AMD Radeon R7 M460 vs NVIDIA GeForce GTX 580M Comparison

The Verdict

The benchmark data places the AMD Radeon R7 M460 and NVIDIA GeForce GTX 580M in the same performance tier, but with a clear, if narrow, edge for the AMD part. In the single available head-to-head benchmark (Geekbench OpenCL), the R7 M460 scores 6612 against the GTX 580M's 6389, a 3.5% advantage. Both GPUs sit at the 37th-38th percentile of all GPUs, meaning they are entry-level performers by modern standards. The R7 M460 is the choice for anyone prioritizing raw compute throughput in OpenCL workloads, while the GTX 580M offers a much wider memory bus and higher bandwidth for memory-intensive tasks. However, given that the R7 M460 achieves its win with a dramatically smaller die (125 mm² vs 332 mm²) and fewer transistors (1,550 million vs 1,950 million), it represents the more efficient design. For a user selecting between these two end-of-life mobile parts, the R7 M460 is the better default, but the GTX 580M's 96.00 GB/s bandwidth versus 36.00 GB/s makes it the pick for texture-heavy or bandwidth-bound scenarios.

Where Each One Wins

The AMD Radeon R7 M460 wins the only benchmark where both were tested. Its Geekbench OpenCL score of 6612 exceeds the GTX 580M's 6389 by 3.5%. This suggests AMD's GCN 3.0 architecture handles compute-style workloads slightly better in this comparison. The R7 M460 also has a substantial clock speed advantage: its boost clock reaches 1024 MHz, while the GTX 580M has no base or boost clock listed in the data. The AMD part's newer process node (28 nm vs 40 nm) and higher transistor density (12.4M / mm² vs 5.9M / mm²) contribute to its efficiency.

The NVIDIA GeForce GTX 580M wins in memory architecture. Its 256-bit bus width is four times wider than the R7 M460's 64-bit bus. This yields 96.00 GB/s of memory bandwidth versus just 36.00 GB/s for the AMD part. The GTX 580M also has significantly more texture mapping units (64 vs 24) and render output units (32 vs 8), giving it a 39.68 GTexel/s texture rate versus 24.58 GTexel/s for the R7 M460. For traditional rasterization workloads that depend on fill rate and bandwidth, the GTX 580M is structurally superior. Its pixel rate of 9.920 GPixel/s also edges out the R7 M460's 8.192 GPixel/s.

In terms of API support, the R7 M460 supports DirectX 12 (12_0) and Vulkan 1.2.170, while the GTX 580M only supports DirectX 12 (11_0) and has no Vulkan support listed. This makes the AMD part more future-proof for modern games and applications that leverage these newer APIs. The R7 M460 also has a higher FP32 throughput of 786.4 GFLOPS, though this is lower than the GTX 580M's 952.3 GFLOPS. The GTX 580M leads in raw floating-point compute, but the R7 M460's newer architecture and API support give it advantages in software compatibility.

Architecture Differences

The two GPUs come from different architectural generations. The AMD Radeon R7 M460 uses the Meso chip built on GCN 3.0 architecture, part of the Gem System (R7 M400) generation. It is manufactured on a 28 nm process at TSMC, with a die size of 125 mm² and 1,550 million transistors. The NVIDIA GeForce GTX 580M uses the GF114 chip on Fermi 2.0 architecture, part of the GeForce 500M generation. It is built on a 40 nm process, also at TSMC, but with a much larger die of 332 mm² and 1,950 million transistors. This makes the GTX 580M's die roughly 2.7 times larger, yet it delivers a smaller transistor density advantage to AMD: 12.4M / mm² versus 5.9M / mm².

Both GPUs have 384 shading units, but their supporting hardware differs. The R7 M460 has 24 texture mapping units and 8 render output units, while the GTX 580M has 64 TMUs and 32 ROPs. The GTX 580M's broader memory interface (256-bit vs 64-bit) gives it 96.00 GB/s of bandwidth versus 36.00 GB/s. Memory clocks differ too: the R7 M460 runs its GDDR5 at 1125 MHz (4.5 Gbps effective), while the GTX 580M runs its GDDR5 at 750 MHz (3 Gbps effective). Despite the lower clock, the GTX 580M's wider bus delivers far more bandwidth.

The R7 M460 has a boost clock of 1024 MHz (base 730 MHz), whereas the GTX 580M has no listed base or boost clock. The AMD part supports FP16 at 786.4 GFLOPS (1:1 ratio with FP32), while the GTX 580M has no FP16 support listed. The GTX 580M has a TDP of 100 W and uses an MXM-B (3.0) interface, while the R7 M460 uses PCIe 3.0 x8 and has no TDP listed. The GTX 580M's power connectors are listed as "None" and its display outputs are "Portable Device Dependent," reflecting its mobile MXM form factor.

