Intel Iris Pro Graphics P580 vs NVIDIA GeForce GTX 1660 Ti Comparison

The NVIDIA GeForce GTX 1660 Ti is a discrete, dual-slot graphics card built on the Turing architecture at a 12 nm process node, while the Intel Iris Pro Graphics P580 is an integrated GPU (IGP) on Intel's Generation 9.0 architecture using a 14 nm+ node. In the two shared benchmark tests, the GTX 1660 Ti wins both, with a massive 461.9% lead in Geekbench OpenCL and a narrower 10.8% advantage in Geekbench Vulkan, yielding a 2-0 head-to-head win count.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 1660 Ti has an average benchmark score of 7723, while the Intel Iris Pro Graphics P580 scores 7170. The GTX 1660 Ti sits at the 41st percentile of all GPUs, compared to the P580's 39th percentile.

Q: What is the performance gap between the two in Geekbench OpenCL?

A: The GTX 1660 Ti scores 51029 in Geekbench OpenCL versus the P580's 9082, a delta of 461.9% favoring NVIDIA. This is the largest single benchmark discrepancy between the two.

Q: How close is the Geekbench Vulkan result?

A: The GTX 1660 Ti posts 5827 in Geekbench Vulkan, only 10.8% ahead of the P580's 5258. This is a relatively tight margin compared to the OpenCL gap.

Q: What are the nearest rivals for each GPU?

A: For the GTX 1660 Ti, the nearest rivals are the AMD Radeon 540 (0.7% delta), AMD Radeon Pro WX 3100 (1.9%), AMD Radeon R7 250 (2.2%), and Intel Arc A310 (2.3%). For the P580, the nearest rivals are the NVIDIA GeForce GTX 560 SE (0% delta), NVIDIA GeForce GTX 970 (0.2%), AMD Radeon Vega 8 Mobile (-0.5%), and NVIDIA GeForce GTX 750 (-0.7%).

Q: Do both GPUs support DirectX 12?

A: Yes, both support DirectX 12 (12_1) and OpenGL 4.6. The GTX 1660 Ti supports Vulkan 1.4, while the P580 supports Vulkan 1.3.

Q: What is the difference in shading units and texture mapping units?

A: The GTX 1660 Ti has 1536 shading units and 96 TMUs. The P580 has 576 shading units and 72 TMUs, which is fewer in both categories.

The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 1660 Ti is the superior GPU for any workload that leverages compute or rendering performance. It wins both head-to-head benchmarks, and its average benchmark score of 7723 is 553 points higher than the P580's 7170. The GTX 1660 Ti's 41st percentile rank versus the P580's 39th percentile confirms a consistent, if not overwhelming, edge in overall standing.

For users who need a dedicated card with a 6 GB GDDR6 memory buffer, a 192-bit bus, and 288.0 GB/s of bandwidth, the GTX 1660 Ti is the clear choice. Its pixel rate of 84.96 GPixel/s and texture rate of 169.9 GTexel/s dwarf the P580's 9.000 GPixel/s and 72.00 GTexel/s, respectively. The FP32 throughput of 5.437 TFLOPS versus 1,152.0 GFLOPS means the NVIDIA card is roughly 4.7 times faster in raw single-precision compute.

The Intel Iris Pro Graphics P580 is an integrated solution with a 15 W TDP, no standalone memory (System Shared), and a Ring Bus interface. It is not a competitor for the GTX 1660 Ti in any benchmark listed. The P580's only comparative advantage is its low power draw and integrated form factor, but the performance data shows it loses decisively in every measured test. Users with the P580 should expect it to handle basic tasks, but the GTX 1660 Ti is the only viable option for demanding graphics or compute workloads.

Head-to-Head Benchmarks

The two GPUs share exactly two benchmark results: Geekbench OpenCL and Geekbench Vulkan. In Geekbench OpenCL, the GTX 1660 Ti scores 51029 against the P580's 9082. This 461.9% delta is the single largest performance margin observed in the data. The OpenCL result reflects the GTX 1660 Ti's superior shading units (1536 vs 576), higher boost clock (1770 MHz vs 1000 MHz), and dedicated GDDR6 memory with 288.0 GB/s bandwidth versus the P580's system-shared, bandwidth-dependent memory.

In Geekbench Vulkan, the gap narrows considerably. The GTX 1660 Ti scores 5827, while the P580 scores 5258, a delta of only 10.8%. This suggests that the P580's Vulkan implementation is relatively efficient, but it still falls short. The GTX 1660 Ti maintains its lead, but the smaller margin indicates that the P580 is less disadvantaged in this API. Overall, the GTX 1660 Ti wins both tests, giving it a 2-0 record in head-to-head comparisons.

