AMD Radeon R9 M380 vs NVIDIA GeForce RTX 2060 Comparison

The AMD Radeon R9 M380 and the NVIDIA GeForce RTX 2060 represent two vastly different eras of mobile and desktop graphics, separated by nearly four years of architectural evolution. The data reveals a stark performance disparity, with the RTX 2060 dominating the only shared benchmark, yet the R9 M380 holds its own in the broader context of GPU percentile rankings. Both cards sit at the 58th percentile against all GPUs, according to the provided data, which suggests that while their average scores are close in some comparisons, the nature of their workloads and the specific tests used paint a more nuanced picture.

Head-to-Head Benchmarks

The single direct comparison available is the Geekbench OpenCL test, and the results are not close. The NVIDIA GeForce RTX 2060 scores 65,014 points, while the AMD Radeon R9 M380 manages 12,565 points. This translates to a deltaPct of -80.7% for the R9 M380, meaning the RTX 2060 is roughly four times faster in this compute-heavy workload. The margin is enormous, reflecting not just a generational leap but a fundamental difference in compute capability. The RTX 2060’s score is so high that it dwarfs the R9 M380’s entire benchmark profile; the older card’s Geekbench Metal score of 18,476 is still lower than the RTX 2060’s OpenCL result.

However, the head-to-head data is limited to this one test, which heavily favors the newer architecture. The RTX 2060 also shows its strength in other tests not shared with the R9 M380, such as a Passmark G3D score of 14,111 and a Geekbench Vulkan score of 65,846. These figures, while not direct comparisons, indicate a consistent pattern of high throughput across different APIs. The R9 M380, with no Vulkan score listed and only a modest OpenCL result, appears optimized for older or different workloads. The deltaPct of -80.7 is the single most telling statistic: it is not a marginal lead but a categorical one, suggesting the R9 M380 is outclassed in any scenario that stresses raw parallel processing.

Where Each One Wins

Based strictly on the data, the RTX 2060 wins the only direct head-to-head benchmark, so it is the clear victor in OpenCL-based compute tasks. Its Geekbench OpenCL score of 65,014 is over five times higher than the R9 M380’s 12,565, making it the only logical choice for applications that leverage this API, such as certain scientific simulations, video encoding, or machine learning inference. The RTX 2060 also demonstrates versatility with high scores across DirectX 12 (Passmark 53), DirectX 11 (Passmark 110), and DirectX 9 (Passmark 190), though these are not directly compared to the R9 M380.

The R9 M380, despite losing the compute battle, shows a relative strength in the Geekbench Metal test, scoring 18,476. This is its highest benchmark result and suggests it may be better suited for Apple-specific Metal-based applications, where its GCN 2.0 architecture can still deliver acceptable performance. In contrast, the RTX 2060 has no Metal score listed, indicating that the R9 M380 might be the only option for users constrained to that API. However, the R9 M380’s OpenCL score of 12,565 is less than half its Metal score, implying its compute performance is inconsistent across different frameworks. Therefore, the R9 M380 wins only in the narrow niche of Metal-accelerated workloads, while the RTX 2060 wins everything else, including all shared and unshared benchmarks where it has a score.

Architecture Differences

The architectural gap between these two GPUs is immense, as detailed in the FACT PACK. The AMD Radeon R9 M380 is built on GCN 2.0 architecture, using the Strato chip, and is fabricated on a 28 nm process at TSMC. It packs 2,080 million transistors onto a 160 mm² die, yielding a transistor density of 13.0M per mm². In contrast, the NVIDIA GeForce RTX 2060 uses the Turing architecture with the TU106 chip, manufactured on a 12 nm process, also at TSMC. This newer node allows for 10,800 million transistors on a 445 mm² die, with a density of 24.3M per mm². The RTX 2060’s transistor count is over five times higher, and its density is nearly double, indicating a far more complex and efficient design.

The core configurations diverge sharply. The R9 M380 has 768 shading units, 48 texture mapping units (TMUs), and 16 raster operations pipelines (ROPs). The RTX 2060, by contrast, features 1,920 shading units, 120 TMUs, and 48 ROPs. Beyond these traditional units, the RTX 2060 introduces 30 RT cores and 240 tensor cores, which are entirely absent from the R9 M380. These dedicated hardware blocks enable real-time ray tracing and AI-accelerated features, respectively, which the GCN 2.0 architecture cannot perform. The RTX 2060 also supports DirectX 12 Ultimate (12_2), while the R9 M380 is limited to DirectX 12 (12_0), meaning the newer card can handle more advanced rendering features like mesh shaders and variable rate shading. Both support OpenGL 4.6, but the RTX 2060 has Vulkan 1.4 support compared to the R9 M380’s Vulkan 1.2.170, showing a more modern driver stack.

