Hi:
If the L1P, L1D and L2 on C674x on the OMAPL138/L132 are programmed as SRAMs, instead of cache memories, then do they all have the same speed or is the L1 SRAM faster than the L2 SRAM?
Thanks a lot!
Cheers,
Mushtaq
This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
Hi:
If the L1P, L1D and L2 on C674x on the OMAPL138/L132 are programmed as SRAMs, instead of cache memories, then do they all have the same speed or is the L1 SRAM faster than the L2 SRAM?
Thanks a lot!
Cheers,
Mushtaq
You'll achieve single cycle access to L1. A cache miss will be about 10 cycles to fetch from L2. An L2 miss will be 100-200 cycles. I strongly suggest keeping at least some amount of L1 cache in the system if you are dealing with any external memory.
Hi Brad:
Thanks a lot!
I am wondering if the numbers you have quoted are for L1 and L2 programmed as cache memories. Is this correct?
We wont be using external memories. We want to use the L1 and L2 memories as SRAMs. Then will we have single cycle access to both the SRAMS?
Thanks a lot!
Cheers,
Mushtaq
See Table 3-2. L1D Performance Parameters (Number of Stalls) of the Cache User's Guide.