AMD Radeon RX 580 vs AMD Radeon RX 6600S Comparison

Head-to-Head Benchmarks

The benchmark database records eight direct comparisons between the AMD Radeon RX 580 and the AMD Radeon RX 6600S. The RX 6600S wins seven of those eight tests, often by substantial margins. The RX 580 claims a single victory, in the Passmark G2D test, where it scores 769 against the RX 6600S's 647, a lead of 18.9%. This 2D graphics result stands as the only category where the older Polaris card outruns the RDNA 2 mobile part.

The most dramatic gap appears in Geekbench OpenCL. The RX 6600S posts 66435, while the RX 580 manages 37453. That difference translates to a 43.6% advantage for the RX 6600S. This compute-heavy workload shows the architectural leap between the two generations, as the newer card more than doubles the raw score of its predecessor.

Passmark DirectX 10 and DirectX 11 results follow a similar pattern. The RX 6600S scores 81 and 105 respectively, against the RX 580's 46 and 60. Both represent roughly 43% improvements for the RX 6600S. DirectX 9 shows a narrower gap: the RX 6600S scores 176 versus the RX 580's 124, a 29.5% lead. DirectX 12 narrows further still, with the RX 6600S at 56 and the RX 580 at 43, a 23.2% difference.

The Passmark G3D test, which serves as a general 3D graphics performance indicator, sees the RX 6600S score 12649 against the RX 580's 8813. That is a 30.3% advantage. The GPU compute test shows a similar story: the RX 6600S scores 4879 while the RX 580 scores 3488, a 28.5% lead.

Looking at average benchmark scores, the RX 580 records 12928 across all its tests, while the RX 6600S records 10629. The RX 580's average is dragged upward by its strong Geekbench scores and its Passmark G3D result, while the RX 6600S has fewer recorded benchmarks but wins nearly every head-to-head comparison. The RX 580 sits at the 53rd percentile of all GPUs in the database, while the RX 6600S sits at the 49th percentile. The RX 580's nearest rivals include the NVIDIA GeForce RTX 3050 Ti Mobile at an average score of 12940 (a 0.1% difference) and the NVIDIA GeForce GTX 1660 SUPER at 12986 (0.4% difference). The RX 6600S's nearest rivals include the AMD Radeon R9 M275X at 10582 (0.4% difference) and the NVIDIA GeForce GTX 560 Ti at 10690 (0.6% difference).

Architecture Differences

The two cards come from different architectural eras entirely. The RX 580 uses the Polaris 20 chip built on GCN 4.0 architecture, fabricated on a 14 nm process at GlobalFoundries. The RX 6600S uses the Navi 23 chip built on RDNA 2.0 architecture, fabricated on a 7 nm process at TSMC. The transistor counts reflect the process difference: the RX 580 packs 5,700 million transistors on a 232 mm² die, while the RX 6600S packs 11,060 million transistors on a 237 mm² die. Transistor density jumps from 24.6M per mm² on the RX 580 to 46.7M per mm² on the RX 6600S.

The RX 580 features 2304 shading units, 144 texture mapping units, and 32 render output units. The RX 6600S has fewer shading units at 1792, fewer TMUs at 112, but twice the ROPs at 64. The RX 6600S also includes 28 ray tracing cores, a feature entirely absent from the RX 580. The pixel rate tells the story of the ROP difference: the RX 6600S achieves 128.0 GPixel/s against the RX 580's 42.88 GPixel/s. The texture rate, however, favors the RX 6600S less dramatically: 224.0 GTexel/s versus 193.0 GTexel/s.

Memory configurations diverge significantly. The RX 580 carries 8 GB of GDDR5 on a 256-bit bus, yielding 256.0 GB/s of bandwidth. The RX 6600S carries 4 GB of GDDR6 on a 128-bit bus, yielding 224.0 GB/s of bandwidth. The newer memory type compensates for the narrower bus, though the RX 580 retains a bandwidth advantage of 32 GB/s.

Clock speeds show the efficiency gains of the newer process. The RX 580 runs at a base of 1257 MHz and boosts to 1340 MHz, with memory at 2000 MHz (8 Gbps effective). The RX 6600S runs at 1700 MHz base and 2000 MHz boost, with a game clock of 1881 MHz and memory at 1750 MHz (14 Gbps effective). Despite the higher clocks, the RX 6600S draws only 80 W compared to the RX 580's 185 W, a massive efficiency improvement. The RX 6600S is listed as an integrated graphics processor form factor with no power connectors, while the RX 580 is a dual-slot card requiring a single 8-pin connector and a 450 W power supply.

API support differs as well. The RX 580 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The RX 6600S supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 6600S also uses a PCIe 4.0 x8 interface, while the RX 580 uses PCIe 3.0 x16.

FAQ

Q: Which card wins more head-to-head benchmark comparisons?

A: The AMD Radeon RX 6600S wins 7 of the 8 recorded head-to-head tests. The only test the RX 580 wins is Passmark G2D, where it scores 769 against the RX 6600S's 647.

Q: How large is the performance gap in compute workloads?

A: In Geekbench OpenCL, the RX 6600S scores 66435 against the RX 580's 37453, a 43.6% advantage. In Passmark GPU compute, the RX 6600S scores 4879 against the RX 580's 3488, a 28.5% lead.