Specification Differences

The specification differences beyond the core architecture are equally pronounced. The R9 M380 has 4 GB of GDDR5 memory on a 128-bit bus, delivering 96.00 GB/s of bandwidth. The RTX 2060 offers 6 GB of GDDR6 memory on a 192-bit bus, with a bandwidth of 336.0 GB/s—a 3.5x improvement. Clock speeds also favor the newer card: the R9 M380 runs at 900 MHz base and 1000 MHz boost, while the RTX 2060 clocks at 1365 MHz base and 1680 MHz boost. This leads to vastly different fill rates: the R9 M380 produces 16.00 GPixel/s and 48.00 GTexel/s, while the RTX 2060 achieves 80.64 GPixel/s and 201.6 GTexel/s.

Compute performance is where the gap becomes a chasm. The R9 M380’s FP32 throughput is 1.536 TFLOPS, with no FP16 capability listed. The RTX 2060 delivers 6.451 TFLOPS of FP32 and 12.90 TFLOPS of FP16 (2:1), meaning it can process half-precision data at twice the rate. Power consumption is not listed for the R9 M380, but the RTX 2060 has a TDP of 160 W and requires a 450 W suggested PSU, along with a single 8-pin power connector. The RTX 2060 is also physically a dual-slot card measuring 229 mm in length, 113 mm in height, and 35 mm in width, with display outputs including 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, and 1x USB Type-C. The R9 M380 has no listed dimensions or display outputs, though it uses the same PCIe 3.0 x16 interface. Finally, the RTX 2060 has a launch MSRP of 349 USD, a fact that can be stated once but not analyzed further.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon R9 M380 has an average benchmark score of 15,521, while the NVIDIA GeForce RTX 2060 scores 15,290, a difference of 1.5% in favor of the R9 M380.

Q: How does the RTX 2060 compare to its closest rival, the GTX 580?

A: The RTX 2060 has an average score of 15,290, which is exactly equal to the GTX 580’s average score of 15,283, resulting in a deltaPct of 0%.

Q: What is the memory bandwidth difference between the two cards?

A: The R9 M380 has 96.00 GB/s of bandwidth from 4 GB of GDDR5 on a 128-bit bus, while the RTX 2060 has 336.0 GB/s from 6 GB of GDDR6 on a 192-bit bus.

Q: Does the R9 M380 support ray tracing?

A: No, the R9 M380 has no RT cores listed in its specifications, whereas the RTX 2060 includes 30 RT cores for dedicated ray tracing hardware.

Q: What is the transistor density of each chip?

A: The R9 M380’s Strato chip has a density of 13.0M transistors per mm², while the RTX 2060’s TU106 chip has a density of 24.3M per mm².

Q: Which card has a higher boost clock?

A: The RTX 2060 boosts to 1680 MHz, which is significantly higher than the R9 M380’s boost clock of 1000 MHz.

The Verdict

The data is unambiguous for most use cases: the NVIDIA GeForce RTX 2060 is the superior performer, winning the only direct benchmark by a margin of over 80%. Its architectural advantages—more shading units, higher clock speeds, dedicated RT and tensor cores, and 3.5x the memory bandwidth—make it the clear choice for modern gaming, compute, or any workload that leverages DirectX 12 Ultimate or Vulkan 1.4. The RTX 2060’s 6.451 TFLOPS of FP32 performance is over four times the R9 M380’s 1.536 TFLOPS, and its FP16 capability of 12.90 TFLOPS is entirely absent on the older card. For users who need maximum compute throughput, the RTX 2060 is the only rational pick.

However, the R9 M380 is not without a niche. Its Geekbench Metal score of 18,476 is its strongest result, and it is the only card with any Metal performance data. In an Apple-centric ecosystem where Metal is the primary API, the R9 M380 may still serve adequately, especially given its lower transistor count and older process node suggest it could be a lower-power part (though TDP is unlisted). Its average score of 15,521 is also marginally higher than the RTX 2060’s 15,290, which could indicate better optimization in certain non-OpenCL tests. But this is a slim consolation. The RTX 2060, with its 58th percentile ranking and a broader suite of benchmark scores, is the definitive choice for anyone seeking a capable, modern GPU. The R9 M380 should only be considered if Metal compatibility is a hard requirement, and even then, its compute limitations make it a legacy option rather than a competitive one.