• State Accepted Answer
  • +1 person also asked this people also asked this
  • Locked Locked
  • Replies 12 replies
  • Subscribers 137 subscribers
  • Views 3539 views
  • Users 0 members are here
Options
Related
How was your experience today?
This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

confusion of fp32 operations per cycle

Venkatesh K R

Hello community,

In GPU datasheet, the fp32 operations per cycle is 256 for immortalis-g715. Is this for all 16 cores or 1 core only?

Thanks,

Venkatesh.

Parents
  • 0 Arm Employee Badge in reply to Venkatesh K R

    Industry convention for GPUs is to only count FMAs, and count them as two operations (mul + add), so the data sheet saying 256 fp32 ops/cy means that each shader core can do 128 fp32 FMA operations per clock cycle. These numbers completely ignore the CVT and SFU units.

    Whether you get more than 256 ops/cy because of the CVT and SFU units depends on the operation and GPU generation. Some can issue in parallel, some can't,  as we continuously rebalance the shader core design to get the right balance of operations for industry content trends and to optimize for energy efficiency. 

Reply
  • 0 Arm Employee Badge in reply to Venkatesh K R

    Industry convention for GPUs is to only count FMAs, and count them as two operations (mul + add), so the data sheet saying 256 fp32 ops/cy means that each shader core can do 128 fp32 FMA operations per clock cycle. These numbers completely ignore the CVT and SFU units.

    Whether you get more than 256 ops/cy because of the CVT and SFU units depends on the operation and GPU generation. Some can issue in parallel, some can't,  as we continuously rebalance the shader core design to get the right balance of operations for industry content trends and to optimize for energy efficiency. 

Children