Intel Arc B770 vs Intel Iris Xe Graphics 80EU Mobile Comparison

Intel Arc B770 and Intel Iris Xe Graphics 80EU Mobile occupy opposite ends of the Intel graphics lineup. The Arc B770 is a discrete, dual-slot desktop card built on the Battlemage architecture, while the Iris Xe 80EU is an integrated processor graphics solution for mobile Raptor Lake systems. The recorded data shows a massive performance gap, but the comparison is not simply about speed; it is about positioning, architectural intent, and the specific workloads each part is designed to handle. This analysis walks through the benchmark implications, architectural differences, and practical use-case splits based solely on the specifications and performance indicators in the database.

Head-to-Head Benchmarks

The database lists no direct head-to-head benchmark results between the Intel Arc B770 and the Intel Iris Xe Graphics 80EU Mobile. The `headToHeadBenchmarks` field is empty, and both parts show an average benchmark score of 0 with a percentile rank of 50 against all GPUs. This means no measured performance data exists in the database to compare them directly. However, the raw compute and throughput figures in the specification table provide a clear picture of the relative capability.

The most significant disparity is in FP32 throughput. The Arc B770 delivers 19.66 TFLOPS of single-precision compute, while the Iris Xe 80EU delivers 1.856 TFLOPS. That is a factor of roughly 10.6 times in favor of the discrete card. This ratio is not a benchmark score, but it directly reflects the shader throughput available for general-purpose graphics and compute workloads. In practical terms, the Arc B770 processes over ten times as many floating-point operations per second, which translates to substantially higher frame rates in games and faster execution in GPGPU tasks.

Memory bandwidth shows an even larger gap. The Arc B770 uses 16 GB of GDDR6 memory on a 256-bit bus, yielding 512.0 GB/s of bandwidth. The Iris Xe 80EU uses system shared memory with a bandwidth listed as "System Dependent." There is no fixed number for the integrated part, but the discrete card's dedicated bandwidth is a hard specification. The gap is not just quantitative; it is qualitative. The Arc B770 has its own memory pool, eliminating contention with the CPU, while the Iris Xe shares memory and bus bandwidth with the processor, which can throttle under load.

Pixel and texture rates reinforce the same story. The Arc B770 achieves 307.2 GPixel/s and 614.4 GTexel/s. The Iris Xe 80EU manages 29.00 GPixel/s and 58.00 GTexel/s. These are exactly 10.6 times and 10.6 times lower, respectively, matching the FP32 ratio. This consistency indicates that the shading unit count, texture mapping units, and render output units scale in lockstep between the two designs. The Arc B770 has 4096 shading units, 256 TMUs, and 128 ROPs. The Iris Xe has 640 shading units, 40 TMUs, and 20 ROPs. The ratios are 6.4, 6.4, and 6.4 respectively, but the clock speeds differ. The Arc B770 boosts to 2400 MHz, while the Iris Xe boosts to 1450 MHz. The combination of more units and higher clocks produces the final throughput figures.

The memory clock also differs fundamentally. The Arc B770 runs its GDDR6 at 2000 MHz with 16 Gbps effective data rate. The Iris Xe has no dedicated memory clock, relying on system memory. This means the discrete card has a deterministic, high-speed memory subsystem, while the integrated part is bounded by the platform's RAM speed and configuration.

Architecture Differences

The two GPUs come from entirely different architectural lineages. The Intel Arc B770 uses the Xe2-HPG architecture, specifically the BMG-G31 chip, and belongs to the Battlemage (Arc 7) generation. The Iris Xe Graphics 80EU Mobile uses the Generation 12.2 architecture, built on the Raptor Lake chip, and is part of the HD Graphics-M (Raptor Lake) family. These are not iterative steps; they are separate design generations with different goals.

The process node highlights the divergence. The Arc B770 is fabricated on a 5 nm process at TSMC. The Iris Xe uses a 10 nm process at Intel. The smaller node allows the Arc B770 to pack 4096 shading units into a 368 mm² die. The Iris Xe die size is not listed, but its 640 shading units on a 10 nm process indicate a much smaller and less dense implementation. The transistor count for the Arc B770 is listed as unknown, and the Iris Xe transistor count is null, so no direct comparison is possible from the database.

The memory architecture is fundamentally different. The Arc B770 has 16 GB of GDDR6 on a 256-bit bus, with a fixed bandwidth of 512.0 GB/s. The Iris Xe has "System Shared" memory, meaning it uses the CPU's main memory pool. The bus width is also "System Shared," and the bandwidth is "System Dependent." This is not a minor difference; it changes how each GPU handles data. The discrete card can sustain high bandwidth for texture-heavy scenes or large datasets, while the integrated part is limited by the system memory controller and the shared bus.