Specification Differences

The GTX 1660 Ti and P580 differ across nearly every specification field. The GTX 1660 Ti uses a 12 nm process node from TSMC, while the P580 uses Intel's 14 nm+ process. The GTX 1660 Ti has 6,600 million transistors on a 284 mm² die, with a transistor density of 23.2M / mm²; the P580 has no listed transistor count, die size, or density data.

Clock speeds diverge sharply: the GTX 1660 Ti runs at 1500 MHz base and 1770 MHz boost, with memory at 1500 MHz (12 Gbps effective). The P580 runs at 350 MHz base and 1000 MHz boost, with system-shared memory. The GTX 1660 Ti has 6 GB of GDDR6 on a 192-bit bus delivering 288.0 GB/s; the P580's memory is fully system-dependent.

The GTX 1660 Ti has 1536 shading units, 96 TMUs, and 48 ROPs, versus the P580's 576 shading units, 72 TMUs, and 9 ROPs. Pixel rates are 84.96 GPixel/s versus 9.000 GPixel/s, and texture rates are 169.9 GTexel/s versus 72.00 GTexel/s. FP32 performance is 5.437 TFLOPS versus 1,152.0 GFLOPS, and FP16 is 10.87 TFLOPS (2:1) versus 2.304 TFLOPS (2:1).

Power and physical specs also differ: the GTX 1660 Ti has a 120 W TDP, dual-slot width, a 1x 8-pin power connector, a 300 W suggested PSU, and a PCIe 3.0 x16 interface. The P580 has a 15 W TDP, is an IGP, has no power connector or suggested PSU, and uses a Ring Bus interface. Display outputs are 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a for NVIDIA, versus motherboard-dependent outputs for Intel.

Architecture Differences

The GTX 1660 Ti is built on NVIDIA's Turing architecture, designated as the GeForce 16 generation, using the TU116 chip. It succeeds the GeForce 10 series and precedes the GeForce 20 series. The P580 is based on Intel's Generation 9.0 architecture, using the Skylake GT4e chip, and is part of the HD Graphics-W (Skylake) generation.

The process nodes differ: TSMC's 12 nm for NVIDIA versus Intel's 14 nm+ for the integrated part. The GTX 1660 Ti has a dedicated 6 GB GDDR6 memory subsystem, while the P580 relies on system-shared memory, making its bandwidth system-dependent. The GTX 1660 Ti's shading unit count (1536) is 2.67 times higher than the P580's (576), and its ROP count (48) is over five times higher (9 ROPs).

Both support DirectX 12 (12_1) and OpenGL 4.6, but the GTX 1660 Ti supports Vulkan 1.4, while the P580 supports Vulkan 1.3. Neither has ray tracing or tensor cores. The GTX 1660 Ti's boost clock of 1770 MHz is 77% higher than the P580's 1000 MHz boost, contributing to its substantial compute advantage.

Where Each One Wins

The NVIDIA GeForce GTX 1660 Ti wins in every benchmark category where both are tested. In Geekbench OpenCL, its 51029 score is 461.9% higher, making it the dominant choice for OpenCL-accelerated workloads such as general-purpose GPU compute, scientific simulations, and rendering tasks that leverage the card's 5.437 TFLOPS FP32 performance and 6 GB of dedicated GDDR6 memory.

In Geekbench Vulkan, the GTX 1660 Ti wins with a 10.8% margin (5827 vs 5258). This smaller gap suggests that Vulkan-based games or applications are a more level playing field, but the NVIDIA card still holds the edge. For users prioritizing raw performance in any listed benchmark, the GTX 1660 Ti is the only logical selection.

The Intel Iris Pro Graphics P580 has no benchmark wins in the head-to-head data. Its only potential advantages are qualitative: a 15 W TDP versus 120 W, an integrated form factor that requires no slot or power connector, and system-shared memory that eliminates dedicated VRAM costs. These factors make it suitable for low-power, embedded, or motherboard-dependent systems where discrete graphics are impractical. However, in terms of measured performance, the P580 loses both tests, and its 7170 average score places it just below the GTX 1660 Ti's 7723. Users seeking any level of competitive gaming, high-resolution rendering, or compute acceleration should choose the GTX 1660 Ti; the P580 is best reserved for basic display output and minimal graphics tasks.