Intel Arc Graphics 4 Xe Mobile vs Intel Arc Pro B390 Comparison

Head-to-Head Benchmarks

The recorded data contains no direct head-to-head benchmark scores for either part. Both the Intel Arc Graphics 4 Xe Mobile and the Intel Arc Pro B390 show an empty benchmark result set, so there are no measured frame rates, compute scores, or synthetic test deltas to compare. The database lists neither a wins tally for the mobile part nor a wins tally for the professional part. Without benchmark entries, a numerical comparison of application performance cannot be established from the database. The only performance figures available are the theoretical throughput rates derived from clock speeds and core counts, which are detailed in the specification sections below.

What the data does provide is a theoretical peak performance profile for each GPU. The Arc Pro B390 delivers a pixel rate of 60.00 GPixel/s and a texture rate of 120.0 GTexel/s, while the Arc Graphics 4 Xe Mobile reaches 36.80 GPixel/s and 73.60 GTexel/s respectively. In raw floating-point throughput, the Pro B390 achieves 7.680 TFLOPS for FP32 and 15.36 TFLOPS for FP16 (2:1), compared to 2.355 TFLOPS and 4.710 TFLOPS for the mobile part. These figures indicate the Pro B390 has roughly 3.26 times the FP32 throughput of the mobile GPU, and its pixel and texture rates are about 1.63 times higher. Boost clock speeds differ as well, with the Pro B390 at 2500 MHz versus 2300 MHz for the mobile part, while both share a 300 MHz base clock. The database does not include any nearest rival entries, so comparisons against external GPUs are not possible from this record.

FAQ

Q: What is the difference in FP32 floating-point performance between the two GPUs?

A: The Intel Arc Pro B390 delivers 7.680 TFLOPS of FP32 compute, while the Intel Arc Graphics 4 Xe Mobile delivers 2.355 TFLOPS. The Pro B390 therefore provides approximately 3.26 times the FP32 throughput.

Q: Do both GPUs use the same architecture and manufacturing process?

A: Yes. Both are based on the Xe3-LPG architecture, use the Panther Lake chip, and are manufactured on a 3 nm process at Intel.

Q: What are the boost clock speeds for each part?

A: The Intel Arc Pro B390 has a boost clock of 2500 MHz. The Intel Arc Graphics 4 Xe Mobile has a boost clock of 2300 MHz. Both share a base clock of 300 MHz.

Q: How do the core configurations differ?

A: The Arc Pro B390 contains 1536 shading units, 48 texture mapping units, 24 raster output units, and 12 ray tracing cores. The Arc Graphics 4 Xe Mobile contains 512 shading units, 32 TMUs, 16 ROPs, and 4 ray tracing cores.

Q: What power draw does each GPU have?

A: The Intel Arc Pro B390 has a TDP of 80 W. The Intel Arc Graphics 4 Xe Mobile has a TDP of 25 W.

Q: Are there any differences in API support?

A: No. Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Architecture Differences

Both GPUs are built on the Xe3-LPG architecture, using the Panther Lake chip, and are fabricated on Intel's 3 nm process. The core counts differ substantially. The Intel Arc Pro B390 carries 1536 shading units, 48 texture mapping units, 24 raster output units, and 12 ray tracing cores. The Intel Arc Graphics 4 Xe Mobile carries 512 shading units, 32 texture mapping units, 16 raster output units, and 4 ray tracing cores. This means the Pro B390 has three times the shading units and ray tracing cores, 1.5 times the TMUs, and 1.5 times the ROPs relative to the mobile part. The larger core configuration drives the Pro B390's higher theoretical throughput rates: 60.00 GPixel/s and 120.0 GTexel/s versus 36.80 GPixel/s and 73.60 GTexel/s. These are architectural capacity differences, not efficiency differences, since both share the same node and architecture generation.

The ray tracing core count difference is notable for workloads that use hardware acceleration for ray traversal and intersection. The Pro B390's 12 RT cores provide triple the ray tracing hardware of the mobile part's 4 RT cores. Similarly, the shading unit count directly scales FP32 and FP16 compute throughput. The Pro B390 reaches 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1), while the Arc Graphics 4 Xe Mobile reaches 2.355 TFLOPS FP32 and 4.710 TFLOPS FP16 (2:1). The FP16 to FP32 ratio is identical at 2:1 for both, indicating the same compute path structure. Both GPUs expose the same API set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so feature-level software support is consistent.

The memory subsystem is identical on paper. Both use System Shared memory with a System Shared bus width, and bandwidth is listed as System Dependent. Neither GPU has a dedicated memory pool, so effective bandwidth depends on the host platform's memory configuration. The database does not specify a transistor count, die size, or transistor density for either chip, so physical die-level comparisons are not possible. Both parts are marked as Active production status and were released on the same date.