Ray tracing capability splits the pair even further. The Arc B770 has 32 dedicated RT cores. The Iris Xe has no RT cores listed, with a null value in the database. This means hardware-accelerated ray tracing is available on the Arc B770 but not on the Iris Xe. The API support reflects this: the Arc B770 supports DirectX 12 Ultimate (12_2), which includes ray tracing and mesh shaders, while the Iris Xe supports DirectX 12 (12_1), which lacks the full Ultimate feature set. Both support OpenGL 4.6 and Vulkan 1.4, so the API baseline is similar outside of the DirectX tier.

The power envelope is also a defining architectural difference. The Arc B770 has a TDP of 225 W, while the Iris Xe has a TDP of 15 W. This is a 15-fold difference. The discrete card requires a dual-slot cooler, a 6-pin and an 8-pin power connector, and a 550 W suggested PSU. The integrated part draws power from the motherboard and requires no additional connectors. The slot width for the Arc B770 is dual-slot, while the Iris Xe is an IGP, meaning it sits inside the processor package.

The bus interface differs as well. The Arc B770 uses PCIe 4.0 x16, a dedicated high-bandwidth connection to the system. The Iris Xe uses a "Ring Bus," which is the internal fabric connecting the CPU cores and integrated graphics. This means the discrete card can transfer data over a dedicated PCIe link, while the integrated part shares the ring bus with CPU cores, cache, and other components.

Where Each One Wins

The data indicates that the Intel Arc B770 wins in every measurable performance category. It has higher FP32 throughput, higher pixel rate, higher texture rate, more shading units, more TMUs, more ROPs, more RT cores, and dedicated high-bandwidth memory. There is no benchmark category in the database where the Iris Xe 80EU leads the Arc B770. The only advantages the Iris Xe holds are in power consumption and physical integration, not in raw performance.

The Iris Xe wins in scenarios where a discrete GPU is not an option. Its 15 W TDP makes it suitable for thin-and-light laptops where battery life and thermal limits are critical. The Arc B770, with a 225 W TDP, requires a desktop chassis with robust cooling and a sufficient power supply. The Iris Xe is an IGP, meaning it is always present in the processor package, while the Arc B770 is an optional add-in card.

For workloads that require dedicated graphics memory, the Arc B770 is the clear choice. The 16 GB of GDDR6 and 512.0 GB/s bandwidth support large textures, high-resolution framebuffers, and compute workloads that exceed the memory capacity of a shared system. The Iris Xe, with system shared memory, is dependent on the system's RAM size and speed, which varies by platform.

For ray tracing, the Arc B770 has hardware RT cores and DirectX 12 Ultimate support. The Iris Xe has no RT cores and only DirectX 12 (12_1). Any workload that relies on hardware-accelerated ray tracing must use the Arc B770. The Iris Xe cannot execute ray tracing in hardware, and its API support does not include the full ray tracing pipeline.

The Arc B770 also wins in raw compute throughput for FP16 operations. It delivers 39.32 TFLOPS (2:1), while the Iris Xe delivers 3.712 TFLOPS (2:1). This is a 10.6 times advantage, matching the FP32 ratio. Applications that use mixed-precision arithmetic, such as AI inference or scientific simulation, will scale directly with this difference.

Specification Differences

The following table highlights only the fields where the two GPUs differ, based on the database:

| Field | Intel Arc B770 | Intel Iris Xe Graphics 80EU Mobile |

|---|---|---|

| Chip | BMG-G31 | Raptor Lake |

| Architecture | Xe2-HPG | Generation 12.2 |

| Generation | Battlemage (Arc 7) | HD Graphics-M (Raptor Lake) |

| Process Node | 5 nm | 10 nm |

| Foundry | TSMC | Intel |

| Die Size | 368 mm² | null |

| Base Clock | 2100 MHz | 300 MHz |

| Boost Clock | 2400 MHz | 1450 MHz |

| Memory Clock | 2000 MHz (16 Gbps effective) | System Shared |

| Memory Size | 16 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Bus Width | 256 bit | System Shared |

| Bandwidth | 512.0 GB/s | System Dependent |

| Shading Units | 4096 | 640 |

| TMUs | 256 | 40 |

| ROPs | 128 | 20 |

| RT Cores | 32 | null |

| Pixel Rate | 307.2 GPixel/s | 29.00 GPixel/s |

| Texture Rate | 614.4 GTexel/s | 58.00 GTexel/s |

| FP32 | 19.66 TFLOPS | 1.856 TFLOPS |

| FP16 | 39.32 TFLOPS (2:1) | 3.712 TFLOPS (2:1) |

| TDP | 225 W | 15 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 6-pin + 1x 8-pin | null |

