Intel Arc Pro A40

Intel Arc Pro A40

Intel Arc Pro A40: A Compact Graphics Card for Professionals and Enthusiasts

April 2025


Introduction

Intel's Arc Pro series graphics cards are aimed at users who need a balance of performance, energy efficiency, and affordability. The Arc Pro A40, released in 2024, is positioned as a solution for compact workstations, video editing, and moderate gaming. In this article, we will examine how well it meets its stated goals and who should pay attention to it.


1. Architecture and Key Features

Xe-HPG 2.0 Architecture

The A40 is based on the updated Xe-HPG 2.0 architecture, optimized for parallel computing and graphical tasks. The chip is manufactured using TSMC's 6nm process, providing a good balance between performance and power consumption.

Unique Features

- XeSS (Xe Super Sampling): Artificial intelligence upscale images from a lower resolution, increasing FPS without significant loss of detail. In games like Cyberpunk 2077, enabling XeSS yields a boost of 30-40% in frames per second.

- Hardware Ray Tracing: The Ray Tracing Units (RTUs) provide realistic lighting and shadows, but there are fewer than in top-tier NVIDIA GPUs.

- AV1 Encoding/Decoding: Full support for the AV1 codec for streaming and editing 8K video.


2. Memory: Fast, but Modest

GDDR6 and Bandwidth

The A40 is equipped with 8 GB of GDDR6 memory with a 128-bit bus. The bandwidth is 192 GB/s, which is lower than its competitors with a 256-bit bus (e.g., NVIDIA RTX 4060 – 272 GB/s). This is sufficient for 1080p gaming, but there may be memory shortages in 4K or when working with heavy textures in 3D editors.

Optimizations through Software

Intel compensates for the memory limitations with technologies like DirectStorage and Resizable BAR, which speed up resource loading. In tests, this reduces latency in games by 15-20% compared to the previous generation.


3. Gaming Performance: Modest Ambitions

1080p: Comfortable Levels

In Fortnite (Epic, ray tracing off), the A40 delivers 85-90 FPS, with XeSS enabled—up to 110 FPS. In Dota 2, it maintains a steady 120 FPS at maximum settings.

1440p and 4K: Compromise Required

In Cyberpunk 2077 (1440p, ultra settings): 45-50 FPS without XeSS, 60-65 FPS with XeSS. At 4K, even with XeSS, the average FPS barely reaches 35-40, making the resolution uncomfortable for dynamic scenes.

Ray Tracing: An Expensive Luxury

Enabling RT in Control reduces FPS by 40-50%, but with XeSS, frame rates recover to a manageable 50-55 FPS in 1080p. For smooth gameplay in 1440p with RT, it’s better to opt for a GPU at the level of RTX 4070.


4. Professional Tasks: Surprisingly Strong Areas

Video Editing and Rendering

Thanks to AV1 and Quick Sync support, the A40 encodes 4K video in DaVinci Resolve 20% faster than the NVIDIA RTX A2000. For editing in Premiere Pro 2025, 32 GB of RAM is recommended to offset the limited VRAM capacity.

3D Modeling and Scientific Computing

In Blender (Cycles), rendering a BMW scene takes 8.5 minutes, compared to 6 minutes for the RTX A2000. However, in tasks optimized for OpenCL (e.g., simulations in MATLAB), the A40 demonstrates parity with competitors.

API Support

- OpenCL 3.0 and SYCL: For scientific computing and machine learning.

- OneAPI: Integration with Intel's developer tools.


5. Power Consumption and Thermal Output

TDP 65W: Energy Efficiency First

The A40 does not require extra power—PCIe x16 is sufficient. This makes it ideal for compact PCs and SFF cases.

Cooling

The system features passive and active cooling (depending on the model). Under load, the temperature does not exceed 75°C, but in dense cases without ventilation, throttling may occur. Cases with at least one 120mm fan are recommended.


6. Comparison with Competitors

NVIDIA RTX A2000 (12 GB, 2024):

- Pros: More memory, better optimization for professional applications.

- Cons: Price $450 vs $299 for the A40.

