Home GPU Comparison NVIDIA GeForce RTX 3050 Mobile Refresh vs AMD Radeon E9174 MXM

NVIDIA GeForce RTX 3050 Mobile Refresh vs AMD Radeon E9174 MXM

We compared two Mobile platform GPUs: 6GB VRAM GeForce RTX 3050 Mobile Refresh and 4GB VRAM Radeon E9174 MXM to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 3050 Mobile Refresh 's Advantages
Released 4 years and 9 months late
Boost Clock has increased by 22% (1492MHz vs 1219MHz)
More VRAM (6GB vs 4GB)
Larger VRAM bandwidth (144.0GB/s vs 96.00GB/s)
1536 additional rendering cores
AMD Radeon E9174 MXM 's Advantages
Lower TDP (50W vs 75W)

Score

Benchmark

FP32 (float)
GeForce RTX 3050 Mobile Refresh +389%
6.111 TFLOPS
Radeon E9174 MXM
1.248 TFLOPS
VS

Graphics Card

Jul 2022
Release Date
Oct 2017
GeForce 30 Mobile
Generation
Embedded
Mobile
Type
Mobile
PCIe 4.0 x8
Bus Interface
MXM-A (3.0)

Clock Speeds

1237 MHz
Base Clock
1124 MHz
1492 MHz
Boost Clock
1219 MHz
1500 MHz
Memory Clock
1500 MHz

Memory

6GB
Memory Size
4GB
GDDR6
Memory Type
GDDR5
96bit
Memory Bus
128bit
144.0GB/s
Bandwidth
96.00GB/s

Render Config

-
Compute Units
8
16
SM Count
-
2048
Shading Units
512
64
TMUs
32
32
ROPs
16
64
Tensor Cores
-
16
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
2 MB
L2 Cache
512 KB
-
-
-

Theoretical Performance

47.74 GPixel/s
Pixel Rate
19.50 GPixel/s
95.49 GTexel/s
Texture Rate
39.01 GTexel/s
6.111 TFLOPS
FP16 (half)
1248 GFLOPS
6.111 TFLOPS
FP32 (float)
1248 GFLOPS
95.49 GFLOPS
FP64 (double)
78.02 GFLOPS

Board Design

75W
TDP
50W
-
-
-
No outputs
Outputs
No outputs
None
Power Connectors
None

Graphics Processor

GA107
GPU Name
Lexa
-
GPU Variant
E9170
Ampere
Architecture
GCN 4.0
Samsung
Foundry
GlobalFoundries
8 nm
Process Size
14 nm
Unknown
Transistors
2.2 billion
Unknown
Die Size
103 mm²

Graphics Features

12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
8.6
CUDA
-
6.6
Shader Model
6.4

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy