iCubecorp MVP Harmony Unified Processor Technology

http://icubecorp.com

The Harmony Unified Processor Technology marks a milestone in the semiconductor industry by genuinely integrating two different processor types:

    • a central processing unit (CPU) and a graphics processing unit (GPU), into one unified core.
    • This technology consists of the Multi-Thread Virtual Pipeline parallel computing core, an independent instruction set architecture (ISA), an optimizing compiler and the Agile Switch dynamic load balancer.
    • It brings the most cost efficient and power efficient performance to the mobile computing and mobile communication markets
    • .  targeted to tap into the booming Android-based tablet computer market.
    • The Harmony Unified Processor Technology sets a new industry standard of performance by processing up to four threads (tasks) in each core.

Multi-thread Virtual Pipeline Processor

MVP Core Technology Specifications
  • A processor core based on parallel-computing with an integrated ISA
  • Up to 600 MHz. clock frequency on 65 nm process,4 threads
  • Super-scalar execution pipeline, offering sustainable performance of 2580 DMIPS (4.3 DMIPS/MHz) or 3.6 GFLOPS (6 MFLOPS/MHz.)
  • Up to 8 dynamically scheduled kernel instances with hardware load balancing and fine-grained simultaneous multithreading (SMT)
  • Data-parallel, task-parallel, and function-parallel computational models with minimum interrupts and context switches
  • 64KB I-Cache , 64KB D-Cache, 64KB SRAM and 32-bit GPR, 8-channel DMA and 16-source interrupt controller
  • Core area 3.0mm^2, including memory, with operating power of about 300mw
  • Support both homogeneous and heterogeneous parallel programming APIs through native compiler and MVP drivers

 

ICube’s IC1 Product Information

CPU

Dual-MVP
  • Simultaneously-multi-threading (SMT) to efficiently accelerate
  • Symmetrical-multi-processing (SMP)
  • Homogeneous parallel programs
  • Java applications
  • Support Pthread, OpenMP

GPU

  • Data parallel, Task parallel, and/or Function parallel computing as programmable unified shader, multi-standard and media processor, and heterogeneous GPGPU applications.
  • Support OpenGL ES2.0, OpenCL
  • 70 million triangles / sec,600 million pixel / sec
  • System Clock
    600Mhz
  • Multi-thread Processing
    Simultaneous 8 threads
  • Processing Power
    5160DMIPS, a peak performance similar to a 4.8GHz single serial core processor
  • Display System
    LCD: Maximum pixel clock: 165MHz@16.7M (24-bit) true color, HDMI/DVI output capable
  • Camera
    8/10 bit camera data interface
  • Video
    Support HD 720p H.264 decoding
  • Audio
    Max. 5.1 channel audio
  • Memory
    Support SD, HCSD, MMC card, USB mass storage device, Nand flash, NOR flash, DDR2 SDRAM
  • Power Control
    6 independent power domain, 3 low power modes
  • Supported OS
    Android, Embedded Linux
  • Supported Connectivity
    USB host/slave, WiFi, UART, 3G modem, GPS
  • Keypad
    12 keypad I/O for Qwerty keyboard

About laotsao 老曹

HopBit GridComputing LLC Rockscluster Gridengine Solaris Zone, Solaris Cluster, OVM SPARC/Ldom Exadata, SPARC SuperCluster
This entry was posted in china chip, General. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s