AMD Radeon R9 M375 vs NVIDIA GeForce GTX 960A Comparison

Where Each One Wins

The recorded benchmark data splits these two mobile-class GPUs along a single measurable axis. The NVIDIA GeForce GTX 960A takes the only head-to-head win in the database, beating the AMD Radeon R9 M375 in the Geekbench OpenCL test by a decisive 14.7%. That is the sole benchmark where both parts have a direct comparison, so the GTX 960A claims all of the wins in this matchup.

The AMD Radeon R9 M375 does have a second benchmark entry, a Geekbench Vulkan score of 9682, but the GTX 960A has no corresponding Vulkan result in the database. Without a direct head-to-head Vulkan comparison, the data cannot award that test to either card. For OpenCL workloads, which is the only shared test, the GTX 960A is clearly the stronger performer.

Looking at the broader database context, the GTX 960A sits at the 51st percentile among all GPUs, while the R9 M375 sits at the 48th. That three-percentile gap aligns with the 14.7% OpenCL delta. The GTX 960A's average benchmark score of 11998 places it alongside much more recent desktop parts, within 0.3% of the GeForce GTX 1080 and 3.2% of the Radeon RX 7800 XT. The R9 M375's average score of 10070 puts it in the company of older mobile workstation parts like the Quadro K5100M, which it edges by 0.3%. These percentile and rival comparisons reinforce that the GTX 960A is the pick for raw compute throughput, while the R9 M375 trails by a noticeable margin.

Architecture Differences

The two GPUs come from different architectural families, and the data shows several fundamental design splits. The GTX 960A uses the GM107 chip built on NVIDIA's Maxwell architecture, fabricated by TSMC on a 28 nm process. The R9 M375 uses the Tropo chip based on AMD's GCN 1.0 architecture, also fabricated by TSMC on 28 nm. Both share the same process node, but the chips themselves differ in scale. The GM107 packs 1,870 million transistors into a 148 mm² die, giving a transistor density of 12.6 million per square millimeter. The Tropo chip has 1,500 million transistors on a 123 mm² die, for a density of 12.2 million per square millimeter.

The compute resources are identical in count: both have 640 shading units, 40 texture mapping units, and 16 ROPs. The clock speeds, however, favor the NVIDIA part. The GTX 960A runs at a base clock of 1097 MHz with a boost of 1176 MHz. The R9 M375 runs at 1000 MHz base and 1015 MHz boost. That higher clock speed, combined with the architectural efficiency of Maxwell, translates into better throughput numbers. The GTX 960A delivers 18.82 GPixel/s pixel rate, 47.04 GTexel/s texture rate, and 1.505 TFLOPS of FP32 compute. The R9 M375 delivers 16.24 GPixel/s, 40.60 GTexel/s, and 1,299.2 GFLOPS. Every throughput metric favors the GTX 960A.

Memory is another major divergence. The GTX 960A uses 2 GB of GDDR5 on a 128-bit bus, achieving 80.19 GB/s of bandwidth at an effective 5 Gbps. The R9 M375 also has 2 GB on a 128-bit bus, but it uses DDR3 at an effective 1800 Mbps, yielding just 28.80 GB/s. That is a massive bandwidth deficit for the AMD part, roughly 64% less memory throughput. For texture-heavy or bandwidth-sensitive workloads, this difference alone would put the GTX 960A ahead even if compute rates were similar.

Bus interfaces also differ. The GTX 960A uses an MXM-B (3.0) interface with an MXM Module slot width and no power connectors. The R9 M375 uses PCIe 3.0 x16. The NVIDIA part is a portable-device-dependent display output, while the AMD part has no recorded display output information. The AMD card also has no recorded TDP, while the GTX 960A is rated at 75 W.

Head-to-Head Benchmarks

The database contains exactly one direct head-to-head benchmark between these two cards: Geekbench OpenCL. The GTX 960A scores 11998, while the R9 M375 scores 10457. That is a 14.7% advantage for the NVIDIA part. In practical terms, this means the GTX 960A completes OpenCL compute tasks roughly 15% faster than the R9 M375, which can translate into faster rendering, video encoding, or other GPU-accelerated workloads that rely on OpenCL.

To put that 11998 score in context, the GTX 960A sits within 0.3% of the GeForce GTX 1080's average score of 11960. It is 1.3% ahead of the Radeon RX 6500 XT (11842), 2.7% ahead of the GeForce GTX 1660 (11680), and 3.2% ahead of the Radeon RX 7800 XT (11627). Those are all desktop-class parts from much later generations, which indicates the GTX 960A's OpenCL showing is unusually strong for its mobile MXM form factor.

The R9 M375's 10457 OpenCL score places it within 0.3% of the Quadro K5100M (10043), 0.6% of the Radeon Pro 5300M (10013), and 1.1% of the GeForce GTX 870M (9959). The closest rival is the GeForce GTX 950A, which scores 10273 and beats the R9 M375 by 2%. That negative delta of 2% shows the R9 M375 is not even the strongest card in its own immediate family, trailing the GTX 950A by a small but measurable amount.

