AMD Radeon 8060S vs Intel Arc A580 Comparison

Head-to-Head Benchmarks

The benchmark data presents a close contest between the Intel Arc A580 and the AMD Radeon 8060S, with the Intel part securing two of three head-to-head victories. In the modern DirectX 12 workload of 3DMark Steel Nomad, the Arc A580 scores 2229 against the Radeon 8060S’s 2162, a 3.1% advantage that signals a meaningful edge in current-generation rasterization. This is not a marginal win; a 3.1% delta in a synthetic DirectX 12 test often translates to measurable frame-rate differences in real titles.

The gap widens considerably in the Geekbench OpenCL compute test, where the Arc A580 posts 91657 versus the Radeon 8060S’s 84626. That 8.3% lead suggests the Intel architecture has a distinct advantage in general-purpose GPU compute workloads, likely stemming from its higher shading unit count and dedicated hardware resources. For users running OpenCL-accelerated applications — video encoding, physics simulations, or productivity tools — this delta is the most substantial differentiator in the entire comparison.

However, the Radeon 8060S strikes back in Geekbench Vulkan, scoring 80483 against the Arc A580’s 79381. The 1.4% margin is narrow, but it flips the narrative: in Vulkan-based games and applications, the AMD part demonstrates slightly better API-level efficiency despite its lower raw shading unit count. This Vulkan win is important because it shows the Radeon 8060S can overcome a hardware deficit through architectural efficiency in certain workloads.

Looking at broader context, the Arc A580’s average benchmark score of 57756 places it among rivals like the AMD Radeon RX 5600 OEM (58085, -0.6%) and the Intel Arc A570M (58239, -0.8%), while also edging out the AMD Radeon RX 6950 XT (58392, -1.1%) and the AMD Radeon RX 9070 GRE (57367, 0.7%). The Radeon 8060S, with an average of 55757, sits near the AMD Radeon RX 6750 GRE 12 GB (55698, 0.1%) and trails the NVIDIA GeForce RTX 5080 (56083, -0.6%) by a hair, while leading the AMD Radeon Pro W5700X (54828, 1.7%) and the NVIDIA GeForce RTX 4080 (54247, 2.8%). Both GPUs occupy the 87th percentile of all GPUs, meaning they are effectively peers in overall performance distribution, but their head-to-head deltas reveal workload-specific strengths that matter more than the aggregate.

Architecture Differences

The architectural chasm between these two parts is stark. The Intel Arc A580 uses the DG2-512 chip built on TSMC’s 6 nm process, implementing the Xe-HPG architecture from the Alchemist generation. It packs 21,700 million transistors onto a 406 mm² die, yielding a transistor density of 53.4 million per square millimeter. The Radeon 8060S, by contrast, uses the Strix Halo chip on TSMC’s 4 nm node, implementing RDNA 3.5 from the Navi Mobile (RX 8000M) generation. Its die size is 308 mm², and while transistor count is listed as unknown, the smaller die on a more advanced node suggests a fundamentally different design philosophy focused on efficiency.

The Intel part fields 3072 shading units, 192 TMUs, and 96 ROPs, alongside 24 ray tracing cores. The AMD part counters with 2560 shading units, 160 TMUs, and 64 ROPs, but doubles the ray tracing cores to 40. This is a fascinating inversion: AMD uses fewer traditional execution units but more dedicated ray tracing hardware. The FP32 throughput figures reflect this: the Arc A580 delivers 12.29 TFLOPS, while the Radeon 8060S pushes 14.85 TFLOPS. Despite having 512 fewer shading units, the AMD part achieves higher raw floating-point performance, likely due to its higher boost clock of 2900 MHz versus the Intel part’s 2000 MHz. The base clocks tell a similar story — 1295 MHz for AMD versus 1700 MHz for Intel — showing Intel starts higher but AMD finishes much higher.

