AMD Radeon R7 M380 vs AMD Radeon R9 M360 Comparison

Head-to-Head Benchmarks

The database records a single direct benchmark comparison between the AMD Radeon R7 M380 and the AMD Radeon R9 M360. The sole recorded test, Geekbench OpenCL, shows a decisive win for the R7 M380. The R7 M380 scores 9,313 points, while the R9 M360 scores 8,211 points. This translates to a 13.4% delta in favor of the R7 M380, a substantial margin in compute workloads.

Contextualizing the R7 M380's score against its nearest rivals shows it sits in a tight cluster. The R7 M380's 9,313 score places it 0.1% ahead of the NVIDIA GeForce GTX 850M (9,302), 0.2% ahead of the NVIDIA GeForce GTX 465 (9,294), and 0.4% ahead of the NVIDIA GeForce GTX 960 (9,273). It also holds a 1% lead over the AMD Radeon Vega 8 (9,221). These results indicate that the R7 M380's compute performance is competitive with a range of desktop and mobile GPUs, with the margin over the closest rival being razor-thin.

The R9 M360's own rival list tells a different story. Its 8,211 OpenCL score is 0.1% behind the NVIDIA GeForce GTX 950M (8,135), a negligible difference. It is 0.4% ahead of the NVIDIA GeForce 945M (8,099) and 0.6% ahead of the NVIDIA GRID K2 (8,080). Interestingly, the data shows the R9 M360 is 0.5% behind the NVIDIA GeForce GTX 980 (8,167), a desktop-class card. This places the R9 M360 in a performance bracket that is measurably below the R7 M380, despite both cards sharing the same chip and architecture generation.

The head-to-head result is unambiguous. The R7 M380 wins the only recorded benchmark, and the win is not marginal but a clear 13.4% advantage. The R9 M360's higher boost clock and faster memory type do not translate into a compute advantage in the recorded data; instead, the R7 M380's larger shader array proves decisive.

The Verdict

Based strictly on the recorded data, the AMD Radeon R7 M380 is the superior performer. It wins the sole benchmark comparison by a wide margin and achieves a higher percentile ranking among all GPUs. The R7 M380 sits at the 46th percentile, while the R9 M360 sits at the 42nd percentile. This difference, while not enormous, is consistent with the 13.4% lead in compute performance.

The R7 M380 is the card to choose if the primary criterion is raw compute throughput in OpenCL workloads. Its 1,171.2 GFLOPS FP32 performance, enabled by 640 shading units and 40 texture mapping units, is a significant advantage over the R9 M360's 947.2 GFLOPS and 512 shading units. The R7 M380 also has a higher texture rate at 36.60 GTexel/s versus 29.60 GTexel/s, which will benefit texture-heavy workloads.

The R9 M360, however, has its own strengths in the data. Its memory configuration is notably faster: it uses GDDR5 memory with a bandwidth of 72.00 GB/s, compared to the R7 M380's DDR3 memory at 32.00 GB/s. This is a 2.25x advantage in memory bandwidth, which could be relevant for certain memory-bound tasks. The R9 M360 also has a slightly higher boost clock at 925 MHz versus 915 MHz, and a higher pixel rate at 14.80 GPixel/s versus 14.64 GPixel/s, though these differences are small.

In practice, the R9 M360's memory bandwidth advantage may help in some scenarios, but the recorded compute benchmark shows a clear win for the R7 M380. For users prioritizing general compute performance, the R7 M380 is the clear choice. For users who might value memory bandwidth characteristics, the R9 M360 offers that specific advantage, but it comes with a significant overall performance deficit.

FAQ

Q: Which GPU has a higher Geekbench OpenCL score?

A: The AMD Radeon R7 M380 scores 9,313, while the AMD Radeon R9 M360 scores 8,211. The R7 M380 leads by 13.4%.

Q: How does the R7 M380 compare to the NVIDIA GeForce GTX 850M?

