Skip to content

acl: introduce AVX512 classify methods

Konstantin Ananyev dpdk-dev 4 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v4 Latest14 patches 10 repliesIn review
  2. v314 patches 4 repliesSuperseded
  3. v212 patches 5 repliesSuperseded
Earlier versions · 1
VersionPostedPatchesRepliesStatus
v17 patches0 repliesSuperseded

Changes in v4 from the cover letter

Fix problems with meson 0.47
Updates to conform latest changes in the mainline (removal of RTE_MACHINE_CPUFLAG_*)
Fix checkpatch warnings

Patches in v4 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/14acl: fix x86 build when compiler doesn't support AVX2lib/librte_acl/rte_acl.c+1 -11 reply
2/14doc: fix missing classify methods in ACL guidedoc/guides/prog_guide/packet_classif_access_ctrl.rst+6 -01 reply
3/14acl: remove of unused enum valuedoc/guides/rel_notes/deprecation.rst doc/guides/rel_notes/release_20_11.rst lib/librte_acl/rte_acl.h+4 -50 replies
4/14acl: remove library constructorlib/librte_acl/rte_acl.c lib/librte_acl/rte_acl.h+132 -350 replies
5/14app/acl: few small improvementsapp/test-acl/main.c+10 -50 replies
6/14test/acl: expand classify test coverageapp/test/test_acl.c+51 -520 replies
7/14acl: add infrastructure to support AVX512 classifyconfig/x86/meson.build lib/librte_acl/acl.h lib/librte_acl/acl_run_avx512.c +3 more+131 -12 replies
8/14acl: introduce 256-bit width AVX512 classify implementationdoc/guides/prog_guide/packet_classif_access_ctrl.rst doc/guides/rel_notes/release_20_11.rst lib/librte_acl/acl.h +3 more+788 -10 replies
9/14acl: update default classify algorithm selectionlib/librte_acl/rte_acl.c+1 -00 replies
10/14acl: introduce 512-bit width AVX512 classify implementationdoc/guides/prog_guide/packet_classif_access_ctrl.rst doc/guides/rel_notes/release_20_11.rst lib/librte_acl/acl_run_avx512.c +1 more+750 -10 replies
11/14acl: for AVX512 classify use 4B load whenever possiblelib/librte_acl/acl.h lib/librte_acl/acl_bld.c lib/librte_acl/acl_run_avx512.c +3 more+46 -80 replies
12/14acl: deduplicate AVX512 code pathslib/librte_acl/acl_run_avx512_common.h lib/librte_acl/acl_run_avx512x16.h lib/librte_acl/acl_run_avx512x8.h+654 -9572 replies
13/14test/acl: add AVX512 classify supportapp/test/test_acl.c+4 -23 replies
14/14app/acl: add AVX512 classify supportapp/test-acl/main.c+8 -00 replies

Reviews trailers per patch

4 of 14 patches have a Reviewed-by or Acked-by.

PatchRuifeng WangBruce RichardsonDavid Marchand
1/14R-b
2/14R-b
3/14R-b
4/14
5/14
6/14
7/14A-b
8/14
9/14
10/14
11/14
12/14
13/14
14/14

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 3 reviewers.

Read the v4 thread

Cover letter [dpdk-dev] [PATCH v4 00/14] acl: introduce AVX512 classify methods

These patch series introduce support of AVX512 specific classify implementation for ACL library.
It adds two new algorithms:
- RTE_ACL_CLASSIFY_AVX512X16 - can process up to 16 flows in parallel. It uses 256-bit width instructions/registers only
(to avoid frequency level change).
On my SKX box test-acl shows ~15-30% improvement (depending on rule-set and input burst size)
when switching from AVX2 to AVX512X16 classify algorithms.
- RTE_ACL_CLASSIFY_AVX512X32 - can process up to 32 flows in parallel. It uses 512-bit width instructions/registers and provides higher performance then AVX512X16, but can cause frequency level change. On my SKX box test-acl shows ~50-70% improvement (depending on rule-set and input burst size)
when switching from AVX2 to AVX512X32 classify algorithms. ICX and CLX testing showed similar level of speedup.

Current AVX512 classify implementation is only supported on x86_64. Note that this series introduce a formal ABI incompatibility with previous versions of ACL library.

Depends-on: patch-79310 ("eal/x86: introduce AVX 512-bit type")

v3 -> v4
Fix problems with meson 0.47
Updates to conform latest changes in the mainline (removal of RTE_MACHINE_CPUFLAG_*)
Fix checkpatch warnings

v2 -> v3:
Fix checkpatch warnings
Split AVX512 algorithm into two and deduplicate common code
v1 -> v2:
Deduplicated 8/16 code paths as much as possible Updated default algorithm selection
Removed library constructor to make it easier integrate with
https://patches.dpdk.org/project/dpdk/list/?series=11831
Updated docs

Konstantin Ananyev (14):
acl: fix x86 build when compiler doesn't support AVX2
doc: fix missing classify methods in ACL guide
acl: remove of unused enum value
acl: remove library constructor
app/acl: few small improvements
test/acl: expand classify test coverage
acl: add infrastructure to support AVX512 classify
acl: introduce 256-bit width AVX512 classify implementation
acl: update default classify algorithm selection
acl: introduce 512-bit width AVX512 classify implementation
acl: for AVX512 classify use 4B load whenever possible
acl: deduplicate AVX512 code paths
test/acl: add AVX512 classify support
app/acl: add AVX512 classify support

 app/test-acl/main.c                           |  23 +-
 app/test/test_acl.c                           | 105 ++--
 config/x86/meson.build                        |   3 +-
 .../prog_guide/packet_classif_access_ctrl.rst |  20 +
 doc/guides/rel_notes/deprecation.rst          |   4 -
 doc/guides/rel_notes/release_20_11.rst        |  12 +
 lib/librte_acl/acl.h                          |  16 +
 lib/librte_acl/acl_bld.c                      |  34 ++
 lib/librte_acl/acl_gen.c                      |   2 +-
 lib/librte_acl/acl_run_avx512.c               | 164 ++++++
 lib/librte_acl/acl_run_avx512_common.h        | 477 ++++++++++++++++++
 lib/librte_acl/acl_run_avx512x16.h            | 341 +++++++++++++
 lib/librte_acl/acl_run_avx512x8.h             | 253 ++++++++++
 lib/librte_acl/meson.build                    |  48 ++
 lib/librte_acl/rte_acl.c                      | 212 ++++++--
 lib/librte_acl/rte_acl.h                      |   4 +-
 16 files changed, 1618 insertions(+), 100 deletions(-)
 create mode 100644 lib/librte_acl/acl_run_avx512.c
 create mode 100644 lib/librte_acl/acl_run_avx512_common.h
 create mode 100644 lib/librte_acl/acl_run_avx512x16.h
 create mode 100644 lib/librte_acl/acl_run_avx512x8.h
Signature · 1 line
2.17.1