Intel Arc A770M vs NVIDIA GeForce GTX 1080 Ti Comparison

Head-to-Head Benchmarks

The recorded benchmark data splits cleanly between legacy DirectX workloads and modern API or compute tests. The Intel Arc A770M wins 4 of the 10 head-to-head comparisons, while the NVIDIA GeForce GTX 1080 Ti wins 6, but the margin of victory tells a more nuanced story than the raw win count.

Starting with the modern API tests, the Arc A770M dominates. In Geekbench Vulkan, the Intel part scores 74422 against 40511 for the GTX 1080 Ti, a delta of 83.7%. That is nearly double the NVIDIA card's output in a cross-platform graphics API. Geekbench OpenCL shows a similar pattern: 89494 for Intel versus 67929 for NVIDIA, a 31.7% advantage. These are not small gaps; they represent a generational shift in compute throughput per clock.

The 3DMark Steel Nomad DX12 test is closer. The Arc A770M scores 2278, the GTX 1080 Ti scores 2231, and the Intel card wins by just 2.1%. Both cards are effectively tied in this modern DirectX 12 workload, which suggests that raw shader throughput is comparable in this specific rasterization test. The PassMark DirectX 12 benchmark also goes to Intel, with 70 versus 66, a 6.1% margin.

Now the legacy tests. The GTX 1080 Ti wins PassMark DirectX 11 by a wide margin: 151 versus 69, a delta of -54.3% for the Intel card. DirectX 10 is similarly lopsided: 118 versus 56, a -52.5% gap. Even DirectX 9, an ancient API, favors NVIDIA by 22.9% (231 versus 178). These results indicate the Pascal architecture retains strong driver optimization for older DirectX feature levels, while the Arc A770M's Xe-HPG architecture clearly prioritizes modern API paths.

The overall PassMark G3D score heavily favors NVIDIA. The GTX 1080 Ti posts 18600, while the Arc A770M manages 11774, a 36.7% deficit. That is a substantial gap in a general-purpose gaming benchmark. PassMark GPU Compute also goes to NVIDIA: 9632 versus 4778, a 50.4% deficit. The 2D test, PassMark G2D, favors NVIDIA as well, 939 versus 711, a 24.3% difference.

The Verdict

The data does not point to a single universal winner. The Arc A770M is the clear choice for compute-heavy workloads and modern API games, particularly those built around Vulkan or DirectX 12 Ultimate features. The 83.7% lead in Vulkan and 31.7% lead in OpenCL are decisive. If your software stack leans on those APIs, the Intel card is the better pick.

The GTX 1080 Ti remains the stronger option for DirectX 11 and older titles. Its 54.3% lead in DirectX 11 and 52.5% lead in DirectX 10 are exactly the kind of margins that matter for a library of legacy games. The 36.7% advantage in PassMark G3D also suggests better overall rasterization throughput in mixed workloads, even if the modern API tests show parity or Intel wins.

For a new build today, the Arc A770M offers more future-proofing through its DirectX 12 Ultimate support and its larger 16 GB frame buffer. The GTX 1080 Ti, with 11 GB of GDDR5X, still has enough memory for most current titles, but its DirectX 12_1 feature level limits its reach into next-generation rendering techniques.

Where Each One Wins

Intel Arc A770M wins in: Vulkan-based games and applications, OpenCL compute workloads, DirectX 12 titles that leverage mesh shaders or other 12_2 features, and scenarios where the 16 GB memory pool prevents spills into system RAM. The 512.0 GB/s bandwidth also gives it a theoretical edge in memory-heavy tasks.

NVIDIA GeForce GTX 1080 Ti wins in: DirectX 11 and DirectX 9 games, older emulated titles, 2D desktop workloads (PassMark G2D 939 versus 711), and general-purpose GPU compute in the PassMark suite. The 11 GB memory is still sufficient for 1440p gaming, and the 484.4 GB/s bandwidth is close enough that memory bandwidth is not a differentiator in most games.

If you are building a machine for competitive esports titles that still run on DirectX 11, the GTX 1080 Ti is the safer bet. If you are developing or running Vulkan-based software, or you play modern AAA games that use DirectX 12 Ultimate, the Arc A770M is the data-supported choice.

FAQ

Q: Which card has the higher average benchmark score?

