Intel UHD Graphics 16EU (Alder Lake-N)

Intel UHD Graphics 16EU (Alder Lake-N)
Intel UHD Graphics 16EU (Alder Lake-N) graphics card review

Intel UHD Graphics 16EU (Alder Lake-N): N95 Tests, Gaming, and 4K Video

Intel UHD Graphics 16EU (Alder Lake-N) is the integrated graphics for the Intel N95 and N50 processors, which are used in budget mini-PCs and laptops. It supports hardware decoding of AV1 and outputs 4K video at 60 Hz, but gaming performance remains entry-level. In a system with the N95, Dota 2 at 720p and minimum settings averaged 68.7 FPS, while Shadow of the Tomb Raider achieved only 13 FPS.

Differences Between N95 and N50 Versions

Intel UHD Graphics 16EU belongs to the Intel Xe family and is used in the Alder Lake-N processors introduced in early 2023. The designation 16EU indicates the number of execution units.

The GPU in the Intel N95 operates at a frequency of up to 1.2 GHz, while in the N50, it reaches 750 MHz. The N50 also has two CPU cores instead of four found in the N95, so the performance results for the N95 do not reflect that of the N50.

Intel specifies the TDP of 15 W for the N95 and 6 W for the N50. These values pertain to the entire processor, including integrated graphics. Actual performance also depends on the power and cooling limits set by the manufacturer.

Memory and Its Impact on Graphics

The GPU uses the computer's RAM. Both the N95 and N50 support DDR4-3200, DDR5-4800, and LPDDR5-4800, with the specific type of memory depending on the device. The memory controller is single-channel: installing a second module does not enable dual-channel mode.

DDR5-4800 provides higher bandwidth than DDR4-3200. Upgrading from 8 to 16 GB reduces the risk of running out of RAM for applications and integrated graphics, but this alone does not guarantee an increase in FPS.

Benchmarks of Specific Devices

The table below presents the results of the graphics sub-tests Time Spy and Fire Strike from Notebookcheck reviews. Three systems are equipped with the N95 with 16 EU, while the N100 and N97 with 24 EU are included for comparison.

Device Processor EU RAM Time Spy Graphics (points) Fire Strike Graphics (points)
NiPoGi GK3 Plus Intel N95 16 16 GB DDR4-2666 317 1080
Acemagic S1 Intel N95 16 16 GB DDR4-3200 314 1106
Blackview MP80 Intel N95 16 16 GB DDR5-4800 321 1172
Trigkey G4 Intel N100 24 16 GB DDR4-3200 316 1184
Acemagic S1 Intel N97 24 16 GB DDR4-3200 473 1646

In the Blackview MP80, the DDR5 memory was manually set in the BIOS to 4800 MT/s instead of the standard 3200 MT/s for the test sample.

The three systems with the N95 show a spread of about 2% in Time Spy and roughly 9% in Fire Strike. The Blackview MP80 leads in both tests, but the entire increase cannot be attributed solely to DDR5: the systems vary in power limits, cooling, and driver versions.

The Trigkey G4 with the N100 shows nearly the same score despite having 24 EU instead of 16. The maximum GPU frequency in the N100 is 750 MHz versus 1.2 GHz in the N95.

In the N97, the 24 EU operate at up to 1.2 GHz. Acemagic S1 with this processor outperforms the N95 version by approximately 51% in Time Spy Graphics and 49% in Fire Strike Graphics. Both versions of the S1 were tested with a sustained power limit of PL1 at 25 W, but with different drivers.

Gaming Performance

The Acemagic S1 with Intel N95 and 16 GB DDR4-3200 showed the following results. The GTA V data pertains to the original version for PC, later named Legacy.

Game Resolution Settings Average FPS
Dota 2 Reborn 1280 × 720 Minimum 68.7
GTA V, original version 1366 × 768 Normal, MSAA off, AF 4x 41.9
The Witcher 3 1024 × 768 Low 23.1
Shadow of the Tomb Raider 1280 × 720 Lowest 13
Shadow of the Tomb Raider 1920 × 1080 Medium 6

Dota 2 remains the only game among those listed where the N95 averages over 60 FPS. The Witcher 3 and Shadow of the Tomb Raider do not reach 30 FPS even at low settings and at resolutions below Full HD.

Video and Monitor Connection

The video block hardware decodes H.264, HEVC, VP9, and AV1. This reduces the load on the CPU when playing compatible video, including 4K.

