1. 20 Aug, 2018 2 commits
  2. 06 Aug, 2018 4 commits
    • Swann Perarnau's avatar
      [fix] Align mbind arguments properly. · 30d3840a
      Swann Perarnau authored
      mbind requires that the input ptr be aligned on a page.
      
      NOTE: we could also figure out a way to ask jemalloc
      for page-aligned allocations, but that would probably
      be too much for each alloc.
      30d3840a
    • Swann Perarnau's avatar
      [fix] Force mbind on allocation from arena · 759ec35a
      Swann Perarnau authored
      The way jemalloc handles big allocations can often result in surprising
      calls to mmap/mbind (splitting allocations, rounded up sizes). It also
      makes the path between an aml_alloc and mbind quite difficult to see.
      More worrying, if jemalloc reuses a previous allocation, the mbind will
      not be called again, which might result in the wrong binding happening.
      
      To fix those issues, we move the mbind logic to be around the
      allocations returned from jemalloc. This will ensure that we always bind
      properly. The only issue is that it might slow down allocations.
      
      It can also cause issues if the same arena is used by multiple areas, as
      allocations might be overlapping a page. We will move away from sharing
      arenas for benchmarks from now on.
      759ec35a
    • Swann Perarnau's avatar
      [feature/fix] add column-major 2D tiling · 9764f3c6
      Swann Perarnau authored
      Fix dgemm_noprefetch to match pattern from @suchyb in #19.
      In order to do so we split our 2d tiling into column-major and
      row-major ones. Note that those are refering to the order of the tiles,
      not the internal data of a tile, as a tiling should be agnostic to it.
      9764f3c6
    • Swann Perarnau's avatar
      [feature] add 2d tiling of contiguous tiles · 508c4695
      Swann Perarnau authored
      Add a tiling representing a 2d array of contiguous tiles. Also add a
      ndims function to retrieve the dimensions in tiles of the tiling.
      
      It also became quite obvious that the iterators are useless right now.
      We should think about changing that.
      508c4695
  3. 30 Jul, 2018 1 commit
  4. 25 Jul, 2018 2 commits
    • Brian Suchy's avatar
      [feature] add 2D tiling, additional methods. · a13ddad2
      Brian Suchy authored
      Implement a 2D tiling with continuous tiles in memory, with tiles
      organized in row-major order inside the virtual address range.
      
      Also adds functions to query the size of a tile inside the tiling.
      a13ddad2
    • Swann Perarnau's avatar
      [fix] Avoid conflicts when jemalloc is used twice · c1ec7da8
      Swann Perarnau authored
      When a code using aml is also linking against jemalloc, errors can occur
      because we use the default jemk prefix for the aml specific jemalloc
      install. To fix these issues, we instead use a prefix aml-specific.
      
      Discovered when using mkl on a knl box.
      c1ec7da8
  5. 05 Jul, 2018 1 commit
  6. 30 Mar, 2018 2 commits
    • Swann Perarnau's avatar
      [fix] unlocks are too early in dma_linux_* · c445b498
      Swann Perarnau authored
      We were unlocking the dma before the request type get set to a
      proper value, resulting in requests sometimes overlapping when
      multiple threads were used in benchmarks.
      c445b498
    • Swann Perarnau's avatar
      [feature] add function to release a scratch tile · 7260868d
      Swann Perarnau authored
      When a user doesn't need a tile to be pushed back into the scratchpad,
      it is better to just `release` that tile instead. This is particularly
      useful for read-only data for applications that are bandwidth limited.
      7260868d
  7. 29 Mar, 2018 2 commits
  8. 28 Mar, 2018 7 commits
    • Swann Perarnau's avatar
      [feature] make scratch_par thread-safe · 1e1f1ced
      Swann Perarnau authored
      Add mutex to make request creation and destruction thread-safe. As for
      scratch_seq, we need to deal both with requests and tiles during these
      functions, so we lock the entire section.
      1e1f1ced
    • Swann Perarnau's avatar
      [feature] make scratch_seq thread-safe · cd9dba51
      Swann Perarnau authored
      Add mutex to make request creation and destruction thread-safe. As we
      need to deal both we requests and tiles during these functions, we lock
      the entire section.
      cd9dba51
    • Swann Perarnau's avatar
      [feature] make dma_linux_par thread-safe · 7a69c840
      Swann Perarnau authored
      Add mutex to make request creation and destruction thread-safe. Same as
      dma_linux_seq, the changes are quite simple, as we only need to protect
      modifications to the requests array.
      7a69c840
    • Swann Perarnau's avatar
      [feature] make dma_linux_seq thread-safe · 9f2b685d
      Swann Perarnau authored
      Add a mutex to make request creation and destruction thread-safe. As the
      code here is quite simple, we only need to protect modifications to the
      request array.
      9f2b685d
    • Swann Perarnau's avatar
      [refactor] remove extra tiling from request · b52f0e52
      Swann Perarnau authored
      scratch_request_seq contains one extra tiling that is unnecessary.
      Remove it.
      b52f0e52
    • Swann Perarnau's avatar
      [refactor] remove unnecessary data from request · 22063684
      Swann Perarnau authored
      The request type contains two much stuff, remove extra pointers to win
      some space.
      22063684
    • Swann Perarnau's avatar
      [feature] add a pthread based scratchpad · fa51aea5
      Swann Perarnau authored
      Add a scratchpad that creates one pthread per request, to call
      synchronous dma operations.
      
