Intel Iris Pro Graphics P580 vs NVIDIA GeForce GTX 650 Ti Comparison

Head-to-Head Benchmarks

The recorded data shows a clear split between the two contenders depending on the workload. In the Geekbench OpenCL test, the Intel Iris Pro Graphics P580 posts a score of 9082, while the NVIDIA GeForce GTX 650 Ti manages 7877. That gives Intel a 13.3% advantage in this compute-oriented benchmark. The delta is substantial, and it flips the expected narrative for anyone who assumes a discrete graphics card always beats an integrated solution.

The Vulkan results tell the opposite story. Here, the NVIDIA GeForce GTX 650 Ti scores 8229, while the Intel Iris Pro Graphics P580 falls to 5258. That is a 56.5% lead for NVIDIA. The gap is massive, far larger than Intel's margin in OpenCL. If you are looking at modern graphics APIs, the GTX 650 Ti is the clear winner based on the numbers alone.

Looking at average benchmark scores across the database, the NVIDIA GeForce GTX 650 Ti sits at 8053, which places it in the 42nd percentile of all GPUs. The Intel Iris Pro Graphics P580 averages 7170, putting it in the 39th percentile. The difference is about 883 points, roughly a 12% gap in the aggregate. Interestingly, the GTX 650 Ti's nearest rivals include the GTX 650 Ti Boost at 8067 (a 0.2% difference) and the GRID K2 at 8080 (a 0.3% difference). The Intel part sits near the GTX 560 SE at 7171 (a 0% delta) and the GTX 750 at 7222 (a 0.7% difference). These rival placements show that both parts land in a crowded midrange band, but NVIDIA's card holds a higher overall position.

Breaking down the individual wins, the GTX 650 Ti takes one benchmark and the Iris Pro P580 takes the other. That means the head-to-head record is 1-1. However, the magnitude of the Vulkan victory for NVIDIA (56.5%) outweighs the OpenCL victory for Intel (13.3%) in terms of sheer score difference. A user prioritizing raw compute throughput in OpenCL would favor the Intel solution, while anyone running Vulkan-based applications would see a far stronger result from the NVIDIA card.

Architecture Differences

The two parts come from completely different design philosophies. The NVIDIA GeForce GTX 650 Ti uses the GK106S chip built on the Kepler architecture, manufactured by TSMC on a 28 nm process. The die contains 2,540 million transistors across a 221 mm² area, giving a transistor density of 11.5M per mm². The Intel Iris Pro Graphics P580 uses the Skylake GT4e chip with Intel's Generation 9.0 architecture, built on a 14 nm+ process at Intel's own foundry. No transistor count or die size is recorded for the Intel part, so a direct density comparison is not possible from the data.

The NVIDIA card has 768 shading units, 64 texture mapping units, and 16 ROPs. The Intel part counters with 576 shading units, 72 TMUs, and only 9 ROPs. The higher TMU count on the Intel side explains its texture rate of 72.00 GTexel/s, which beats NVIDIA's 59.39 GTexel/s. Conversely, the GTX 650 Ti's pixel rate of 14.85 GPixel/s is well ahead of Intel's 9.000 GPixel/s, a direct consequence of having more ROPs. In raw FP32 throughput, the NVIDIA card delivers 1,425.4 GFLOPS versus 1,152.0 GFLOPS for the Intel part, a 23.7% advantage for NVIDIA. The Intel chip also supports FP16 at 2.304 TFLOPS (2:1), a feature the GTX 650 Ti does not list.

Memory architecture is fundamentally different. The GTX 650 Ti uses 1024 MB of dedicated GDDR5 on a 128-bit bus, delivering 86.40 GB/s of bandwidth. The Iris Pro P580 uses system shared memory, with bandwidth listed as system dependent. That means the Intel solution's memory performance varies with the host platform, while NVIDIA's is fixed by its own VRAM configuration. The NVIDIA card's memory clock is 1350 MHz (5.4 Gbps effective), whereas the Intel part has no dedicated memory clock.

Clock behavior also differs. The Intel chip has a base clock of 350 MHz and a boost of 1000 MHz. The GTX 650 Ti has no base or boost clock listed in the database, only its memory clock. The TDP gap is enormous: the GTX 650 Ti draws 110 W and requires a 6-pin power connector with a suggested 300 W power supply, while the Iris Pro P580 has a 15 W TDP and no power connector. The NVIDIA card is a single-slot PCIe 3.0 x16 board measuring 145 mm (5.7 inches), while the Intel part is an IGP connected via Ring Bus with motherboard-dependent display outputs.

API support differs in interesting ways. The GTX 650 Ti supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Iris Pro P580 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The Intel part has a higher DirectX feature level and a newer Vulkan version, which may explain its lower Vulkan score if driver optimization or feature-level overhead plays a role, though the data does not specify the cause.

The Verdict

Choose the NVIDIA GeForce GTX 650 Ti if your workload leans on Vulkan or traditional rasterization. Its 56.5% lead in the Vulkan benchmark is decisive, and its higher FP32 throughput (1,425.4 GFLOPS versus 1,152.0 GFLOPS), higher pixel rate (14.85 GPixel/s versus 9.000 GPixel/s), and dedicated 86.40 GB/s memory bandwidth all point to stronger graphics performance in most real-world scenarios. The 42nd percentile ranking versus the Intel part's 39th also supports NVIDIA in the aggregate.

