AMD Radeon R7 M380 vs NVIDIA GeForce MX350 Comparison

Head-to-Head Benchmarks

The database contains a single direct benchmark comparison between the NVIDIA GeForce MX350 and the AMD Radeon R7 M380, and it favors the AMD part. In the Geekbench OpenCL test, the AMD Radeon R7 M380 scores 9,313 points, while the NVIDIA GeForce MX350 scores 8,689 points. This is a 6.7% deficit for the NVIDIA GPU; the data shows the AMD part finishing ahead by that margin in this compute-oriented workload.

However, a single benchmark does not tell the whole story. The NVIDIA GeForce MX350 also has a recorded Geekbench Vulkan score of 13,077, but the AMD Radeon R7 M380 has no Vulkan result in the database, so no direct comparison can be made on that API. The average benchmark score across all recorded tests for the MX350 is 10,883, which is higher than the R7 M380’s 9,313. That average includes the Vulkan result, which boosts the NVIDIA part’s standing. For the R7 M380, the average score is identical to its single OpenCL score, since that is the only test recorded for it.

Looking at the broader competitive context, the MX350’s average score of 10,883 places it in the 49th percentile of all GPUs in the database, slightly above the midpoint. Its nearest rivals include the AMD Radeon Pro 450 at 10,804 (0.7% behind the MX350), the NVIDIA Quadro K2200 at 10,761 (1.1% behind), the NVIDIA GeForce GTX 1650 SUPER at 11,047 (1.5% ahead of the MX350), and the AMD Radeon RX 550 at 11,075 (1.7% ahead). These are tight margins; the MX350 is essentially within a couple of percentage points of a cluster of mid-range discrete GPUs.

The R7 M380, with an average score of 9,313, sits in the 46th percentile of all GPUs, three points lower than the MX350. Its nearest rivals are the NVIDIA GeForce GTX 850M at 9,302 (0.1% behind the R7 M380), the NVIDIA GeForce GTX 465 at 9,294 (0.2% behind), the NVIDIA GeForce GTX 960 at 9,273 (0.4% behind), and the AMD Radeon Vega 8 at 9,221 (1% behind). The R7 M380 edges out all of these, but the gaps are very small, under one percentage point in most cases.

The head-to-head result shows the R7 M380 winning the only shared test, but the MX350’s higher average score across all tests indicates that its Vulkan performance is strong enough to lift its overall standing above that of the AMD part. The data suggests that the MX350 is the more versatile GPU for compute workloads across multiple APIs, even though it loses the single OpenCL comparison.

Architecture Differences

The two GPUs come from different architectural eras and foundries. The NVIDIA GeForce MX350 is built on the Pascal architecture, using the GP107S chip, and is fabricated on a 14 nm process at Samsung. The AMD Radeon R7 M380 uses the GCN 1.0 architecture, based on the Tropo chip, and is manufactured on a 28 nm process at TSMC. The process node difference is significant: 14 nm versus 28 nm, meaning the MX350 uses a much more modern manufacturing process.

Transistor counts and die sizes reflect this generational gap. The MX350 packs 3,300 million transistors into a die size of 132 mm², resulting in a transistor density of 25.0 million transistors per mm². The R7 M380 has 1,500 million transistors on a 123 mm² die, with a density of 12.2 million per mm². The MX350 has more than double the transistor count on a slightly larger die, giving it a density advantage of roughly 2x.

Clock speeds also differ substantially. The MX350 runs at a base clock of 1354 MHz and a boost clock of 1468 MHz. The R7 M380 operates at a base clock of 900 MHz and a boost of 915 MHz. In raw clock terms, the MX350 is about 50% faster in both base and boost states, which is typical of a newer process node allowing higher frequencies.

