AMD Radeon RX 6600S vs Intel Arc A380 Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6600S records an average benchmark score of 10629, while the Intel Arc A380 scores 8558. The AMD part sits at the 49th percentile of all GPUs, compared to the Intel part's 44th percentile.

Q: How much faster is the RX 6600S in DirectX 11 and DirectX 12 tests?

A: In PassMark DirectX 11, the RX 6600S scores 105 versus 38 for the Arc A380, a 176.3% advantage. In DirectX 12, the RX 6600S scores 56 versus 35, a 60% lead.

Q: Does the Intel Arc A380 have a higher memory capacity?

A: Yes. The Arc A380 comes with 6 GB of GDDR6 memory, while the RX 6600S has 4 GB. However, the RX 6600S has a wider 128-bit bus and higher bandwidth at 224.0 GB/s, versus the Arc's 96-bit bus and 186.0 GB/s.

Q: What is the transistor density difference between the two chips?

A: The RX 6600S uses a 7 nm process with 11,060 million transistors on a 237 mm² die, giving a density of 46.7M/mm². The Arc A380 uses a 6 nm process with 7,200 million transistors on a 157 mm² die, for a density of 45.9M/mm². They are nearly identical per square millimeter.

Q: Which GPU supports the same modern API features?

A: Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Neither has tensor cores listed, and both include ray tracing cores (28 on AMD, 8 on Intel).

Q: How does the Arc A380 compare to its nearest rivals in the database?

A: The Arc A380's average score of 8558 is 0.4% behind the AMD FirePro W5170M, and 1.1%, 1.2%, and 1.4% ahead of the AMD Radeon HD 8870M, NVIDIA GeForce MX330, and AMD Radeon 880M, respectively.

Architecture Differences

The architectural split between these two is significant. The AMD Radeon RX 6600S is built on RDNA 2.0, using the Navi 23 chip, while the Intel Arc A380 uses the Xe-HPG architecture with the DG2-128 chip. Manufacturing processes differ: the RX 6600S uses TSMC's 7 nm node, while the Arc A380 uses TSMC's 6 nm node. Despite the process difference, transistor density is nearly identical: 46.7M/mm² for AMD versus 45.9M/mm² for Intel.

The AMD chip packs considerably more compute resources. It has 1792 shading units, 112 texture mapping units, and 64 ROPs. The Intel chip has 1024 shading units, 64 TMUs, and 32 ROPs. Ray tracing hardware also differs: the RX 6600S has 28 RT cores, while the Arc A380 has 8. The AMD part's raw FP32 throughput is 7.168 TFLOPS, versus 4.198 TFLOPS for Intel. FP16 performance follows the same 2:1 ratio on both, with 14.34 TFLOPS for AMD and 8.397 TFLOPS for Intel.

Memory architecture diverges as well. The RX 6600S uses 4 GB of GDDR6 on a 128-bit bus, achieving 224.0 GB/s. The Arc A380 uses 6 GB of GDDR6 on a 96-bit bus, achieving 186.0 GB/s. The AMD card has higher bandwidth but less capacity. Clock behavior differs: the RX 6600S has a 1700 MHz base, 1881 MHz game clock, and 2000 MHz boost. The Arc A380 has a 2000 MHz base and 2050 MHz boost, with no listed game clock.

Physical design and power delivery also set them apart. The RX 6600S is an integrated mobile part (IGP) with no power connectors and an 80 W TDP. The Arc A380 is a dual-slot add-in card, 222 mm long, requiring a single 8-pin connector and a 250 W suggested PSU, with a 75 W TDP. The AMD part's display outputs are "portable device dependent," while the Intel card offers 1x HDMI 2.1 and 3x DisplayPort 2.0. Both use PCIe 4.0 x8.

Head-to-Head Benchmarks

The recorded data shows a decisive sweep: the AMD Radeon RX 6600S wins all 8 head-to-head tests, with 0 wins for the Intel Arc A380. The margin varies by workload, from modest to overwhelming.

In compute-oriented tests, the RX 6600S leads by a wide margin. Geekbench OpenCL shows 66435 for AMD versus 38224 for Intel, a 73.8% difference. PassMark GPU Compute gives AMD 4879 versus 2762, a 76.6% lead. These results indicate the AMD part has substantially more raw compute throughput, consistent with its higher FP32 and FP16 ratings.

The largest deltas appear in legacy and feature-specific DirectX tests. In PassMark DirectX 11, the RX 6600S scores 105 versus 38, a 176.3% advantage. DirectX 9 shows a 141.1% lead (176 versus 73). DirectX 10 gives a 118.9% edge (81 versus 37). Even in DirectX 12, where both are modern parts, AMD leads by 60% (56 versus 35). These numbers suggest the AMD architecture handles the full range of DirectX feature levels with more efficiency.

The overall PassMark G3D score amplifies the gap: 12649 for AMD versus 6252 for Intel, a 102.3% difference. This is the headline metric for general gaming performance, and it doubles the Intel part's result. The closest margin is in PassMark G2D, where AMD scores 647 versus 610, a 6.1% lead. This indicates that 2D desktop workloads are nearly tied, while 3D and compute tasks strongly favor AMD.

