Intel Iris Pro Graphics P580 vs NVIDIA GeForce GTX 460 Comparison

The Verdict

The database comparison places the NVIDIA GeForce GTX 460 and the Intel Iris Pro Graphics P580 in adjacent performance percentiles, but the recorded benchmark data shows a clear winner for compute workloads. The Intel Iris Pro Graphics P580 holds a 12.7% advantage over the NVIDIA GeForce GTX 460 in the sole head-to-head benchmark, the Geekbench OpenCL test, scoring 9082 against 7925. The GTX 460 sits at the 41st percentile among all GPUs, while the Iris Pro P580 sits at the 39th percentile, a narrow gap that the raw scores contradict in Intel's favor.

For users seeking a discrete graphics card with a dedicated memory pool and established driver ecosystem, the GTX 460 remains a functional option, but its end-of-life status and lower compute score make it the weaker pick in this matchup. The Iris Pro P580, despite being an integrated processor graphics solution, delivers higher raw compute throughput and adds Vulkan support, which the GTX 460 lacks entirely. The verdict: adopt the Intel Iris Pro Graphics P580 if compute performance and modern API coverage matter, but choose the GTX 460 only if a discrete card with dedicated VRAM is a hard requirement. The data does not support the GTX 460 as the faster part.

Architecture Differences

The two products diverge fundamentally in design philosophy and manufacturing approach. The NVIDIA GeForce GTX 460 uses the GF104 chip built on Fermi architecture, produced on a 40 nm process at TSMC. The die measures 332 mm² and packs 1,950 million transistors, yielding a transistor density of 5.9 million per square millimeter. The Intel Iris Pro Graphics P580, by contrast, uses the Skylake GT4e chip on Intel's Generation 9.0 architecture, fabricated on a 14 nm+ process at Intel's own foundry. The database lists no die size or transistor count for the Intel part, reflecting its integrated nature.

The GTX 460 is a discrete card with 768 MB of GDDR5 memory on a 192-bit bus, delivering 86.40 GB/s of bandwidth. The Iris Pro P580 uses system-shared memory with a system-dependent bandwidth figure, meaning its performance scales with the host platform's memory subsystem. This architectural split is stark: one part is a standalone board, the other is an integrated GPU on a ring bus.

Compute resources favor the Intel part numerically. The Iris Pro P580 has 576 shading units, 72 texture mapping units, and 9 ROPs. The GTX 460 has 336 shading units, 56 TMUs, and 24 ROPs. The Intel part also supports FP16 compute at 2.304 TFLOPS, while the GTX 460 has no recorded FP16 capability. Pixel rates are nearly identical at 9.450 GPixel/s for NVIDIA and 9.000 GPixel/s for Intel, but texture rate diverges sharply: 37.80 GTexel/s for the GTX 460 versus 72.00 GTexel/s for the Iris Pro P580. The Intel part's texture throughput is nearly double, a direct consequence of its 72 TMUs.

Process node differences are substantial. The 40 nm TSMC process for Fermi is older and less dense than Intel's 14 nm+ node, explaining the transistor density gap. The GTX 460's 160 W TDP versus the Iris Pro P580's 15 W TDP highlights the efficiency chasm. The NVIDIA card is dual-slot with two 6-pin power connectors and a suggested 450 W power supply, while the Intel part is an IGP with no power connectors and no suggested PSU. API support also differs: the GTX 460 lists DirectX 12 (11_0) and OpenGL 4.6, but no Vulkan; the Iris Pro P580 lists DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3.

Head-to-Head Benchmarks

The database records one head-to-head benchmark between these two parts: Geekbench OpenCL. The Intel Iris Pro Graphics P580 wins with a score of 9082 against the NVIDIA GeForce GTX 460's 7925. The delta percentage is -12.7% from Intel's perspective, meaning Intel leads by 12.7%. This is the only comparison available, so the overall win count is 1 for Intel and 0 for NVIDIA.

Contextualizing the scores against nearest rivals clarifies the performance tier. The GTX 460's 7925 OpenCL score sits within 0.2% of the NVIDIA Quadro K4100M (7906) and 1.4% below the Quadro P5000 (8039) and GeForce GTX 880M (8040). It trails the GeForce GTX 650 Ti (8053) by 1.6%. These deltas are small, indicating the GTX 460 clusters tightly with mid-range mobile and older desktop parts. The Iris Pro P580's 9082 OpenCL score, however, places it 0% from the GeForce GTX 560 SE (7171) and 0.2% above the GeForce GTX 970 (7157), while leading the AMD Radeon Vega 8 Mobile (7203) by 0.5% and the GeForce GTX 750 (7222) by 0.7%. That is a peculiar spread: the P580's OpenCL result is 12.7% higher than the GTX 460's, yet its average benchmark score across all tests is 7170, dragged down by its Vulkan score of 5258.

The data suggests the Iris Pro P580 excels specifically in OpenCL compute, while its Vulkan performance is notably lower. The GTX 460, with only one recorded benchmark, does not have a Vulkan score at all. For raw OpenCL throughput, the Intel part is the clear winner by a margin that exceeds any rival delta in either product's nearest-rival list. The GTX 460's best relative position is its 0.2% lead over the Quadro K4100M, while the Iris Pro P580's best relative position is its 0.2% lead over the GeForce GTX 970, a far more powerful card in the broader database.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The Intel Iris Pro Graphics P580 scores 9082 in Geekbench OpenCL, while the NVIDIA GeForce GTX 460 scores 7925. Intel leads by 12.7%.

Q: Does the NVIDIA GeForce GTX 460 support Vulkan?

