Commit Graph

1871 Commits

Author SHA1 Message Date
verwaest@chromium.org
88b8715f95 Load/Store stub compilation refactoring.
Review URL: https://chromiumcodereview.appspot.com/12426008

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13954 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-15 12:07:35 +00:00
svenpanne@chromium.org
308e665982 Pass Isolate through CompilingCallsToThisStubIsGCSafe calls
BUG=v8:2487

Review URL: https://codereview.chromium.org/12732010

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13950 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-15 11:52:58 +00:00
ulan@chromium.org
80f490085f ARM: Tweak ECMAToInt32VFP to address regression on Nexus 4
After r13912, we saw a small regression in Kraken crypto-aes and
crypto-ccm on Nexus 4. This patch, proposed by Rodolph Perfetta,
addresses that without regressing other platforms.

Instead of looking at the exponent of double_input and trying to figure
out if the conversion will overflow, eagerly do the VCVT and return
early unless it saturated.

BUG=none

Review URL: https://chromiumcodereview.appspot.com/12544025
Patch from Hans Wennborg <hans@chromium.org>.

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13948 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-14 15:28:15 +00:00
svenpanne@chromium.org
aaf6340eb3 Fixed two register allocator bugs (off-by-one error/failure propagation).
Minor cleanups on the way, e.g. making sure that we never use something after an allocation failed. Style question: Should we switch to some kind of MUST_USE_RESULT-style to ensure that we handle failures consistently? Not sure...

BUG=v8:2576

Review URL: https://codereview.chromium.org/12867002

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13946 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-14 14:42:00 +00:00
hpayer@chromium.org
05a71fc9e4 Allow direct allocation in old pointer space.
BUG=

Review URL: https://codereview.chromium.org/12314155

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13940 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-14 08:32:52 +00:00
dcarney@chromium.org
fbe34d4ba5 remove latin-1 flag
R=yangguo@chromium.org
BUG=

Review URL: https://codereview.chromium.org/12700008

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13939 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-13 20:04:50 +00:00
yangguo@chromium.org
a722726dc4 Parallel recompilation: fewer handle dereferences and tighter checks.
BUG=

Review URL: https://chromiumcodereview.appspot.com/12832002

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13935 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-13 16:13:05 +00:00
verwaest@chromium.org
569d9c59b9 Refactoring Store ICs. A first step towards polymorphic store ICs.
Review URL: https://chromiumcodereview.appspot.com/12781004

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13934 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-13 14:11:05 +00:00
danno@chromium.org
cfb957af15 Use IsRuntimeEntry for RUNTIME_ENTRY comparison
Review URL: https://codereview.chromium.org/12702005
Patch from Haitao Feng <haitao.feng@intel.com>.

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13929 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-13 11:40:26 +00:00
mvstanton@chromium.org
30ca31f470 HInnerAllocatedObject instruction allows hydrogen code to carve up
allocated regions into sub objects.

BUG=

Review URL: https://codereview.chromium.org/12812002

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13928 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-13 11:05:48 +00:00
yangguo@chromium.org
479e39a058 Parallel recompilation: remove interrupt for code generation.
R=jkummerow@chromium.org
BUG=

Review URL: https://chromiumcodereview.appspot.com/12488006

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13917 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-12 18:03:18 +00:00
rodolph.perfetta@gmail.com
1c6d5e4cf4 ARM: Optimsisation of ECMA ToInt32.
BUG=none
TEST=none

Review URL: https://codereview.chromium.org/12567004

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13912 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-12 11:25:50 +00:00
danno@chromium.org
8dc25d2b29 Use direct jump and call instruction for X64 when the deoptimization entries are in the code range.
Review URL: https://codereview.chromium.org/11574027
Patch from Haitao Feng <haitao.feng@intel.com>.

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13903 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-11 14:11:03 +00:00
danno@chromium.org
19badfdda5 Revert r13901 to reland with proper credit to external contributor.
TBR=svenpanne@chromium.org

Review URL: https://codereview.chromium.org/12638011

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13902 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-11 14:09:21 +00:00
danno@chromium.org
d616baed77 Use direct jump and call instruction for X64 when the deoptimization entries are in the code range.
Review URL: https://codereview.chromium.org/11574027

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13901 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-11 14:05:49 +00:00
yangguo@chromium.org
b85237a0bc Fix white space matching in latin-1 strings wrt \u00a0.
R=dcarney@chromium.org
BUG=181422

Review URL: https://chromiumcodereview.appspot.com/12644008

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13898 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-11 11:52:11 +00:00
mvstanton@chromium.org
1691f43b8b To fully support hydrogen code stubs which accept a variable number of arguments,
the HReturn/LReturn instruction needs to be able to determine argument count
from a stack evaluation rather than as a constant from scope.

