Intel Arc B580 vs Intel Arc Graphics 2 Xe Mobile Comparison

Intel Arc B580 is a discrete desktop graphics card built on the Xe2-HPG architecture, using the BMG-G21 chip manufactured on a 5 nm process at TSMC. Intel Arc Graphics 2 Xe Mobile is an integrated graphics processor based on the Xe3-LPG architecture, using the Wildcat Lake chip manufactured on a 3 nm process at Intel. The two products serve different segments, and the benchmark data reflects that separation.

Where Each One Wins

The Intel Arc B580 wins in every measurable compute and graphics workload recorded in the database. Its average benchmark score is 23021, while the Intel Arc Graphics 2 Xe Mobile has an average benchmark score of 0 because no benchmark entries exist for it. The B580 sits at the 68th percentile among all GPUs, while the mobile part sits at the 50th percentile, though that percentile is based on its product class rather than measured performance data.

The B580 delivers 13.67 TFLOPS of FP32 compute and 27.34 TFLOPS of FP16 compute. The mobile part delivers 1,280.0 GFLOPS of FP32 and 2.560 TFLOPS of FP16. That is a substantial gap in raw arithmetic throughput. The B580 also has 2560 shading units, 160 texture mapping units, and 80 render output units. The mobile part has 256 shading units, 16 TMUs, and 8 ROPs. The B580 has 20 ray tracing cores, the mobile part has 2.

For memory, the B580 uses 12 GB of GDDR6 on a 192 bit bus, yielding 456.0 GB/s of bandwidth. The mobile part uses system shared memory with system dependent bandwidth. The B580 has a pixel rate of 213.6 GPixel/s and a texture rate of 427.2 GTexel/s. The mobile part has a pixel rate of 20.00 GPixel/s and a texture rate of 40.00 GTexel/s.

The mobile part wins on power efficiency and integration. Its TDP is 25 W, compared to 190 W for the B580. It requires no power connectors and no external power supply rating, while the B580 uses a single 8-pin connector and suggests a 450 W power supply. The mobile part is an IGP with no slot width, while the B580 is a dual-slot card measuring 272 mm in length. The mobile part is also built on a newer 3 nm process at Intel, while the B580 uses TSMC's 5 nm node.

FAQ

Q: Which GPU has the higher FP32 compute throughput?

A: The Intel Arc B580 delivers 13.67 TFLOPS of FP32 compute, while the Intel Arc Graphics 2 Xe Mobile delivers 1,280.0 GFLOPS. The B580 is roughly 10.7 times higher in FP32 throughput.

Q: What is the memory configuration of each product?

A: The B580 has 12 GB of GDDR6 on a 192 bit bus with 456.0 GB/s bandwidth. The mobile part uses system shared memory, with system dependent bandwidth and no dedicated VRAM.

Q: Do both GPUs support the same graphics APIs?

A: Yes. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the power draw difference?

A: The B580 has a TDP of 190 W and requires a 450 W suggested power supply. The mobile part has a TDP of 25 W and requires no external power supply.

Q: Which GPU has more ray tracing cores?

A: The B580 has 20 ray tracing cores. The mobile part has 2 ray tracing cores.

Q: What is the process node for each chip?

A: The B580 uses a 5 nm process at TSMC. The mobile part uses a 3 nm process at Intel.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between these two products. The B580 has ten recorded benchmark scores across multiple suites. The mobile part has zero recorded benchmark scores. This means the comparison relies on the B580's absolute scores and the architectural specifications of both parts.

Looking at the B580's recorded results, the highest score is 109672 in Geekbench Vulkan, followed by 92821 in Geekbench OpenCL. In Passmark, the G3D score is 15748, the GPU compute score is 7729, the G2D score is 709, and the DirectX 9 score is 183. The DirectX 11 score is 128, and both DirectX 10 and DirectX 12 scores are 76. The 3DMark Steel Nomad DX12 score is 3068.

These scores place the B580 near several established discrete GPUs. The nearest rival is the AMD Radeon RX 580 2048SP with an average score of 23061, a delta of -0.2 percent against the B580. The NVIDIA GeForce RTX 2080 sits at 22895, a delta of 0.6 percent, meaning the B580 scores slightly higher. The NVIDIA GeForce RTX 3080 sits at 23172, a delta of -0.7 percent, meaning the B580 scores slightly lower. The NVIDIA P106-100 sits at 23249, a delta of -1 percent. These deltas are all within a narrow band, indicating that the B580's average benchmark score is comparable to last-generation high-end and current-generation mid-range discrete GPUs.

The mobile part has no rival data and no scores, so its relative position cannot be quantified. Its 50th percentile ranking suggests it sits in the middle of the GPU distribution, but without benchmark entries, that ranking cannot be tied to specific workloads. What can be stated is that its specification limits, such as 256 shading units and 25 W TDP, place it in a fundamentally different performance class than the B580.

