AMD Radeon R7 M380 vs AMD Radeon RX 6600S Comparison

The AMD Radeon RX 6600S and the AMD Radeon R7 M380 occupy very different positions in the mobile graphics landscape, separated by nearly seven years of architectural evolution. The RX 6600S is a modern RDNA 2.0 part built for thin-and-light gaming laptops, while the R7 M380 is a GCN 1.0-era chip from 2015 that now sits firmly in legacy territory. The recorded data shows a decisive gap in raw performance, but the comparison also reveals how far mobile GPU design has progressed in terms of efficiency, feature support, and compute capability.

Where Each One Wins

The benchmark results are unambiguous: the RX 6600S wins the only shared test, Geekbench OpenCL, by a margin of 613.4 percent. Its score of 66435 dwarfs the R7 M380's 9313. That single data point defines the entire head-to-head comparison, but looking at the broader benchmark suite for each card tells a more complete story about where each product excels.

The RX 6600S has a full set of recorded benchmarks covering DirectX 9, 10, 11, and 12, plus 2D, 3D, and compute workloads. Its Passmark G3D score of 12649 places it in the 49th percentile of all GPUs in the database, meaning it sits right at the middle of the performance distribution. The compute score of 4879 and the DirectX 11 score of 105 suggest a card that handles modern game workloads competently, while the DirectX 9 score of 176 shows strong legacy compatibility. The DirectX 12 score of 56 is lower than the DirectX 11 result, which is typical for cards of this generation where early DX12 drivers were not fully optimized.

The R7 M380 has only one recorded benchmark, Geekbench OpenCL, with a score of 9313. This places it in the 46th percentile of all GPUs, just three points below the RX 6600S in percentile terms despite the massive raw score gap. The lack of other benchmark data means the database cannot confirm how it performs in DirectX workloads, older APIs, or compute tasks. What the percentile figure does show is that the R7 M380 is not an outlier in the database; it sits among a cluster of mid-range cards from its era, including the NVIDIA GeForce GTX 850M and GTX 465, both of which score within 0.2 percent of it.

The practical interpretation is simple: the RX 6600S wins every measurable comparison, and the R7 M380's only strength is that it exists in a similar performance percentile when normalized against its contemporaries. For modern gaming, the RX 6600S is the clear choice. For legacy systems running older software, the R7 M380 might still function, but the data does not support any scenario where it outperforms the newer card.

Architecture Differences

The architectural gulf between these two GPUs is enormous. The RX 6600S uses the Navi 23 chip built on RDNA 2.0, fabricated on a 7 nm TSMC process. It packs 11,060 million transistors into a 237 mm² die, yielding a transistor density of 46.7 million per square millimeter. The R7 M380 uses the Tropo chip based on GCN 1.0, built on a 28 nm process with 1,500 million transistors across a 123 mm² die, for a density of 12.2 million per square millimeter. The newer process node allows the RX 6600S to fit over seven times more transistors in roughly twice the die area.

The compute resources differ by a similar magnitude. The RX 6600S has 1792 shading units, 112 texture mapping units, and 64 raster output units. It also includes 28 ray tracing cores, a feature completely absent from the R7 M380. The older card has 640 shading units, 40 TMUs, and 16 ROPs, which is roughly one-third the shader count and one-quarter the ROP count of the newer part. The RX 6600S supports DirectX 12 Ultimate (12_2), while the R7 M380 only reaches DirectX 12 (11_1), a significant gap for modern titles that require feature level 12_2.

Memory architecture further separates the two. The RX 6600S uses 4 GB of GDDR6 on a 128-bit bus, delivering 224.0 GB/s of bandwidth. The R7 M380 also has 4 GB, but it uses DDR3 on the same 128-bit bus, yielding just 32.00 GB/s. That is a seven-fold difference in memory bandwidth, which directly impacts texture fill rates and high-resolution performance. The RX 6600S achieves a texture rate of 224.0 GTexel/s and a pixel rate of 128.0 GPixel/s, while the R7 M380 manages 36.60 GTexel/s and 14.64 GPixel/s respectively.

Clock speeds reinforce the gap. The RX 6600S runs at a base of 1700 MHz with a boost of 2000 MHz and a game clock of 1881 MHz. The R7 M380 operates at just 900 MHz base and 915 MHz boost. The memory clock tells a similar story: the RX 6600S uses 1750 MHz (14 Gbps effective) GDDR6, while the R7 M380 runs at 1000 MHz (2 Gbps effective) DDR3.

Other interface differences matter for system integration. The RX 6600S uses PCIe 4.0 x8, while the R7 M380 uses PCIe 3.0 x16. The newer card has a TDP of 80 W and is classified as an integrated graphics processor, meaning it is designed to be soldered onto the motherboard. The R7 M380 has no recorded TDP or slot width, but its older architecture and separate chip design suggest a discrete mobile GPU. The RX 6600S supports Vulkan 1.4 and OpenGL 4.6, while the R7 M380 supports Vulkan 1.2.170 and OpenGL 4.6.

Head-to-Head Benchmarks

The only direct comparison available in the database is the Geekbench OpenCL test. The RX 6600S scores 66435, while the R7 M380 scores 9313. The delta is 613.4 percent in favor of the RX 6600S. This is not a close race; it is a generational knockout. To put that number in context, the RX 6600S's average benchmark score across all recorded tests is 10629, while the R7 M380's average is 9313. Even if the RX 6600S only matched its average, it would still outperform the R7 M380 by roughly 14 percent.

