Age | Commit message (Collapse) | Author | Files | Lines |
|
Change-Id: If23a04623a7138c9f6c98ee9ecfa587396618a60
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
The macro for x86 platform is wrong, and the patch fixes it.
Change-Id: I4f0ed254b177d6863fbe9113308c6a8b4478e0b2
Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com>
|
|
Change-Id: I6934beaf5c08bae2d4f0bd3a6bb811810407c1f9
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
A simple memcmp won't work when comparing pointer-keys, such as those
used by the bihash_vec8_8.h template.
Change-Id: I77e59f3fd7f7740ef42908ace90ed4843e1c9ac7
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I26c704ec27b8f5431faef08156778f53ea454269
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I81bd967a580ae3b476dfd731e9933a9898568a91
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ie504603c2e42cae3ad592952b2b166919420e5f7
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Problems Addressed:
- Contention of cursize by producer and consumer.
- Reduce the no of modulo operations.
Changes:
- Synchronization between producer and consumer changed from cursize
to head and tail indexes
Implications: reduces the usable size of fifo by 1.
- Using weaker memory ordering C++11 atomics to access head and tail
based on producer and consumer role.
- Head and tail indexes are unsigned 32 bit integers. Additions and
subtraction on them are implicit 32 bit Modulo operation.
- Adding weaker memory ordering variants of max_enq, max_deq, is_empty
and is_full Using them appropriately in all places.
Perfomance improvement (iperf3 via Hoststack):
iperf3 Server: Marvell ThunderX2(AArch64) - iperf3 Client: Skylake(x86)
~6%(256 rxd/txd) - ~11%(2048 rxd/txd)
Change-Id: I1d484e000e437430fdd5a819657d1c6b62443018
Signed-off-by: Sirshak Das <sirshak.das@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
|
|
Algorithm from CLRS, Introduction to Algorithms 3rd Edition, Ch. 13
Change-Id: I5bc2c507593770939cd5584f21dacf36ebd2b4c1
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I54d6fb1a2721b548620eb66cea254d0103deca32
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Iefe9d20799a6f5f271aa5b675ea2b19ac3efbe1e
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
when mspace_get_aligned try to malloc a chunk with align greater than 16
Change-Id: Ic3b91fc9532248482662f019bbfa073da18645ed
Signed-off-by: Wei CHEN <weichen@astri.org>
|
|
Change-Id: I33cd6e44d126c73c1f4c16b2041ea607b4d7f39f
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I7d39cb184f1f9ad24276183c29969327681a1f82
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I2294982e6df41a13e61783e18f947da0bdd4b499
Signed-off-by: Dave Wallace <dwallacelf@gmail.com>
|
|
Change-Id: I38e0be777199654ece286fdd1a42931ed99bbe8a
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
nonexistent elements
If we are testing for an index whose membership bitmask happens to sit in LSB of uword,
and there is nothing else set in that uword in the member bitmask, the shortcut path
returning the valid index is taken even if the element with a given index doesn't
exist in the sparse vector. This happens because the count of leading zeroes on the
value of 0 is zero, which is equal to the value taken modulo bitsize uword.
Take care of that case.
Also add unittests showing the problem and verifying that sparse_vec_index2 does not
have the same issue.
Change-Id: I19117e13817c3e5de579b9250bb741de42491985
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
|
|
Change-Id: I52198e97397bb6f3b5c0c30c44aac34c17650d4d
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: Ic2a61c45face18b6dd23d5509d75367d3b2441e9
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ia88c7228a46e251b8a7815240da6ddbbcde08bc7
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: Id4a8b6a31fc3e88af2f075cb97c85d3f9b738d9e
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ibe7f806b9d600994e83c9f1be526fdb0a1ef1833
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Iea2c173000570043beafef58ca923463ce76d872
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I0ed28846060a774b1f6cdc1e4e5974a7e16f9f16
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I79f65d7bd19af035442dca48b7be6c94de20c167
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
int vaddvq_u8 (uint8x16_t __a) is not appropriate to implement xxx_is_all_zero,
as there may be overflow causing incorrect return value.
