GX 1650 vs XCKU15P
A comparison of the Altera Stratix 10 GX/SX GX 1650 and the AMD Kintex UltraScale+ XCKU15P using the data from both vendors' selection guides.
Side-by-side specifications
| GX 1650 | XCKU15P | |
|---|---|---|
| Vendor / family | Altera Stratix 10 GX/SX | AMD Kintex UltraScale+ |
| Logic (LUT4-equivalent) | 1,101,080 | 836,800 |
| LUTs as published | 550,540 ALMs | 523,000 LUT6 |
| Vendor logic figure | 1,624,000 LE | 1,143,000 SLC |
| DSP | 3,145 variable-precision DSP blocks | 1,968 DSP slices |
| Block RAM | 114 Mb | 34.6 Mb |
| Large RAM | — | 36 Mb |
| Max. user I/O | 704 | 668 |
| Transceivers | 64 × XCVR 28.3 Gb/s, 32 × XCVR 17.4 Gb/s | 44 × GTH 16.3 Gb/s, 32 × GTY 32.75 Gb/s |
| Hard PCI Express | Gen3 x16 | Gen3 x16 |
| Hard processor | None | None |
| Process | 14 nm | 16 nm |
| Configuration memory | SRAM | SRAM |
| Packages | 2 | 4 |
| Design tool | Altera Quartus Prime | AMD Vivado |
Highlighted values are higher. Logic is compared in LUT4 equivalents; see how FPGA vendors count logic.
Key differences
The GX 1650 has about 32% more logic capacity (1101K vs 837K LUT4 equivalents).
They use different logic architectures: the GX 1650 is built from ALMs and the XCKU15P from LUT6, so the raw LUT counts (551K vs 523K) are not directly comparable.
For arithmetic, the GX 1650 has 3,145 variable-precision DSP blocks against 1,968 DSP slices on the XCKU15P.
The GX 1650 has more on-chip memory (114 Mb vs 70.6 Mb).
Both have transceivers: 96 at up to 28.3 Gb/s on the GX 1650 and 76 at up to 32.75 Gb/s on the XCKU15P.
The GX 1650 is designed with Altera Quartus Prime and the XCKU15P with AMD Vivado.
Full specifications
See the complete spec sheets with packages and grades: GX 1650 (Stratix 10 GX/SX) and XCKU15P (Kintex UltraScale+).