GPU Comparison
RADEON
AMD Radeon RX 640 OEM
CORE STATE
Polaris 23
VRAM
4 GB
CLOCK SPEED
—
TDP
50 W
BUS WIDTH
128 bit
ARCHITECTURE
GCN 4.0
PROCESS
14 nm
LAUNCH DATE
2020
VS
GEFORCE
GeForce4 Ti 4200-8X
CORE STATE
NV28
VRAM
64 MB
CLOCK SPEED
—
TDP
—
BUS WIDTH
128 bit
ARCHITECTURE
Kelvin
PROCESS
150 nm
LAUNCH DATE
2002
DETAILED SPECIFICATIONS
SPECIFICATION
RX 640 OEM
GeForce4 Ti 4200-8X
Core Specs
Shading Units
640
—
Shaders
640
—
TMUs
40
8
-80.0%
ROPs
16
4
-75.0%
Compute Units
10
—
Clocks
GPU Clock
1295 MHz
250 MHz
Memory Clock
1500 MHz
6 Gbps effective
250 MHz
Memory
Memory Size
4 GB
64 MB
VRAM (MB)
4,096
64
-98.4%
Memory Type
GDDR5
SDR
Memory Bus
128 bit
128 bit
Bandwidth
96.00 GB/s
4.000 GB/s
Cache
L1 Cache
16 KB (per CU)
—
L2 Cache
512 KB
—
Performance
Pixel Rate
20.72 GPixel/s
1.000 GPixel/s
Texture Rate
51.80 GTexel/s
2.000 GTexel/s
FP32 (TFLOPS)
1.658 TFLOPS
—
FP64 (TFLOPS)
103.6 GFLOPS (1:16)
—
FP16 (TFLOPS)
1.658 TFLOPS (1:1)
—
Power
TDP
50 W
—
TDP (W)
50
—
Suggested PSU
250 W
200 W
Power Connectors
None
None
Architecture
Architecture
GCN 4.0
Kelvin
GPU Name
Polaris 23
NV28
Generation
Polaris
(RX 600)
GeForce 4 Ti
Process Size
14 nm
150 nm
Transistors
2,200 million
63 million
Die Size
103 mm²
142 mm²
Foundry
GlobalFoundries
TSMC
Density
21.4M / mm²
443.7K / mm²
API Support
DirectX
12 (12_0)
8.1
OpenGL
4.6
1.5
Vulkan
1.3
—
OpenCL
2.1
—
Shader Model
6.7
—
Physical
Slot Width
Single-slot
Single-slot
Outputs
1x DisplayPort 1.4a2x mini-DisplayPort 1.4a
1x DVI1x VGA1x S-Video
Bus Interface
PCIe 3.0 x8
AGP 8x
Other
Production
End-of-life
End-of-life
Predecessor
Polaris
GeForce 4 MX
Successor
Vega
GeForce FX