FPGA & adaptive SoC databook · online editionRev. 2026.10

A27F110 vs XCVP2802

A comparison of the Altera Agilex 27 A27F110 and the AMD Versal Premium XCVP2802 using the data from both vendors' selection guides.

Side-by-side specifications

A27F110XCVP2802
Vendor / familyAltera Agilex 27AMD Versal Premium
LUTs as published3,625,037 ALMs3,349,120 LUT6
LUT typeadaptive logic module: fracturable 8-input LUT (one 6-input or two independent 4-input functions)6-input look-up table, fracturable into two LUT5 with shared inputs
LUT4 equivalent (approx.)≈7,250,074≈5,358,592
CoreScore (SERV cores)——
Vendor logic figure11,200,000 LE7,326,000 SLC
DSP13,306 AI Tensor DSP blocks14,304 DSP Engines
Block RAM520 Mb174 Mb
Large RAM693 Mb717 Mb
Max. user I/O986702
Transceivers160 × GX 128 Gb/s28 × GTYP 32.75 Gb/s, 140 × GTM 58 Gb/s
Hard PCI ExpressGen7 x8Gen5 x8, Gen5 x4
Hard processor4× Arm Cortex-A720 + Cortex-A520 (optional)2× Arm Cortex-A72
Process—7 nm
Configuration memorySRAMSRAM
Packages11
Design toolAltera Quartus PrimeAMD Vivado

Highlighted values are higher. LUT counts are shown as published; the LUT4 equivalent is an approximation to compare different LUT types, see how FPGA vendors count logic. Add up to two more devices to this comparison.

Key differences

The A27F110 has about 35% more logic capacity (7250K vs 5359K LUT4 equivalents).

They use different logic architectures: the A27F110 is built from ALMs and the XCVP2802 from LUT6, so the raw LUT counts (3625K vs 3349K) are not directly comparable.

For arithmetic, the XCVP2802 has 14,304 DSP Engines against 13,306 AI Tensor DSP blocks on the A27F110.

The A27F110 has more on-chip memory (1213 Mb vs 891 Mb).

Both have transceivers: 160 at up to 128 Gb/s on the A27F110 and 168 at up to 58 Gb/s on the XCVP2802.

The A27F110 is designed with Altera Quartus Prime and the XCVP2802 with AMD Vivado.

Full specifications

See the complete spec sheets with packages and grades: A27F110 (Agilex 27) and XCVP2802 (Versal Premium).