Specification Differences

The two GPUs differ in several recorded specification fields. The generation labels differ: the Arc Graphics 4 Xe Mobile belongs to Arc Graphics-M (Panther Lake), while the Arc Pro B390 belongs to Arc Graphics-WM (Panther Lake). The Arc Pro B390 has a listed predecessor, HD Graphics-WM, while the mobile part has no predecessor entry. The boost clock differs: 2500 MHz for the Pro B390 versus 2300 MHz for the mobile GPU. The TDP differs: 80 W for the Pro B390 versus 25 W for the mobile part. Core counts differ as detailed above: 1536 shading units, 48 TMUs, 24 ROPs, 12 RT cores for the Pro B390 versus 512 shading units, 32 TMUs, 16 ROPs, 4 RT cores for the mobile part. The pixel rate differs: 60.00 GPixel/s versus 36.80 GPixel/s. The texture rate differs: 120.0 GTexel/s versus 73.60 GTexel/s. FP32 throughput differs: 7.680 TFLOPS versus 2.355 TFLOPS. FP16 throughput differs: 15.36 TFLOPS versus 4.710 TFLOPS.

All other fields are identical. Both have the same base clock of 300 MHz, System Shared memory size, type, and bus width, System Dependent bandwidth, no power connectors, an IGP slot width, Portable Device Dependent display outputs, the same DirectX, OpenGL, and Vulkan versions, the same 3 nm process node, Intel foundry, and the same release date. Neither part has a launch MSRP in the database, so no price information is available. Both are classified as IGP parts with no external power connector requirement.

The Verdict

The data clearly separates these two GPUs by compute capacity and power envelope. The Intel Arc Pro B390 is the higher-performance part across every measured theoretical metric. It delivers 7.680 TFLOPS FP32 versus 2.355 TFLOPS for the Arc Graphics 4 Xe Mobile, a 3.26x advantage. Its pixel rate of 60.00 GPixel/s exceeds the mobile part's 36.80 GPixel/s, and its texture rate of 120.0 GTexel/s exceeds 73.60 GTexel/s. The Pro B390 also carries more shading units, TMUs, ROPs, and ray tracing cores, and has a higher boost clock at 2500 MHz versus 2300 MHz. The tradeoff is power: the Pro B390 draws 80 W TDP against 25 W for the mobile part. Both share the same Xe3-LPG architecture, 3 nm process, system-shared memory, and API support, so the differences are entirely in execution resources and clock speed.

The Arc Graphics 4 Xe Mobile is positioned for lower-power integrated graphics scenarios where the 25 W TDP and smaller core count are appropriate. Its 2.355 TFLOPS FP32 and 4.710 TFLOPS FP16 are sufficient for lighter workloads, and its 4 ray tracing cores provide entry-level RT capability. The Arc Pro B390, with its 80 W TDP and 1536 shading units, is the choice for workloads that demand higher throughput in a professional-oriented segment, as indicated by its predecessor HD Graphics-WM and the "Pro" naming. The database shows no benchmark results for either part, so real-world application performance cannot be ranked beyond these theoretical specifications.

Where Each One Wins

The Intel Arc Pro B390 wins on every performance metric recorded in the database. It has higher FP32 compute (7.680 TFLOPS vs 2.355 TFLOPS), higher FP16 compute (15.36 TFLOPS vs 4.710 TFLOPS), higher pixel rate (60.00 GPixel/s vs 36.80 GPixel/s), higher texture rate (120.0 GTexel/s vs 73.60 GTexel/s), more shading units (1536 vs 512), more TMUs (48 vs 32), more ROPs (24 vs 16), more ray tracing cores (12 vs 4), and a higher boost clock (2500 MHz vs 2300 MHz). This makes it the stronger candidate for compute-heavy tasks such as rendering, simulation, or any workload that scales with shading unit count and clock speed. The 12 RT cores give it a clear advantage in ray-traced workloads over the mobile part's 4 RT cores.

The Intel Arc Graphics 4 Xe Mobile wins on power efficiency. Its 25 W TDP is one-third of the Pro B390's 80 W TDP, while still delivering 2.355 TFLOPS FP32 and 4.710 TFLOPS FP16. For a given power budget, the mobile part achieves higher throughput per watt, although the database does not provide efficiency ratios. It also shares the same architecture, process node, and API support, so software compatibility is identical. The mobile GPU is the appropriate choice for portable or low-power integrated designs where the 25 W envelope is a constraint. The Pro B390, at 80 W, requires a larger thermal and power delivery budget, making it suited for systems that can accommodate that draw and that need the higher compute throughput. The database lists no benchmark wins for either part, so the split is purely based on the recorded specification sheets: the Pro B390 for maximum throughput, the mobile part for minimal power consumption.