You are viewing a plain text version of this content. The canonical link for it is here.

Posted to discuss-archive@tvm.apache.org by zj via TVM Discuss <no...@discuss.tvm.ai> on 2020/08/31 08:17:47 UTC

[TVM Discuss] [Questions] How do parallelism run


hi
I am new learner to TVM and VTA. What confuse me is how parallelism run? I may get the idea of it with virtual and block diagram in VTA paper, but the code in vta-hw/src confuse me, as in that code, module load, compute and store are serialized. What is my problem? I will appreciate if any clue you would provide me.

best regards





---
[Visit Topic](https://discuss.tvm.ai/t/how-do-parallelism-run/7768/1) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/58eb9b62307ae16ee4d9b7ed96f23607e52617fa11059830a36b52ec6742292c).

[TVM Discuss] [Questions] How do parallelism run

Posted by zj via TVM Discuss <no...@discuss.tvm.ai>.


Very appreciate @hjiang, that’s the key point. Your recommendation is my top consideration to deep into study. Here is another issue to understand why there is two dependence queues(fifo) between modules? In the perspective of software multi threads coding, that require only one queue which is read by consumer and wrote by producer, and another extra work is to locked the queue before accessed, for getting out of bank conflict.

Best regards





---
[Visit Topic](https://discuss.tvm.ai/t/how-do-parallelism-run/7768/3) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/e244c69d3a7b0a67d06adb134c3fa8cb71561aa01cf136cb404fc5bc536c3d0e).

[TVM Discuss] [Questions] How do parallelism run

Posted by huajsj via TVM Discuss <no...@discuss.tvm.ai>.


Hi Paddi,

Good to know have interest with VTA and TLPP, about your question load/compute/store are serialized, I think you may means the logic in 
unit test function VTA(),  the VTA(...) actually is not get involved when
FPGA do real compute and such function only work when do unit test,

For the running time VTA FPGA logic for sure it is parallel and the TLPP
logic already there, I would recommend you go through FSIM source code
first which have a software level simulation for TLPP  maybe more 
straightforward for understanding.

Regards

Hua





---
[Visit Topic](https://discuss.tvm.ai/t/how-do-parallelism-run/7768/2) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/b2b672ff9cadd4f8e5c73882bbf6b8f54077762df3bd54337a8e18287b1d2d31).