The two GPUs have the same number of shading units at 640, but the rest of the execution resources differ. The MX350 has 32 texture mapping units and 16 ROPs. The R7 M380 has 40 texture mapping units and 16 ROPs. The AMD part has more texture units, but the NVIDIA part achieves a higher pixel rate of 23.49 GPixel/s versus 14.64 GPixel/s for the R7 M380, and a higher texture rate of 46.98 GTexel/s versus 36.60 GTexel/s. This is driven by the MX350’s higher clocks. In floating-point compute, the MX350 delivers 1.879 TFLOPS of FP32 performance, while the R7 M380 delivers 1,171.2 GFLOPS (which converts to about 1.171 TFLOPS). The MX350 is roughly 60% ahead in FP32 throughput.

Memory subsystems are quite different. The MX350 has 2 GB of GDDR5 memory on a 64-bit bus, with a bandwidth of 56.06 GB/s and an effective memory clock of 7 Gbps. The R7 M380 has 4 GB of DDR3 memory on a 128-bit bus, with a bandwidth of 32.00 GB/s and an effective clock of 2 Gbps. The MX350 has nearly double the bandwidth despite the narrower bus, because GDDR5 runs at much higher effective speeds. The R7 M380 has twice the capacity, which can matter for certain workloads, but the bandwidth advantage clearly belongs to the NVIDIA part.

The MX350 supports a higher feature set: DirectX 12 (12_1) versus DirectX 12 (11_1) for the R7 M380, and Vulkan 1.4 versus Vulkan 1.2.170. Both support OpenGL 4.6. The MX350 uses a PCIe 3.0 x4 interface, while the R7 M380 uses a PCIe 3.0 x16 interface. The R7 M380 has more PCIe lanes, but the MX350’s lower bandwidth requirements from the narrower bus suggest it was designed for portable systems. The MX350 has a stated TDP of 20 W and no power connectors, while the R7 M380 has no TDP listed in the database.

Where Each One Wins

The AMD Radeon R7 M380 wins the only direct head-to-head benchmark, the Geekbench OpenCL test, by 6.7%. This suggests that for OpenCL compute workloads, the R7 M380 has an edge despite its older architecture and lower clock speeds. The R7 M380 also has 4 GB of memory versus 2 GB on the MX350, which could be an advantage for applications that need larger working sets, even if the bandwidth is lower.

The NVIDIA GeForce MX350 wins on overall average benchmark score, 10,883 versus 9,313, and it has a Vulkan score of 13,077, which the R7 M380 cannot match because it has no recorded Vulkan result. This makes the MX350 the better choice for Vulkan-based applications, games, or compute tasks that can leverage that API. The MX350 also has a significant edge in raw FP32 compute, texture fillrate, and pixel fillrate, based on the recorded data.

The MX350’s higher bandwidth (56.06 GB/s versus 32.00 GB/s) and faster memory type (GDDR5 versus DDR3) suggest it will handle memory-intensive workloads more smoothly, even with a smaller capacity. The R7 M380’s larger 128-bit bus and 4 GB capacity mean it can address more data at once, but at a lower speed.

Specification Differences

The following fields differ between the two GPUs, according to the database:

• Manufacturer: NVIDIA versus AMD
• Chip: GP107S versus Tropo
• Architecture: Pascal versus GCN 1.0
• Generation: GeForce MX (3xx) versus Gem System (R7 M300)
• Process node: 14 nm versus 28 nm
• Foundry: Samsung versus TSMC
• Transistors: 3,300 million versus 1,500 million
• Die size: 132 mm² versus 123 mm²
• Transistor density: 25.0M / mm² versus 12.2M / mm²
• Base clock: 1354 MHz versus 900 MHz
• Boost clock: 1468 MHz versus 915 MHz
• Memory clock: 1752 MHz (7 Gbps effective) versus 1000 MHz (2 Gbps effective)
• Memory size: 2 GB versus 4 GB
• Memory type: GDDR5 versus DDR3
• Memory bus width: 64 bit versus 128 bit
• Memory bandwidth: 56.06 GB/s versus 32.00 GB/s
• TMUs: 32 versus 40
• Pixel rate: 23.49 GPixel/s versus 14.64 GPixel/s
• Texture rate: 46.98 GTexel/s versus 36.60 GTexel/s
• FP32: 1.879 TFLOPS versus 1,171.2 GFLOPS
• FP16: 29.36 GFLOPS (1:64) versus not available
• TDP: 20 W versus not listed
• Power connectors: None versus not listed
• Bus interface: PCIe 3.0 x4 versus PCIe 3.0 x16
• Display outputs: Portable Device Dependent versus not listed
• DirectX support: 12 (12_1) versus 12 (11_1)
• Vulkan support: 1.4 versus 1.2.170
• Release date: 2020-02-09 versus 2015-05-04
• Predecessor: not listed versus Solar System
• Successor: not listed versus Polaris Mobile

