GPU Comparison
GEFORCE
NVIDIA CMP 50HX
CORE STATE
TU102
VRAM
10 GB
CLOCK SPEED
1545 MHz
TDP
250 W
BUS WIDTH
320 bit
ARCHITECTURE
Turing
PROCESS
12 nm
LAUNCH DATE
2021
VS
GEFORCE
GeForce MX350
CORE STATE
GP107S
VRAM
2 GB
CLOCK SPEED
1468 MHz
TDP
20 W
BUS WIDTH
64 bit
ARCHITECTURE
Pascal
PROCESS
14 nm
LAUNCH DATE
2020
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 50HX
MX350
Core Specs
Shading Units
3,584
640
-82.1%
Shaders
3,584
640
-82.1%
TMUs
192
32
-83.3%
ROPs
80
16
-80.0%
SM Count
56
5
-91.1%
Clocks
Base Clock
1350 MHz
1354 MHz
Boost Clock
1545 MHz
1468 MHz
Memory Clock
1750 MHz
14 Gbps effective
1752 MHz
7 Gbps effective
Memory
Memory Size
10 GB
2 GB
VRAM (MB)
10,240
2,048
-80.0%
Memory Type
GDDR6
GDDR5
Memory Bus
320 bit
64 bit
Bandwidth
560.0 GB/s
56.06 GB/s
Cache
L1 Cache
64 KB (per SM)
48 KB (per SM)
L2 Cache
5 MB
512 KB
Performance
Pixel Rate
123.6 GPixel/s
23.49 GPixel/s
Texture Rate
296.6 GTexel/s
46.98 GTexel/s
FP32 (TFLOPS)
11.07 TFLOPS
1.879 TFLOPS
FP64 (TFLOPS)
346.1 GFLOPS (1:32)
58.72 GFLOPS (1:32)
FP16 (TFLOPS)
22.15 TFLOPS (2:1)
29.36 GFLOPS (1:64)
AI/RT
RT Cores
56
—
Tensor Cores
448
—
Power
TDP
250 W
20 W
TDP (W)
250
20
-92.0%
Suggested PSU
600 W
—
Power Connectors
2x 8-pin
None
Architecture
Architecture
Turing
Pascal
GPU Name
TU102
GP107S
Generation
Mining GPUs
GeForce MX
(3xx)
Process Size
12 nm
14 nm
Transistors
18,600 million
3,300 million
Die Size
754 mm²
132 mm²
Foundry
TSMC
Samsung
Density
24.7M / mm²
25.0M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
7.5
6.1
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
—
Length
267 mm
10.5 inches
—
Height
116 mm
4.6 inches
—
Outputs
No outputs
Portable Device Dependent
Bus Interface
PCIe 1.0 x4
PCIe 3.0 x4
Other
Production
End-of-life
End-of-life