AMD Radeon R7 350 vs AMD Radeon R9 M375X Comparison

The Verdict

The data presents a clear hierarchy between these two AMD GCN 1.0 parts. The AMD Radeon R9 M375X wins both recorded head-to-head benchmarks, taking the OpenCL test with a 6.2% delta and the Vulkan test with a substantial 18.7% delta. Its average benchmark score of 8325 places it at the 43rd percentile of all GPUs, while the Radeon R7 350 sits at 7425 and the 40th percentile.

The R9 M375X is the stronger performer, and its nearest rival list confirms this positioning. It sits within 1.6% of the GeForce MX330 and 1.3% of the Radeon 880M, while running ahead of the Quadro K1200 by 0.7%. The R7 350, by contrast, sits just 0.2% behind the Intel UHD Graphics 750 and only 0.3% ahead of the older Radeon HD 8850M. Its 1.7% gap behind the Intel Arc A310 shows the ceiling of its performance class.

For a user choosing between these two, the verdict is straightforward: the R9 M375X offers measurably better compute performance in both APIs tested, with the Vulkan advantage being particularly pronounced. The R7 350 does bring a lower power footprint at 55 W and a single-slot design, which makes it the more appropriate choice for constrained chassis, but the performance data does not favor it in any benchmark.

Architecture Differences

Both GPUs share the same GCN 1.0 architecture, are built on TSMC's 28 nm process, and use the same Tropo and Cape Verde silicon family lineage. Both chips pack 1,500 million transistors on a 123 mm² die, yielding a transistor density of 12.2M per mm². The R9 M375X belongs to the Gem System (R9 M300) generation, while the R7 350 comes from the Pirate Islands (R7 300) generation, though both trace their lineage through AMD's mobile and desktop GCN parts.

The key architectural difference lies in the compute configuration. The R9 M375X carries 640 shading units, 40 texture mapping units, and 16 ROPs. The R7 350 is trimmed to 512 shading units, 32 TMUs, and the same 16 ROPs. That is a 25% reduction in shader count and a 20% reduction in texture units, which directly explains the performance gap. The R9 M375X also runs its core at a base clock of 925 MHz with a boost of 1015 MHz, while the R7 350 has no recorded base or boost clock in the database, leaving its core frequency unspecified.

Memory subsystems are identical on paper. Both use 2 GB of GDDR5 on a 128-bit bus with a 1125 MHz memory clock and 4.5 Gbps effective data rate, producing exactly 72.00 GB/s of bandwidth. Neither card supports ray tracing cores or tensor cores. Both expose the same API surface: DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The R7 350 adds physical details the R9 M375X lacks, including a single-slot cooler, no power connectors, a 250 W suggested PSU, and DisplayPort 1.2, HDMI 1.4a, and DVI outputs.

FAQ

Q: Which GPU is faster in OpenCL compute workloads?

A: The R9 M375X scores 8273 in Geekbench OpenCL versus 7792 for the R7 350, a 6.2% advantage for the R9 M375X.

Q: How large is the Vulkan performance gap between the two?

A: The R9 M375X scores 8377 in Geekbench Vulkan versus 7057 for the R7 350, an 18.7% delta. This is the largest single benchmark difference in the recorded data.

Q: Do both GPUs have the same memory configuration?

A: Yes. Both have 2 GB of GDDR5, a 128-bit bus, and 72.00 GB/s of bandwidth with a 1125 MHz memory clock.

Q: What are the core clock speeds for each card?

A: The R9 M375X has a base clock of 925 MHz and a boost clock of 1015 MHz. The R7 350 has no base or boost clock recorded in the database.

Q: Which GPU has a higher overall percentile ranking?

A: The R9 M375X ranks at the 43rd percentile of all GPUs, while the R7 350 ranks at the 40th percentile.

Q: What is the power requirement for the R7 350?

A: The R7 350 has a 55 W TDP, requires no power connectors, and lists a 250 W suggested PSU. The R9 M375X has no TDP or PSU data recorded.