For context, the RX 6600S's average score of 10629 places it 0.4% ahead of the AMD Radeon R9 M275X and 1.4% ahead of the AMD Radeon RX 550X. The Arc A380's 8558 average sits near the AMD FirePro W5170M (0.4% behind) and the AMD Radeon 880M (1.4% ahead). The benchmark data places the RX 6600S in a higher performance tier overall.

The Verdict

Based solely on the recorded measurements, the AMD Radeon RX 6600S is the stronger GPU. It wins every benchmark in the head-to-head comparison, and its average score is 24.2% higher than the Intel Arc A380's (10629 versus 8558). The 49th percentile ranking versus 44th further confirms the AMD part's superior standing in the full GPU database.

The RX 6600S is the choice for anyone prioritizing raw performance, especially in 3D rendering, compute workloads, and DirectX 11 legacy titles where it doubles or nearly doubles the Intel part's scores. Its higher texture rate (224.0 GTexel/s versus 131.2 GTexel/s) and pixel rate (128.0 GPixel/s versus 65.60 GPixel/s) translate directly into better fill-rate-bound scenarios.

The Intel Arc A380 is not without merit, but its advantages are narrower. It offers more memory (6 GB versus 4 GB), a smaller physical footprint (dual-slot, 222 mm length versus integrated), and a lower TDP (75 W versus 80 W). It also has a slightly higher base clock (2000 MHz versus 1700 MHz) and a wider display output configuration. However, these do not overcome the benchmark deficits. The Arc A380's launch MSRP was 149 USD, but the database shows no such figure for the RX 6600S.

For a builder choosing between these two, the data is unambiguous: the RX 6600S delivers roughly twice the 3D performance in most tests, with a smaller memory pool being its only notable compromise. The Arc A380 suits scenarios where the 6 GB frame buffer is essential and the performance gap is acceptable, but it is not a competitive replacement for the RX 6600S in raw speed.

Specification Differences

The two GPUs differ across nearly every specification field. Process node: 7 nm (AMD) versus 6 nm (Intel). Transistor count: 11,060 million versus 7,200 million. Die size: 237 mm² versus 157 mm². Transistor density: 46.7M/mm² versus 45.9M/mm².

Compute units: 1792 shading units versus 1024. TMUs: 112 versus 64. ROPs: 64 versus 32. RT cores: 28 versus 8. Pixel rate: 128.0 GPixel/s versus 65.60 GPixel/s. Texture rate: 224.0 GTexel/s versus 131.2 GTexel/s. FP32: 7.168 TFLOPS versus 4.198 TFLOPS. FP16: 14.34 TFLOPS versus 8.397 TFLOPS.

Memory: 4 GB versus 6 GB, both GDDR6. Bus width: 128-bit versus 96-bit. Bandwidth: 224.0 GB/s versus 186.0 GB/s. Memory clock: 1750 MHz (14 Gbps effective) versus 1937 MHz (15.5 Gbps effective). Base clock: 1700 MHz versus 2000 MHz. Boost clock: 2000 MHz versus 2050 MHz. Game clock: 1881 MHz (AMD only, none listed for Intel).

Power and physical: TDP 80 W versus 75 W. Slot width: IGP versus dual-slot. Power connectors: none versus 1x 8-pin. Suggested PSU: not listed versus 250 W. Dimensions: not listed versus 222 mm length, 114 mm height, 42 mm width. Display outputs: portable device dependent versus 1x HDMI 2.1 and 3x DisplayPort 2.0.

APIs are identical: DirectX 12 Ultimate (12_2), OpenGL 4.6, Vulkan 1.4. Bus interface is the same: PCIe 4.0 x8. Production status for both is end-of-life. Release dates differ: 2022-01-03 for AMD, 2022-06-13 for Intel. Predecessors: Polaris Mobile versus Xe Graphics. Successor: none listed versus Battlemage.

Where Each One Wins

The AMD Radeon RX 6600S wins in every measured benchmark category. Its largest advantages are in DirectX 11 (176.3% ahead), DirectX 9 (141.1%), DirectX 10 (118.9%), and PassMark G3D (102.3%). These are the tests that matter most for gaming and general 3D performance. The RX 6600S also leads in compute-heavy workloads: Geekbench OpenCL by 73.8% and PassMark GPU Compute by 76.6%. The only close contest is 2D performance, where it leads by 6.1%.

The Intel Arc A380's wins are not in benchmarks but in specific hardware attributes. It offers 50% more memory capacity (6 GB versus 4 GB), which matters for texture-heavy modern games or compute workloads that exceed 4 GB. It has a higher base clock (2000 MHz versus 1700 MHz), though the boost clocks are similar (2050 MHz versus 2000 MHz). Its dual-slot form factor with dedicated display outputs (1x HDMI 2.1, 3x DisplayPort 2.0) makes it more suitable for desktop use with multiple monitors. Its lower TDP (75 W versus 80 W) and single 8-pin connector simplify power delivery.

For a use-case split: choose the RX 6600S for maximum frame rates, legacy DirectX titles, and compute tasks. Choose the Arc A380 when you need the larger frame buffer, require a discrete desktop card with multiple display outputs, or want the slightly lower power draw. The RX 6600S is the performance pick; the Arc A380 is the capacity and connectivity pick.