A: The Intel Arc A770M has an average benchmark score of 18383, while the NVIDIA GeForce GTX 1080 Ti scores 15548. The Intel card sits at the 62nd percentile among all GPUs, the NVIDIA card at the 58th.

Q: How do these cards compare to their nearest rivals?

A: The Arc A770M is essentially tied with the AMD Radeon RX 460 (0.1% delta) and the AMD Radeon Pro 5700 (1.1% ahead). The GTX 1080 Ti is 0.2% ahead of the AMD Radeon R9 M380 and 1.7% ahead of both the NVIDIA GeForce RTX 2060 and the NVIDIA GeForce GTX 580.

Q: Is the GTX 1080 Ti better in DirectX 12?

A: No. The Arc A770M wins the PassMark DirectX 12 test (70 versus 66) and the 3DMark Steel Nomad DX12 test (2278 versus 2231). The NVIDIA card wins older DirectX versions only.

Q: What is the memory configuration difference?

A: The Arc A770M has 16 GB of GDDR6 on a 256-bit bus with 512.0 GB/s bandwidth. The GTX 1080 Ti has 11 GB of GDDR5X on a 352-bit bus with 484.4 GB/s bandwidth. The Intel card has more capacity and higher bandwidth.

Q: Which card has better compute performance?

A: The Arc A770M wins Geekbench OpenCL by 31.7% and Geekbench Vulkan by 83.7%. The GTX 1080 Ti wins PassMark GPU Compute by 50.4%. The result depends on the benchmark methodology.

Q: What are the power requirements?

A: The Arc A770M is rated at 120 W TDP and is an IGP (integrated graphics package). The GTX 1080 Ti is rated at 250 W TDP, is a dual-slot card, requires one 6-pin and one 8-pin power connector, and has a suggested PSU of 600 W.

Architecture Differences

The two cards come from different architectural eras. The Intel Arc A770M uses the DG2-512 chip built on the Xe-HPG architecture, fabricated on a 6 nm process at TSMC. It contains 21,700 million transistors on a 406 mm² die, yielding a transistor density of 53.4 million per mm². The NVIDIA GeForce GTX 1080 Ti uses the GP102 chip on the Pascal architecture, built on a 16 nm process at TSMC. It has 11,800 million transistors on a 471 mm² die, for a density of 25.1 million per mm².

The Intel chip is smaller in die area but packs nearly twice the transistor count. That is a direct result of the 6 nm process node versus the older 16 nm node. The Arc A770M also has hardware ray tracing cores (32 of them), while the GTX 1080 Ti has none. The Intel card supports DirectX 12 Ultimate (12_2), while the NVIDIA card is limited to DirectX 12 (12_1).

Both cards support OpenGL 4.6 and Vulkan 1.4, but the feature level differences matter for modern rendering. The Arc A770M's 4096 shading units, 256 TMUs, and 128 ROPs outnumber the GTX 1080 Ti's 3584 shading units, 224 TMUs, and 88 ROPs. The Intel card also has a higher pixel rate (262.4 GPixel/s versus 139.2 GPixel/s) and texture rate (524.8 GTexel/s versus 354.4 GTexel/s).

Specification Differences

The bus interface differs: the Arc A770M uses PCIe 4.0 x16, while the GTX 1080 Ti uses PCIe 3.0 x16. Clock speeds also differ. The Intel card has a base clock of 1650 MHz and a boost clock of 2050 MHz. The NVIDIA card has a base clock of 1481 MHz and a boost clock of 1582 MHz. The Intel card runs its memory at 2000 MHz (16 Gbps effective), while the NVIDIA card runs at 1376 MHz (11 Gbps effective).

FP32 throughput is higher on the Intel card: 16.79 TFLOPS versus 11.34 TFLOPS. FP16 is dramatically different: the Arc A770M delivers 33.59 TFLOPS (2:1 ratio), while the GTX 1080 Ti delivers 177.2 GFLOPS (1:64 ratio). That is a factor of nearly 190 in half-precision compute.

The physical form factors are entirely different. The Arc A770M is an IGP with no slot width, while the GTX 1080 Ti is a dual-slot card measuring 267 mm by 112 mm by 40 mm. The NVIDIA card has display outputs of 1x HDMI 2.0 and 3x DisplayPort 1.4a, while the Intel card's outputs are listed as portable device dependent. The GTX 1080 Ti launched on 2017-03-09 with a launch MSRP of 699 USD. Both cards are end-of-life.