MX 1650 vs XCVU160
A comparison of the Altera Stratix 10 MX MX 1650 and the AMD Virtex UltraScale XCVU160 using the data from both vendors' selection guides.
Side-by-side specifications
| MX 1650 | XCVU160 | |
|---|---|---|
| Vendor / family | Altera Stratix 10 MX | AMD Virtex UltraScale |
| LUTs as published | 569,200 ALMs | 926,400 LUT6 |
| LUT type | adaptive 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.) | ≈1,138,400 | ≈1,482,240 |
| CoreScore (SERV cores) | — | — |
| Vendor logic figure | 1,679,000 LE | 2,027,000 SLC |
| DSP | 3,326 variable-precision DSP blocks | 1,560 DSP slices |
| Block RAM | 120 Mb | 115.2 Mb |
| Large RAM | — | — |
| Max. user I/O | 656 | 702 |
| Transceivers | 64 × GXT 28.3 Gb/s, 32 × GX 17.4 Gb/s | 52 × GTH 16.3 Gb/s, 52 × GTY 30.5 Gb/s |
| Hard PCI Express | Gen3 x16 | Gen3 |
| Hard processor | None | None |
| Process | 14 nm | 20 nm |
| Configuration memory | SRAM | SRAM |
| Packages | 1 | 2 |
| Design tool | Altera Quartus Prime | AMD 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 XCVU160 has about 30% more logic capacity (1482K vs 1138K LUT4 equivalents).
They use different logic architectures: the MX 1650 is built from ALMs and the XCVU160 from LUT6, so the raw LUT counts (569K vs 926K) are not directly comparable.
For arithmetic, the MX 1650 has 3,326 variable-precision DSP blocks against 1,560 DSP slices on the XCVU160.
Both have transceivers: 96 at up to 28.3 Gb/s on the MX 1650 and 104 at up to 30.5 Gb/s on the XCVU160.
The MX 1650 is designed with Altera Quartus Prime and the XCVU160 with AMD Vivado.
Full specifications
See the complete spec sheets with packages and grades: MX 1650 (Stratix 10 MX) and XCVU160 (Virtex UltraScale).