS WIDTH
256 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2019
DETAILED SPECIFICATIONS
SPECIFICATION
3dfx Voodoo4 4500 AGP
RTX 2070 Max-Q
Core Specs
Shading Units
—
2,304
Shaders
—
2,304
TMUs
2
144
+7100.0%
ROPs
2
64
+3100.0%
SM Count
—
36
Clocks
Base Clock
—
885 MHz
Boost Clock
—
1185 MHz
GPU Clock
166 MHz
—
Memory Clock
166 MHz
1500 MHz
12 Gbps effective
Memory
Memory Size
32 MB
8 GB
VRAM (MB)
32
8,192
+25500.0%
Memory Type
SDR
GDDR6
Memory Bus
128 bit
256 bit
Bandwidth
2.656 GB/s
384.0 GB/s
Cache
L1 Cache
—
64 KB (per SM)
L2 Cache
—
4 MB
Performance
Pixel Rate
332.0 MPixel/s
75.84 GPixel/s
Texture Rate
332.0 MTexel/s
170.6 GTexel/s
FP32 (TFLOPS)
—
5.460 TFLOPS
FP64 (TFLOPS)
—
170.6 GFLOPS (1:32)
FP16 (TFLOPS)
—
10.92 TFLOPS (2:1)
AI/RT
RT Cores
—
36
Tensor Cores
—
288
Power
TDP
15 W
90 W
TDP (W)
15
90
+500.0%
Suggested PSU
200 W
—
Power Connectors
None
None
Architecture
Architecture
Voodoo Scalable
Turing
GPU Name
VSA-100
TU106
Generation
Voodoo4
GeForce 20 Mobile
Process Size
250 nm
12 nm
Transistors
14 million
10,800 million
Die Size
112 mm²
445 mm²
Foundry
TSMC
TSMC
Density
125.0K / mm²
24.3M / mm²
API Support
DirectX
6.0
12 Ultimate (12_2)
OpenGL
1.1
4.6
Vulkan
—
1.4
OpenCL
—
3.0
CUDA
—
7.5
Shader Model
—
6.8
Physical
Slot Width
Single-slot
MXM Module
Outputs
1x VGA
Portable Device Dependent
Bus Interface
AGP 4x
PCIe 3.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Voodoo3
GeForce 10 Mobile
Successor
Voodoo4-2
GeForce 30 Mobile