The R7 M460 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The GTX 580M supports DirectX 12 (11_0) and OpenGL 4.6, but no Vulkan. Both are end-of-life products, with the R7 M460 releasing on 2016-05-14 and the GTX 580M on 2011-06-27. The R7 M460's predecessor is Solar System and its successor is Polaris Mobile; the GTX 580M's predecessor is GeForce 400M and its successor is GeForce 600M.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The AMD Radeon R7 M460 scores 6612 in Geekbench OpenCL, while the NVIDIA GeForce GTX 580M scores 6389. The R7 M460 leads by 3.5%.

Q: How much memory bandwidth does each GPU provide?

A: The GTX 580M provides 96.00 GB/s of bandwidth via its 256-bit bus, while the R7 M460 provides 36.00 GB/s via a 64-bit bus. Both have 2 GB of GDDR5 memory.

Q: Which GPU has better API support for modern applications?

A: The R7 M460 supports DirectX 12 (12_0) and Vulkan 1.2.170. The GTX 580M supports DirectX 12 (11_0) but has no Vulkan support listed.

Q: What are the process nodes and die sizes of these GPUs?

A: The R7 M460 is built on a 28 nm process with a 125 mm² die. The GTX 580M is built on a 40 nm process with a 332 mm² die.

Q: How do the texture and pixel rates compare?

A: The GTX 580M has a texture rate of 39.68 GTexel/s and a pixel rate of 9.920 GPixel/s. The R7 M460 has a texture rate of 24.58 GTexel/s and a pixel rate of 8.192 GPixel/s.

Q: Which GPU has higher raw floating-point performance?

A: The GTX 580M delivers 952.3 GFLOPS of FP32 performance, compared to the R7 M460's 786.4 GFLOPS. The R7 M460 additionally supports FP16 at 786.4 GFLOPS.

Head-to-Head Benchmarks

In the only direct comparison available, the Geekbench OpenCL test, the AMD Radeon R7 M460 outscores the NVIDIA GeForce GTX 580M by a margin of 3.5%. The R7 M460 posts 6612 points versus 6389 for the GTX 580M. This is a narrow win, and the margin is within the range of run-to-run variance for many benchmark suites, but the data shows a consistent advantage for AMD in compute workloads. The R7 M460's nearest rival is the NVIDIA GeForce GT 1010, which scores 6698 (1.3% higher), and the AMD Radeon HD 7730M, which scores 6581 (0.5% lower). The GTX 580M's nearest rival is the NVIDIA GeForce GTX 460 SE, which scores identically at 6389, and the NVIDIA RTX PRO 5000 72 GB Blackwell, which scores 6407 (0.3% lower).

The GTX 580M's structural advantages do not translate into a benchmark win. Despite having 64 TMUs versus 24, 32 ROPs versus 8, and 96.00 GB/s bandwidth versus 36.00 GB/s, the GTX 580M still loses the OpenCL test. This suggests that the newer GCN 3.0 architecture in the R7 M460 executes compute shaders more efficiently than the older Fermi 2.0 design. The R7 M460's higher boost clock of 1024 MHz likely contributes to this result, as does its support for DirectX 12 (12_0) features that may be exercised by the OpenCL benchmark path. The GTX 580M's higher FP32 throughput (952.3 GFLOPS) and texture rate (39.68 GTexel/s) do not overcome the architectural efficiency gap.

The deltaPct values in the nearestRivals data provide context. The R7 M460 is 0.5% faster than the AMD Radeon HD 7730M and 0.9% faster than the Intel UHD Graphics P750. It is 1.3% slower than the NVIDIA GeForce GT 1010 and 1.5% faster than the NVIDIA GeForce GTX 670M. The GTX 580M is exactly tied with the NVIDIA GeForce GTX 460 SE, 0.3% slower than the NVIDIA RTX PRO 5000 72 GB Blackwell, 0.9% faster than the AMD Radeon Pro WX 4100, and 1% faster than the AMD Radeon R7 M350. These numbers place both GPUs in a tight cluster of mid-to-low-tier mobile parts, with the R7 M460 sitting at the 38th percentile of all GPUs and the GTX 580M at the 37th.

The wins tally favors AMD: the R7 M460 records 1 win in the head-to-head comparison, while the GTX 580M records 0. This is a single-test result, but it is the only data available. For users prioritizing compute performance in OpenCL environments, the R7 M460 is the clear choice. For users who need maximum memory bandwidth for large textures or data sets, the GTX 580M's 96.00 GB/s remains its strongest asset, even if it does not translate to a benchmark victory in this test.