Intel Quick Sync allows hardware encoding of H.264 and HEVC during screen recording and video transcoding. This graphics does not support hardware encoding of AV1.

The N95 and N50 support up to three displays, and the stated maximum for HDMI and DisplayPort is 4096 × 2160 at 60 Hz. The specific set of video outputs depends on the mini-PC or laptop.

Conclusion

Intel UHD Graphics 16EU (Alder Lake-N) is primarily designed for office tasks, web applications, and video playback. The results from the three N95 systems are close, so when choosing a mini-PC, memory configuration, the set of video outputs, and power limits are more important.

At a comparable price, the N97 offers significantly higher gaming performance. For modern demanding games, much more powerful graphics are required.

GPU Comparison

Compare UHD Graphics 16EU (Alder Lake-N) with other GPUs

Please select GPU from the dropdown list.

Basic

Label Name
Intel
Platform
Integrated
Launch Date
January 2023
Former Codename
Alder Lake-N GT1
GPU Lithography
Intel 7
Model Name
Intel UHD Graphics 16EU (Alder Lake-N)
Generation
Alder Lake-N
Boost Clock
750-1200 MHz (CPU dependent)
RT Cores
No
Compute Units
16
Tensor Cores
?
Tensor Cores are specialized processing units designed specifically for deep learning, providing higher training and inference performance compared to FP32 training. They enable rapid computations in areas such as computer vision, natural language processing, speech recognition, text-to-speech conversion, and personalized recommendations. The two most notable applications of Tensor Cores are DLSS (Deep Learning Super Sampling) and AI Denoiser for noise reduction.
No
Foundry
Intel
Process Size
10 nm
Architecture
Xe-LP (Generation 12.2)
Used in CPUs

Memory Specifications

Memory Size
System Shared
Memory Type
DDR4 / DDR5 / LPDDR5 (System Shared)
Memory Bus
?
The memory bus width refers to the number of bits of data that the video memory can transfer within a single clock cycle. The larger the bus width, the greater the amount of data that can be transmitted instantaneously, making it one of the crucial parameters of video memory. The memory bandwidth is calculated as: Memory Bandwidth = Memory Frequency x Memory Bus Width / 8. Therefore, when the memory frequencies are similar, the memory bus width will determine the size of the memory bandwidth.
System Dependent
Memory Clock
System Shared
Bandwidth
?
Memory bandwidth refers to the data transfer rate between the graphics chip and the video memory. It is measured in bytes per second, and the formula to calculate it is: memory bandwidth = working frequency × memory bus width / 8 bits.
System Dependent

Display and Media

AV1 Encode/Decode
Decode Only
DisplayPort Extensions
1.4
H.264 Hardware Encode/Decode
Yes
H.265 HEVC Hardware Encode/Decode
Yes
HDMI Version
2.1
Intel Quick Sync Video
Yes
Max Resolution DP
4096 x 2160 @ 60Hz
Max Resolution HDMI
4096 x 2160 @ 60Hz
Number of Displays Supported
3
Outputs
eDP 1.4b, DP 1.4, HDMI 2.1, MIPI-DSI 1.3

Theoretical Performance

FP32 (float)
?
An important metric for measuring GPU performance is floating-point computing capability. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
0.307 TFLOPS

Miscellaneous

Shading Units
?
The most fundamental processing unit is the Streaming Processor (SP), where specific instructions and tasks are executed. GPUs perform parallel computing, which means multiple SPs work simultaneously to process tasks.
128
Vulkan Version
?
Vulkan is a cross-platform graphics and compute API by Khronos Group, offering high performance and low CPU overhead. It lets developers control the GPU directly, reduces rendering overhead, and supports multi-threading and multi-core processors.
1.4
OpenCL Version
3.0
OpenGL
4.6
CUDA
No
DirectX
12.1
Power Connectors
None

Benchmarks

FP32 (float)
Score
0.307 TFLOPS
3DMark Time Spy
Score
338
Vulkan
Score
3553
OpenCL
Score
3127

Compared to Other GPU

FP32 (float) / TFLOPS
1.007 +228%
0.988 +221.8%
0.92 +199.7%
Vulkan
59828 +1583.9%
34688 +876.3%
OpenCL
A2
35144 +1023.9%
20836 +566.3%
12393 +296.3%
8849 +183%