XCVM2152 vs XCZU65DR
A comparison of the AMD Versal Prime XCVM2152 and the AMD Zynq UltraScale+ RFSoC XCZU65DR using the data from both vendors' selection guides.
Side-by-side specifications
| XCVM2152 | XCZU65DR | |
|---|---|---|
| Vendor / family | AMD Versal Prime | AMD Zynq UltraScale+ RFSoC |
| LUTs as published | 346,112 LUT6 | 224,000 LUT6 |
| LUT type | 6-input look-up table, fracturable into two LUT5 with shared inputs | 6-input look-up table, fracturable into two LUT5 with shared inputs |
| LUT4 equivalent (approx.) | ≈553,779 | ≈358,400 |
| CoreScore (SERV cores) | — | — |
| Vendor logic figure | 757,000 SLC | 489,000 SLC |
| DSP | 1,704 DSP Engines | 1,872 DSP slices |
| Block RAM | 27 Mb | 22.8 Mb |
| Large RAM | 54 Mb | 45 Mb |
| Max. user I/O | 428 | 154 |
| Transceivers | 8 × GTYP 32.75 Gb/s, 8 × GTM 58 Gb/s | 8 × GTY 28.21 Gb/s |
| Hard PCI Express | Gen5 x4 | None |
| Hard processor | 2× Arm Cortex-A72 | 4× Arm Cortex-A53 |
| Process | 7 nm | 16 nm |
| Configuration memory | SRAM | SRAM |
| Packages | 2 | 1 |
| Design tool | AMD Vivado | 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 XCVM2152 has about 55% more logic capacity (554K vs 358K LUT4 equivalents).
For arithmetic, the XCZU65DR has 1,872 DSP slices against 1,704 DSP Engines on the XCVM2152.
The XCVM2152 has more on-chip memory (81 Mb vs 67.8 Mb).
Both have transceivers: 16 at up to 58 Gb/s on the XCVM2152 and 8 at up to 28.21 Gb/s on the XCZU65DR.
The XCVM2152 is designed with AMD Vivado and the XCZU65DR with AMD Vivado.
Full specifications
See the complete spec sheets with packages and grades: XCVM2152 (Versal Prime) and XCZU65DR (Zynq UltraScale+ RFSoC).