      The intent is to end up with a cross product of programming language
      support between dma and scratch:
      - scratch_par + dma_seq gives users parallel scratch requests
      - scratch_seq + dma_par gives users sequential access to parallel moves
      
      The two other options don't make as much sense though.
      fa51aea5
  9. 27 Mar, 2018 3 commits
    • Swann Perarnau's avatar
      [refactor] use vector in scratch · 20354336
      Swann Perarnau authored
      Replace custom code with generic vectors for the scratch implementation.
      In the process, fix a bug in the management of tiles, as they were being
      freed on pull completion, which is wrong.
      20354336
    • Swann Perarnau's avatar
      [refactor] use request vector for dma · 61160adf
      Swann Perarnau authored
      Use the newly introduced vector type to manage requests inside dmas.
      This cleans up the API a bit, and remove dubious ops from the dma
      internals.
      61160adf
    • Swann Perarnau's avatar
      [feature] add generic vector type to library · 72c8508d
      Swann Perarnau authored
      Add a generic vector type to the library, with some special features:
      - the elements are embedded in the vector, and not pointers
      - each element must include an int field that is used as a "key"
      - the element has a "null" value for its key, used to indicate that this
      element of the vector is null.
      - add/remove functions provide access to a new element/free it from the
      vector, but don't "destroy" it.
      - resize on add is exponential.
      
      This patch includes implementation and unit test.
      72c8508d
  10. 26 Mar, 2018 2 commits
    • Swann Perarnau's avatar
      [feature] make scratchpad track its own tiles · be88fe46
      Swann Perarnau authored
      Move the scratchpad tiles into an internal concern:
      - the scratchpad does the allocation
      - the scratchpad tracks available tiles internally
      - the user can ask for the scratch baseptr.
      
      This is necessary to abstract move-based scratchs, and to remove from the
      user responsibility of maintaining tiling and baseptr tracking.
      
      We still fail-hard when tiles are not available, and the design is not
      thread safe. But we are getting there.
      be88fe46
    • Swann Perarnau's avatar
      [feature] add sequential, copy-based scratchpad · 73b57ae5
      Swann Perarnau authored
      This is the initial implementation and validation of a scratchpad: a
      logic unit that handles tracking data across a "main" area and a
      "scratch" area.
      
      The API and internals will probably change again soon, as there's no
      clear way to implement a move based scratchpad on this one.
      
      Note that this implementation doesn't do any tracking, not really, and
      that's the next step.
      73b57ae5
  11. 23 Mar, 2018 5 commits
    • Kamil Iskra's avatar
      [feature] support offsets for file mappings · b698c7eb
      Kamil Iskra authored
      Replace the unused "max" argument for file-based mappings with an offset
      argument (until now the offset was hardcoded to 0).
      b698c7eb
    • Swann Perarnau's avatar
      [test] add working test for dma_linux_par · 12e946e0
      Swann Perarnau authored
      Add working implementation of copy and move to dma_linux_par, and
      corresponding unit test.
      12e946e0
    • Swann Perarnau's avatar
      [fix] fix typos across dma_seq code · 7bfa666c
      Swann Perarnau authored
      Fix a few typos in the dma_linux_seq code, that for some reason didn't
      raise any flags so far. Also add a small validation to the unit test.
      7bfa666c
    • Swann Perarnau's avatar
      [feature] add parallel, on-demand dma · 428ec530
      Swann Perarnau authored
      Add a dma that spawns a fixed amount of theads for each request created.
      The number of threads is configured at dma creation time.
      428ec530
    • Swann Perarnau's avatar
      [refactor] remove generic functions from requests · 0a66735a
      Swann Perarnau authored
      This patch refactors dma request types to remove generic function
      pointers from the library. This include modifying the linux_seq
      implementation to:
      - move the copy/move implementation to the dma ops
      - remove one layer of indirection, as the request type no longer need
      _data and _ops substructures.
      
      Enforcing dma requests to have a fully qualified generic type, with
      function pointers, will cause issues for future kinds of dma
      implementation, that might require a different way of handling requests
      altogether.
      
      This work is driven by our current work on a parallel dma implementation.
      0a66735a
  12. 22 Mar, 2018 3 commits
  13. 11 Mar, 2018 4 commits
    • Swann Perarnau's avatar
      [feature] implement simple, working dma engine · 15cd651b
      Swann Perarnau authored
      This patch adds the basics for a dma interface, including
      type-dependent requests structures, and an API based on explicit
      copy/move calls.
      
      The APIs is flexible enough to deal with sync/async calls. The internal
      design is inspired by aml_area, with the goal that create/init stay type
      specific, but the core interactions are generic.
      15cd651b
    • Swann Perarnau's avatar
      [refactor/feature] change tilings to use uuids · 8a150cf2
      Swann Perarnau authored
      Using variable arguments on the tile id for retrieving tiling info makes
      the API difficult to use when more than one tile must be used at the
      same time.
      
      We change the API to use a tileid, with the assumption that any valuable
      tiling will be able to define a workable uuid scheme.
      8a150cf2
    • Swann Perarnau's avatar
      [features] add missing macros and prototypes · 24a640a2
      Swann Perarnau authored
      A few missing declarations in aml.h, to make it easier to deal with the
      library.
      24a640a2
    • Swann Perarnau's avatar
      [fix] area_binding should create the binding · f79e5b43
      Swann Perarnau authored
      As we cannot find out in advance the binding an area uses, it is not
      possible to use a correctly allocated pointer to aml_area_binding.
      
      Fixes a segfault we observed outside of current unit-tests.
      f79e5b43
  14. 08 Mar, 2018 2 commits