AMD Radeon HD 8970M

AMD Radeon HD 8970M

AMD Radeon HD 8970M: Review of an Obsolete Mobile GPU in 2025

April 2025


Introduction

The AMD Radeon HD 8970M is a mobile graphics card released in 2013. Despite its venerable age, it can still be found in older gaming laptops and workstations. In this article, we will examine what this GPU is capable of in 2025, who might still find it useful, and what limitations should be considered.


1. Architecture and Key Features

Architecture: The HD 8970M is built on the first generation of Graphics Core Next (GCN 1.0). This was a revolutionary architecture for its time, offering improved parallel data processing and support for DirectX 11.2.

Manufacturing Process: 28 nm — the standard from 2012 to 2014. By modern standards, it is considered a "dinosaur": in comparison, contemporary GPUs from AMD and NVIDIA utilize 5–7 nm manufacturing processes.

Unique Features:

- Mantle API — the predecessor to Vulkan, optimized for multi-core CPUs.

- Eyefinity — support for multiple monitors (up to 6 simultaneously).

- PowerTune — dynamic power management.

Lack of Modern Technologies:

- Ray Tracing (RTX) and DLSS (NVIDIA) are not supported.

- FidelityFX Super Resolution (FSR) from AMD is also unavailable — this technology emerged in 2021.


2. Memory: Speed and Impact on Performance

Type and Capacity: GDDR5, 4 GB. For the 2013 era, this was a top specification, but today even budget graphics cards are equipped with 6–8 GB of GDDR6.

Bus and Bandwidth:

- Bus Width: 256 bits.

- Effective Speed: 4.8 Gbps per chip.

- Bandwidth: 153.6 GB/s — half that of modern mobile GPUs (e.g., NVIDIA RTX 4050 Mobile — 336 GB/s).

Impact on Gaming: In older titles (e.g., Skyrim, Battlefield 4), the memory is sufficient for medium settings at 1080p. However, in modern games like Starfield or Cyberpunk 2077, 4 GB of GDDR5 becomes a "bottleneck," causing FPS drops and low-quality textures.


3. Gaming Performance

1080p (Low/Medium):

- CS:GO — 100–120 FPS (Medium).

- GTA V — 45–55 FPS (Medium).

- Cyberpunk 2077 — 15–20 FPS (Low).

1440p and 4K: Not recommended — the GPU cannot handle even the minimum settings.

Ray Tracing: No hardware support available. Software implementations (e.g., via DirectX Raytracing) reduce FPS to 5–10 frames, making them impractical.

Advice: To enjoy gaming comfortably in 2025, it’s better to choose titles from the 2010–2015 era or indie games with low requirements.


4. Professional Tasks

Video Editing:

- OpenCL 1.2 support allows for accelerated rendering in DaVinci Resolve or Adobe Premiere Pro, but only in simple projects.

- Converting 4K video will take 3–4 times longer than on a modern laptop with an RTX 4060.

3D Modeling:

- In Autodesk Maya or Blender, the GPU can handle basic scenes, but it lacks the computing power for complex tasks (sculpting, simulations).

Scientific Calculations:

- Open-source software on OpenCL (e.g., GROMACS) can utilize the HD 8970M, but the efficiency is 5–7 times lower than that of modern cards with CUDA.


5. Power Consumption and Heat Dissipation

TDP: 100 W — a high figure even for modern mobile GPUs (e.g., RTX 4070 Mobile — 80–100 W).

Cooling:

- Requires a system with 2–3 heat pipes and a large heatsink.

- In thin laptops (thickness < 20 mm), overheating is possible (up to 90–95°C under load).

Recommendations:

- Regularly clean fans and replace thermal paste.

- Use cooling pads for laptops.


6. Comparison with Competitors

2013:

- NVIDIA GTX 780M — the main competitor. The HD 8970M had an advantage in memory bandwidth but lagged in energy efficiency.

2025:

- AMD Radeon RX 7600M XT (price: $450–$500): 3–4 times faster in games, supports FSR 3.0 and ray tracing.

- NVIDIA RTX 4050 Mobile ($350–$400): More energy-efficient, offers DLSS 3.5 and full RTX capabilities.

Conclusion: The HD 8970M is outdated even for office tasks but can serve as a temporary solution for undemanding users.


7. Practical Tips

Power Supply: Laptops with the HD 8970M require a PSU of 150–180 W. Using weaker adapters (e.g., 90 W) will lead to throttling.

Compatibility:

- Windows: Official drivers have not been updated since 2018. Windows 11 works, but issues may arise.

- Linux: Open-source AMDGPU drivers support the card but with limited functionality.

Optimization:

- Install the latest available driver (Adrenalin 18.5.1).

- For gaming, use resolution reduction mods (e.g., FSR 1.0 via third-party utilities).


8. Pros and Cons

Pros:

- Low price on the secondary market ($50–$80).

- Reliable build (many units are still operational).

- Support for older APIs (DirectX 11, OpenGL 4.2).

Cons:

- No support for modern technologies (FSR, RTX).

- High power consumption.

- Limited performance in new games.


9. Final Conclusion: Who Is the HD 8970M For?

This graphics card is a choice for:

1. Owners of older laptops looking to extend their life for office applications or older games.

2. Retro hardware enthusiasts collecting classic gaming systems.

3. Educational projects where learning about GCN architecture is needed.

Not Recommended For:

- Gamers expecting comfortable gameplay in 2020+ projects.

- Professionals working with 3D rendering or 4K video.


Conclusion:

The AMD Radeon HD 8970M is a symbol of an era when mobile GPUs were just beginning to fight for a place in the sun. In 2025, it is relevant only as a historical artifact or a temporary solution. For modern tasks, it is better to look at budget newcomers like the Radeon RX 7600M or RTX 4050 Mobile.

Basic

Label Name
AMD
Platform
Mobile
Launch Date
May 2013
Model Name
Radeon HD 8970M
Generation
Solar System
Base Clock
850MHz
Boost Clock
900MHz
Bus Interface
PCIe 3.0 x16
Transistors
2,800 million
Compute Units
20
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.
80
Foundry
TSMC
Process Size
28 nm
Architecture
GCN 1.0

Memory Specifications

Memory Size
4GB
Memory Type
GDDR5
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.
256bit
Memory Clock
1200MHz
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.
153.6 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.
28.80 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.
72.00 GTexel/s
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.
144.0 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.
2.35 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.
1280
L1 Cache
16 KB (per CU)
L2 Cache
512KB
TDP
100W
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.
1.2
OpenCL Version
1.2
OpenGL
4.6
DirectX
12 (11_1)
Shader Model
5.1
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

Benchmarks

FP32 (float)
Score
2.35 TFLOPS

Compared to Other GPU

FP32 (float) / TFLOPS
2.446 +4.1%
2.402 +2.2%
2.285 -2.8%