Q: What memory configurations do the two cards use?

A: The RX 580 uses 8 GB of GDDR5 on a 256-bit bus with 256.0 GB/s bandwidth. The RX 6600S uses 4 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth.

Q: Do both cards support ray tracing?

A: No. The RX 6600S includes 28 ray tracing cores and supports DirectX 12 Ultimate (12_2). The RX 580 has no ray tracing cores and supports only DirectX 12 (12_0).

Q: How do the power requirements compare?

A: The RX 580 has a TDP of 185 W and requires a 450 W power supply with a single 8-pin connector. The RX 6600S has a TDP of 80 W, uses no power connectors, and is listed as an IGP form factor.

Q: Which card has higher clock speeds?

A: The RX 6600S runs at 1700 MHz base and 2000 MHz boost, with a game clock of 1881 MHz. The RX 580 runs at 1257 MHz base and 1340 MHz boost.

Specification Differences

| Specification | AMD Radeon RX 580 | AMD Radeon RX 6600S |

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

| Chip | Polaris 20 | Navi 23 |

| Architecture | GCN 4.0 | RDNA 2.0 |

| Process Node | 14 nm | 7 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | 5,700 million | 11,060 million |

| Die Size | 232 mm² | 237 mm² |

| Transistor Density | 24.6M / mm² | 46.7M / mm² |

| Base Clock | 1257 MHz | 1700 MHz |

| Boost Clock | 1340 MHz | 2000 MHz |

| Game Clock | N/A | 1881 MHz |

| Memory Clock | 2000 MHz (8 Gbps effective) | 1750 MHz (14 Gbps effective) |

| Memory Size | 8 GB | 4 GB |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bus | 256 bit | 128 bit |

| Memory Bandwidth | 256.0 GB/s | 224.0 GB/s |

| Shading Units | 2304 | 1792 |

| TMUs | 144 | 112 |

| ROPs | 32 | 64 |

| Ray Tracing Cores | N/A | 28 |

| Pixel Rate | 42.88 GPixel/s | 128.0 GPixel/s |

| Texture Rate | 193.0 GTexel/s | 224.0 GTexel/s |

| FP32 Performance | 6.175 TFLOPS | 7.168 TFLOPS |

| FP16 Performance | 6.175 TFLOPS (1:1) | 14.34 TFLOPS (2:1) |

| TDP | 185 W | 80 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 450 W | N/A |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |

| DirectX Support | 12 (12_0) | 12 Ultimate (12_2) |

| Vulkan Support | 1.3 | 1.4 |

| Release Date | 2017-04-17 | 2022-01-03 |

The Verdict

The recorded data points to a clear generational shift. The RX 6600S wins 7 of 8 direct comparisons, with margins ranging from 23.2% to 43.6%. Its FP32 throughput of 7.168 TFLOPS exceeds the RX 580's 6.175 TFLOPS, and its FP16 performance of 14.34 TFLOPS doubles the RX 580's 6.175 TFLOPS. The RX 6600S also achieves a higher pixel rate of 128.0 GPixel/s versus 42.88 GPixel/s, and a higher texture rate of 224.0 GTexel/s versus 193.0 GTexel/s.

The RX 580's advantages are narrower but real. It offers double the memory capacity at 8 GB versus 4 GB, a wider 256-bit memory bus versus 128-bit, and higher memory bandwidth at 256.0 GB/s versus 224.0 GB/s. Its average benchmark score of 12928 exceeds the RX 6600S's 10629, and it sits at the 53rd percentile of all GPUs versus the RX 6600S's 49th percentile. The RX 580 also wins the G2D test outright.

The RX 6600S, however, delivers its performance at 80 W compared to the RX 580's 185 W, a power efficiency gap that cannot be overstated. It also brings ray tracing support, DirectX 12 Ultimate, and Vulkan 1.4 to the table, features the RX 580 cannot offer. For workloads that leverage these newer APIs, the RX 6600S is the only option of the two.

Where Each One Wins

The RX 6600S wins in every 3D graphics and compute scenario recorded in the database. Its Passmark G3D score of 12649 versus 8813 makes it the stronger choice for general 3D rendering. Its Geekbench OpenCL score of 66435 versus 37453 indicates superior compute throughput for GPU-accelerated tasks. Its DirectX 10, 11, and 12 scores all exceed the RX 580's by margins between 23.2% and 43.2%. Its GPU compute score of 4879 versus 3488 reinforces this pattern.

The RX 580 wins in the 2D graphics test, scoring 769 versus the RX 6600S's 647. The data also shows the RX 580 has double the video memory, which matters for workloads that require more than 4 GB of frame buffer. Its higher memory bandwidth of 256.0 GB/s versus 224.0 GB/s gives it an edge in memory-intensive scenarios that fit within its capacity.

For users considering the RX 580, the key advantages are memory capacity and bandwidth. For users considering the RX 6600S, the key advantages are raw performance, feature support, and power efficiency. The RX 6600S is the stronger performer in nearly every measured category, but the RX 580's larger memory pool and higher average benchmark score keep it relevant for specific use cases. The production status of both cards is listed as end-of-life, so availability may factor into any decision. The RX 580's launch MSRP was 229 USD.