CXL memory expansion
Overview
DenseMem increases effective CXL Type 3 Device memory capacity by a factor of 2x through transparent, in-line memory compression/decompression with minimal impact to latency and badwidth. DenseMem is available as an area and power efficient drag and drop IP block portable across the latest process nodes.
Key Features
- Turn key solution: compression, compaction, memory management
- Automatic compressed memory tier
- Multi-instance support to match interface throughput
- Cache line granularity decompression for highest read performance (proprietary algorithm)
Benefits
- Standards
- Protocol: CXL 2.0, 3.0, 3.1, cxl.mem
- Compression: LZ4, ZID (proprietary)
- AMBA interface: AXI4, CHI
- Architecture
- Transparent addressing to host
- Arbitrary cache line read/ write
- Bridge to cxl.mem, optionally to cxl.io
- Support for DCD, optional custom interface
- Type 3 device support, NUMA based memory tiering
Deliverables
- FPGA evaluation license
- Encrypted IP delivery (Xilinx)
- HDL Source Licenses
- Synthesizable System Verilog RTL (encrypted)
- Implementation constraints
- UVM testbench (self-checking)
- Vectors for testbench and expected results
- User Documentation
Technical Specifications
Maturity
Tape-out
Availability
Immediate
Related IPs
- High-Performance Memory Expansion IP for AI Accelerators
- Quad SPI Flash Memory Controller
- Stallable 1toN Expansion Pipeline Register
- Universal Multi-port Memory Controller for RLDRAM2/3, DDR5/4/3, DDR4 3DS and LPDDR3/2 and LPDDR3/2
- I2C Controller IP – Slave, Parameterized FIFO, Hs-Mode (3.4 Mbps) AXI/AHB/APB/Avalon Buses or direct to/from Registers or Memory
- Universal Multi-port Memory Controller for RLDRAM2/3, DDR4/3, DDR4 3DS and LPDDR3/2 and LPDDR3/2