Memory architecture diverges completely. The Arc A580 has 8 GB of dedicated GDDR6 on a 256-bit bus, delivering 512.0 GB/s of bandwidth. The Radeon 8060S uses system shared memory, with type, bus width, and bandwidth all listed as system dependent. This is a fundamental design choice: the Intel card is a traditional discrete GPU with its own memory pool, while the AMD part is an integrated graphics processor that borrows from system RAM. The 512.0 GB/s dedicated bandwidth of the Arc A580 will be far more consistent than any shared memory solution, though the actual performance of the Radeon 8060S’s memory depends entirely on the host system’s configuration.

Pixel and texture rates reinforce the efficiency story. The Arc A580 achieves 192.0 GPixel/s and 384.0 GTexel/s, while the Radeon 8060S hits 185.6 GPixel/s and 464.0 GTexel/s. The AMD part has a higher texture rate despite fewer TMUs, again pointing to the clock speed advantage. FP16 performance also differs: Intel offers 24.58 TFLOPS (2:1 ratio), while AMD provides 14.85 TFLOPS (1:1 ratio), meaning the Intel part can accelerate FP16 workloads twice as fast as its FP32 rate, whereas AMD treats them equally.

FAQ

Q: Which GPU won more head-to-head benchmarks?

A: The Intel Arc A580 won 2 out of 3 head-to-head tests, taking 3DMark Steel Nomad DX12 (2229 vs 2162, +3.1%) and Geekbench OpenCL (91657 vs 84626, +8.3%). The AMD Radeon 8060S won Geekbench Vulkan (80483 vs 79381, +1.4%).

Q: How do their average benchmark scores compare?

A: The Arc A580 averages 57756, while the Radeon 8060S averages 55757. That is a 3.6% gap in the Intel part’s favor. Both sit at the 87th percentile of all GPUs, so they are closely matched overall.

Q: What is the biggest performance delta between them?

A: The largest margin is in Geekbench OpenCL, where the Arc A580 leads by 8.3%. The smallest is in Geekbench Vulkan, where the Radeon 8060S leads by 1.4%.

Q: Do they use the same manufacturing process?

A: No. The Arc A580 uses TSMC’s 6 nm process, while the Radeon 8060S uses TSMC’s 4 nm process. The AMD part’s die is smaller at 308 mm² versus 406 mm² for Intel.

Q: How do their memory configurations differ?

A: The Arc A580 has 8 GB of dedicated GDDR6 on a 256-bit bus with 512.0 GB/s bandwidth. The Radeon 8060S uses system shared memory, with bandwidth listed as system dependent.

Q: Which GPU has more ray tracing cores?

A: The AMD Radeon 8060S has 40 ray tracing cores, while the Intel Arc A580 has 24. This is despite the Intel part having more shading units overall.

Specification Differences

| Specification | Intel Arc A580 | AMD Radeon 8060S |

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

| Chip | DG2-512 | Strix Halo |

| Architecture | Xe-HPG | RDNA 3.5 |

| Generation | Alchemist (Arc 5) | Navi Mobile (RX 8000M) |

| Process Node | 6 nm | 4 nm |

| Die Size | 406 mm² | 308 mm² |

| Transistors | 21,700 million | unknown |

| Transistor Density | 53.4M / mm² | null |

| Base Clock | 1700 MHz | 1295 MHz |

| Boost Clock | 2000 MHz | 2900 MHz |

| Memory Size | 8 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus Width | 256 bit | System Shared |

| Memory Bandwidth | 512.0 GB/s | System Dependent |

| Shading Units | 3072 | 2560 |

| TMUs | 192 | 160 |

| ROPs | 96 | 64 |

| RT Cores | 24 | 40 |

| Pixel Rate | 192.0 GPixel/s | 185.6 GPixel/s |

| Texture Rate | 384.0 GTexel/s | 464.0 GTexel/s |

| FP32 | 12.29 TFLOPS | 14.85 TFLOPS |

| FP16 | 24.58 TFLOPS (2:1) | 14.85 TFLOPS (1:1) |

| TDP | 175 W | 55 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 2x 8-pin | None |

