Configuration |
- Dedicated Secure Device Manager
- Software programmable device configuration
- Serial and parallel flash interface
- Configuration via protocol (CvP) using PCI Express* Gen1/Gen2/Gen3/Gen4
- Fine-grained partial reconfiguration of core fabric
- Dynamic reconfiguration of transceivers and PLLs
- Comprehensive set of security features including AES-256, SHA-256/384, and ECDSA-256/384 accelerators, and multi-factor authentication
- Physically Unclonable Function (PUF) service
|
Core clock networks |
- Programmable clock tree synthesis, backwards compatible with global, regional and peripheral clock networks
- Clocks only synthesized where needed, to minimize dynamic power
- 667 MHz external memory interface clocking, supports 2666 Mbps DDR4 interface
- 800 MHz LVDS interface clocking, supports 1600 Mbps LVDS interface
|
Core process technology |
- 14 nm Intel® tri-gate (FinFET) process technology
- SmartVID controlled core voltage, standard power devices
|
Embedded hard IP |
- PCIe* Gen1/Gen2/Gen3/Gen4 x16 complete protocol stack, endpoint and root port, multiple independent controllers, SR-IOV, VIRTIO, Intel® Scalable IOV, and transaction layer bypass
- Intel® UPI hard IP requires Intel® soft IP (separate licensing required, selected customers only, 1SD210 and 1SD280 devices only)
- 100 GbE MAC, Reed-Solomon FEC hard IP, and KP-FEC hard IP
- DDR4/DDR3 hard memory controller (RLDRAM3/QDR II+/QDR IV using soft memory controller)
- HBM2 DRAM hard memory controller (select devices)
- Hard Processor system, Quad-core 64-bit Arm* Cortex* -A53 (select devices)
|
General purpose I/Os |
- Up to 816 total GPIO available
- 1.6 Gbps LVDS—every pair can be configured as an input or output
- Up to 2400 megatransfers per second DDR-T external memory interface ( Intel® soft IP license required)
- 1333 MHz/2666 Mbps DDR4 external memory interface
- 1067 MHz/2133 Mbps DDR3 external memory interface
- 1.2 V to 1.8 V single-ended LVCMOS/LVTTL interfacing
- On-chip termination (OCT)
|
High performance monolithic core fabric |
- Intel® Hyperflex™ core architecture with Hyper-Registers everywhere throughout the interconnect routing and at the inputs of all functional blocks
- Monolithic fabric minimizes compile times and increases logic utilization
- Enhanced adaptive logic module (ALM)
- Improved multi-rack routing architecture reduces congestion and improves compile times
- Hierarchical core clocking architecture with programmable clock tree synthesis
- Fine-grained partial reconfiguration
|
Internal memory blocks |
- eSRAM—47.25 Mbit with hard ECC support (select devices)
- M20K—20 kilobit (Kb) with hard ECC support
- MLAB—640 bit distributed LUTRAM
|
Low power serial transceivers |
- Up to 84 total transceivers available
- Continuous operating range of 1 Gbps to 57.8 Gbps PAM4 and 28.9 Gbps NRZ (E-tile transceivers)
- Backplane support up to 57.8 Gbps PAM4 and 28.9 Gbps NRZ (E-tile transceivers)
- Transmit pre-emphasis and de-emphasis
- Dynamic partial reconfiguration of individual transceiver channels
- On-chip instrumentation (Eye Viewer non-intrusive data eye monitoring)
|
Packaging |
- Intel® Embedded Multi-die Interconnect Bridge (EMIB) packaging technology
- 1.0 mm ball-pitch FBGA packaging
- Lead and lead-free package options
|
Phase locked loops (PLLs) |
- Integer PLLs adjacent to general purpose I/Os, support external memory, and LVDS interfaces, clock delay compensation, zero delay buffering
|
Power management |
- SmartVID controlled core voltage, standard power devices
- Intel® Quartus® Prime Pro Edition integrated power analysis
|
Software and tools |
- Intel® Quartus® Prime Pro Edition design suite with new compiler and Hyper-Aware design flow
- Fast Forward compiler to allow Intel® Hyperflex™ architecture performance exploration
- Transceiver toolkit
- Platform Designer system integration tool
- DSP Builder system integration tool
- OpenCL* support
|
Variable precision DSP blocks |
- IEEE 754-compliant hard single-precision floating point capability
- Supports signal processing with precision ranging from 18x19 up to 54x54
- Native 27x27 and 18x19 multiply modes
- 64-bit accumulator and cascade for systolic FIRs
- Internal coefficient memory banks
- Pre-adder/subtractor improves efficiency
- Additional pipeline register increases performance and reduces power
|