Here's an example.
u8x16 x = {0 <repeats 12 times>, 1, 255, 0, 0};
Change-Id: Ia6a10bdf8da360dec12db902d028751a1a77e9a4
Signed-off-by: Lijian Zhang <Lijian.Zhang@arm.com>
Reviewed-by: Sirshak Das <Sirshak.Das@arm.com>
|
|
Change-Id: Ibfdcec60567ec357205fa137257f2d8cba44b01c
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Icc9bef32d1bb2b8f277598c50c69343c81f22cd2
Signed-off-by: Tom Seidenberg <tseidenb@cisco.com>
|
|
Use of scalar AVX512 instructions impacts the maximum CPU frequency
as they require CPU to request level 1 power license.
So sparse use of AVX512 like we do, typically causes more harm than
improvement.
This patch makes AVX2 higher priority than AVX512, but still there
is option to change it on per-node basis:
vpp# set node function ethernet-input avx512
Change-Id: I42e03510a6efc1756e22fbb70e8c76d7f74f59d7
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I8b59b2e1c0525abf4b0492e50a7af57df4cd3ce2
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
mmap does not fail but writing to mapped memory is causing sigbus.
Change-Id: I5135f32eede67fccb4aaa07a501cd262d254ed8d
Signed-off-by: Artem Belov <artem.belov@xored.com>
|
|
Some x86 CPUs have IOMMU capable dealing only with 39-bit address space
This patch also adds option to specify physmem base address from
startup.conf
Change-Id: I9e8abd26efb60e9c4ad54c035fb1751a4a61f4dc
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
It is causing compilation sloness with gcc-7 so removing it
before it was originally planned.
So far macros are left in the tree so we can know which nodes to
convert to new multiarch code.
Change-Id: Idb14622ca61fdce1eba59723b20d98715b7971e6
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
This patch introduces following changes:
- deprecated free lists which are not used and not compatible
with external buffer managers (i.e. DPDK)
- introduces native support for per-numa buffer pools
- significantly improves performance of buffer alloc and free
Change-Id: I4a8e723ae47056717afd6cac0efe87cb731b5be7
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I79b213b34c6071d14acf1922f89037a4a5a36c45
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: Ic141162acaf39878ab978a997e3f6757d4f7c240
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I975d46a82e9f884a9cd0ac2bd5f57181695f4124
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
The 'example' keyword triggers the creation of very out-of-context
example in the "Examples" top level of documentation. Rename the
keyword in the comment so the comment is still readable, but
does not trigger the doxygen.
Change-Id: Iecbdc236918f9178a034817aa6cea7ab6b2c1654
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
(cherry picked from commit 1705599efe5eec09c09d2214da776d92d0e4f1cf)
|
|
Change-Id: If88ccd965122b9318a39a8d71b53334cd1fd81e4
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I3bab0ab05b4f552ad64392439fb48409ab0ab8c0
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Storing buffer in local template seems to be better option....
Change-Id: I1a2fdd68cb956f99a5b36d2cd810fc623e089bcf
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I721542aca139d7908a4f917629856f82cae79962
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Given n equals to the maximum number of bytes to copy from src in the API,
or the rough estimate strlen of src, strncpy_s_inline should not copy more
than the number of bytes, computed by strlen(src), to dst if n is greater than
strlen(src). The number of bytes to copy is computed by strnlen(src,n), not n.
Change-Id: I088b46125d9776962750e121f1fbf441952efc2b
Signed-off-by: Steven <sluong@cisco.com>
|
|
Change-Id: Ia34a4278eedc8cf450688b1fa0291e1f976868d3
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
* u32/u64/uword mismatches
* pointer-to-int fixes
* printf formatting issues
* issues with incorrect "ULL" and related suffixes
* structure alignment and padding issues
Change-Id: I70b989007758755fe8211c074f651150680f60b4
Signed-off-by: David Johnson <davijoh3@cisco.com>
|
|
Change-Id: I31a3ff9e8f70468196c091027592a3aed2d09ac3
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
With this simple tweak, vpp is OK for "make test" or non-dpdk driver
operation over a kernel which doesn't support hugepages at all.
Tested on a Raspberry-pi 3B+ running the Ubuntu 18.04 64-bit server
beta image. It's amazing that such a minimal system will not only
self-compile vpp, but also run the unit tests. It's slow, but what do
you expect for that amount of money?
Change-Id: I7f080f871c828cc4b44be13809495278fadbd717
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I188e2dfd187d7b2ab7e0fbb11461f3db052f3224
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I1f42644f143bb65ee764c0f869b402595126adac
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: If5c44241577bc5a42d33f1ec5a62097974d6fda8
Signed-off-by: Florin Coras <fcoras@cisco.com>
|