The R9 M375's Vulkan score of 9682, while not directly comparable to the GTX 960A, does give a sense of its API-level performance. The GTX 960A supports Vulkan 1.4, while the R9 M375 supports Vulkan 1.2.170. The NVIDIA part also lists DirectX 12 (11_0) support versus the AMD part's DirectX 12 (11_1), and both list OpenGL 4.6.

FAQ

Q: Which GPU is faster in OpenCL performance?

A: The NVIDIA GeForce GTX 960A scores 11998 in Geekbench OpenCL, while the AMD Radeon R9 M375 scores 10457. The GTX 960A leads by 14.7%.

Q: Do both cards have the same memory configuration?

A: Both have 2 GB on a 128-bit bus, but the GTX 960A uses GDDR5 with 80.19 GB/s bandwidth, while the R9 M375 uses DDR3 with only 28.80 GB/s.

Q: How do these cards compare in compute unit counts?

A: They are identical in shading units (640), texture mapping units (40), and ROPs (16). The differences come from clock speeds and architecture.

Q: What is the clock speed advantage for the GTX 960A?

A: The GTX 960A runs at 1097 MHz base and 1176 MHz boost. The R9 M375 runs at 1000 MHz base and 1015 MHz boost.

Q: Which card has better API support?

A: The GTX 960A supports Vulkan 1.4 and DirectX 12 (11_0). The R9 M375 supports Vulkan 1.2.170 and DirectX 12 (11_1). Both support OpenGL 4.6.

Q: How does the R9 M375 compare to its nearest rival, the GTX 950A?

A: The GTX 950A scores 10273 in OpenCL, which is 2% higher than the R9 M375's 10457. The R9 M375 is the slower card of the two.

Specification Differences

The following fields differ between the two GPUs in the database:

• Chip: GM107 (NVIDIA) vs Tropo (AMD)
• Architecture: Maxwell vs GCN 1.0
• Generation: GeForce 900A vs Gem System (R9 M300)
• Transistors: 1,870 million vs 1,500 million
• Die Size: 148 mm² vs 123 mm²
• Transistor Density: 12.6M / mm² vs 12.2M / mm²
• Base Clock: 1097 MHz vs 1000 MHz
• Boost Clock: 1176 MHz vs 1015 MHz
• Memory Clock: 1253 MHz (5 Gbps effective) vs 900 MHz (1800 Mbps effective)
• Memory Type: GDDR5 vs DDR3
• Memory Bandwidth: 80.19 GB/s vs 28.80 GB/s
• Pixel Rate: 18.82 GPixel/s vs 16.24 GPixel/s
• Texture Rate: 47.04 GTexel/s vs 40.60 GTexel/s
• FP32 Compute: 1.505 TFLOPS vs 1,299.2 GFLOPS
• TDP: 75 W vs not recorded
• Slot Width: MXM Module vs not recorded
• Power Connectors: None vs not recorded
• Bus Interface: MXM-B (3.0) vs PCIe 3.0 x16
• Display Outputs: Portable Device Dependent vs not recorded
• DirectX Support: 12 (11_0) vs 12 (11_1)
• Vulkan Support: 1.4 vs 1.2.170
• Release Date: 2015-03-12 vs 2015-05-04
• Predecessor: GeForce 800A vs Solar System
• Successor: not recorded vs Polaris Mobile
• Benchmark Scores: OpenCL 11998 vs OpenCL 10457 and Vulkan 9682
• Average Benchmark Score: 11998 vs 10070
• Percentile Vs All GPUs: 51 vs 48

The Verdict

The data points to one clear conclusion: the NVIDIA GeForce GTX 960A is the stronger GPU for OpenCL compute workloads. It wins the only direct head-to-head benchmark by 14.7%, has substantially higher memory bandwidth (80.19 GB/s vs 28.80 GB/s), higher clock speeds, and better throughput across every measured metric. Its 51st percentile ranking versus 48th for the AMD part further confirms the gap. If the workload relies on OpenCL, the GTX 960A is the correct choice.

The AMD Radeon R9 M375 does offer a Vulkan benchmark result, which the GTX 960A lacks, so for Vulkan-specific tasks the AMD card at least has recorded performance data. However, its Vulkan score of 9682 is lower than its own OpenCL score of 10457, suggesting it is not a particularly strong Vulkan performer either. The GTX 960A also supports a newer Vulkan version (1.4 vs 1.2.170), which may matter for future software compatibility.

For a builder choosing between these two end-of-life mobile GPUs, the decision comes down to the workload. The GTX 960A wins on raw compute, memory bandwidth, and overall benchmark standing. The R9 M375 has the advantage of a second benchmark entry and a PCIe 3.0 x16 interface, which could be easier to integrate into a standard desktop or laptop slot system compared to the MXM-B interface of the NVIDIA part. But on the recorded performance data alone, the GTX 960A is the faster card, and the margin is not small. The 14.7% OpenCL lead, combined with nearly triple the memory bandwidth, makes the GTX 960A the clear pick for compute-heavy use. The R9 M375 should only be considered if the bus interface or Vulkan support is a hard requirement, since its benchmark scores trail across the board.