AMD Radeon R9 M380 vs NVIDIA GeForce RTX 2060 SUPER Comparison

Where Each One Wins

The benchmark data splits these two GPUs into completely different performance tiers. The NVIDIA GeForce RTX 2060 SUPER dominates every shared workload, with the sole head-to-head result showing a 512.5% advantage over the AMD Radeon R9 M380 in Geekbench OpenCL. That is not a marginal gap; it is a generational chasm.

The RTX 2060 SUPER wins the only direct comparison available, but its broader benchmark suite reveals where it excels. Its PassMark G3D score of 16462 places it in the upper midrange of all GPUs, with a percentile ranking of 62. The card's compute-oriented workloads, measured by PassMark GPU Compute at 6721, and its DirectX 11 score of 130 indicate strong general-purpose and legacy API performance. The Geekbench Vulkan result of 77402 further confirms its capability in modern cross-platform graphics APIs.

The AMD Radeon R9 M380 has no wins in the recorded head-to-head data. Its strengths, if any, must be inferred from its limited benchmark presence. The card only has two recorded scores: Geekbench Metal at 18476 and Geekbench OpenCL at 12565. The Metal score is notably higher than its OpenCL score, suggesting the GCN 2.0 architecture performs better in Apple's Metal API than in the more generic OpenCL framework. However, even its stronger Metal result does not approach the RTX 2060 SUPER's OpenCL or Vulkan numbers.

For use-case selection, the data points clearly. The RTX 2060 SUPER is the choice for any application leveraging OpenCL, Vulkan, or DirectX 11 and 12. The R9 M380's only potential niche is Metal-based workflows, though the absence of comparative Metal data for the NVIDIA card means this cannot be quantified. In every measurable shared metric, the RTX 2060 SUPER is categorically superior, and the R9 M380 should be considered only for legacy systems where its API support aligns with specific software requirements.

Architecture Differences

The architectural gap between these two GPUs is as wide as the performance gap. The RTX 2060 SUPER uses NVIDIA's Turing architecture on a 12 nm TSMC process, while the R9 M380 uses AMD's GCN 2.0 architecture on a 28 nm TSMC process. The node difference alone, 12 nm versus 28 nm, explains much of the efficiency and density disparity.

The transistor counts tell a stark story. The RTX 2060 SUPER packs 10,800 million transistors into a 445 mm² die, yielding a transistor density of 24.3M per mm². The R9 M380 contains 2,080 million transistors on a 160 mm² die, with a density of 13.0M per mm². The NVIDIA chip has over five times the transistor count and nearly three times the die area, which directly translates into its massive compute advantage.

Memory subsystems diverge completely. The RTX 2060 SUPER features 8 GB of GDDR6 memory on a 256-bit bus, delivering 448.0 GB/s of bandwidth. The R9 M380 offers 4 GB of GDDR5 on a 128-bit bus, with 96.00 GB/s of bandwidth. That is a 352 GB/s bandwidth deficit for the AMD card, a 4.67x difference that severely limits its ability to feed its shader units.

The compute resources are equally lopsided. The RTX 2060 SUPER has 2176 shading units, 136 texture mapping units, and 64 raster output units. The R9 M380 has 768 shading units, 48 TMUs, and 16 ROPs. The NVIDIA card also adds dedicated hardware the AMD card lacks entirely: 34 ray tracing cores and 272 tensor cores. These are not present in the R9 M380, which means no hardware-accelerated ray tracing or AI inference capabilities.

Clock speeds and output rates follow the same pattern. The RTX 2060 SUPER runs at a 1470 MHz base and 1650 MHz boost, while the R9 M380 runs at 900 MHz base and 1000 MHz boost. The pixel rate of the RTX 2060 SUPER is 105.6 GPixel/s versus 16.00 GPixel/s for the AMD card. Texture rate is 224.4 GTexel/s versus 48.00 GTexel/s. Floating-point performance shows the largest gap: 7.181 TFLOPS FP32 for the NVIDIA card versus 1.536 TFLOPS for the AMD card, a 4.67x difference.

API support also differs. The RTX 2060 SUPER supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The R9 M380 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The NVIDIA card's newer DirectX feature level and Vulkan version provide access to more modern rendering techniques. The R9 M380 also lacks any FP16 support, while the RTX 2060 SUPER delivers 14.36 TFLOPS FP16 (2:1 ratio).

Head-to-Head Benchmarks

The only direct comparison recorded between these two cards is the Geekbench OpenCL test, and the result is decisive. The RTX 2060 SUPER scores 76957, while the R9 M380 scores 12565. The delta is 512.5% in favor of the NVIDIA card. This is not a close contest by any measure; the RTX 2060 SUPER outperforms the AMD card by a factor of roughly six in raw OpenCL compute.

To contextualize this result, the RTX 2060 SUPER's nearest rivals in the database include the NVIDIA GeForce RTX 3060 Mobile with an average score of 18159 and a delta of -0.4%, the AMD Radeon Pro 5700 at 18189 with a delta of -0.5%, and the AMD Radeon RX 460 at 18373 with a delta of -1.5%. The RTX 2060 SUPER's average benchmark score of 18093 sits within 1.6% of these cards, meaning it trades blows with modern midrange mobile and desktop parts.