| Suggested PSU | 450 W | null |

| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |

| Display Outputs | 1x HDMI 2.1, 3x DisplayPort 2.0 | Portable Device Dependent |

| Release Date | 2023-10-09 | 2025-01-05 |

| Predecessor | Xe Graphics | Polaris Mobile |

| Successor | Battlemage | null |

The Verdict

The data paints a clear picture of two GPUs designed for different worlds. The Intel Arc A580 is a traditional discrete graphics card: 175 W TDP, dual-slot cooler, 2x 8-pin power connectors, and a suggested 450 W PSU. It demands a dedicated power budget and physical space inside a desktop chassis. The AMD Radeon 8060S is an integrated graphics processor with a 55 W TDP, no power connectors, and an IGP slot width — it lives inside a portable device and consumes a fraction of the power. The release dates reinforce this: Intel launched in October 2023 as a standalone card, while AMD arrived in January 2025 aimed at mobile platforms.

Performance-wise, the Arc A580 wins in DirectX 12 and OpenCL, while the Radeon 8060S wins in Vulkan. The Intel part’s 8.3% OpenCL advantage is its most decisive victory, suggesting compute-heavy applications favor it. The AMD part’s Vulkan win, though smaller at 1.4%, shows it can hold its own in modern cross-platform APIs. The average benchmark scores — 57756 for Intel versus 55757 for AMD — indicate the Arc A580 is the faster GPU overall, but the Radeon 8060S achieves this with dramatically lower power consumption and a much smaller physical footprint.

For a desktop user with a PSU and case space, the Arc A580 is the straightforward choice based on raw performance metrics. For a mobile or compact system where power and space are constrained, the Radeon 8060S offers competitive performance at 55 W, which is less than one-third of the Intel part’s TDP. The architectural trade-off is clear: Intel trades efficiency for raw compute power, while AMD trades some rasterization muscle for ray tracing hardware and a vastly lower power envelope.

Where Each One Wins

The Intel Arc A580 wins decisively in DirectX 12 workloads, as shown by its 3.1% lead in 3DMark Steel Nomad DX12. This suggests it is the better option for modern Windows gaming titles that leverage DX12 features. Its OpenCL dominance — 8.3% ahead — makes it the pick for compute-heavy applications like video processing, scientific computing, or any workload that utilizes OpenCL acceleration. The 512.0 GB/s dedicated memory bandwidth gives it a consistent advantage in memory-bound scenarios, since performance does not depend on system RAM speed or configuration.

The AMD Radeon 8060S wins in Vulkan, with a 1.4% edge in Geekbench Vulkan. This makes it the stronger choice for Vulkan-based games and applications, which include many Linux titles and an increasing number of Windows games. Its 40 ray tracing cores versus Intel’s 24 suggest it may handle ray-traced effects more efficiently, though the benchmark data does not directly test this. The 14.85 TFLOPS FP32 throughput and 464.0 GTexel/s texture rate indicate it can process certain workloads faster despite fewer shading units, thanks to its 2900 MHz boost clock.

The power efficiency angle cannot be overstated. The Radeon 8060S’s 55 W TDP versus the Arc A580’s 175 W means the AMD part delivers 77% of the average benchmark score (55757 versus 57756) while consuming roughly 31% of the power. For battery-powered devices, thin-and-light laptops, or compact systems with limited cooling, this efficiency is the deciding factor. The Arc A580’s 450 W suggested PSU further cements its desktop-only status, while the Radeon 8060S requires no external power at all. The choice ultimately comes down to platform: desktop users should favor the Arc A580 for its higher aggregate performance and dedicated memory; mobile users have no real choice but the Radeon 8060S, which offers surprisingly competitive performance in a fraction of the power envelope.