Specification Differences

The two products differ in nearly every measured specification. The B580 uses the BMG-G21 chip, the mobile part uses Wildcat Lake. The B580 is a discrete dual-slot card with a 272 mm length, 115 mm height, and 45 mm width. The mobile part is an IGP with no dimensions listed.

Clock speeds differ significantly. The B580 runs at a base clock of 2670 MHz and a boost clock of 2670 MHz, with memory at 2375 MHz or 19 Gbps effective. The mobile part runs at a base clock of 300 MHz and a boost clock of 2500 MHz, with system shared memory.

Memory capacity, type, bus width, and bandwidth all differ. The B580 has 12 GB GDDR6, 192 bit bus, 456.0 GB/s. The mobile part has system shared memory, system dependent bandwidth, and no dedicated bus width.

The B580 has 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. The mobile part has 256 shading units, 16 TMUs, 8 ROPs, and 2 ray tracing cores. The B580 has a transistor count of 19,600 million on a 272 mm² die, giving a transistor density of 72.1M per mm². The mobile part's transistor count and die size are unknown.

Power delivery differs completely. The B580 uses a 190 W TDP, a single 8-pin connector, and a suggested 450 W power supply. The mobile part uses 25 W TDP, no power connectors, and no suggested PSU.

Display outputs also differ. The B580 has 1x HDMI 2.1a and 3x DisplayPort 2.1. The mobile part's display outputs are portable device dependent.

Release dates differ. The B580 was released on 2024-12-12 with a launch MSRP of 249 USD. The mobile part has a release date of 2026-04-15 and no launch MSRP. The B580's predecessor is Alchemist, the mobile part's predecessor is HD Graphics-M.

Architecture Differences

The B580 uses the Xe2-HPG architecture, part of the Battlemage generation under the Arc 5 product tier. The mobile part uses the Xe3-LPG architecture, part of the Arc Graphics-M generation under Wildcat Lake. These are different architecture generations with different design goals. Xe2-HPG targets high performance graphics with dedicated memory and high power envelopes. Xe3-LPG targets integrated graphics with low power and shared system memory.

The manufacturing process differs. The B580 uses a 5 nm process at TSMC with 19,600 million transistors on a 272 mm² die. The mobile part uses a 3 nm process at Intel with unknown transistor count and die size. The newer 3 nm node allows the mobile part to operate at 25 W while still reaching a 2500 MHz boost clock.

Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both also expose FP16 at a 2:1 ratio relative to FP32, but the absolute numbers differ. The B580's FP16 is 27.34 TFLOPS, the mobile part's is 2.560 TFLOPS.

The B580 has a PCIe 4.0 x8 bus interface. The mobile part uses an IGP bus interface, meaning it communicates over the internal fabric rather than a PCIe slot. This reflects the fundamental design difference: one is an add-in board, the other is embedded in a processor.

Memory architecture is another major difference. The B580 has dedicated GDDR6 with fixed bandwidth. The mobile part relies on system shared memory, making its bandwidth system dependent. This gives the B580 predictable memory performance, while the mobile part's performance varies with the host system's memory configuration.

The mobile part's pixel rate of 20.00 GPixel/s and texture rate of 40.00 GTexel/s are direct consequences of its 8 ROPs and 16 TMUs. The B580's 213.6 GPixel/s and 427.2 GTexel/s come from its 80 ROPs and 160 TMUs. The fill rate difference is roughly a factor of ten, matching the shading unit difference.

The ray tracing capabilities also differ by a factor of ten in core count. The B580 has 20 ray tracing cores, the mobile part has 2. Both support ray tracing at the API level through DirectX 12 Ultimate, but the workload capacity is vastly different.

The Verdict

The data confirms that the Intel Arc B580 is a high-performance discrete graphics card. Its 23021 average benchmark score places it among the top third of all GPUs, and its nearest rivals include the NVIDIA GeForce RTX 2080 and RTX 3080, with score deltas within one percent. Its 12 GB GDDR6 memory, 456.0 GB/s bandwidth, and 13.67 TFLOPS FP32 compute make it suitable for demanding rendering and compute workloads. Its 190 W TDP requires a power supply rated at 450 W and a dual-slot chassis.

The Intel Arc Graphics 2 Xe Mobile is a low-power integrated GPU. Its 25 W TDP, lack of power connectors, and IGP form factor make it suitable for portable devices. Its 256 shading units, 2 ray tracing cores, and system shared memory indicate a design focused on basic graphics output and light acceleration rather than high-end rendering. Its 3 nm process at Intel and 2500 MHz boost clock show an emphasis on efficiency within a constrained power envelope.

There is no recorded benchmark overlap between the two products. The B580 has ten benchmark scores, the mobile part has none. The mobile part's 50th percentile ranking comes from its product class, not from measured results. Any direct performance comparison between these two would require data that does not exist in the database.

For users building a desktop system with dedicated graphics needs, the B580 is the only option with recorded performance data. For users in the portable device segment, the mobile part is the only option, but its performance must be inferred from its specifications rather than measured scores. The two products do not compete in the same market, and the data supports that conclusion.