AMD Radeon R7 M380 vs NVIDIA GeForce GTX 460 Comparison

FAQ

Q: Which GPU is faster in the Geekbench OpenCL benchmark?

A: The AMD Radeon R7 M380 scores 9313, while the NVIDIA GeForce GTX 460 scores 7925. The AMD part leads by 17.5% in this test.

Q: How does the memory configuration differ between the two cards?

A: The AMD Radeon R7 M380 uses 4 GB of DDR3 on a 128-bit bus, yielding 32.00 GB/s bandwidth. The NVIDIA GeForce GTX 460 uses 768 MB of GDDR5 on a 192-bit bus, delivering 86.40 GB/s.

Q: What are the transistor counts and die sizes for each GPU?

A: The AMD chip (Tropo) packs 1,500 million transistors on a 123 mm² die, while the NVIDIA chip (GF104) contains 1,950 million transistors on a 332 mm² die.

Q: Which GPU has a higher pixel fill rate?

A: The AMD Radeon R7 M380 achieves 14.64 GPixel/s, which is notably higher than the NVIDIA GeForce GTX 460's 9.450 GPixel/s.

Q: What is the TDP of the NVIDIA GeForce GTX 460?

A: The NVIDIA GeForce GTX 460 has a TDP of 160 W and requires a 450 W suggested power supply.

Q: When were these GPUs released?

A: The NVIDIA GeForce GTX 460 launched on 2010-07-11, while the AMD Radeon R7 M380 arrived later on 2015-05-04.

Where Each One Wins

The AMD Radeon R7 M380 dominates the single recorded benchmark, the Geekbench OpenCL test. With a score of 9313 versus 7925, it holds a 17.5% advantage over the NVIDIA GeForce GTX 460. This is the only head-to-head test in the database, so the AMD card wins all one comparison.

The NVIDIA GeForce GTX 460, however, claims clear wins in several specification categories despite losing the benchmark. Its memory bandwidth is far superior: 86.40 GB/s versus 32.00 GB/s, a 2.7x difference. This stems from the GDDR5 memory type and wider 192-bit bus, compared to the AMD card's DDR3 and 128-bit interface. The NVIDIA card also has more texture units (56 versus 40) and more ROPs (24 versus 16), which could favor certain fill-rate-bound workloads.

The AMD card wins on compute throughput. Its FP32 performance stands at 1,171.2 GFLOPS, exceeding the NVIDIA card's 907.2 GFLOPS by roughly 29%. The AMD card also has a much higher shading unit count (640 versus 336), and its pixel rate (14.64 GPixel/s) outpaces the NVIDIA part (9.450 GPixel/s) by 55%.

In practice, the AMD Radeon R7 M380 is the better choice for general compute tasks and OpenCL workloads, as evidenced by the benchmark. The NVIDIA GeForce GTX 460 would be preferable in scenarios where memory bandwidth is the limiting factor, such as high-resolution texture streaming or certain anti-aliasing methods, though the database does not record a direct test confirming this.

Architecture Differences

The AMD Radeon R7 M380 uses the Tropo chip based on GCN 1.0 architecture, built on a 28 nm process at TSMC. The NVIDIA GeForce GTX 460 uses the GF104 chip based on the older Fermi architecture, manufactured on a 40 nm process, also at TSMC. The process node difference is substantial: 28 nm versus 40 nm allows the AMD chip to achieve a transistor density of 12.2M per mm², while the NVIDIA chip manages only 5.9M per mm².

Despite the AMD chip having fewer total transistors (1,500 million versus 1,950 million), its smaller die (123 mm² versus 332 mm²) means a much denser packing. The Fermi architecture on the NVIDIA side is an older design with a larger, less efficient layout.

The AMD card supports newer API features. It lists DirectX 12 (11_1) support, while the NVIDIA card lists DirectX 12 (11_0). Both support OpenGL 4.6. The AMD card also has Vulkan 1.2.170 support, while the NVIDIA card's Vulkan support is listed as null in the database.