However, the Geekbench OpenCL result is far above the RX 6600S's average, which suggests that its compute throughput is a particular strength. The FP32 performance of 7.168 TFLOPS and FP16 performance of 14.34 TFLOPS (2:1) explain why: the RX 6600S is a compute powerhouse relative to its gaming scores. The R7 M380, with 1,171.2 GFLOPS of FP32 and no recorded FP16 capability, cannot compete in any compute-heavy workload.

The nearest rivals for each card provide additional context. The RX 6600S sits within 1.4 percent of the AMD Radeon RX 550X, 1.2 percent of the NVIDIA Quadro K2200, and 0.6 percent of the NVIDIA GeForce GTX 560 Ti. The R7 M380 is within 1 percent of the AMD Radeon Vega 8, 0.4 percent of the NVIDIA GeForce GTX 960, and 0.2 percent of the NVIDIA GeForce GTX 465. These rival clusters show that both cards are mid-range parts, but the RX 6600S is competitive with a much newer set of peers.

The single head-to-head benchmark result is decisive. The RX 6600S wins the only shared test, and the database records one win for it and zero for the R7 M380. No other shared benchmarks exist, so the comparison rests entirely on this one data point plus the architectural specifications.

FAQ

Q: Which GPU has better compute performance?

A: The RX 6600S. Its Geekbench OpenCL score of 66435 is 613.4 percent higher than the R7 M380's 9313. The FP32 rate of 7.168 TFLOPS versus 1,171.2 GFLOPS confirms the gap.

Q: Do both cards support ray tracing?

A: No. The RX 6600S includes 28 ray tracing cores. The R7 M380 has no ray tracing hardware at all.

Q: What memory type does each card use?

A: The RX 6600S uses 4 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The R7 M380 uses 4 GB of DDR3 on a 128-bit bus with 32.00 GB/s bandwidth.

Q: Which card has a higher transistor count?

A: The RX 6600S has 11,060 million transistors, compared to 1,500 million for the R7 M380. The RX 6600S is built on a 7 nm process, while the R7 M380 uses 28 nm.

Q: Is the R7 M380 competitive in any benchmark?

A: The database records only one benchmark for the R7 M380, Geekbench OpenCL, where it scores 9313. It does not win any shared comparison against the RX 6600S.

Q: What is the DirectX support difference?

A: The RX 6600S supports DirectX 12 Ultimate (12_2), while the R7 M380 only reaches DirectX 12 (11_1). The RX 6600S also supports Vulkan 1.4 versus Vulkan 1.2.170 for the R7 M380.

Specification Differences

| Specification | AMD Radeon RX 6600S | AMD Radeon R7 M380 |

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

| Architecture | RDNA 2.0 | GCN 1.0 |

| Process Node | 7 nm | 28 nm |

| Transistors | 11,060 million | 1,500 million |

| Die Size | 237 mm² | 123 mm² |

| Transistor Density | 46.7M / mm² | 12.2M / mm² |

| Base Clock | 1700 MHz | 900 MHz |

| Boost Clock | 2000 MHz | 915 MHz |

| Game Clock | 1881 MHz | None |

| Memory Clock | 1750 MHz (14 Gbps effective) | 1000 MHz (2 Gbps effective) |

| Memory Type | GDDR6 | DDR3 |

| Memory Bandwidth | 224.0 GB/s | 32.00 GB/s |

| Shading Units | 1792 | 640 |

| TMUs | 112 | 40 |

| ROPs | 64 | 16 |

| Ray Tracing Cores | 28 | None |

| Pixel Rate | 128.0 GPixel/s | 14.64 GPixel/s |

| Texture Rate | 224.0 GTexel/s | 36.60 GTexel/s |

| FP32 | 7.168 TFLOPS | 1,171.2 GFLOPS |

| FP16 | 14.34 TFLOPS (2:1) | None |

| TDP | 80 W | None |

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

| DirectX | 12 Ultimate (12_2) | 12 (11_1) |

| Vulkan | 1.4 | 1.2.170 |

| Release Date | 2022-01-03 | 2015-05-04 |

The Verdict

The data points to one conclusion: the AMD Radeon RX 6600S is the superior GPU in every measurable way. It wins the only head-to-head benchmark by 613.4 percent, has more than ten times the transistor count, offers seven times the memory bandwidth, and includes hardware features like ray tracing that the R7 M380 simply does not have. The RX 6600S also sits in the 49th percentile of all GPUs, while the R7 M380 sits in the 46th, but the percentile gap understates the true performance difference because the older card's benchmark data is so limited.

For a user selecting a GPU for any modern workload, the RX 6600S is the only rational choice. Its DirectX 12 Ultimate support, Vulkan 1.4 compatibility, and 7.168 TFLOPS of FP32 compute make it suitable for current games, creative applications, and compute tasks. The R7 M380, with its GCN 1.0 architecture and 1,171.2 GFLOPS, belongs to a different era. It could still run older DirectX 11 titles at modest settings, but the database provides no evidence that it handles anything beyond basic OpenCL workloads.

The R7 M380's only redeeming quality is its longevity. Released in 2015, it remained in the database with a measurable percentile ranking, and its 4 GB of DDR3 memory matches the RX 6600S in capacity. But capacity without bandwidth is meaningless for performance, and the 32.00 GB/s versus 224.0 GB/s gap is insurmountable. The R7 M380 is a legacy part that has been superseded by the Polaris Mobile generation, which itself preceded the RX 6000 series. The RX 6600S is end-of-life as well, but it is a modern end-of-life: its 7 nm process, 28 ray tracing cores, and 80 W TDP make it a capable mobile GPU even today.

The verdict is straightforward. Choose the RX 6600S for any gaming, compute, or modern application workload. Choose the R7 M380 only if you are restoring a 2015-era laptop and need a drop-in replacement that matches the original specifications. The benchmark data does not support any other scenario where the R7 M380 is preferable.