NVIDIA GeForce GTX 580M vs NVIDIA GeForce GTX 765M Comparison

NVIDIA’s GeForce 500M and 700M mobile series represent two distinct eras of laptop graphics. The GTX 580M, built on the Fermi 2.0 architecture, was a flagship part in 2011. The GTX 765M, from the Kepler generation, arrived two years later as a more modern, mainstream offering. The database records show a clear, but not overwhelming, shift in performance and efficiency between these two mobile GPUs. This analysis focuses strictly on the recorded benchmark data, architectural specifications, and comparative standings within the database.

Head-to-Head Benchmarks

The database includes a single direct head-to-head benchmark between the GTX 580M and the GTX 765M: the Geekbench OpenCL test. In this measurement, the GTX 765M scores 7,176 points, while the GTX 580M scores 6,389 points. This gives the GTX 765M an 11% advantage over its older rival. This result indicates that despite the GTX 580M’s higher standing as a former flagship, the newer Kepler-based GPU delivers superior raw compute throughput in this specific OpenCL workload.

Looking at the broader picture, the GTX 765M’s average benchmark score across all recorded tests is 5,501. This average is pulled down by its lower scores in other API tests, such as 2,612 in Geekbench Metal and 6,714 in Geekbench Vulkan. The GTX 580M, with only the single OpenCL test recorded, has an average score of 6,389. The head-to-head data shows the GTX 765M wins the only direct comparison, but the overall average score tells a different story. The GTX 580M’s average is higher than the GTX 765M’s average, due to the GTX 765M’s weaker performance in the Metal test.

The percentile rankings in the database provide additional context. The GTX 580M sits in the 37th percentile of all GPUs, while the GTX 765M sits in the 32nd percentile. This suggests that while the GTX 765M beats the GTX 580M in the direct OpenCL test, its overall performance profile across all its benchmark results places it slightly lower in the global ranking. The GTX 580M’s single, strong OpenCL result keeps its percentile higher.

For the GTX 580M, its nearest rivals in the database are the NVIDIA GeForce GTX 460 SE with an identical average score of 6,389, the NVIDIA RTX PRO 5000 72 GB Blackwell with a score of 6,407 (0.3% higher), the AMD Radeon Pro WX 4100 with 6,330 (0.9% lower), and the AMD Radeon R7 M350 with 6,327 (1% lower). This places the GTX 580M in a tight performance cluster, essentially matching the GTX 460 SE and trading blows with professional and entry-level cards.

The GTX 765M’s nearest rivals are clustered around its 5,501 average. The NVIDIA GeForce MX130 is virtually identical with a 5,508 average (0.1% higher), the AMD Radeon R7 M440 is 0.3% lower at 5,483, the NVIDIA Quadro M4000 is 0.6% lower at 5,467, and the AMD FirePro M4000 is 0.7% lower at 5,537. This indicates the GTX 765M’s overall standing is closely matched with a group of entry-level and mid-range mobile GPUs from a similar era.

The most significant takeaway from the head-to-head is the 11% delta in favor of the GTX 765M in OpenCL. However, the GTX 580M’s higher percentile rank and higher average score, when considering all of the GTX 765M’s benchmark results, show that the older card is not entirely obsolete. The GTX 765M wins the direct comparison, but the GTX 580M holds a better position in the overall database hierarchy.

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The NVIDIA GeForce GTX 580M has a higher average benchmark score of 6,389, compared to the GTX 765M’s average of 5,501. This is despite the GTX 765M winning the head-to-head OpenCL test.

Q: How much faster is the GTX 765M in the Geekbench OpenCL test?

A: The GTX 765M scores 7,176 points in the OpenCL test, which is 11% higher than the GTX 580M’s score of 6,389.

Q: What is the difference in their percentile rankings among all GPUs?

A: The GTX 580M ranks in the 37th percentile of all GPUs, while the GTX 765M ranks in the 32nd percentile. This indicates that the GTX 580M sits higher in the overall performance distribution.

Q: Which GPU has a higher transistor density?

A: The GTX 765M has a significantly higher transistor density at 11.5 million transistors per square millimeter, compared to the GTX 580M’s 5.9 million transistors per square millimeter.

Q: Do both GPUs support the same DirectX version?

A: Yes, both the GTX 580M and the GTX 765M report support for DirectX 12 (11_0) in the database. They also both support OpenGL 4.6.

Q: What is the TDP difference between the two cards?

A: The GTX 580M has a TDP of 100 W, while the GTX 765M has a lower TDP of 75 W. This indicates the GTX 765M is more power-efficient on paper.

The Verdict

Based on the recorded data, the choice between these two GPUs depends on the specific workload. The GTX 765M is the outright winner in the direct Geekbench OpenCL benchmark, posting an 11% higher score. For users prioritizing raw compute in that specific API, the GTX 765M is the clear choice. Its architecture also features a higher base clock of 797 MHz and a boost clock of 863 MHz, which are not present in the GTX 580M’s data.

However, the GTX 580M holds a higher average benchmark score of 6,389 versus 5,501, and a higher percentile rank of 37% versus 32%. This suggests that, when considering all available benchmark results, the GTX 580M may offer more consistent performance across a wider range of tests, despite losing the single OpenCL comparison. The GTX 580M also has a wider memory bus, which will be detailed later, and a larger die size, though this is a physical attribute, not a performance one.

