Cronologia Commit

Autore SHA1 Messaggio Data
  Samuel Thibault f8c7102131 Add missing break 10 anni fa
  Samuel Thibault ecc274e4c0 Distinguish between fetches, prefetches and idle fetches in the paje trace 10 anni fa
  Samuel Thibault 419f4e392c TODOs 10 anni fa
  Samuel Thibault 90bf39960e Vastly improve simgrid simulation time by using wake queues 10 anni fa
  Samuel Thibault d06eb3bbd4 Make reclaiming prevent more fetches on the node being cleaned up, to avoid permanent battle between them 10 anni fa
  Samuel Thibault 8a0144e402 fix crash when an interface without any_to_any is used with disks 10 anni fa
  Samuel Thibault fc5aa874a0 port r15822 from 1.2: fix small issues 10 anni fa
  Samuel Thibault 1683d35a0d Fix msg.h inclusion according to new location 10 anni fa
  Samuel Thibault c8efbb83e8 Inline list heads instead of keeping allocating them 10 anni fa
  Nathalie Furmento bb61f3808d update cnrs copyright 11 anni fa
  Samuel Thibault f7ab9f4b09 Drop assertion when running with CUDA peer support in simgrid mode 11 anni fa
  Samuel Thibault 51e895087b Fix and test disk support with pack/unpack-only interfaces 11 anni fa
  Samuel Thibault aba9b7562b Make disk test actually test all backends. Partly revert r13785 which was using a union as a structure. 11 anni fa
  Samuel Thibault ae1892fa7f Improve the disk documentation, and clean the interface a bit 11 anni fa
  Samuel Thibault 4b1a16edde Fix University name after the fusion.. 11 anni fa
  Samuel Thibault fa816b7fb8 Fix device selection when issuing a gpu-gpu transfer from the source 11 anni fa
  Samuel Thibault 6a0c92daab Avoid void* arithmetic, icc refuses it on windows... 11 anni fa
  Samuel Thibault 7240b27585 port r12759 from 1.1: Make sure we use the local stream, and not the stream of another device. Define separate streams for GPU-GPU transfers, depending on which device emits it 11 anni fa
  Samuel Thibault f255d2c95a port r12703 from 1.1: Allow data to be uninitialized but the application provide an init_cl to initialize it 11 anni fa
  Samuel Thibault f2b1d0f595 port r12584 from 1.1: Re-enable asynchronous transfers from CPUs, now that the issue has been found to be in application code 11 anni fa
  Samuel Thibault 2963604386 port r12554 from 1.1: Disable timing on events for transfers, we don't use it 12 anni fa
  Samuel Thibault 058e113825 port r12533 from 1.1: Do not let non-CUDA workers use non-0 streams, CUDA seems not very threadsafe with that. Make the coherency engine avoid selecting non-CUDA workers to issue transfers, to avoid letting them use the 0 stream. 12 anni fa
  Samuel Thibault b4976f3d00 Use different streams for gpu-gpu transfers 12 anni fa
  Samuel Thibault c77d312268 port r 11535 from 1.1: Add missing termination of data transfers for reclaiming write-back 12 anni fa
  Samuel Thibault b5a335e425 really disable disk aio support 12 anni fa
  Samuel Thibault a0d8553193 Make disk aio take asynchronous_copy_disable flag into account 12 anni fa
  Samuel Thibault 305df11e1f Drop spurious changes 12 anni fa
  Corentin Salingue e66c1994ff add support pack/unpack for out-of-core 12 anni fa
  Corentin Salingue aa9ac54085 begin to add pack/unpack 12 anni fa
  Corentin Salingue 0d30c96822 fix bug for asynchronous input/output, it runs 12 anni fa