GPU Comparison

Where Each One Wins

The benchmark data presents a clear and decisive split between these two NVIDIA parts. The NVIDIA GeForce GTX 580, a desktop enthusiast card from the GeForce 500 generation, does not win a single recorded benchmark in this comparison. The NVIDIA RTX A2000 Mobile, an Ampere-generation professional mobile GPU, takes the sole recorded head-to-head victory.

The GTX 580’s only recorded benchmark is Geekbench OpenCL, where it scores 15,283. That places it at the 58th percentile of all GPUs in the database. Its nearest rivals in that test are the NVIDIA GeForce RTX 2060 (15,290, a 0% delta), the AMD Radeon 680M (15,270, a 0.1% delta), the NVIDIA GeForce RTX 3050 OEM (15,199, a 0.6% delta), and the AMD Radeon RX 7600 (15,171, a 0.7% delta). The data shows the GTX 580 sits in a tight cluster of modern entry-level and integrated-class parts, trading blows within a fraction of a percent, despite being a decade older in architecture.

The RTX A2000 Mobile, by contrast, delivers a Geekbench OpenCL score of 56,518, which is roughly 3.7 times the GTX 580’s result. Its average benchmark score across all recorded tests is 13,821, placing it at the 55th percentile. That average is pulled down by its Passmark DirectX 10, 11, and 12 scores, which are 57, 68, and 47 respectively. Those low-level API tests are not representative of its compute strength. Its Passmark G3D score is 9,611, and its Passmark GPU Compute score is 4,334, while its Geekbench Vulkan score is 53,146. The A2000 Mobile’s nearest rivals by average score include the AMD Radeon 660M (13,812, a 0.1% delta), the AMD Radeon RX 570X (13,871, a -0.4% delta), the AMD Radeon RX 7900 XT (13,745, a 0.6% delta), and the NVIDIA Tesla K10 (14,029, a -1.5% delta).

So the use-case split is stark. The GTX 580 is a legacy desktop part that, in the recorded OpenCL metric, performs on par with modern integrated graphics and low-end discrete cards. The RTX A2000 Mobile is a mobile workstation-class part that dominates in compute-heavy OpenCL workloads, while showing modest DirectX 9 performance (115) and a strong Vulkan showing. The GTX 580 has no recorded Vulkan score, no Passmark scores, and no DirectX 12 Ultimate support, so any workload relying on those APIs is simply unavailable to it.

FAQ

Q: Which GPU has the higher Geekbench OpenCL score?

A: The NVIDIA RTX A2000 Mobile scores 56,518, while the NVIDIA GeForce GTX 580 scores 15,283. The A2000 Mobile leads by a delta of -73% from the GTX 580’s perspective, meaning it is roughly 3.7 times faster in this test.

Q: How does the GTX 580 compare to its nearest rivals in average benchmark score?

A: The GTX 580’s average benchmark score is 15,283. Its nearest rival, the NVIDIA GeForce RTX 2060, scores 15,290 (a 0% delta), followed by the AMD Radeon 680M at 15,270 (0.1%), the RTX 3050 OEM at 15,199 (0.6%), and the AMD Radeon RX 7600 at 15,171 (0.7%). The differences are negligible.

Q: What is the RTX A2000 Mobile’s strongest recorded benchmark?

A: Its strongest score is in Geekbench OpenCL at 56,518, followed closely by Geekbench Vulkan at 53,146. Its Passmark G3D score is 9,611, and its Passmark GPU Compute score is 4,334.

Q: Does the GTX 580 support Vulkan?

A: The database lists no Vulkan version for the GTX 580, whereas the RTX A2000 Mobile supports Vulkan 1.4. This means Vulkan workloads are not recorded for the GTX 580.

Q: Which GPU has the higher pixel fill rate?

A: The RTX A2000 Mobile has a pixel rate of 80.98 GPixel/s, compared to the GTX 580’s 24.70 GPixel/s. The A2000 Mobile is roughly 3.3 times faster in this metric.

Q: What are the production statuses of these two GPUs?

A: Both the NVIDIA GeForce GTX 580 and the NVIDIA RTX A2000 Mobile are listed as end-of-life products in the database.

Head-to-Head Benchmarks

The only head-to-head benchmark recorded between these two GPUs is Geekbench OpenCL. The results are not close. The RTX A2000 Mobile scores 56,518, while the GTX 580 scores 15,283. The delta percentage is -73%, which means the GTX 580 is 73% behind the A2000 Mobile in this test. In practical terms, the A2000 Mobile delivers approximately 3.7 times the OpenCL compute throughput.

This is a massive gap, but it is not surprising given the architectural distance between the two parts. The GTX 580 is a Fermi 2.0 chip from 2010, while the A2000 Mobile is an Ampere chip from 2021. The GTX 580’s FP32 throughput is 1.581 TFLOPS, whereas the A2000 Mobile achieves 8.637 TFLOPS. That is a 5.5 times difference in raw floating-point capability, which aligns with the observed OpenCL delta.