A: No. The database lists no Vulkan support for the GTX 460. The Intel Iris Pro Graphics P580 supports Vulkan 1.3.

Q: How do the memory configurations differ?

A: The GTX 460 has 768 MB of dedicated GDDR5 memory on a 192-bit bus with 86.40 GB/s bandwidth. The Iris Pro P580 uses system-shared memory with a system-dependent bandwidth figure.

Q: What is the TDP difference between the two?

A: The GTX 460 has a 160 W TDP and requires a dual-slot cooler with 2x 6-pin power connectors and a 450 W suggested PSU. The Iris Pro P580 has a 15 W TDP and is an IGP with no power connectors or suggested PSU.

Q: Which GPU has more shading units?

A: The Intel Iris Pro Graphics P580 has 576 shading units, compared to the GTX 460's 336 shading units. The Intel part also has 72 TMUs versus 56, but only 9 ROPs versus 24.

Q: What are the release dates and production statuses?

A: The GTX 460 was released on 2010-07-11 and is end-of-life. The Iris Pro P580 was released on 2015-08-31 and is also end-of-life.

Where Each One Wins

The Intel Iris Pro Graphics P580 wins the only recorded head-to-head benchmark, the Geekbench OpenCL test, with a 12.7% lead. This makes it the stronger choice for compute-oriented workloads that leverage OpenCL, such as general-purpose GPU computing tasks. Its higher shading unit count (576 versus 336), higher TMU count (72 versus 56), and double texture rate (72.00 GTexel/s versus 37.80 GTexel/s) support this advantage. The Intel part also offers FP16 compute at 2.304 TFLOPS, a capability the GTX 460 lacks, which could benefit workloads using half-precision arithmetic. Vulkan 1.3 support gives the Iris Pro P580 a modern API pathway that the GTX 460 cannot access.

The NVIDIA GeForce GTX 460, despite losing the benchmark, holds advantages in specific hardware features. It has 24 ROPs versus the Intel part's 9, giving it a higher pixel rate at 9.450 GPixel/s versus 9.000 GPixel/s. Dedicated GDDR5 memory with 86.40 GB/s bandwidth provides a fixed memory pipeline independent of system RAM, whereas the Iris Pro P580 relies on system-shared memory with system-dependent bandwidth. The GTX 460's 192-bit bus is a dedicated interface, while the Intel part uses a ring bus. For legacy DirectX 11 workloads, the GTX 460's DirectX 12 (11_0) support matches the Intel part's DirectX 12 (12_1) in terms of API generation, though the Intel part supports a higher feature level.

The percentile data complicates the picture. The GTX 460 ranks at the 41st percentile among all GPUs, two points higher than the Iris Pro P580's 39th percentile. Yet the OpenCL score tells the opposite story. This discrepancy likely stems from the Intel part's Vulkan score of 5258, which pulls its average benchmark score down to 7170. The GTX 460, with only one benchmark, has an average equal to its OpenCL score of 7925. The database records 0 wins for the GTX 460 and 1 win for the Iris Pro P580, so the win-based verdict is unambiguous.

For users prioritizing compute density and efficiency, the Iris Pro P580 wins decisively. Its 15 W TDP versus 160 W TDP means it operates at a fraction of the power draw while delivering higher OpenCL throughput. For users prioritizing pixel fill rate and dedicated memory, the GTX 460 offers specific but narrow advantages. The data does not show any benchmark where the GTX 460 wins, so its strengths are theoretical rather than measured.

Specification Differences

The following fields differ between the NVIDIA GeForce GTX 460 and the Intel Iris Pro Graphics P580:

• Chip: GF104 versus Skylake GT4e
• Architecture: Fermi versus Generation 9.0
• Generation: GeForce 400 versus HD Graphics-W (Skylake)
• Process Node: 40 nm versus 14 nm+
• Foundry: TSMC versus Intel
• Transistors: 1,950 million versus not listed
• Die Size: 332 mm² versus not listed
• Transistor Density: 5.9M / mm² versus not listed
• Base Clock: not listed versus 350 MHz
• Boost Clock: not listed versus 1000 MHz
• Memory Clock: 900 MHz, 3.6 Gbps effective versus system shared
• Memory Size: 768 MB versus system shared
• Memory Type: GDDR5 versus system shared
• Bus Width: 192 bit versus system shared
• Bandwidth: 86.40 GB/s versus system dependent
• Shading Units: 336 versus 576
• TMUs: 56 versus 72
• ROPs: 24 versus 9
• Pixel Rate: 9.450 GPixel/s versus 9.000 GPixel/s
• Texture Rate: 37.80 GTexel/s versus 72.00 GTexel/s
• FP32: 907.2 GFLOPS versus 1,152.0 GFLOPS
• FP16: not listed versus 2.304 TFLOPS (2:1)
• TDP: 160 W versus 15 W
• Slot Width: Dual-slot versus IGP
• Power Connectors: 2x 6-pin versus not listed
• Suggested PSU: 450 W versus not listed
• Bus Interface: PCIe 2.0 x16 versus Ring Bus
• Display Outputs: 2x DVI, 1x mini-HDMI 1.3a versus motherboard dependent
• DirectX: 12 (11_0) versus 12 (12_1)
• Vulkan: not listed versus 1.3
• Dimensions: 210 mm, 8.3 inches length versus not listed
• Release Date: 2010-07-11 versus 2015-08-31
• Launch MSRP: 199 USD versus not listed
• Predecessor: GeForce 200 versus not listed
• Successor: GeForce 500 versus not listed