The bus interface differs: the AMD card uses PCIe 3.0 x16, while the NVIDIA card uses PCIe 2.0 x16. This could affect data transfer speeds with the host system, though the benchmark data does not separate this factor.

The NVIDIA card has a dual-slot form factor, 210 mm (8.3 inches) in length, and requires two 6-pin power connectors. The AMD card's dimensions and power connectors are not listed, so the physical comparison remains incomplete.

Specification Differences

The two GPUs differ across nearly every major specification field. The AMD Radeon R7 M380 has 640 shading units, 40 TMUs, and 16 ROPs. The NVIDIA GeForce GTX 460 has 336 shading units, 56 TMUs, and 24 ROPs. AMD leads in shading units, NVIDIA leads in TMUs and ROPs.

Clock speeds: the AMD card runs at a base clock of 900 MHz with a boost of 915 MHz. The NVIDIA card has no listed base or boost clocks, only a memory clock of 900 MHz (3.6 Gbps effective). The AMD memory clock is 1000 MHz (2 Gbps effective).

Memory: the AMD card has 4 GB of DDR3 on a 128-bit bus, providing 32.00 GB/s bandwidth. The NVIDIA card has 768 MB of GDDR5 on a 192-bit bus, providing 86.40 GB/s bandwidth. The NVIDIA card has 2.7x more bandwidth but only 19% of the capacity.

Compute rates: the AMD card achieves 1,171.2 GFLOPS FP32, 14.64 GPixel/s pixel rate, and 36.60 GTexel/s texture rate. The NVIDIA card achieves 907.2 GFLOPS FP32, 9.450 GPixel/s pixel rate, and 37.80 GTexel/s texture rate. AMD wins FP32 and pixel rate; NVIDIA wins texture rate by a small margin.

Power: the NVIDIA card has a TDP of 160 W, a dual-slot cooler, two 6-pin power connectors, and a suggested PSU of 450 W. The AMD card has no TDP, slot width, or power connector data listed.

Release dates: the NVIDIA card launched on 2010-07-11, the AMD card on 2015-05-04. Both are end-of-life products.

Head-to-Head Benchmarks

The only recorded head-to-head benchmark is Geekbench OpenCL. The AMD Radeon R7 M380 scores 9313, the NVIDIA GeForce GTX 460 scores 7925. The AMD card wins by 17.5%. This is a significant margin, placing the AMD card in the 46th percentile of all GPUs, while the NVIDIA card sits in the 41st percentile.

To contextualize the AMD score, its nearest rivals in the database are the NVIDIA GeForce GTX 850M (9302, 0.1% slower), the NVIDIA GeForce GTX 465 (9294, 0.2% slower), the NVIDIA GeForce GTX 960 (9273, 0.4% slower), and the AMD Radeon Vega 8 (9221, 1% slower). The AMD R7 M380 essentially trades blows with these cards, sitting at the top of this cluster.

The NVIDIA GeForce GTX 460's nearest rivals include the NVIDIA Quadro K4100M (7906, 0.2% slower), the NVIDIA Quadro P5000 (8039, 1.4% faster), the NVIDIA GeForce GTX 880M (8040, 1.4% faster), and the NVIDIA GeForce GTX 650 Ti (8053, 1.6% faster). The GTX 460 sits near the bottom of this group.

The gap between the two cards is consistent with their architectural differences. The AMD card's higher FP32 throughput (1,171.2 GFLOPS versus 907.2 GFLOPS) and greater shading unit count (640 versus 336) likely drive its OpenCL advantage. The NVIDIA card's superior memory bandwidth (86.40 GB/s versus 32.00 GB/s) does not compensate in this particular compute workload.

The database shows zero wins for the NVIDIA card and one win for the AMD card. Every measurable performance indicator in the head-to-head comparison favors the AMD Radeon R7 M380. The NVIDIA GeForce GTX 460 remains competitive only in certain theoretical throughput metrics like texture rate (37.80 GTexel/s versus 36.60 GTexel/s) and ROP count, but these advantages do not translate to a benchmark victory in the recorded data.