Intel Arc A580 vs Intel Arc B770 Comparison

FAQ

Q: What is the core architectural difference between the Intel Arc A580 and the Intel Arc B770?

A: The Arc A580 uses the Xe-HPG architecture on the DG2-512 chip, built on a 6 nm process at TSMC. The Arc B770 uses the newer Xe2-HPG architecture on the BMG-G31 chip, built on a 5 nm process at TSMC. This represents a shift from the Alchemist generation to the Battlemage generation.

Q: How do the memory configurations compare between the two cards?

A: The Arc A580 has 8 GB of GDDR6 memory on a 256-bit bus with 512.0 GB/s bandwidth. The Arc B770 doubles the capacity to 16 GB of GDDR6 on the same 256-bit bus with identical 512.0 GB/s bandwidth. Both run memory at 2000 MHz with 16 Gbps effective speed.

Q: What benchmark data is available for each card in the database?

A: The Arc A580 has three recorded benchmarks: 3DMark Steel Nomad DX12 (2229), Geekbench OpenCL (91657), and Geekbench Vulkan (79381). The Arc B770 currently has no recorded benchmark scores in the database, with an average benchmark score of 0.

Q: How does the Arc A580's average benchmark score compare to its nearest rivals?

A: The Arc A580 has an average benchmark score of 57756, which places it 0.6% behind the AMD Radeon RX 5600 OEM (58085), 0.7% ahead of the AMD Radeon RX 9070 GRE (57367), 0.8% behind the Intel Arc A570M (58239), and 1.1% behind the AMD Radeon RX 6950 XT (58392).

Q: What are the thermal and power requirements for each card?

A: The Arc A580 has a TDP of 175 W, uses dual-slot cooling, requires two 8-pin power connectors, and has a suggested PSU of 450 W. The Arc B770 has a TDP of 225 W, also uses dual-slot cooling, requires one 6-pin plus one 8-pin power connector, and has a suggested PSU of 550 W.

Q: What display outputs do these cards offer?

A: The Arc A580 provides 1x HDMI 2.1 and 3x DisplayPort 2.0. The Arc B770 provides 1x HDMI 2.1a and 3x DisplayPort 2.1. The newer card supports the newer DisplayPort revision.

Architecture Differences

The Intel Arc A580 belongs to the Alchemist generation (Arc 5) and uses the DG2-512 chip with the Xe-HPG architecture. The Intel Arc B770 belongs to the Battlemage generation (Arc 7) and uses the BMG-G31 chip with the Xe2-HPG architecture. This generational leap brings a change in manufacturing process: the A580 is fabricated on a 6 nm process at TSMC, while the B770 uses a 5 nm process at TSMC. The die sizes are similar but not identical, with the A580 measuring 406 mm² and the B770 measuring 368 mm². The A580 packs 21,700 million transistors, resulting in a transistor density of 53.4M per mm², while the B770's transistor count is listed as unknown in the database.

The compute resources differ substantially. The A580 contains 3072 shading units, 192 texture mapping units, 96 render output units, and 24 ray tracing cores. The B770 scales up to 4096 shading units, 256 TMUs, 128 ROPs, and 32 ray tracing cores. Neither card lists tensor cores in the database. The clock speeds also differ: the A580 has a base clock of 1700 MHz and a boost clock of 2000 MHz, while the B770 runs at 2100 MHz base and 2400 MHz boost. These higher clocks on the B770 combine with its larger compute unit count to produce significantly higher theoretical throughput.

The memory subsystem shows both similarities and differences. Both cards use GDDR6 memory on a 256-bit bus with 512.0 GB/s bandwidth and 2000 MHz memory clock at 16 Gbps effective. The key difference is capacity: 8 GB on the A580 versus 16 GB on the B770. The B770's larger framebuffer is a notable architectural advantage for workloads that exceed 8 GB.

Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The display output specifications differ slightly, with the A580 offering HDMI 2.1 and DisplayPort 2.0, while the B770 offers HDMI 2.1a and DisplayPort 2.1. Both use the PCIe 4.0 x16 bus interface. The B770's predecessor is listed as Alchemist, which is the generation that includes the A580.

Where Each One Wins

The Arc A580 has measurable benchmark results, so its strengths can be identified from recorded data. With 8 GB of memory and a 175 W TDP, it occupies a lower power envelope and requires only a 450 W suggested PSU. Its dual-slot cooler and two 8-pin connectors are straightforward. The A580's average benchmark score of 57756 places it in the 87th percentile of all GPUs in the database, which indicates it holds its own against a cluster of rivals within roughly one percentage point.

The Arc B770 has no recorded benchmark scores, so direct performance comparisons cannot be established from the database. Its advantages are structural: 16 GB of memory versus 8 GB, 4096 shading units versus 3072, and a newer 5 nm process. The B770 also has higher pixel rate (307.2 GPixel/s versus 192.0 GPixel/s) and texture rate (614.4 GTexel/s versus 384.0 GTexel/s). Its FP32 throughput of 19.66 TFLOPS exceeds the A580's 12.29 TFLOPS by a wide margin, and its FP16 throughput of 39.32 TFLOPS doubles the A580's 24.58 TFLOPS.

