Difference between revisions of "VPP/AArch64"
GabrielGanne (Talk | contribs) (→Meeting Minutes) |
GabrielGanne (Talk | contribs) m (→AArch64 Porting & Tuning) |
||
Line 172: | Line 172: | ||
| [https://jira.fd.io/browse/VPP-1066 VPP-1066] || Use ISB or YIELD on ARM64 | | [https://jira.fd.io/browse/VPP-1066 VPP-1066] || Use ISB or YIELD on ARM64 | ||
|- | |- | ||
− | | [https://jira.fd.io/browse/VPP-1067 VPP-1067] || Use REV on ARM64 [https://gerrit.fd.io/r/#/c/9505/ merged | + | | [https://jira.fd.io/browse/VPP-1067 VPP-1067] || Use REV on ARM64 [https://gerrit.fd.io/r/#/c/9505/ (merged)] |
− | + | ||
|} | |} | ||
Revision as of 15:32, 30 November 2017
Contents
Meeting Details
Weekly on Wednesdays, 8-9am PT. FD.io Zoom Meeting room
Join from PC, Mac, Linux, iOS or Android: https://zoom.us/j/5301185804 or https://zoom.us/my/fastdata Or iPhone one-tap (US Toll): +14086380968,,5301185804# or +16465588656,,5301185804# Or Telephone: Dial: +1 408 638 0968 (US Toll) or +1 646 558 8656 (US Toll) +1 855 880 1246 (US Toll Free) +1 877 369 0926 (US Toll Free) Meeting ID: 530 118 5804 International numbers available: https://zoom.us/zoomconference?m=ppBOQMQTVxGYmbxNsVemC6KNo8eX2ptF
IRC Channel
#fdio-arm
on freenode.net
Recent Patches
support modern device id | Merged 11/28 | https://gerrit.fd.io/r/#/c/9596/ |
enable crc32 on aarch64 (fixup) | Merged 11/15 | https://gerrit.fd.io/r/#/c/9418/ |
BIER tests fix | Merged 11/14 | https://gerrit.fd.io/r/#/c/9413/ |
Map SVM regions at a sane offset on arm64 | Merged 11/10 | https://gerrit.fd.io/r/#/c/9342/ |
bfd tests fix | Merged 11/07 | https://gerrit.fd.io/r/#/c/9243/ |
debian packaging fix | Merged 11/06 | https://gerrit.fd.io/r/#/c/9239/ |
lb test fix | Merged 10/31 | https://gerrit.fd.io/r/#/c/9067/ |
conditional x86intrin.h inclusion | Merged 10/25 | https://gerrit.fd.io/r/#/c/8952/ |
fix test_lb_ip4_gre6() cleanup (not enough to fix the tests completely) | Merged 10/24 | https://gerrit.fd.io/r/#/c/8992/ |
null-terminate some formatted string | Merged 10/20 | https://gerrit.fd.io/r/#/c/8922/ |
lb plugin - fix format() type mismatches | Merged 10/16 | https://gerrit.fd.io/r/#/c/8755/ |
Use AESNI=y only on x86_64 machines | Merged 10/14 | https://gerrit.fd.io/r/#/c/8622/ |
Improved arm64 chip detection | Merged 09/11 | https://gerrit.fd.io/r/#/c/8372/ |
Native arm64 build: dpdk/Makefile change | Merged 08/31 | https://gerrit.fd.io/r/#/c/8228/ |
Might want to have a look at this patch which adds "make config"
https://gerrit.fd.io/r/#/c/9200/
Also this other patch proposal (probably not as complete) allows to toggle off some parts of the code such as libvom, and therefore allows compilation on small systems
https://gerrit.fd.io/r/#/c/9186/
Known Issues
Compilation may fail on systems with less than 1GB memory per core. One workaround is to search for -j
in build-root/Makefile
and multiply by 1 instead of 2.
GCC 5.3.x ICEs during FP register allocation. Please use GCC 5.4+.
Unit tests
Cmd | Status / Issues |
---|---|
make test
|
1 |
make test-all
|
1 |
make test-debug
|
1, 2 |
make test-all-debug
|
1, 2 |
Timing consideration on platform: Hierofalcon with Cortex-A57 & Fedora 26
Cmd | Timing |
---|---|
make build
|
~12 min |
make build-release
|
~16 min |
make test
|
~20 min |
make test-debug
|
~23 min |
Issues
1. Random initialization failures; "Map SVM regions at a sane offset on arm64" is committed
2. Some tests need timeout finetuning:
Example test_cflow_packet:
assertAlmostEqual(cflow[IPFIX].exportTime, nowUTC, delta=5)
Test order
Some tests are not meant to be played alone.