A: The R7 M380 scores 9,313, which is 0.1% higher than the GTX 850M's 9,302. The two are essentially tied in compute performance.

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

A: The R9 M360 has a memory bandwidth of 72.00 GB/s using GDDR5 memory, while the R7 M380 has 32.00 GB/s using DDR3 memory. The R9 M360 has more than double the bandwidth.

Q: Which card has more shading units?

A: The R7 M380 has 640 shading units, while the R9 M360 has 512 shading units. The R7 M380 has 128 more shading units.

Q: How does the R9 M360 perform relative to the NVIDIA GeForce GTX 950M?

A: The R9 M360 scores 8,211, which is 0.1% higher than the GTX 950M's 8,135. The two are effectively tied.

Q: What are the percentile rankings for each GPU?

A: The R7 M380 is at the 46th percentile among all GPUs, while the R9 M360 is at the 42nd percentile.

Specification Differences

The two cards share the same chip, architecture, process node, foundry, transistor count, and die size. The key differences lie in the compute configuration, memory subsystem, and clock speeds.

The R7 M380 has 640 shading units and 40 texture mapping units, while the R9 M360 has 512 shading units and 32 texture mapping units. Both have 16 raster operation pipelines. This gives the R7 M380 a clear advantage in compute and texture work, as reflected in its FP32 performance of 1,171.2 GFLOPS versus 947.2 GFLOPS for the R9 M360.

The R7 M380's base clock is 900 MHz with a boost of 915 MHz, while the R9 M360 has the same 900 MHz base but a slightly higher boost of 925 MHz. The memory clocks differ significantly: the R7 M380 runs at 1000 MHz (2 Gbps effective), while the R9 M360 runs at 1125 MHz (4.5 Gbps effective). This, combined with the memory type difference, results in the R9 M360's higher bandwidth.

Memory size and bus width are identical: both have 4 GB on a 128-bit bus. The pixel rate is nearly the same, with the R9 M360 at 14.80 GPixel/s versus the R7 M380's 14.64 GPixel/s. The texture rate favors the R7 M380 at 36.60 GTexel/s versus 29.60 GTexel/s.

Both cards use a PCIe 3.0 x16 bus interface and support DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. Both are end-of-life products released on the same date, May 4, 2015, and both list Solar System as their predecessor and Polaris Mobile as their successor.

Architecture Differences

Both the AMD Radeon R7 M380 and the AMD Radeon R9 M360 are built on the Tropo chip using the GCN 1.0 architecture. They are manufactured on a 28 nm process at TSMC, with 1,500 million transistors on a 123 mm² die, yielding a transistor density of 12.2M per mm². The architecture is identical, and both belong to the Gem System generation, with the R7 M380 in the R7 M300 series and the R9 M360 in the R9 M300 series.

The fundamental architectural difference is in the execution resources. The R7 M380 implements the full complement of 640 shading units and 40 TMUs, while the R9 M360 has a reduced configuration of 512 shading units and 32 TMUs. This means the R7 M380 has 25% more shading units and 25% more texture mapping units than the R9 M360. The ROP count is identical at 16, so the pixel throughput is nearly the same, as evidenced by the similar pixel rates.

The memory architecture differs in type and resulting bandwidth. The R7 M380 uses DDR3 memory with a bandwidth of 32.00 GB/s, while the R9 M360 uses GDDR5 memory with a bandwidth of 72.00 GB/s. Both use a 128-bit memory bus and 4 GB of capacity. The GDDR5 memory in the R9 M360 operates at a higher effective data rate of 4.5 Gbps compared to the R7 M380's 2 Gbps.

The API support is identical, with both cards reporting DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. Neither card has dedicated ray tracing or tensor cores. The boost clock is marginally higher on the R9 M360 at 925 MHz versus 915 MHz, but this does not compensate for the reduced shader count in compute workloads. The recorded benchmark data confirms that the R7 M380's larger shader array provides a substantial performance advantage, despite the R9 M360's faster memory subsystem.