AMD Radeon R9 M375 vs NVIDIA GeForce GTX 675MX Comparison

Head-to-Head Benchmarks

The only direct benchmark comparison recorded between the AMD Radeon R9 M375 and the NVIDIA GeForce GTX 675MX is the Geekbench OpenCL test. In this test, the NVIDIA GeForce GTX 675MX scores 10,723 points, while the AMD Radeon R9 M375 records 10,457 points. This gives the NVIDIA part a 2.5% advantage, a modest but measurable lead in raw compute throughput.

Looking at the broader database averages, the picture becomes more nuanced. The AMD Radeon R9 M375 holds an average benchmark score of 10,070, while the NVIDIA GeForce GTX 675MX averages 8,427. That is a 19.5% gap in favor of the AMD part when considering all recorded workloads, despite losing the single OpenCL head-to-head. The discrepancy suggests the GTX 675MX performs well specifically in OpenCL compute tasks, while the R9 M375 holds up better across the wider range of tests that feed the average.

The percentile rankings also favor the AMD card. The R9 M375 sits at the 48th percentile among all GPUs in the database, while the GTX 675MX ranks at the 43rd percentile. This five-point difference in percentile placement reinforces the average score gap, indicating the AMD part generally lands ahead of more of its peers.

For context on the AMD side, the R9 M375's nearest rivals include the NVIDIA Quadro K5100M at 10,043 (0.3% behind), the AMD Radeon Pro 5300M at 10,013 (0.6% behind), and the NVIDIA GeForce GTX 870M at 9,959 (1.1% behind). The only rival ahead of it is the NVIDIA GeForce GTX 950A at 10,273, which leads by 2%. These tight margins show the R9 M375 sits in a crowded band of comparable mobile GPUs.

On the NVIDIA side, the GTX 675MX's nearest rivals cluster even more tightly. The AMD Radeon 880M scores 8,436 (0.1% ahead), the NVIDIA GeForce MX330 scores 8,458 (0.4% ahead), and the AMD Radeon HD 8870M scores 8,462 (0.4% ahead). The AMD Radeon R9 M375X trails at 8,325, putting the GTX 675MX 1.2% ahead of that part. The GTX 675MX therefore sits in a very dense pack where single-digit percentage differences separate it from its immediate competition.

Architecture Differences

The two GPUs come from different architectural lineages entirely. The AMD Radeon R9 M375 is built on GCN 1.0 architecture, using the Tropo chip, and belongs to the Gem System generation (R9 M300 series). The NVIDIA GeForce GTX 675MX uses Kepler architecture with the GK104 chip, part of the GeForce 600M generation. Both are fabricated on a 28 nm process at TSMC, so the manufacturing node is identical.

Transistor counts differ dramatically. The AMD chip packs 1,500 million transistors on a 123 mm² die, while the NVIDIA chip contains 3,540 million transistors on a 294 mm² die. Transistor density is nearly the same: 12.2 million per mm² for AMD versus 12.0 million per mm² for NVIDIA. The NVIDIA die is therefore much larger to accommodate more than double the transistors, but the efficiency per area is almost identical.

Compute resources also diverge. The AMD R9 M375 has 640 shading units, 40 texture mapping units, and 16 raster operation units. The GTX 675MX has 960 shading units, 80 TMUs, and 32 ROPs. In every category of execution hardware, the NVIDIA part has more units. This explains why the GTX 675MX leads in pixel rate and texture rate. The AMD card posts a pixel rate of 16.24 GPixel/s and a texture rate of 40.60 GTexel/s. The NVIDIA card posts 13.08 GPixel/s and 52.32 GTexel/s. The AMD part wins on pixel throughput, while NVIDIA wins on texture throughput. The higher pixel rate on AMD likely stems from its higher clock speeds.

Clock behavior separates the two as well. The R9 M375 has a base clock of 1000 MHz and a boost clock of 1015 MHz. The GTX 675MX has no recorded base or boost clock in the database. Memory clocks are both listed at 900 MHz, but the effective data rates differ. The AMD memory runs at 1800 Mbps effective, while the NVIDIA memory runs at 3.6 Gbps effective. The NVIDIA memory is also a different type: GDDR5 versus DDR3 on the AMD card.

Memory configuration heavily favors NVIDIA. Both cards have 2 GB of video memory, but the bus widths are 128 bit for AMD and 256 bit for NVIDIA. This yields a bandwidth of 28.80 GB/s for the R9 M375 and 115.2 GB/s for the GTX 675MX, a 4x difference. The combination of GDDR5 memory, double the bus width, and double the effective data rate gives NVIDIA a commanding lead in memory bandwidth.

API support is similar but not identical. Both support DirectX 12, though AMD lists it as 12 (11_1) while NVIDIA lists 12 (11_0). Both support OpenGL 4.6. The Vulkan versions differ slightly: AMD lists 1.2.170, NVIDIA lists 1.2.175. Power characteristics are only recorded for the NVIDIA card, which has a 100 W TDP, an MXM Module slot width, no power connectors, and a portable-device-dependent display output. The AMD card lists no TDP or slot width in the database.

The Verdict

The data presents a split verdict. For users whose workloads emphasize OpenCL compute, the NVIDIA GeForce GTX 675MX is the stronger choice, with a 2.5% lead over the AMD Radeon R9 M375 in the direct head-to-head test. Its larger shading unit count, 960 versus 640, and its 4x memory bandwidth advantage (115.2 GB/s versus 28.80 GB/s) support this result. The GTX 675MX also has a higher texture rate, 52.32 GTexel/s versus 40.60 GTexel/s, which can benefit texture-heavy rendering workloads.

