Introduction

The release of Intel's Arc B580 graphics cards heralds two pieces of good news—first, it's the 2nd generation Xe Battlemage graphics architecture; and second, that Intel is here to stay in the PC gaming graphics hardware industry. This is important, because for all the gloom that's associated with Intel these days, the company remains one of Silicon Valley's tallest giants, holds the vast majority of the PC and server processor markets, and IP invented or acquired over a period of half a century. If there's anyone that can keep both NVIDIA and AMD on notice, and spring surprises, it's Intel. The company's first-gen Xe Alchemist architecture may not have unseated the incumbents, but Intel demonstrated capability in engineering a modern discrete GPU that meets the latest DirectX 12 Ultimate API, including a sophisticated ray tracing hardware pipeline, and a robust software backend.

With Battlemage, things are only heating up—Intel claims 70% generational increases in SIMD performance of its Xe cores, and a 50% increase in performance-per-watt, due in part to the switch to 5 nm EUV foundry node. This has allowed the company to debut the architecture with the Arc B580, which succeeds the mid-range A580, and not the company's flagship A770. The B580 is claimed by Intel to be faster than most of the Arc A-series, including the A750.



Perhaps the most interesting aspect of the Arc B580 launch is its price of $250, and the fact that Intel is positioning it against the NVIDIA GeForce RTX 4060 and the AMD Radeon RX 7600 XT. If you turn the clocks back to 2022, the top A770 and A750 were only compared to the RTX 3060, nothing faster, and so the B580 being compared to the RTX 4060 at a $50 (15%) lower price means that Intel wants to gun for market share against NVIDIA's most popular SKU from its current GeForce Ada Lovelace generation. NVIDIA is rumored to launch the successor to the RTX 4060 only by March 2025, which means Intel has headroom in which to grab some sales away from the RTX 4060 and the RX 7600/7600 XT.

The Arc B580 is based on the 5 nm BMG-G21 silicon, and comes with 20 Xe2 cores, for 128 execution units, or 2,560 unified shaders. There are also 20 Ray Tracing Units, and 160 XMX matrix accelerators. For a mid-range SKU, Intel has given the B580 some solid raster 3D chops, with 160 TMUs, and 80 ROPs. You get 12 GB of 19 Gbps GDDR6 memory across a 192-bit memory bus, which offers nearly 50% more memory bandwidth than the memory interfaces of the RTX 4060 and the RX 7600 XT.

Battlemage introduces the new Xe2 Core, with large generational improvements in compute performance, and Intel studied the nuts and bolts of the graphics rendering pipeline through its sales and software-side long-term support of the Arc A-series, to identify key areas of improvement in its hardware. The Ray Tracing Unit of Battlemage gets special attention, with a 50-100% boost in performance of specific areas of the ray tracing stack. This works to reduce the overhead of ray tracing on the SIMD units and the CPU, and the overall performance cost of ray tracing.

Intel also introduced XeSS 2, which is a collection of three technologies—XeSS SR (super resolution), the new XeSS FG (frame generation), and XeLL (latency reduction technology). XeSS FG nearly doubles frame rates, and when combined with XeSS SR and XeLL, should significantly uplift the capability of the B580 from being a mid-range product, if you know your way around settings. There's also a driver-based low latency mode that works on any game, even if it's not explicitly optimized for XeSS 2.

In this review, we have with us the Intel Arc B580 Limited Edition, a reference-design product which will be sold directly by Intel (just like its processors). This is a modest $250 graphics card, yet Intel made great effort to make the product design stand out. It is strictly 2 slots-thick, and needs no more than one 8-pin PCI power connector. Tomorrow we will have additional reviews of partner design cards for the B580.

Xe2 Battlemage Architecture

The Arc B580 debuts Intel's second discrete gaming GPU architecture, codenamed Xe2 "Battlemage." A variant of Xe2 is used in the integrated graphics solution of Intel's Core Ultra 200V "Lunar Lake" mobile processors, the one today is its fully-fledged discrete gaming GPU version, with all hardware components enabled. The Arc B580 is a mid-range model based on the BMG-G21 silicon. The B580 likely does not max-out the silicon, since it is meant to succeed the mid-range A580 "Alchemist." We asked, but Intel would not comment on future products. The BMG-G21 is built on the TSMC N5 (5 nm EUV) foundry node, and packs 19.6 billion transistors across a 272 mm² monolithic die. The 5 nm node is contemporary, given that both NVIDIA "Ada" and AMD RDNA 3 gaming GPUs use it.

The BMG-G21 GPU features a PCI-Express 4.0 x8 host interface on the Arc B580 and B570. It is configured with a 192-bit GDDR6 memory bus on the B580, and a 160-bit bus on the B570. The GPU is organized in a very similar manner to modern GPUs from NVIDIA and AMD—a Global Dispatch processor distributes work among the five Render Slices, which talk to each other over the GPU's fabric and memory sub-system. The GPU's internal last-level cache is 18 MB in size. Besides the five Render Slices, there is the Media Engine, consisting of two MFX (multi-format x-coders (encoders/decoders); there are two sets of hardware encoders and decoders. Then there's the GDDR6 memory controller and the Display Engine, with four display interfaces.