| Suggested PSU | 550 W | null |

| Bus Interface | PCIe 4.0 x16 | Ring Bus |

| Display Outputs | 1x HDMI 2.1a, 3x DisplayPort 2.1 | Portable Device Dependent |

| DirectX | 12 Ultimate (12_2) | 12 (12_1) |

| Production Status | null | Active |

| Release Date | 2025-12-31 | 2023-01-03 |

| Successor | null | Arc Graphics-M |

The base clock difference is stark: 2100 MHz versus 300 MHz. The Arc B770 runs at a base clock seven times higher than the Iris Xe's base, and its boost clock of 2400 MHz is 950 MHz higher than the Iris Xe's boost of 1450 MHz. The Iris Xe's low base clock is typical for integrated graphics, which idle at low frequencies to save power and ramp up under load.

The display outputs differ completely. The Arc B770 has fixed outputs: one HDMI 2.1a and three DisplayPort 2.1. The Iris Xe's outputs are "Portable Device Dependent," meaning the laptop manufacturer decides which ports are available. This is a practical distinction for desktop versus mobile use.

The release dates are far apart. The Iris Xe launched on 2023-01-03, while the Arc B770 is dated 2025-12-31. The Iris Xe has a defined successor, Arc Graphics-M, and its production status is active. The Arc B770 has no listed successor and no production status.

FAQ

Q: How much faster is the Intel Arc B770 in FP32 compute compared to the Iris Xe 80EU?

A: The Arc B770 delivers 19.66 TFLOPS, while the Iris Xe delivers 1.856 TFLOPS. The Arc B770 is approximately 10.6 times faster in FP32 throughput.

Q: Does the Iris Xe 80EU support hardware ray tracing?

A: No. The database lists no RT cores for the Iris Xe, and it supports DirectX 12 (12_1), which does not include the full ray tracing feature set. The Arc B770 has 32 RT cores and supports DirectX 12 Ultimate (12_2).

Q: What memory configuration does each GPU use?

A: The Arc B770 has 16 GB of GDDR6 on a 256-bit bus with 512.0 GB/s bandwidth. The Iris Xe uses system shared memory with a bus width, size, and bandwidth all listed as system dependent or shared.

Q: What is the power draw difference between the two?

A: The Arc B770 has a TDP of 225 W and requires a dual-slot cooler plus a 6-pin and an 8-pin power connector. The Iris Xe has a TDP of 15 W and uses no additional power connectors.

Q: Which GPU has a higher pixel rate?

A: The Arc B770 achieves 307.2 GPixel/s, while the Iris Xe achieves 29.00 GPixel/s. The Arc B770 is 10.6 times higher.

Q: Are both GPUs based on the same architecture?

A: No. The Arc B770 uses Xe2-HPG from the Battlemage generation, while the Iris Xe uses Generation 12.2 from the Raptor Lake generation. They are built on different process nodes: 5 nm for the Arc B770 and 10 nm for the Iris Xe.

The Verdict

The data supports a clear split. The Intel Arc B770 is designed for discrete desktop graphics, with high compute throughput, dedicated memory, and hardware ray tracing. The Intel Iris Xe Graphics 80EU Mobile is an integrated solution for mobile processors, prioritizing low power and small physical footprint over performance.

The Arc B770 is the only choice for workloads that demand raw graphics performance. Its 4096 shading units, 32 RT cores, and 512.0 GB/s memory bandwidth put it in a different performance class. The FP32 throughput of 19.66 TFLOPS and pixel rate of 307.2 GPixel/s are over ten times the Iris Xe's figures. Any application that relies on shader complexity, ray tracing, or high-resolution textures will favor the Arc B770.

The Iris Xe is the appropriate part for systems where a discrete GPU is not feasible. Its 15 W TDP makes it suitable for thin laptops, and its integration into the Raptor Lake processor removes the need for a separate card. It supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, covering standard graphics APIs. Its performance is limited to 1.856 TFLOPS FP32 and 29.00 GPixel/s, which is sufficient for basic rendering and light compute tasks.

The release timeline also matters. The Iris Xe launched in January 2023 and has a defined successor, Arc Graphics-M. The Arc B770 is dated at the end of 2025, indicating a more recent design. The production status of the Arc B770 is not listed, while the Iris Xe is active.

For a desktop user building a system with a dedicated power supply and cooling, the Arc B770 is the clear pick. For a mobile user who needs integrated graphics with minimal power draw, the Iris Xe is the only option in this comparison. The database shows no overlap in performance; the Arc B770 wins every measurable category, and the Iris Xe wins only in power efficiency and integration. The choice is not between two competitors, but between two product categories.