For users looking at overall benchmark averages and percentile placement, the AMD Radeon R9 M375 is the better performer. Its average benchmark score of 10,070 is 19.5% higher than the GTX 675MX's 8,427, and it sits at the 48th percentile versus the 43rd percentile. The AMD card also has a higher pixel rate, 16.24 GPixel/s versus 13.08 GPixel/s, which can matter for fill-rate-bound scenarios.

The GTX 675MX is an end-of-life product from 2012, while the R9 M375 is also end-of-life but released in 2015. The newer architecture generation and smaller die suggest the AMD part achieves its results more efficiently, though the database does not record a TDP for the AMD card to confirm this. The NVIDIA card's 100 W TDP is documented, but without an AMD figure there is no direct power comparison available.

FAQ

Q: Which GPU wins the recorded OpenCL benchmark?

A: The NVIDIA GeForce GTX 675MX wins the Geekbench OpenCL test with a score of 10,723 versus 10,457 for the AMD Radeon R9 M375, a 2.5% difference.

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R9 M375 has an average benchmark score of 10,070, compared to 8,427 for the NVIDIA GeForce GTX 675MX, making the AMD part 19.5% higher on average.

Q: How do the memory systems compare?

A: The AMD card uses 2 GB of DDR3 on a 128 bit bus with 28.80 GB/s bandwidth. The NVIDIA card uses 2 GB of GDDR5 on a 256 bit bus with 115.2 GB/s bandwidth, a 4x bandwidth advantage.

Q: What are the shading unit counts?

A: The AMD Radeon R9 M375 has 640 shading units. The NVIDIA GeForce GTX 675MX has 960 shading units.

Q: Which GPU has a better percentile rank among all GPUs?

A: The AMD Radeon R9 M375 ranks at the 48th percentile, while the NVIDIA GeForce GTX 675MX ranks at the 43rd percentile.

Q: Are both GPUs built on the same manufacturing process?

A: Yes, both are fabricated on a 28 nm process at TSMC. AMD uses a 123 mm² die, while NVIDIA uses a 294 mm² die.

Where Each One Wins

The NVIDIA GeForce GTX 675MX wins in compute-oriented tasks that resemble the OpenCL benchmark. Its 960 shading units and 115.2 GB/s memory bandwidth give it a structural advantage for data-parallel workloads. Texture-heavy applications also favor the NVIDIA card, as it delivers 52.32 GTexel/s relative to 40.60 GTexel/s on the AMD part. The GDDR5 memory with a 256 bit bus provides a 4x bandwidth advantage that can dominate memory-intensive scenarios.

The AMD Radeon R9 M375 wins in the overall database average, suggesting it performs more consistently across a wider variety of recorded workloads. Its higher pixel rate of 16.24 GPixel/s versus 13.08 GPixel/s makes it preferable for fill-rate-bound rendering. The 48th percentile placement, five points above the GTX 675MX, indicates the AMD card ranks ahead of a larger share of the GPU population. The 2015 release date also means it comes from a later generation, which may explain its stronger average performance despite losing the single OpenCL test.

Specification Differences

The two cards differ across nearly every recorded specification. The AMD Radeon R9 M375 uses the Tropo chip with GCN 1.0 architecture from the Gem System generation, while the NVIDIA GeForce GTX 675MX uses the GK104 chip with Kepler architecture from the GeForce 600M generation. The AMD card has 1,500 million transistors on a 123 mm² die; the NVIDIA card has 3,540 million transistors on a 294 mm² die. Transistor density is nearly identical at 12.2M/mm² for AMD and 12.0M/mm² for NVIDIA.

Clock speeds differ in that the AMD card has recorded base and boost clocks of 1000 MHz and 1015 MHz, while the NVIDIA card has no recorded clocks. Memory clocks are both 900 MHz, but effective rates are 1800 Mbps for AMD and 3.6 Gbps for NVIDIA. Memory type differs: DDR3 for AMD, GDDR5 for NVIDIA. The bus width is 128 bit for AMD and 256 bit for NVIDIA. Bandwidth is 28.80 GB/s versus 115.2 GB/s.

Compute unit counts all favor NVIDIA: 960 shading units, 80 TMUs, and 32 ROPs versus 640 shading units, 40 TMUs, and 16 ROPs. Pixel rate favors AMD at 16.24 GPixel/s versus 13.08 GPixel/s. Texture rate favors NVIDIA at 52.32 GTexel/s versus 40.60 GTexel/s. FP32 compute is close: 1,299.2 GFLOPS for AMD and 1,255.7 GFLOPS for NVIDIA.

The NVIDIA card has a documented TDP of 100 W, an MXM Module slot width, no power connectors, and portable-device-dependent display outputs. The AMD card has no TDP, slot width, or display output data recorded. The bus interface is PCIe 3.0 x16 for AMD and MXM-B (3.0) for NVIDIA. API support shows DirectX 12 (11_1) for AMD and 12 (11_0) for NVIDIA, OpenGL 4.6 for both, and Vulkan 1.2.170 for AMD versus 1.2.175 for NVIDIA. Release dates are May 2015 for AMD and September 2012 for NVIDIA. Both are end-of-life products.