Open MPI User's Mailing List Archives

Subject: Re: [OMPI users] SM btl slows down bandwidth?
From: Ron Brightwell (rbbrigh_at_[hidden])
Date: 2008-08-13 11:46:34

• Next message: Yvan Fournier: "[OMPI users] bug in MPI_File_get_position_shared ?"
• Previous message: Tom Riddle: "Re: [OMPI users] MPI_ERR_TRUNCATE with MPI_Revc without Infinipath"
• Maybe in reply to: Daniël Mantione: "[OMPI users] SM btl slows down bandwidth?"
• Next in thread: Jeff Squyres: "Re: [OMPI users] SM btl slows down bandwidth?"
• Reply: Jeff Squyres: "Re: [OMPI users] SM btl slows down bandwidth?"

> [...]
>
> MPICH2 manages to get about 5GB/s in shared memory performance on the
> Xeon 5420 system.

Does the sm btl use a memcpy with non-temporal stores like MPICH2?
This can be a big win for bandwidth benchmarks that don't actually
touch their receive buffers at all...

-Ron

• Next message: Yvan Fournier: "[OMPI users] bug in MPI_File_get_position_shared ?"
• Previous message: Tom Riddle: "Re: [OMPI users] MPI_ERR_TRUNCATE with MPI_Revc without Infinipath"
• Maybe in reply to: Daniël Mantione: "[OMPI users] SM btl slows down bandwidth?"
• Next in thread: Jeff Squyres: "Re: [OMPI users] SM btl slows down bandwidth?"
• Reply: Jeff Squyres: "Re: [OMPI users] SM btl slows down bandwidth?"