Choose the Intel Iris Pro Graphics P580 if OpenCL compute is your priority. Its 9082 score in that test beats the GTX 650 Ti by 13.3%, and its texture rate of 72.00 GTexel/s is the highest between the two. The 15 W TDP is a massive advantage for low-power or mobile systems, though the database does not record a suggested PSU for the Intel part. Its Vulkan score of 5258 is a serious weakness, and the system shared memory means bandwidth is not guaranteed.

The data does not support a universal winner. Each part dominates in one recorded benchmark, and the differences are large enough that workload selection matters more than brand loyalty.

Specification Differences

The two differ on nearly every hardware field. The process node: 28 nm for NVIDIA, 14 nm+ for Intel. Transistors: 2,540 million for NVIDIA, not recorded for Intel. Die size: 221 mm² for NVIDIA, not recorded for Intel. Shading units: 768 versus 576. TMUs: 64 versus 72. ROPs: 16 versus 9. Pixel rate: 14.85 GPixel/s versus 9.000 GPixel/s. Texture rate: 59.39 GTexel/s versus 72.00 GTexel/s. FP32: 1,425.4 GFLOPS versus 1,152.0 GFLOPS. FP16: not listed for NVIDIA, 2.304 TFLOPS for Intel. TDP: 110 W versus 15 W.

Memory size: 1024 MB versus system shared. Memory type: GDDR5 versus system shared. Bus width: 128 bit versus system shared. Bandwidth: 86.40 GB/s versus system dependent. Memory clock: 1350 MHz (5.4 Gbps effective) versus no dedicated clock. Power connectors: 1x 6-pin versus none. Suggested PSU: 300 W versus not listed. Slot width: single-slot versus IGP. Bus interface: PCIe 3.0 x16 versus Ring Bus. Display outputs: 2x DVI and 1x mini-HDMI 1.4a versus motherboard dependent. DirectX: 12 (11_0) versus 12 (12_1). Vulkan: 1.2.175 versus 1.3.

Release dates differ: the GTX 650 Ti launched on 2012-10-08, while the Iris Pro P580 arrived on 2015-08-31. The NVIDIA card has a recorded launch MSRP of 149 USD, while the Intel part has no MSRP field. Both are end-of-life products.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 650 Ti averages 8053, while the Intel Iris Pro Graphics P580 averages 7170. That puts NVIDIA about 12% higher in the aggregate.

Q: How big is the Vulkan performance gap?

A: The GTX 650 Ti scores 8229 in Geekbench Vulkan, versus 5258 for the Iris Pro P580. That is a 56.5% lead for NVIDIA.

Q: Does the Intel integrated GPU win any benchmark?

A: Yes, the Iris Pro P580 scores 9082 in Geekbench OpenCL, beating the GTX 650 Ti's 7877 by 13.3%.

Q: What is the memory setup for each?

A: The GTX 650 Ti uses 1024 MB of GDDR5 on a 128-bit bus with 86.40 GB/s bandwidth. The Iris Pro P580 uses system shared memory with system dependent bandwidth.

Q: How do power requirements compare?

A: The GTX 650 Ti has a 110 W TDP and requires a 6-pin power connector with a suggested 300 W PSU. The Iris Pro P580 has a 15 W TDP and no power connector.

Q: Which part has higher texture fill rate?

A: The Intel Iris Pro P580 has a texture rate of 72.00 GTexel/s, which beats the GTX 650 Ti's 59.39 GTexel/s, despite having fewer shading units.

Where Each One Wins

The NVIDIA GeForce GTX 650 Ti wins in Vulkan-based workloads by a wide margin. Its 8229 Vulkan score versus 5258 for Intel represents a 56.5% advantage, and its higher FP32 throughput (1,425.4 GFLOPS) and pixel rate (14.85 GPixel/s) make it the better choice for games or applications that rely on these traditional graphics paths. The dedicated 86.40 GB/s memory bandwidth removes any dependence on system memory performance, which is a real advantage for consistency. The GTX 650 Ti also places higher in the overall percentile ranking (42nd versus 39th), and its average score of 8053 puts it in the same class as the GTX 650 Ti Boost and GRID K2, while the Intel part sits near the GTX 560 SE and GTX 750.

The Intel Iris Pro Graphics P580 wins in OpenCL compute tasks. Its 9082 score is 13.3% higher than the GTX 650 Ti's 7877, and its texture rate of 72.00 GTexel/s is higher than NVIDIA's 59.39 GTexel/s. The 15 W TDP makes it a fit for systems where power draw is a hard constraint, and the absence of a power connector simplifies installation. The newer Vulkan 1.3 API support and DirectX 12 (12_1) feature level are also recorded advantages over the GTX 650 Ti's Vulkan 1.2.175 and DirectX 12 (11_0). For systems with fast system memory, the shared memory architecture could be sufficient, though the data does not quantify that scenario.

Use-case split: for Vulkan gaming, emulation, or any modern graphics API workload, the GTX 650 Ti is the stronger choice based on the recorded data. For OpenCL-heavy compute, low-power builds, or systems where a discrete card cannot be installed, the Iris Pro P580 has the edge. The 1-1 head-to-head record confirms that neither part dominates across the board, so the decision should hinge on which benchmark aligns with your primary application.