Home / Intel / Intel Arc B570: Performance and Specs

Intel Arc B570

Intel Arc B570: A Detailed Review of the New Graphics Card for Gamers and Professionals

Exploring the capabilities, performance, and features of Intel's GPU

1. Architecture and Key Features

Xe-HPG: The Foundation for a New Generation

The Intel Arc B570 graphics card is built on the Xe-HPG architecture, specifically designed for gaming and professional tasks. Key elements include:

- Manufacturing Process: 6nm (TSMC N6), providing a balance between energy efficiency and performance.

- Compute Units: Up to 32 Xe cores (512 execution units), supporting hardware-accelerated ray tracing.

- XMX Matrix Cores: Analogous to NVIDIA's tensor cores, responsible for AI algorithm processing, including the XeSS (Intel’s Xe Super Sampling) technology.

Unique Features

- XeSS: Improves FPS through upscaling using artificial intelligence. In games like Cyberpunk 2077, the boost reaches 30-40% at 4K resolution.

- Hardware Ray Tracing: Supports ray tracing, but with lower efficiency compared to NVIDIA's RTX 40 series (approximately on par with RTX 3060 Ti).

- Deep Link: Optimizes collaboration with Intel integrated graphics for streaming and rendering.

2. Memory: Speed and Capacity

GDDR6: The Standard for Mid-Range

- Capacity: 12 GB — optimal for modern gaming and working with 3D models.

- Bus: 192-bit, providing a bandwidth of 384 GB/s (comparable to NVIDIA RTX 4060).

- Impact on Performance: In games with high textures (Horizon Forbidden West, Call of Duty: Modern Warfare III), 12 GB prevents FPS drops at ultra settings in 1440p.

3. In-Game Performance: Numbers and Resolutions

1080p: Maximum Comfort

- Apex Legends: 144 FPS (Ultra).

- Elden Ring: 68 FPS (maximum settings, no ray tracing).

- Cyberpunk 2077: 55 FPS (Ultra, XeSS Quality).

1440p: The Sweet Spot

- Red Dead Redemption 2: 62 FPS (High).

- Starfield: 48 FPS (Ultra, with XeSS Performance).

4K: For Enthusiasts with Caveats

- Forza Horizon 5: 45 FPS (Extreme, XeSS Balanced).

- Ray Tracing: Enabling it reduces FPS by 25-35%. For instance, Control: 32 FPS (1440p, RT Medium).

4. Professional Tasks: Not Just Gaming

Video Editing and Rendering

- DaVinci Resolve: Accelerated H.265 encoding via Quick Sync — rendering a 4K video is 20% faster than with the RTX 3060.

- Blender: Supports OpenCL and oneAPI, but rendering speed is 1.5 times slower than NVIDIA (due to the lack of CUDA).

Scientific Calculations

- TensorFlow/PyTorch: Compatibility with AI frameworks via plugins, but requires manual setup.

5. Power Consumption and Thermal Output

TDP and Recommendations

- TDP: 185 W — comparable to AMD RX 7600 XT.

- Cooling: Reference system with two 90mm fans. For stable operation under overclocking, a case with 3-4 fans is recommended.

- Power Supply: Minimum of 550 W (650 W recommended for overhead).

6. Comparison with Competitors

NVIDIA RTX 4060

- Pros of Arc B570: +4 GB of memory, better upscaling quality (XeSS vs DLSS 3).

- Cons: Weaker in ray tracing (by 15-20%), poorer driver optimization.

AMD RX 7600 XT

- Pros of Arc B570: Better support for professional tasks.

- Cons: RX 7600 XT is faster in Vulkan games (Doom Eternal).

7. Practical Tips

PC Building

- Motherboard: Must have UEFI with Resizable BAR (increases FPS by 10-15%).

- Drivers: Regularly update via Intel Driver & Support Assistant — stability improves with each month.

Game Optimization

- Enable XeSS in settings — it provides a greater boost than FSR 2.0.

- For ray tracing, choose Medium/High rather than Ultra.

8. Pros and Cons

Pros:

- Excellent price/performance ratio in DX12 and Vulkan.

- 12 GB of memory for future projects.

- Versatility for gaming and creative tasks.

Cons:

- Drivers are still "raw" for older games (e.g., GTA V).

- High power consumption at idle.

9. Final Conclusion: Who is the Arc B570 For?

This graphics card is a good choice for:

- Gamers who prefer modern games at 1440p with future-proofing.

- Content creators in need of an affordable GPU for editing and 3D work.

- Enthusiasts willing to experiment with drivers for cost savings.

Intel Arc B570 proves that there is room for a third player in the GPU market. It may not be perfect, but it offers impressive functionality for its price.

Basic

Label Name

Intel

Platform

Desktop

Launch Date

December 2024

Model Name

Arc B570

Generation

Battlemage(Arc 5)

Base Clock

1700 MHz

Boost Clock

2600 MHz

Bus Interface

PCIe 4.0 x8

Transistors

21.7 billion

RT Cores

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.

288

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.

144

Foundry

TSMC

Process Size

6 nm

Architecture

Generation 12.7

Memory Specifications

Memory Size

10GB

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.

160bit

Memory Clock

2400 MHz

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.

384.0GB/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.

208.0 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.

374.4 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.

23.96 TFLOPS

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.

11.74 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.

2304

L2 Cache

10 MB

TDP

150W

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

2x 8-pin

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.

Suggested PSU

450 W

Benchmarks

FP32 (float)

Score

11.74 TFLOPS

Blender

Score

1408.8

Compared to Other GPU

FP32 (float) / TFLOPS

GeForce RTX 3060 8 GB

12.485 +6.3%

Arc A580

12.044 +2.6%

Arc B570

11.74

GeForce RTX 3060 Mobile

11.159 -4.9%

Arctic Sound 1T

10.839 -7.7%

Blender

H100 PCIe

5111 +262.8%

GeForce RTX 3060 8 GB

2484 +76.3%

Arc B570

1408.8

GeForce GTX 1660

794 -43.6%

GeForce GTX 1650 Max Q

375 -73.4%