The GTX 580’s texture rate is 49.41 GTexel/s against the A2000 Mobile’s 135.0 GTexel/s, a 2.7 times difference. Its pixel rate is 24.70 GPixel/s versus 80.98 GPixel/s, a 3.3 times difference. Memory bandwidth is nearly identical: 192.4 GB/s for the GTX 580 and 192.0 GB/s for the A2000 Mobile. So the A2000 Mobile wins overwhelmingly on compute and texture throughput, while memory bandwidth is a tie.

The GTX 580 has no other recorded benchmarks, so no comparison is possible for DirectX 9, 10, 11, 12, Vulkan, or 2D tests. The A2000 Mobile’s Passmark DirectX 9 score is 115, which is its best legacy API result, but the GTX 580 has no corresponding score. The database simply does not contain those measurements for the GTX 580.

Specification Differences

The two GPUs differ in nearly every core specification. The GTX 580 has 512 shading units, 64 texture mapping units, and 48 ROPs. The RTX A2000 Mobile has 2,560 shading units, 80 TMUs, and 48 ROPs. The shading unit count is 5 times higher on the A2000 Mobile, while TMUs are 1.25 times higher, and ROPs are equal.

Memory configurations also differ. The GTX 580 has 1,536 MB of GDDR5 on a 384-bit bus, resulting in 192.4 GB/s of bandwidth. The A2000 Mobile has 4 GB of GDDR6 on a 128-bit bus, resulting in 192.0 GB/s of bandwidth. The A2000 Mobile has more capacity but a narrower bus, netting out to nearly identical bandwidth.

Clock behavior is different as well. The GTX 580 lists a memory clock of 1,002 MHz (4 Gbps effective) and no base or boost clock data. The A2000 Mobile has a base clock of 1,215 MHz, a boost clock of 1,687 MHz, and a memory clock of 1,500 MHz (12 Gbps effective).

Power and physical specifications diverge sharply. The GTX 580 has a TDP of 244 W, is a dual-slot card, requires 1x 6-pin and 1x 8-pin power connectors, and lists a suggested PSU of 550 W. The A2000 Mobile has a TDP of 95 W, is an IGP (integrated graphics processor) form factor, requires no power connectors, and has no suggested PSU listed. The GTX 580 is 267 mm long and 111 mm tall, while the A2000 Mobile has no dimensions listed.

Bus interface and display outputs differ. The GTX 580 uses PCIe 2.0 x16 and outputs 2x DVI and 1x mini-HDMI 1.3a. The A2000 Mobile uses PCIe 4.0 x16 and its display outputs are listed as “Portable Device Dependent.”

API support differs significantly. The GTX 580 supports DirectX 12 (11_0) and OpenGL 4.6, with no Vulkan listed. The A2000 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Architecture Differences

The GTX 580 is built on the GF110 chip using the Fermi 2.0 architecture, fabricated on a 40 nm process at TSMC. It contains 3,000 million transistors on a die size of 520 mm², giving a transistor density of 5.8M per mm². It has no ray tracing cores and no tensor cores. Its FP16 performance is not listed, indicating no dedicated half-precision path.

The RTX A2000 Mobile is built on the GA107 chip using the Ampere architecture, fabricated on an 8 nm process at Samsung. It contains 8,700 million transistors on a die size of 200 mm², giving a transistor density of 43.5M per mm². That is 7.5 times higher density than the GTX 580. The A2000 Mobile includes 20 ray tracing cores and 80 tensor cores, features entirely absent from the GTX 580. Its FP16 throughput is 8.637 TFLOPS, matching its FP32 rate at a 1:1 ratio, which indicates a modern unified compute design.

The generation gap is also visible in the product lineage. The GTX 580 belongs to the GeForce 500 generation, succeeding the GeForce 400 and preceding the GeForce 600. The A2000 Mobile belongs to the Ampere-MW (Ax000) generation, succeeding Quadro Turing-M and preceding Ada-MW. The release dates are 2010-11-08 for the GTX 580 and 2021-04-11 for the A2000 Mobile, a gap of over a decade.

The GTX 580 has a launch MSRP of 499 USD, while the A2000 Mobile has no launch MSRP recorded. The foundry choices also differ: TSMC for the GTX 580, Samsung for the A2000 Mobile. The GTX 580’s transistor count is 3,000 million, while the A2000 Mobile’s is 8,700 million, a 2.9 times increase despite a 2.6 times smaller die. This reflects the process node advantage of 8 nm over 40 nm.

In summary, the architectural differences are fundamental: Fermi 2.0 is a fixed-function, non-ray-tracing design with no tensor acceleration, while Ampere is a modern GPU with dedicated ray tracing, tensor cores, and a unified FP16/FP32 pipeline. The recorded benchmark data reflects this gap most clearly in OpenCL compute, where the A2000 Mobile is roughly 3.7 times faster. The GTX 580’s only recorded score places it in a dead heat with modern integrated graphics, while the A2000 Mobile’s compute result puts it in a different performance class entirely.