For use cases involving large textures, high-resolution assets, or workloads that approach the 8 GB ceiling, the B770's 16 GB capacity provides headroom the A580 cannot offer. For scenarios where power draw and PSU requirements are constrained, the A580's lower 175 W TDP and 450 W suggested PSU versus the B770's 225 W and 550 W suggested PSU make it the lighter option. The B770 also supports DisplayPort 2.1, while the A580 tops out at DisplayPort 2.0.

Specification Differences

The two cards differ across nearly every major specification category. The chip design changes from DG2-512 to BMG-G31, and the architecture advances from Xe-HPG to Xe2-HPG. The generation shifts from Alchemist (Arc 5) to Battlemage (Arc 7). The process node improves from 6 nm to 5 nm, both at TSMC. The die size decreases from 406 mm² to 368 mm², while the A580's 21,700 million transistors have no recorded counterpart for the B770.

Clock speeds increase on the B770: base clock rises from 1700 MHz to 2100 MHz, and boost clock from 2000 MHz to 2400 MHz. Memory capacity doubles from 8 GB to 16 GB, while memory type, bus width, bandwidth, and memory clock remain identical. Compute resources scale up: shading units from 3072 to 4096, TMUs from 192 to 256, ROPs from 96 to 128, and ray tracing cores from 24 to 32.

Rates and throughput figures all favor the B770. Pixel rate jumps from 192.0 GPixel/s to 307.2 GPixel/s, texture rate from 384.0 GTexel/s to 614.4 GTexel/s, FP32 from 12.29 TFLOPS to 19.66 TFLOPS, and FP16 from 24.58 TFLOPS to 39.32 TFLOPS. Power requirements increase as well: TDP from 175 W to 225 W, power connectors from 2x 8-pin to 1x 6-pin + 1x 8-pin, and suggested PSU from 450 W to 550 W. Display outputs change from HDMI 2.1 with DisplayPort 2.0 to HDMI 2.1a with DisplayPort 2.1.

The production status differs: the A580 is listed as Active, while the B770 has no production status recorded. Release dates also differ, with the A580 released in October 2023 and the B770 listed with a December 2025 release date. The A580's predecessor is Xe Graphics and its successor is Battlemage, while the B770's predecessor is Alchemist.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for this pair, and the wins counter shows zero for both cards. The Arc B770 has an empty benchmarks array, so no direct comparison scores exist. This absence of recorded data limits any quantitative comparison to the A580's individual benchmark results and the structural specifications of both cards.

The Arc A580's recorded scores are 2229 in 3DMark Steel Nomad DX12, 91657 in Geekbench OpenCL, and 79381 in Geekbench Vulkan. These scores contribute to its average benchmark score of 57756 and its 87th percentile ranking among all GPUs. Its nearest rivals in the database are the AMD Radeon RX 5600 OEM (58085, 0.6% higher), AMD Radeon RX 9070 GRE (57367, 0.7% lower), Intel Arc A570M (58239, 0.8% higher), and AMD Radeon RX 6950 XT (58392, 1.1% higher). The data shows the A580 sits in a tight competitive cluster, with all four rivals within a 1.1% band around its average score.

For the B770, the database records a 50th percentile ranking and an average benchmark score of 0, with no nearest rivals listed. This means the B770's performance position cannot be established from measurements. The only quantitative comparison possible comes from the theoretical specification differences: the B770's 19.66 TFLOPS FP32 is roughly 60% higher than the A580's 12.29 TFLOPS, and its 307.2 GPixel/s pixel rate is 60% higher than the A580's 192.0 GPixel/s. The texture rate comparison shows a similar ratio, with 614.4 GTexel/s versus 384.0 GTexel/s.

The Verdict

The data presents an asymmetric comparison. The Arc A580 is a measured product with three benchmark scores, an 87th percentile ranking, and a clear competitive position against four named rivals within a 1.1% performance band. The Arc B770 has no benchmark measurements, no rival comparisons, and a 50th percentile placeholder ranking with an average score of 0.

From the recorded data, the A580 is a functional, competitive card whose average score of 57756 puts it in the same class as the AMD Radeon RX 5600 OEM, RX 9070 GRE, Intel Arc A570M, and RX 6950 XT. Its 8 GB memory and 175 W TDP define its practical limits. The B770, based solely on its specifications, offers double the memory, 33% more shading units, 33% more ray tracing cores, higher clocks, and roughly 60% higher theoretical throughput in FP32, pixel rate, and texture rate. Its 225 W TDP and 550 W suggested PSU indicate a higher power class.

The choice between them depends on whether a user values the A580's confirmed benchmark presence or the B770's structural advantages. The A580 is the only one of the two with verified performance data in the database, and that data shows it competing tightly with several AMD offerings. The B770's specifications suggest a substantially more capable card on paper, but the database contains no measurements to confirm that expectation. The B770's 16 GB framebuffer and newer 5 nm process are unambiguous advantages for memory-heavy workloads, while the A580's lower power draw and smaller PSU requirement suit more modest builds. Until the B770 receives benchmark entries, its performance claims rest entirely on its specification sheet.