Specification Differences

The two GPUs share their manufacturing process, transistor count, die size, memory configuration, and API support, but diverge in several key areas.

The R9 M375X has 640 shading units against 512 for the R7 350. It also carries 40 TMUs versus 32, while both have 16 ROPs. Pixel rate for the R9 M375X is 16.24 GPixel/s versus 12.80 GPixel/s for the R7 350. Texture rate is 40.60 GTexel/s versus 25.60 GTexel/s. FP32 compute is rated at 1,299.2 GFLOPS for the R9 M375X and 819.2 GFLOPS for the R7 350, a difference of roughly 58.6% in raw floating-point throughput.

The R9 M375X has a base clock of 925 MHz and a boost of 1015 MHz, whereas the R7 350 has neither a base nor a boost clock in the database. The R7 350 is the only one with a recorded TDP of 55 W, a single-slot width, no power connectors, a 250 W suggested PSU, a 168 mm (6.6 inches) length, and display outputs of 1x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The R9 M375X lacks all of those fields.

Generation names also differ: the R9 M375X is part of Gem System (R9 M300), and the R7 350 belongs to Pirate Islands (R7 300). Their release dates differ as well, with the R9 M375X releasing in 2015 and the R7 350 in 2016. The R9 M375X lists its predecessor as Solar System and successor as Polaris Mobile, while the R7 350 lists Volcanic Islands and Arctic Islands respectively.

Head-to-Head Benchmarks

The recorded head-to-head data contains two benchmark tests, and the R9 M375X wins both. In Geekbench OpenCL, the R9 M375X scores 8273 against 7792 for the R7 350. That is a 6.2% delta, a moderate but consistent advantage. In Geekbench Vulkan, the R9 M375X scores 8377 against 7057, an 18.7% delta that shows the R9 M375X pulling far ahead when the workload shifts to a lower-level graphics API.

The Vulkan result is particularly telling. The R9 M375X actually improves its score from OpenCL to Vulkan, moving from 8273 to 8377, while the R7 350 drops from 7792 to 7057. That divergence suggests the R7 350's reduced shader count and texture unit count are more heavily penalized under Vulkan, or that its driver path is less optimized for that API. Either way, the delta more than triples between the two tests.

Wins are tallied at 2 for the R9 M375X and 0 for the R7 350. There are no benchmark categories in the database where the R7 350 comes out ahead.

Where Each One Wins

The R9 M375X wins every recorded benchmark category, so any workload represented by Geekbench OpenCL or Geekbench Vulkan will favor it. The OpenCL test shows a 6.2% advantage, making the R9 M375X the better choice for general compute tasks that use OpenCL. The Vulkan test shows an 18.7% advantage, making it the clear pick for any Vulkan-based application or game.

The R7 350 has no benchmark wins in the database. Its only advantages come from physical and power characteristics. It is rated at 55 W TDP, requires no power connectors, and suggests a 250 W PSU, whereas the R9 M375X has no recorded power data at all. It is also a single-slot card with a 168 mm length and includes DVI, HDMI 1.4a, and DisplayPort 1.2 outputs. For a system with strict power limits or a narrow chassis, the R7 350 is the only one of the two with documented compatibility data.

Looking at the nearest rival lists, the R9 M375X competes in a higher performance bracket. It trails the GeForce GTX 675MX by 1.2%, the Radeon 880M by 1.3%, and the GeForce MX330 by 1.6%, while edging the Quadro K1200 by 0.7%. The R7 350, meanwhile, sits in a lower tier, just 0.2% behind the Intel UHD Graphics 750 and 0.3% ahead of the Radeon HD 8850M, while trailing the GeForce GTX 1650 by 0.6% and the Arc A310 by 1.7%. The percentile gap of 43 versus 40 mirrors this positioning.

For users who need maximum compute throughput in either OpenCL or Vulkan, the R9 M375X is the only choice between these two. For users who need a low-power, single-slot card with no auxiliary power and documented display outputs, the R7 350 has the only recorded specifications to evaluate. The data does not show any performance scenario where the R7 350 takes the lead.