Processors

Kalray_Banner_MPPA_Manycore_Processor_1920x1080.jpg
Kalray's MPPA® Processors
A New Class of Processors, Specialized in Intelligent Data Processing, for Infrastructure, Compute and AI Acceleration

Coolidge™ is the third generation of Kalray’s MPPA® Intelligent Data Processors. Coolidge™ is natively capable of managing multiple workloads in parallel with no bottlenecks to enable smarter, more efficient and energy-wise data-intensive applications.

Taking full advantage of Kalray’s patented MPPA® (Massively Parallel Processor Array) architecture, Coolidge™ is a scalable 80-core processor designed for intelligent data processing. It offers a unique alternative to GPU, ASIC or FPGA, bringing unique value to multiple applications from Data Centers, to the Edge and in Embedded systems.

  • MPPA_processor_1920x1318
Key Benefits of MPPA® Intelligent Processor
  1. High Performance Computing: Performance scalability within die, die-to-die, many dies.
  2. Heterogeneous Multi-processing: Parallel execution of dozens of heterogeneous critical tasks, including AI inference.
  3. Easy Programming: C/C++ / Open CL™ / Linux / POSIX / RTOS
  4. Real-time Data Processing: High speed I/O, RDMA architecture type
  5. Power Efficiency
  6. Security/Safety: Determinism, Freedom from interference, Secure boot

Use Cases

  • Datacenter 3840x2160
    Use Case

    Develop Next Gen Storage and Networking Systems

    Flexible integration in state-of-the-art PCIe Gen4, 100GbE appliances:
    - JBOF Target controller, I/O controller, SmartNIC, SmartSSD use cases
    - 2 configurations: stand-alone or x86 CPU offloading
    - Support virtualized, containerized or bare metal infrastructures
    - Dynamic resource allocation for Control, Data & Management Planes
    .

    Acceleration of high-performance protocols, services and QoS:
    - NVMe-oF, RoCE/RDMA, TCP/IP, NVMe, OVS/NFV protocols
    - Smart Load-Balancer, Priority Flow Control, Stateless L1-L4 parsing
    - RAID6: 154 Gbit/s Erasure Coding (Reed-Solomon) per cluster
    - Line-rate encryption/decryption/hash (IPSEC, TLS, XTS, MACsec)
    - AI capability for analytics and adaptive configuration

  • Kalray Data Flows
    Use Case

    Build Accelerated Compute-Intensive Applications

    Acceleration of complex workloads:
    - Patented core + co-processor boosting Machine Learning Inference
    - Computer Vision
    - Signal Processing (e.g. FFT), Cryptography, Mathematics
    .

    Build stand-alone intelligent embedded systems:
    - Multi-OS (Linux, RTOS) systems
    - Support ”Freedom from Interference” for mixed criticality
    .

    Build next gen Edge Computing Systems:
    - Process Data at the Intelligent Edge
    - Real-time analytics for automation, prediction, and control
    - Easy integration into existing systems
    .

  • Processor MPPA_HAND
    Use Case

    With MPPA® Processors, the Possibilities Are Endless Allowing You to Innovate Without Borders

    Powered by 80 cores, MPPA® processor is a new generation of intelligent processor with unique capabilities in terms of programmability, performance, parallel execution of multiple criticial tasks, energy efficiency, safety and security. Our breakthrough MPPA® technology is paving the way to a new data processing era.
    .

    The kind of intelligent processor that give you the power to do more. More to propel fast developing sectors from 5G telecom networks, autonomous vehicles all the way to healthcare equipment, industry 4.0, drones and robots ... and more!

Technical Corner / Key Features

    • 80-Core Architecture

      CORE

      64-bit/32-bit architecture
      From 600MHz to 1.2 GHz
      6-issue VLIW
      16KB instruction cache / 16KB data cache with MMU
      IEEE 754-2008 Floating Point Unit (FPU)
      Square root and reciprocal operations in floating single precision
      64-bit integer multiplication (Asymmetric cryptography)
      Up to 4 execution rings
      Up to 256-bits per cycle Load/Store

       

      CO-PROCESSOR (ONE PER CORE)

      Acceleration of INT8, INT16 or FP16 accuracy
      Up to 128 MAC per cycle

       

      CLUSTER

      16 Application Cores + 1 Management/Security Core
      4 MB of Memory / L2 Cache – 600GB/s Low Latency / High Speed
      Configurable cluster/chip cache coherency & deterministic modes

       

      SYSTEM-ON-CHIP

      5 clusters (total of 80 Application Cores + 5 Management Cores)
      Up to 1.15 TFLOPs (SP) / 384 GFLOPs (DP)
      Up to 3 TFLOPs (16 bits) / 25 TOPs (8bits) for deep learning
      56GB/s chip-to-chip communications (16 +12.5) x 2
      • PCIe Gen4 Interface

        16-lane PCIe GEN4 Endpoint (EP) or Root Complex (RC)
        Bifurcation up to 8 downstream ports in RC mode
        SR-IOV up to 8 Physical Functions / 248 Virtual Functions
        Address translation and protection
        Up to 2048 MSI-X & 64 MSI interrupts
        Support for Hot Plug
        Up to 512 DMAs for multi queues / kernel bypass drivers
        Direct PCIe-to-clusters and PCIe-to-DDR transfers
        Support for NVMe and VIRTIO emulation

         

      • LPDDR4/DDR4 Interface

        64-bit DDR4/LPDDR4-3200 channels with sideband/inline ECC
        Up to two ranks per DDR4 Channel
        2 DDR channels (up to 32GB) with channel interleaving

         

      • 2x100GbE Ethernet Interface

        8x1/8x10/8x25/2x40/4x50/2x100 GbE
        RDMA over Converged Ethernet (RoCE v1 and v2)
        Jumbo Frame Support (9.6KB)
        Support for PTP/IEEE 1588v2
        Priority Flow Control (PFC), IEEE 802.1Qbb
        Checksum offload Header & Payload
        Line rate packet classification/smart load balancing
        Hash & Round-robin based dispatch policy

         

      • Security

        Secure Boot with authentication & encryption
        True Random Number Generators (TRNG)
        RSA, Diffie-Hellman, DSA, ECC, EC-DSA and EC-DH acceleration

         

      • Cryptography Accelerators (optional)

        AES-128/192/256 (ECB/CBC/ICM/CTR/GCM/GMAC/CCM)
        AES-XTS for storage application
        MD5/SHA-1, SHA-2, SHA-3
        Kazumi/Snow 3G, ZUC

         

      • Management/Control Interfaces

        GPIOs/UARTs/SPI/I2C/CAN/PWM
        SSI Controller for serial NOR Flash with optional boot
        SDCARD UHS-I / eMMC 4.51 memory controller
        2x USB 2.0 OTG ULPI
        JTAG IEEE 1149.1
        16-bit Parallel Trace Interface

         

      • Safety & Predictability

        Mix criticality support
        Lockable critical configuration
        Capability to bank memory and caches for non-interference
        & time-predictable execution
        L1 Cache coherency enabling/disabling

         

    Get Started Now!

    Want to learn more about the MPPA®?

    Related Content

    • Product
      Kalray AccessCore Software
      AccessCore®

      Software development environment for developing applications using open coding standards on Kalray's processors.

      Read more
    • Product
      Kalray_K200 Board_1920x1281
      K200™ Cards

      Programmable, low-power PCIe board that can be used in accelerator or in standlone mode.

      Read more
    • Product
      Kalray's K200-LP low profile card
      K200-LP™ Cards

      Fully programmable cards that bring the benefits of the MPPA® DPU technology to data centers for higher performance & more flexible solutions.

      Read more