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
GeForce MX250
CORE STATE
GP108B
VRAM
2 GB
CLOCK SPEED
1038 MHz
TDP
10 W
BUS WIDTH
64 bit
ARCHITECTURE
Pascal
PROCESS
14 nm
LAUNCH DATE
2019
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
RX 640 OEM
MX250
Core Specs
Shading Units
640
384
-40.0%
Shaders
640
384
-40.0%
TMUs
40
24
-40.0%
ROPs
16
16
0.0%
Compute Units
10
—
SM Count
—
3
Clocks
Base Clock
—
937 MHz
Boost Clock
—
1038 MHz
GPU Clock
1295 MHz
—
Memory Clock
1500 MHz
6 Gbps effective
1502 MHz
6 Gbps effective
Memory
Memory Size
4 GB
2 GB
VRAM (MB)
4,096
2,048
-50.0%
Memory Type
GDDR5
GDDR5
Memory Bus
128 bit
64 bit
Bandwidth
96.00 GB/s
48.06 GB/s
Cache
L1 Cache
16 KB (per CU)
48 KB (per SM)
L2 Cache
512 KB
512 KB
Performance
Pixel Rate
20.72 GPixel/s
16.61 GPixel/s
Texture Rate
51.80 GTexel/s
24.91 GTexel/s
FP32 (TFLOPS)
1.658 TFLOPS
797.2 GFLOPS
FP64 (TFLOPS)
103.6 GFLOPS (1:16)
24.91 GFLOPS (1:32)
FP16 (TFLOPS)
1.658 TFLOPS (1:1)
12.46 GFLOPS (1:64)
Power
TDP
50 W
10 W
TDP (W)
50
10
-80.0%
Suggested PSU
250 W
—
Power Connectors
None
None
Architecture
Architecture
GCN 4.0
Pascal
GPU Name
Polaris 23
GP108B
Generation
Polaris
(RX 600)
GeForce MX
(2xx)
Process Size
14 nm
14 nm
Transistors
2,200 million
1,800 million
Die Size
103 mm²
74 mm²
Foundry
GlobalFoundries
Samsung
Density
21.4M / mm²
24.3M / mm²
API Support
DirectX
12 (12_0)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
CUDA
—
6.1
Shader Model
6.7
6.8
Physical
Slot Width
Single-slot
IGP
Outputs
1x DisplayPort 1.4a2x mini-DisplayPort 1.4a
Portable Device Dependent
Bus Interface
PCIe 3.0 x8
PCIe 3.0 x4
Other
Production
End-of-life
End-of-life
Predecessor
Polaris
—
Successor
Vega
—