elias94
New ContributorJoined 5 years ago
User Profile
New Contributor
User Widgets
Contributions
Re: low occupancy of the DDR in HAN Pilot platform with opencl
Hi @BoonBengT_Intel Thank you for your answer the version is the 19.1 and i use the traditional profiler (../altera/quartus19.1/hld/bin/aoc -board=a10s_ddr device/vector_add.cl -o bin/vector_add.aocx -profile) Best regards Ilias3.9KViews0likes0CommentsRe: low occupancy of the DDR in HAN Pilot platform with opencl
Hi @BoonBengT_Altera Thank you for your answer. I have a simple vectorized code where i do 4 consecutive reads and then i write them back (4 writes) in the DDR with a clock frequency of 360 MHZ and i only achieve 10.6% occupancy for the read with a bandwidth of 612MB/s and the same for the writes (i used the profiler). I have also 50% stalls . When i lower the frequency (for example 200 MHZ, i lower the frequency by inserting shift registers) and increase vectorization for example 8 or 16 i get at most an occupancy of 25% and a bandwdith of 1600 MB/s for both reads and writes respectively. I have no stalls at all. The trip count for my loops is the same so i cant see how the link you sent to me can help me Best Wishes elias944KViews0likes0CommentsRe: low occupancy of the DDR in HAN Pilot platform with opencl
Hi Adzim No, it is not a Terasic design. I modified and used the vector_add design provided by intel (examples_aoc). The occupancy that i achieve with one 1 read and 1 write is 77%. But when i increase the reads and writes in parallel, (for example 2,4,8,16) my occupancy is always lower than 30%4.2KViews0likes0Commentslow occupancy of the DDR in HAN Pilot platform with opencl
I have a simple vectorized code with just 4 reads and 4 writes in the DDR with a clock frequency of 360 MHZ and i only achieve 10.6% occupancy for the read with a bandwidth of 612MB/s and the same for the writes. When i lower the frequency (for example 200 MHZ) and increase vectorization for example 8 or 16 i get at most an occupancy of 25% and a bandwdith of 1600 MB/s for both reads and writes respectively. The fpga that i use is the han pilot platform. Is there a way that i can increase the occupancy? I attach the .cl and host file.4.4KViews0likes11Comments