The R9 M380's nearest rivals tell a different story. Its average benchmark score of 15521 places it near the NVIDIA GeForce GTX 1080 Ti, which scores 15548 with a delta of -0.2%, and the AMD Radeon Pro W5500 at 15679 with a delta of -1%. Interestingly, the R9 M380 is 1.5% ahead of the NVIDIA GeForce RTX 2060 in the database, which scores 15290, and 1.6% ahead of the GTX 580 at 15283. This suggests the R9 M380, despite its age, sits in a performance band comparable to high-end cards from earlier generations, but it is nowhere near the RTX 2060 SUPER's league.

Looking at the RTX 2060 SUPER's other benchmarks, its PassMark G3D score of 16462 and Geekbench Vulkan score of 77402 reinforce its dominance. The R9 M380's Geekbench Metal score of 18476 is its best recorded result, but even this cannot challenge the NVIDIA card's OpenCL output. The absence of Vulkan and DirectX benchmarks for the R9 M380 means the only apples-to-apples comparison is OpenCL, and that comparison is overwhelmingly one-sided.

The data indicates the RTX 2060 SUPER outperforms the R9 M380 by 512.5% in the shared OpenCL workload. In terms of average benchmark scores, the RTX 2060 SUPER's 18093 is 16.6% higher than the R9 M380's 15521. This gap, while smaller than the OpenCL delta, still represents a decisive overall performance advantage.

FAQ

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 2060 SUPER has 2176 shading units, while the AMD Radeon R9 M380 has 768 shading units. This 3x difference in shader count is a primary driver of the performance gap.

Q: How do the memory bandwidth figures compare?

A: The RTX 2060 SUPER delivers 448.0 GB/s of bandwidth from its 8 GB GDDR6 memory on a 256-bit bus. The R9 M380 provides 96.00 GB/s from 4 GB GDDR5 on a 128-bit bus. The NVIDIA card has 4.67x more bandwidth.

Q: Does the R9 M380 support hardware ray tracing?

A: No. The R9 M380 has no ray tracing cores listed in the database. The RTX 2060 SUPER includes 34 dedicated ray tracing cores and 272 tensor cores, which the AMD card lacks entirely.

Q: What is the transistor density difference?

A: The RTX 2060 SUPER achieves 24.3M transistors per mm² on its 12 nm process, while the R9 M380 achieves 13.0M per mm² on its 28 nm process. The newer manufacturing node gives the NVIDIA chip a significant density advantage.

Q: Which card has better OpenCL performance?

A: The RTX 2060 SUPER scores 76957 in Geekbench OpenCL, while the R9 M380 scores 12565. This represents a 512.5% advantage for the NVIDIA card in the only direct head-to-head benchmark available.

Q: How do their average benchmark scores compare to rival GPUs?

A: The RTX 2060 SUPER's average score of 18093 places it within 1.6% of the RTX 3060 Mobile, Radeon Pro 5700, RX 460, and Arc A770M. The R9 M380's average of 15521 places it within 1.6% of the GTX 1080 Ti, Radeon Pro W5500, RTX 2060, and GTX 580.

The Verdict

The recorded data makes the choice unambiguous for any workload covered by the benchmarks. The NVIDIA GeForce RTX 2060 SUPER is the superior GPU in every measurable category. Its 512.5% OpenCL advantage over the AMD Radeon R9 M380 is the single largest head-to-head delta in the database comparison, and its average benchmark score of 18093 versus 15521 confirms a 16.6% overall lead.

The RTX 2060 SUPER should be selected by users who need modern API support, high compute throughput, and hardware-accelerated ray tracing. Its 8 GB GDDR6 memory, 448.0 GB/s bandwidth, and 2176 shading units make it suitable for contemporary gaming and compute workloads. Its DirectX 12 Ultimate support and Vulkan 1.4 compatibility ensure access to current rendering features.

The R9 M380 is a legacy part from 2015, built on GCN 2.0 with 2,080 million transistors and 768 shading units. Its only recorded strength is a Geekbench Metal score of 18476, which suggests it may still function in Metal-centric environments, but no comparative Metal data for the RTX 2060 SUPER exists in the database to validate this as a competitive advantage. Its 4 GB GDDR5 memory and 96.00 GB/s bandwidth are severely limited by modern standards.

For users constrained to the R9 M380, the data indicates it performs comparably to the GTX 1080 Ti, Radeon Pro W5500, RTX 2060, and GTX 580, all within a 1.6% band of its 15521 average score. This places it in a historical performance tier that was once high-end but is now firmly midrange. However, when the choice is between these two specific cards, the RTX 2060 SUPER is the only rational selection based on benchmark evidence. The R9 M380 should only be considered for systems where its Metal API support is the sole requirement and the RTX 2060 SUPER's feature set is irrelevant.