For example the test_l2bd_arp_term_\d+ list
- test_1: create 5 hosts
- test_2: delete 3 of the hosts created by test_1
...
Those tests should be played grouped. For example in the case above ;
# works make test TEST=*.TestL2bdArpTerm.* # does not work make test V=1 TEST=*.TestL2bdArpTerm.test_l2bd_arp_term_01 make test V=1 TEST=*.TestL2bdArpTerm.test_l2bd_arp_term_02 ...
Packaging
Distro | Cmd | Status |
---|---|---|
Fedora 26 (Server Edition) | make pkg-rpm
|
OK |
Ubuntu 17.10 | make pkg-deb
|
OK |
Ubuntu 16.04.3 LTS | make pkg-deb
|
OK |
CSIT func & perf
https://wiki.fd.io/view/CSIT/AArch64#TODO
AArch64 Porting & Tuning
VPP-1064 | Support multiple cache line sizes per architecture. AArch64 is currently hard coded to 128B. For native build, inspect ARMv8 Main ID Register in Makefile and pass cache line size as compiler option, e.g. -DCACHE_LINE_SIZE=128
|
VPP-1065 | Investigate "show cpu" output and Arm CPU feature detection (AES, SHA1, SHA2, CRC32, ATOMICS) via hwcaps. src/vppinfra/cpu.[ch]
|
VPP-1066 | Use ISB or YIELD on ARM64 |
VPP-1067 | Use REV on ARM64 (merged) |
- Review use of Arm architected timer in
src/vppinfra/time.[ch]
Review use of __sync_xxx
/__atomic_xxx
builtins to ensure correct memory ordering on non-TSO machines.
- Investigate hash performance (CRC32 vs xxhash) e.g. in
src/vppinfra/bihash_8_8.h
. Dependent on Arm CPU feature detection.
Investigate memcpy performance (src/vppinfra/string.h
); both inlined-by-compiler and libc versions.
Investigate dual/quad loop tuning, e.g. l2_forward().
SIMD
- CLIB_HAVE_VEC128 also covers 256-bit. Add CLIB_HAVE_VEC256?
- ixge.[ch] - 128-bit vector types with plain C. Needs to be enabled.
- mheap.c - requires NEON implementation of
is_equal
- hash.h - requires NEON implementation of
irotate
- vnet_classify.h - 128-bit vector types with plain C. Needs to be enabled.
- vhost-user.c - SSE4.2 only. Implement range search using NEON.
- ip4_mtrie.h - 128-bit vector types with plain C. Needs to be enabled.
Meeting Minutes
11/29/2017
- Can we access the OD1000 in csit lab ?
- currently mainly working with VMs
- added dedicated wiki page for CSIT : https://wiki.fd.io/view/CSIT/AArch64
- WIP : https://gerrit.fd.io/r/#/c/9474/
11/22/2017
- VPP CI
- 3 ThunderX for Chrismas
- CSIT
- func on VM vs perfs on HW
- func on x86 VMs OK with 2 nodes
- DPDK integration WIP : https://gerrit.fd.io/r/#/c/9474/
- issues
- how to access the lab ?
- Next steps
- VPP
- CSIT
- structure work & send email (Gabriel)
- is xxhash vs crc32 finished ? (Gabriel)
- ask Maciek & setup a presentation meeting with someone from CSIT (Tina)
- find a time to reschedule this meeting before the CSIT weekly call (Brian)
11/15/2017
- VPP upstream status
- build && build-release OK
- "make test" && "make test-debug" OK
- packaging:
- Ubuntu 16.04 OK
- Ubuntu 17.10 ? (TBC)
- fedora-26 OK
- vpp continuous test
- all task required for jenkin's "verify" job are ready
- TODO: request gerrit hook to Dave Barachs / vpp-dev (NB & GG)
- set up ci in fdio lab
- CSIT
- setting up env
- ThunderX platforms should arrive this week
- csit work sharing
11/8/2017
- Unit tests
- Tests pass except for random initialization failures
- Need to hear back from upstream about Extended unit tests
- Should we run plugins such as NSH SFC?
- Hardware to lab
- Huawei h/w stalled
- 3x ThunderX shipping to FD.io lab
- CSIT replication
- Cavium replicating on ThunderX2; getting started
- Let's track our work in Jira; Brian to migrate tasks to Jira
10/25/2017
- Gabriel working on vpp init failure in linux_pci_init()
- Kumar to check with GeorgeZ on Huawei boards shipped to CSIT; need to verify tests also on this environment (package versions from distro)
- Brian to check whether anything else needs to be done besides 'make test' for upstream enablement