AMD Radeon Pro W6400 (6 GB):

- Pros: Cheaper ($250), supports DisplayPort 2.1.

- Cons: Weaker in rendering and gaming.

Conclusion: The A40 occupies a niche between budget professional and gaming cards, offering better value for AV1 and XeSS.


7. Practical Tips

Power Supply

A 400W power supply with 80+ Bronze certification is sufficient. For systems with Intel Core i5/i7 13th generation and newer, 500W is recommended.

Compatibility

- Motherboards with PCIe 4.0 x16 (backward compatible with PCIe 3.0).

- Windows 11 23H2 or newer is recommended for full driver support.

Drivers

Intel has significantly improved stability since 2024, but in older games (e.g., Red Dead Redemption 2), artifacts may appear. Update software via Intel Driver & Support Assistant.


8. Pros and Cons

Pros:

- Low power consumption.

- Support for AV1 and XeSS.

- Affordable price ($299).

Cons:

- Only 8 GB of memory.

- Limited performance in 4K.

- Drivers still lag behind NVIDIA in optimization.


9. Final Conclusion: Who is the Arc Pro A40 Suitable For?

- Budget-Conscious Professionals: Video editing, working with AV1, light 3D rendering.

- Compact Build Enthusiasts: Mini-PCs, home servers supporting modern codecs.

- 1080p Gamers: For less demanding projects or with XeSS enabled.

Why A40? It is one of the few cards that for $299 offers hardware AV1 encoding, moderate gaming potential, and compatibility with professional software. If you don’t need maximum performance but value compactness and energy efficiency — the A40 is worth considering.


Prices are current as of April 2025. The listed price is the recommended retail price for new devices.

Basic

Label Name
Intel
Platform
Desktop
Launch Date
August 2022
Model Name
Arc Pro A40
Generation
Alchemist
Base Clock
1500MHz
Boost Clock
1700MHz
Bus Interface
PCIe 4.0 x8
Transistors
7,200 million
RT Cores
8
TMUs
?
Texture Mapping Units (TMUs) serve as components of the GPU, which are capable of rotating, scaling, and distorting binary images, and then placing them as textures onto any plane of a given 3D model. This process is called texture mapping.
64
Foundry
TSMC
Process Size
6 nm
Architecture
Generation 12.7

Memory Specifications

Memory Size
6GB
Memory Type
GDDR6
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.
96bit
Memory Clock
2000MHz
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.
192.0 GB/s

Theoretical Performance

Pixel Rate
?
Pixel fill rate refers to the number of pixels a graphics processing unit (GPU) can render per second, measured in MPixels/s (million pixels per second) or GPixels/s (billion pixels per second). It is the most commonly used metric to evaluate the pixel processing performance of a graphics card.
54.40 GPixel/s
Texture Rate
?
Texture fill rate refers to the number of texture map elements (texels) that a GPU can map to pixels in a single second.
108.8 GTexel/s
FP16 (half)
?
An important metric for measuring GPU performance is floating-point computing capability. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable. 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.
6.963 TFLOPS
FP64 (double)
?
An important metric for measuring GPU performance is floating-point computing capability. Double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy, while single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
870.4 GFLOPS
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.
3.552 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.
1024
L2 Cache
4MB
TDP
50W
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.
1.3
OpenCL Version
3.0
OpenGL
4.6
DirectX
12 Ultimate (12_2)
Power Connectors
None
Shader Model
6.6
ROPs
?
The Raster Operations Pipeline (ROPs) is primarily responsible for handling lighting and reflection calculations in games, as well as managing effects like anti-aliasing (AA), high resolution, smoke, and fire. The more demanding the anti-aliasing and lighting effects in a game, the higher the performance requirements for the ROPs; otherwise, it may result in a sharp drop in frame rate.
32
Suggested PSU
250W

Benchmarks

FP32 (float)
Score
3.552 TFLOPS
OctaneBench
Score
403

Compared to Other GPU

FP32 (float) / TFLOPS
3.894 +9.6%
3.713 +4.5%
3.552
3.393 -4.5%
3.337 -6.1%
OctaneBench
1328 +229.5%
163 -59.6%
87 -78.4%
47 -88.3%