Re: [gem5-dev] Review Request 3751: ruby: Check all VNETs for injection in garnet NetworkInterface
--- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/3751/#review9198 --- Ship it! Ship It! - Jason Lowe-Power On Dec. 8, 2016, 11:32 p.m., Matthew Poremba wrote: > > --- > This is an automatically generated e-mail. To reply, visit: > http://reviews.gem5.org/r/3751/ > --- > > (Updated Dec. 8, 2016, 11:32 p.m.) > > > Review request for Default and Tushar Krishna. > > > Repository: gem5 > > > Description > --- > > Changeset 11758:a3f355233ef0 > --- > ruby: Check all VNETs for injection in garnet NetworkInterface > > The NetworkInterface wakeup currently iterates over all VNETs and breaks the > loop if a VNET is unable to allocate a VC. This can cause a deadlock if a > lower numbered VNET is unable to allocate a VC while a higher numbered VNET > has idle VCs. This seems like a bug as Garnet 1.0 uses a while loop over an > if-statement, suggesting the break was intended for this while loop. This > patch removes the break statement, which allows up to one message to be > dequeued from a VNET and injected into the network. > > > Diffs > - > > src/mem/ruby/network/garnet2.0/NetworkInterface.cc > 78ef8daecd81de0c392034809b3bc155396bf983 > > Diff: http://reviews.gem5.org/r/3751/diff/ > > > Testing > --- > > > Thanks, > > Matthew Poremba > > ___ gem5-dev mailing list gem5-dev@gem5.org http://m5sim.org/mailman/listinfo/gem5-dev
Re: [gem5-dev] Review Request 3751: ruby: Check all VNETs for injection in garnet NetworkInterface
--- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/3751/#review9194 --- Ship it! Ship It! - Tushar Krishna On Dec. 8, 2016, 11:32 p.m., Matthew Poremba wrote: > > --- > This is an automatically generated e-mail. To reply, visit: > http://reviews.gem5.org/r/3751/ > --- > > (Updated Dec. 8, 2016, 11:32 p.m.) > > > Review request for Default and Tushar Krishna. > > > Repository: gem5 > > > Description > --- > > Changeset 11758:a3f355233ef0 > --- > ruby: Check all VNETs for injection in garnet NetworkInterface > > The NetworkInterface wakeup currently iterates over all VNETs and breaks the > loop if a VNET is unable to allocate a VC. This can cause a deadlock if a > lower numbered VNET is unable to allocate a VC while a higher numbered VNET > has idle VCs. This seems like a bug as Garnet 1.0 uses a while loop over an > if-statement, suggesting the break was intended for this while loop. This > patch removes the break statement, which allows up to one message to be > dequeued from a VNET and injected into the network. > > > Diffs > - > > src/mem/ruby/network/garnet2.0/NetworkInterface.cc > 78ef8daecd81de0c392034809b3bc155396bf983 > > Diff: http://reviews.gem5.org/r/3751/diff/ > > > Testing > --- > > > Thanks, > > Matthew Poremba > > ___ gem5-dev mailing list gem5-dev@gem5.org http://m5sim.org/mailman/listinfo/gem5-dev
[gem5-dev] Review Request 3751: ruby: Check all VNETs for injection in garnet NetworkInterface
--- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/3751/ --- Review request for Default and Tushar Krishna. Repository: gem5 Description --- Changeset 11758:a3f355233ef0 --- ruby: Check all VNETs for injection in garnet NetworkInterface The NetworkInterface wakeup currently iterates over all VNETs and breaks the loop if a VNET is unable to allocate a VC. This can cause a deadlock if a lower numbered VNET is unable to allocate a VC while a higher numbered VNET has idle VCs. This seems like a bug as Garnet 1.0 uses a while loop over an if-statement, suggesting the break was intended for this while loop. This patch removes the break statement, which allows up to one message to be dequeued from a VNET and injected into the network. Diffs - src/mem/ruby/network/garnet2.0/NetworkInterface.cc 78ef8daecd81de0c392034809b3bc155396bf983 Diff: http://reviews.gem5.org/r/3751/diff/ Testing --- Thanks, Matthew Poremba ___ gem5-dev mailing list gem5-dev@gem5.org http://m5sim.org/mailman/listinfo/gem5-dev