Featured Articles
Announcing Pi
Technical Specifications
Raspberry Pi FAQs
Win a Pi
Raspberry Pi Wishlist
Actions
Forum Thread Details
  • Replies 8 replies
  • Subscribers 676 subscribers
  • Views 1342 views
  • Users 0 members are here
Related

What does 24GFLOPs GPU speed mean?

Former Member

The 3rd bullet at: 

http://www.element14.com/community/docs/DOC-52938/l/raspberry-pi-model-a--now-available-in-eu

 

says GPU is capable of 24GFLOPs. 

Is this single-precision or double-precision?

Is it sustained or burst-mode only?

Does it rely on operands being in cache memory?

What clock frequency is the GPU?

How many parallel functional units?

What benchmark is used to measure the speed?

 

Parents

  • The core has a 3D hardware acccelerator which consists of a bundle of procesors each capable of running SIMD (Single intruction mulitple data) 32-bit floating point calculations. If you multiply the processors, the data words and the clock you get the 24Gflops/sec.

     

    Post edit: forgot that this is alongside the GPU itself which has a vector floating point processor which does 32, 64 or 80 bit precision floating point operations.

    Which again is along side two general purpose (integer) cores. All of that is working with special H264 hardware accelrated video encode/decode HW and a plethora of other special multi-media cores.

  • in reply to Former Member

    Gert,

      Thanks for the reply.

    We've been told previously that the GPU has a vector unit, but that

    it is integer only, so it wouldn't be possible to develop floating-point

    libraries, such as BLAS.  James wrote:

     

      "BLAS has lots of floating point, and the vector core is integer only unfortunately.

      I'll take a look at the interfaces posted though - should save a bit of specing time."

    http://www.raspberrypi.org/phpBB3/viewtopic.php?p=14633

     

    So is there a vector floating-point unit in addition to a vector

    integer unit?  And if so, would it be theoretically possible to

    develop libraries like BLAS that could demonstrate something

    close to 24GFLOPS?

Reply
  • in reply to Former Member

    Gert,

      Thanks for the reply.

    We've been told previously that the GPU has a vector unit, but that

    it is integer only, so it wouldn't be possible to develop floating-point

    libraries, such as BLAS.  James wrote:

     

      "BLAS has lots of floating point, and the vector core is integer only unfortunately.

      I'll take a look at the interfaces posted though - should save a bit of specing time."

    http://www.raspberrypi.org/phpBB3/viewtopic.php?p=14633

     

    So is there a vector floating-point unit in addition to a vector

    integer unit?  And if so, would it be theoretically possible to

    develop libraries like BLAS that could demonstrate something

    close to 24GFLOPS?

Children
No Data