AMD Radeon R7 350 vs AMD Radeon R7 M370 Comparison

AMD Radeon R7 350 and AMD Radeon R7 M370 are both end-of-life 28nm GCN 1.0 parts, but benchmark data shows a clear hierarchy: the R7 350 wins both head-to-head tests by a healthy margin, with a 10.3% lead in Geekbench OpenCL and a 9.2% lead in Geekbench Vulkan. The R7 350's average benchmark score of 7425 places it at the 40th percentile of all GPUs, while the R7 M370's 6764 average sits at the 38th percentile, a gap that reflects real architectural and configuration differences rather than a close contest.

Head-to-Head Benchmarks

The R7 350 dominates the R7 M370 in every recorded benchmark. In Geekbench OpenCL, the R7 350 scores 7792 against the R7 M370's 7063, producing a 10.3% delta. This is not a marginal victory; it is a decisive advantage that carries over to Vulkan, where the R7 350 posts 7057 versus 6465, a 9.2% gap. Across both tests, the R7 350 wins 2 out of 2 comparisons, with the R7 M370 failing to secure a single victory.

The consistency of these wins matters. The 10.3% OpenCL margin aligns with the R7 350's raw compute advantages: it delivers 819.2 GFLOPS FP32 performance versus 737.3 GFLOPS for the R7 M370, and its texture rate of 25.60 GTexel/s outpaces the R7 M370's 23.04 GTexel/s. The pixel rate gap is even starker — 12.80 GPixel/s versus 7.680 GPixel/s — which explains why the R7 350's lead persists across different API workloads.

Looking at the nearest rivals puts these scores in context. The R7 350's average of 7425 is nearly identical to the Intel UHD Graphics 750 (7441, -0.2%) and the AMD Radeon HD 8850M (7447, -0.3%), meaning the R7 350 trades blows with those parts rather than dominating them. However, it trails the NVIDIA GeForce GTX 1650 (7472, -0.6%) and Intel Arc A310 (7550, -1.7%) by less than 2%. The R7 M370, by contrast, sits 1% ahead of the NVIDIA GeForce GT 1010 (6698) and 2.3% ahead of the AMD Radeon R7 M460 (6612), but it falls 1% behind the AMD FirePro M5100 (6830) and 2.6% behind the NVIDIA GeForce GTX 675M (6946). This positions the R7 M370 as a lower-tier mobile part, while the R7 350 punches closer to entry-level desktop dGPUs.

Where Each One Wins

The R7 350 wins outright in both benchmark categories, so the practical question is which workloads benefit most from its lead. The 10.3% OpenCL advantage suggests the R7 350 is better suited for compute-oriented tasks that leverage general-purpose GPU processing, such as OpenCL-accelerated applications. Its 512 shading units and 32 texture mapping units (TMUs) provide a wider execution width than the R7 M370's 384 shaders and 24 TMUs, which directly translates to higher throughput in parallel workloads.

For Vulkan-based gaming or graphics APIs, the R7 350's 9.2% lead is still substantial, but the gap narrows slightly compared to OpenCL. This indicates that while the R7 350 is clearly faster in real-time rendering scenarios, the R7 M370's relatively stronger Vulkan showing (compared to its own OpenCL result) hints that its 875 MHz base and 960 MHz boost clocks help it close the gap somewhat. The R7 M370's clock speeds are the only specifications where it exceeds the R7 350, whose clocks are not listed in the data — but the R7 350's higher memory bandwidth (72.00 GB/s versus 57.60 GB/s) and faster effective memory speed (4.5 Gbps versus 3.6 Gbps) likely compensate.

The R7 M370's only theoretical edge is its lower transistor count (950 million versus 1,500 million) and smaller die size (77 mm² versus 123 mm²), which historically correlates with lower power consumption. However, no TDP is listed for the R7 M370, so that advantage cannot be quantified. The R7 M370 also uses a PCIe 3.0 x8 interface versus the R7 350's PCIe 3.0 x16, which could bottleneck bandwidth-sensitive tasks, though the practical impact in benchmarks appears minimal given the R7 350's consistent wins.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R7 350 has an average benchmark score of 7425, while the AMD Radeon R7 M370 scores 6764, giving the R7 350 a lead of approximately 9.8% based on those averages.

Q: How much faster is the R7 350 in OpenCL?

A: The R7 350 scores 7792 in Geekbench OpenCL versus 7063 for the R7 M370, which represents a 10.3% delta in favor of the R7 350.

Q: Does the R7 M370 win any benchmark comparison?

A: No. The head-to-head data shows the R7 350 winning both Geekbench OpenCL and Geekbench Vulkan tests, with the R7 M370 recording zero wins.

Q: How do these GPUs compare to their nearest rivals?

A: The R7 350 is within 1.7% of the Intel Arc A310 (7550) and 0.6% of the NVIDIA GeForce GTX 1650 (7472), while the R7 M370 is 2.6% behind the NVIDIA GeForce GTX 675M (6946) and 1% behind the AMD FirePro M5100 (6830).

