4x improvement to vector computation with 4x sustained bandwidth of prior generations

Overview

Building on the highly popular SiFive Intelligence™ X280 products’ success in AI/ML applications across mobile, infrastructure and automotive applications, where they are frequently coupled to hardware accelerators, the X390 brings a 4x improvement to vector computation with its single core configuration, doubled vector length and dual vector ALUs.

This allows 4x the sustained data bandwidth while calling on the quad core configuration. With SiFive VCIX. companies can easily add their own vector instructions and/or acceleration hardware, bringing unprecedented flexibility and allowing them to greatly increase performance with custom instructions.

Key Features

  • 1024-bit VLEN
    • Single / Dual Vector ALU
    • VCIX (2048-bit)
  • SiFive Intelligence Extensions for ML workloads
    • Custom instructions to greatly accelerate Neural Network computation
    • Optimized TensorFlow Lite implementation
    • Hundreds of Neural Network models ported
    • 4.6 TOPS performance
  • 512-bit vector register length processor
    • Variable length operations, up to 512-bits of data per cycle
    • Ideal balance of control logic and data parallel compute
    • Decoupled Vector pipeline
    • INT8 to INT64 integer data type
    • BF16/FP16/FP32/FP64 floating point data type
  • Performance benchmarks
    • 5.75 CoreMarks/MHz
    • 3.25 DMIPS/MHz
    • 4.6 SpecINT2k6/GHz
  • Built on silicon-proven U7-Series core
    • 64-bit RISC-V ISA
    • 8-stage dual-issue in-order pipeline
    • Coherent multi-core, Linux capable
  • High performance vector memory subsystem
    • Memory parallelism provides cache miss tolerance
    • Virtual memory support with precise exceptions
    • Up to 48-bit addressing
  • Multi-core, multi-cluster processor configuration, up to 8 cores

Technical Specifications

×
Semiconductor IP