The GTX 765M’s nearest rivals, such as the MX130 and R7 M440, are all within 0.7% of its average score, indicating it is a solid mid-pack performer. The GTX 580M’s rivals, including the GTX 460 SE and RTX PRO 5000, show it is near the performance of much newer and more expensive hardware, at least in the OpenCL test.

For a user with a workload that relies heavily on OpenCL, the GTX 765M is the better option due to its 11% lead. For general, varied usage that is reflected in the average score, the GTX 580M appears to hold a slight edge in overall standing. The GTX 765M’s lower TDP of 75 W also makes it a more attractive option for thin-and-light laptops, while the GTX 580M’s 100 W TDP suggests it was designed for larger, more power-hungry systems.

In summary, the data shows a trade-off. The newer GTX 765M wins the single head-to-head test and is more power-efficient, but the older GTX 580M has a better average score and higher percentile rank. The decision should be based on whether the specific OpenCL performance is more critical than the overall benchmark average.

Specification Differences

The two GPUs differ in nearly every core specification. The GTX 580M is built on the GF114 chip, while the GTX 765M uses the GK106 chip. The manufacturing process differs significantly: the GTX 580M uses a 40 nm node, while the GTX 765M uses a 28 nm node, both from TSMC. The GTX 580M has 1,950 million transistors on a 332 mm² die, whereas the GTX 765M packs 2,540 million transistors onto a smaller 221 mm² die. This results in a transistor density of 5.9 million per mm² for the GTX 580M and 11.5 million per mm² for the GTX 765M.

Clock speeds are another major difference. The GTX 580M has no listed base or boost clock, but its memory runs at 750 MHz with 3 Gbps effective. The GTX 765M has a base clock of 797 MHz, a boost clock of 863 MHz, and its memory runs at 1002 MHz with 4 Gbps effective.

Memory configuration also differs. Both have 2 GB of GDDR5, but the GTX 580M uses a 256-bit bus, yielding 96.00 GB/s of bandwidth. The GTX 765M uses a narrower 128-bit bus, resulting in 64.13 GB/s of bandwidth.

The compute units are configured differently. The GTX 580M has 384 shading units, 64 TMUs, and 32 ROPs. The GTX 765M has 768 shading units, 64 TMUs, but only 16 ROPs. Pixel and texture rates reflect this: the GTX 580M has a 9.920 GPixel/s pixel rate and a 39.68 GTexel/s texture rate, while the GTX 765M has a 13.81 GPixel/s pixel rate and a 55.23 GTexel/s texture rate. The FP32 compute performance is 952.3 GFLOPS for the GTX 580M and 1,325.6 GFLOPS for the GTX 765M.

The power envelope is also different. The GTX 580M has a TDP of 100 W, while the GTX 765M has a TDP of 75 W. Both use MXM modules with no power connectors and have an MXM-B (3.0) bus interface. Both have portable-device-dependent display outputs. The GTX 580M supports DirectX 12 (11_0) and OpenGL 4.6, but no Vulkan; the GTX 765M adds Vulkan 1.2.175 support.

Architecture Differences

The architectural divide between the GTX 580M and GTX 765M is significant, reflecting the transition from Fermi 2.0 to Kepler. The GTX 580M is based on the Fermi 2.0 architecture, which was a mature iteration of NVIDIA’s Fermi design. It uses a 40 nm process, which is older and less dense than the 28 nm node used by the GTX 765M. The GTX 580M’s die size is larger at 332 mm², but it holds fewer transistors (1,950 million) than the GTX 765M’s 2,540 million on a 221 mm² die.

The Kepler architecture in the GTX 765M represents a major step forward in efficiency. The 28 nm process allows for a much higher transistor density (11.5M / mm² vs 5.9M / mm²). This enables the GTX 765M to double the shading units from 384 to 768, while also increasing the texture rate from 39.68 GTexel/s to 55.23 GTexel/s. The pixel rate also improves from 9.920 GPixel/s to 13.81 GPixel/s, despite having half the ROPs (16 vs 32). This is a direct result of the higher clocks and architectural efficiency.

The GTX 765M has a boost clock of 863 MHz, a feature absent from the GTX 580M’s specifications. This dynamic clocking allows the GPU to run faster when thermal and power headroom permit. The memory architecture also differs: the GTX 580M relies on a 256-bit bus with a total bandwidth of 96.00 GB/s, while the GTX 765M uses a 128-bit bus with 64.13 GB/s. The GTX 765M compensates with a higher effective memory clock of 4 Gbps versus 3 Gbps, but the narrower bus limits its total bandwidth.

The FP32 compute performance is higher on the GTX 765M at 1,325.6 GFLOPS, compared to 952.3 GFLOPS on the GTX 580M. This aligns with the OpenCL benchmark result, where the GTX 765M leads by 11%. The GTX 765M also supports Vulkan 1.2.175, while the GTX 580M does not list Vulkan support. Both support DirectX 12 (11_0) and OpenGL 4.6.

The TDP difference is a key architectural outcome. The GTX 765M delivers more compute performance and higher clock speeds while consuming only 75 W, compared to the GTX 580M’s 100 W. This efficiency gain is a hallmark of the Kepler generation and is directly attributable to the 28 nm process and architectural improvements. The GTX 580M’s Fermi 2.0 architecture, while capable, was less efficient per watt, as evidenced by its higher power draw and lower transistor density.