Q: What memory configuration do both GPUs share?

A: Both the R7 350 and R7 M370 feature 2 GB of GDDR5 memory on a 128-bit bus, but the R7 350's bandwidth is 72.00 GB/s versus 57.60 GB/s for the R7 M370.

Q: Which GPU has a higher pixel rate?

A: The R7 350 achieves 12.80 GPixel/s, which is significantly higher than the R7 M370's 7.680 GPixel/s, a 66.7% advantage for the R7 350.

Specification Differences

The two GPUs diverge on several key specifications. The R7 350 uses the Cape Verde chip with 1,500 million transistors on a 123 mm² die, while the R7 M370 uses the Litho chip with 950 million transistors on a 77 mm² die. The R7 350 features 512 shading units, 32 TMUs, and 16 ROPs, whereas the R7 M370 has 384 shading units, 24 TMUs, and only 8 ROPs. This ROP difference is critical: the R7 350's pixel rate of 12.80 GPixel/s more than doubles the R7 M370's 7.680 GPixel/s.

Memory bandwidth also differs substantially. The R7 350 runs its GDDR5 memory at 1125 MHz (4.5 Gbps effective) for 72.00 GB/s, while the R7 M370 runs at 900 MHz (3.6 Gbps effective) for 57.60 GB/s. The R7 350's compute throughput of 819.2 GFLOPS FP32 exceeds the R7 M370's 737.3 GFLOPS, and its texture rate of 25.60 GTexel/s beats 23.04 GTexel/s.

The R7 350 has a listed TDP of 55 W and uses a single-slot design with no power connectors and a suggested PSU of 250 W. The R7 M370 has no TDP, slot width, power connector, or PSU data listed. The R7 350 connects via PCIe 3.0 x16 and offers display outputs (1x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2), while the R7 M370 uses PCIe 3.0 x8 and lists no display outputs. The R7 350's physical length is 168 mm (6.6 inches), while the R7 M370 has no dimensions listed.

Architecture Differences

Both GPUs share the GCN 1.0 architecture and are manufactured on TSMC's 28 nm process, but their transistor densities are nearly identical: 12.2M / mm² for the R7 350 and 12.3M / mm² for the R7 M370. The R7 350 is part of the Pirate Islands (R7 300) generation and was released on 2016-07-05, succeeding the Volcanic Islands and preceding Arctic Islands. The R7 M370 belongs to the Gem System (R7 M300) generation, released on 2015-05-04, with predecessors and successors in the Solar System and Polaris Mobile lines respectively.

The architectural difference in execution resources is pronounced. The R7 350's 512 shading units represent a 33% increase over the R7 M370's 384, and its 16 ROPs double the R7 M370's 8. This suggests the R7 350 was designed for higher fill-rate workloads, while the R7 M370's smaller die and transistor count point toward a more power-conscious mobile design. Both support DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170, so API compatibility is identical. The R7 M370's clock speeds (875 MHz base, 960 MHz boost) are the only area where it has a specification that the R7 350 lacks, but these clocks cannot overcome the R7 350's superior memory bandwidth and wider execution pipeline.

The transistor count difference — 1,500 million versus 950 million — indicates the R7 350 has 58% more transistors, which aligns with its larger die and higher shading unit count. However, the R7 M370's smaller footprint likely made it easier to integrate into laptops, whereas the R7 350's 168 mm length and single-slot design suggest a desktop-oriented card.

The Verdict

The data is unambiguous: the AMD Radeon R7 350 is the faster GPU in every measured category. With a 10.3% OpenCL win and a 9.2% Vulkan win, it offers a 9.8% higher average benchmark score than the R7 M370. Buyers or system builders choosing between these two should select the R7 350 if performance is the priority, as it delivers superior pixel rate (12.80 GPixel/s), texture rate (25.60 GTexel/s), and FP32 compute (819.2 GFLOPS) — all backed by 72.00 GB/s of memory bandwidth.

The R7 M370's only advantages are its smaller die (77 mm²), lower transistor count (950 million), and listed clock speeds (875 MHz base, 960 MHz boost), but none of these translate into benchmark wins. Its 38th percentile ranking versus the R7 350's 40th percentile confirms the performance gap. If power consumption or physical size were critical constraints, the R7 M370's smaller footprint might be appealing, but the lack of TDP data prevents any quantitative power comparison.

For users targeting OpenCL compute workloads or Vulkan gaming, the R7 350 is the clear choice. For those constrained to a mobile form factor where the R7 M370 would typically reside, the performance penalty is steep — nearly 10% on average. The R7 350 also offers a wider PCIe interface (x16 versus x8) and explicit display outputs, making it more versatile for desktop use. In short, the R7 350 wins on performance, bandwidth, and feature set; the R7 M370 only wins on die size and clock speed listings, which do not translate to better results. Pick the R7 350 unless the R7 M370's smaller physical footprint is a hard requirement.