Intel is claiming a 70% generational increase in performance per Xe Core, the indivisible number-crunching subunit of the GPU; and a 50% generational performance-per-watt increase. The above graphs illustrate the contribution of the individual sub-systems of the Xe2 Battlemage architecture toward these improvements; and how this plays out in a frametime analysis example of a real-world use case.


The Render Slice diagram (above) highlights the biggest chunk of the generational performance increase by Intel. It's thanks to increased IPC from the Xe Core, a more specialized and capable Ray Tracing Unit, a 300% faster Geometry engine, faster Sampler, 50% increase in HiZ, Z, stencil caches, and increases in performance of the pixel backends. Intel's engineering goal has been to reduce latency wherever it can, and reduce software (CPU) overhead as much as it can. The new 2nd Gen Xe Core features eight 512-bit vector engines, with SIMD16-native ALUs, and many more data formats. Rather than two sets of FP and INT units per vector engine, there is just one set of each per vector engine in Xe2, with larger numbers of ALUs.


Intel introduced its 2nd Gen Ray Tracing Unit, with massive generational improvements in performance and capability. It introduces a third Traversal Pipeline, which yields a 50% increase in box intersection performance. A second triangle intersection unit has been added to double the performance of triangle intersections. The BVH cache has doubled in size to 16 KB.

XeSS 2, Frame Generation, and Low Latency

Intel has codified the original XeSS as XeSS Super Resolution (XeSS-SR), as that's what it originally was—a performance enhancement that relies on super-resolution technology. The XeSS-SR SDK gets a new compute dispatcher backend for popular APIs—DirectX 11, DirectX 12, and Vulkan. There are two XeSS-SR models, the regular one, and a XeSS-SR Lite model for GPUs that lack XMX matrix acceleration capability.

XeSS 2 isn't a single technology, or an improvement over XeSS-SR, but a collection of three technologies—the existing XeSS-SR, which deals with performance; the new XeSS Frame Generation (XeSS-FG) technology, which nearly doubles frame rates based on intelligent frame doubling; and the new Xe Low Latency (XeLL) technology, which works to reduce the latency cost of SR and FG, but is something that can be used as a standalone whole-system latency technology, too.


XeSS-FG can either be implemented at native resolution, or in conjunction with XeSS-SR, where it is located right after the XeSS-SR step in the rendering queue. It relies on motion vectors, depth data, temporal frame data, and optical flow reprojection, to create interpolated frames that are then interleaved with the output frames, to effectively double the framerate. The interpolated image is then passed along to the next stage, where the HUD/UI is added at native resolution, and pushed to the frame buffer for output.


The SR + FG passes contribute to frame latency, and so, just as NVIDIA uses Reflex to counteract this latency, Intel innovated XeLL. The technology intelligently compacts the rendering queue to reduce the time it takes for an input to register as motion on-screen. XeLL remains enabled in all workloads the use XeSS-FG, but it can be used as a standalone feature, too. There's also an implicit driver-based low-latency mode that does this without a game having an explicit XeSS 2 or XeLL implementation.


Intel has updated its software package significantly. The new "Intel Graphics Software" replaces the "Arc Control" utility, and gives you a cleaner user interface. There are many new settings related to the display, including display scaling model/method/quantization range; 3D graphics settings, including a driver-based FPS limited, the driver-based low-latency mode; and the exhaustive new Performance and Overclocking controls, which include the ability to set frequency offsets, tinker with the V/F curve, power limits, and GPU and memory clocks. It also integrates Intel's PresentMon metrics.

Packaging

The Card

Intel's new reference design, they call it "Limited Edition," looks great and comes with an extremely clean design language. The dominant color is black, the surface of the cooler is slightly rubberized, to feel a bit soft to the touch. The card uses a short PCB, which allows some airflow through the card for better cooling performance. On the back you get a plastic backplate, which integrates nicely with the rest of the design.


Dimensions of the card are 28.0 x 11.5 cm, and it weighs 786 g.


Compared to last generation's flagship, the Arc A770, the new B580 looks very similar, both in size and design. We can see some improvements near the fan blades, and there's a small design change around the fans.


Installation requires two slots in your system. We measured the card's width to be 45 mm.


Display connectivity includes three standard DisplayPort 2.1 and one HDMI 2.1a. See how the middle DisplayPort is marked with a black outline? That port supports higher bitrates (UHBR13.5), i.e. 4K up to 360 Hz, while the other two ports support up to 240 Hz.

In terms of codecs, you get full support for H.264, H.265, VP9 and AV1, both encode and decode. Worth highlighting is HEVC 4:2:2 10-bit encoding and decoding, which is a unique capability, and AV1 Screen Content encoding, which improves the quality of text in movies—fantastic for screen recordings or screen sharing.


The card uses a single 8-pin connector, plus PCIe slot power, allowing a maximum power draw of 225 W. Intel has configured it with a default power limit of 190 W, which can be raised by 20% in their control panel.


The card comes with an illuminated Intel ARC logo.

Teardown

The main cooler uses four heatpipes and provides cooling for the GPU, memory and VRM circuitry.


On the back, you'll find a plastic backplate with a big cutout to improve airflow.