The shading units (640) and ROPs (16) are the same on both GPUs. Neither has ray tracing cores or tensor cores. The MX350 has no launch MSRP in the database, and the R7 M380 also has no launch MSRP.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce MX350, with an average benchmark score of 10,883, compared to 9,313 for the AMD Radeon R7 M380.

Q: Which GPU wins the Geekbench OpenCL test?

A: The AMD Radeon R7 M380 wins that specific test, scoring 9,313 versus 8,689 for the NVIDIA GeForce MX350, a 6.7% margin.

Q: Does the NVIDIA GeForce MX350 support Vulkan?

A: Yes, it supports Vulkan 1.4 and has a recorded Geekbench Vulkan score of 13,077. The AMD Radeon R7 M380 supports Vulkan 1.2.170 but has no recorded Vulkan benchmark.

Q: How much memory does each GPU have?

A: The NVIDIA GeForce MX350 has 2 GB of GDDR5 memory, while the AMD Radeon R7 M380 has 4 GB of DDR3 memory.

Q: Which GPU has higher memory bandwidth?

A: The NVIDIA GeForce MX350, at 56.06 GB/s, compared to 32.00 GB/s for the AMD Radeon R7 M380.

Q: What is the transistor density difference between the two?

A: The NVIDIA GeForce MX350 has a transistor density of 25.0M / mm², while the AMD Radeon R7 M380 has 12.2M / mm², reflecting the MX350’s newer 14 nm process versus the R7 M380’s 28 nm process.

The Verdict

The data points to the NVIDIA GeForce MX350 as the stronger overall GPU, primarily because of its higher average benchmark score of 10,883, its Vulkan capability, and its significant architectural advantages in clock speed, FP32 compute, texture rate, pixel rate, and memory bandwidth. The MX350 is a Pascal-generation part built on a 14 nm process, with a transistor count over double that of the R7 M380, and it delivers those resources at a much higher efficiency. For users running Vulkan workloads, the MX350 is clearly the better choice, as it has a recorded Vulkan score of 13,077 while the R7 M380 has none.

The AMD Radeon R7 M380 should not be dismissed, however. It wins the only direct OpenCL head-to-head test by 6.7%, and it offers twice the memory capacity at 4 GB, which can be a deciding factor for specific compute tasks that need larger buffers. Its 128-bit memory bus and 40 texture units give it some structural advantages, but its older GCN 1.0 architecture, 28 nm process, and lower clocks limit its overall performance ceiling.

For a user who prioritizes OpenCL compute and needs more memory capacity, the R7 M380 has a defensible position. For anyone who wants a more balanced GPU with better overall benchmark scores, modern API support, and higher throughput metrics, the MX350 is the part the data favors. The percentile rankings also reinforce this: the MX350 sits at the 49th percentile of all GPUs, while the R7 M380 sits at the 46th. The MX350 edges out rivals like the AMD Radeon Pro 450 and NVIDIA Quadro K2200, while the R7 M380 barely leads the NVIDIA GeForce GTX 850M and GTX 960. The verdict is straightforward: the MX350 is the more capable GPU in most measurable ways, with the R7 M380 holding a narrow niche in OpenCL and memory capacity.