R=danno@chromium.org
BUG=

Review URL: https://codereview.chromium.org/12613004

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13888 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-08 21:07:55 +00:00
mstarzinger@chromium.org
0cfe1dce9e Unify deoptimizer for stub failure trampoline frames.
This unifies the translation of a compiled stub frame to a stub failure
trampoline frame. Only the frame's register allocation is different on
each architecture and can be factored out.

R=danno@chromium.org

Review URL: https://codereview.chromium.org/12379045

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13887 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-08 16:18:50 +00:00
danno@chromium.org
bbc599f334 Unify grow mode and stub kind
In the process, ensure that transition-causing element stores handle all cases of the transitioned receiver map.

Review URL: https://codereview.chromium.org/12390031

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13850 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-06 21:51:07 +00:00
mvstanton@chromium.org
a2bd4706c2 Make sure that on x86 we don't generate SSE2 code in the snapshot.
BUG=

Review URL: https://codereview.chromium.org/12391033

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13844 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-06 16:15:01 +00:00
mstarzinger@chromium.org
2b7891c303 Unify deoptimizer for construct stub frames.
This unifies the translation of artificial construct stub frames. The
frame layout is almost the same on all architectures and only differs
in the presence of a slot holding the constructor function.

R=svenpanne@chromium.org

Review URL: https://codereview.chromium.org/12379042

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13843 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-06 16:12:24 +00:00
mvstanton@chromium.org
940ed0dc92 Arm fix: incorrect register used in CompareObjectType
R=verwaest@chromium.org
BUG=

Review URL: https://codereview.chromium.org/12532002

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13841 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-06 15:11:27 +00:00
rodolph.perfetta@gmail.com
50703c70a9 Split and replace the EmitVFPTruncate routine to only do what is needed. Floor
and Round have been rewritten to use the default rounding mode.

BUG=none
TEST=none

Review URL: https://codereview.chromium.org/12393008

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13833 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-05 19:35:59 +00:00
verwaest@chromium.org
34697f5b12 Make IC patching resilient to flushing of the original target() ic.
Review URL: https://chromiumcodereview.appspot.com/12451003

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13831 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-05 17:38:35 +00:00
svenpanne@chromium.org
e4edbb0535 Cleaned up CpuFeature scope handling.
First of all, it has nothing to do with Isolates, it is related to the assembler
at hand. Furthermore, the saving/restoring is platform-independent. Cleaned up
some platform-specific stuff on the way.

Note that there are some things which still need some cleanup, like e.g. using
EnumSet instead of uint64_t, making Probe() more uniform across platforms etc.,
but the CL is already big enough.

BUG=v8:2487

Review URL: https://codereview.chromium.org/12391055

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13823 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-05 10:48:16 +00:00
ulan@chromium.org
be2b1a980f Improve integer division on ARM in favor of power of 2 constant divisor
BUG=none
TEST=none

Review URL: https://chromiumcodereview.appspot.com/12052032
Patch from Rajeev R Krithivasan <rkrithiv@codeaurora.org>.

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13819 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-05 08:47:59 +00:00
mstarzinger@chromium.org
0ca02ee48d Make sure builtin functions don't rely on __proto__.
This makes sure that none of the builtin functions rely on the __proto__
accessor which can now be monkey-patched by applications. Instead use a
separate %SetPrototype() intrinsic or object literals to do the job.

R=rossberg@chromium.org

Review URL: https://codereview.chromium.org/12385082

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13815 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-04 16:05:12 +00:00
rossberg@chromium.org
5c93b18eb2 ES6 symbols: Allow symbols as property names
Since symbols and strings share a common representation, most of this change is about consistently replacing 'String' with 'Name' in all places where property names are expected. In particular, no new logic at all is necessary for maps, property dictionaries, or transitions. :) The only places where an actual case distinction is needed have to do with generated type checks, and with conversions of names to strings (especially in logger and profiler).

Left in some TODOs wrt to the API: interceptors and native getters don't accept symbols as property names yet, because that would require extending the external v8.h.

(Baseline CL: https://codereview.chromium.org/12296026/)

R=verwaest@chromium.org,mstarzinger@chromium.org
BUG=v8:2158

Review URL: https://codereview.chromium.org/12330012

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13811 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-04 15:00:57 +00:00
verwaest@chromium.org
590a3f8811 Polymorphism support for load IC.
Review URL: https://chromiumcodereview.appspot.com/12340112

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13801 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-04 14:03:27 +00:00
mvstanton@chromium.org
46af26a5db A debug code assert needed to be behind the new optimize_constructed_arrays flag.
BUG=

Review URL: https://codereview.chromium.org/12385050

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13791 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-01 16:59:53 +00:00
mvstanton@chromium.org
c4caf766bf Allocation Info Tracking, continued.
Addresses missing cases for array literals.
Adds support for "new Array()" call sites. This isn't complete yet, I have to run with --noinline_new.

BUG=

Review URL: https://codereview.chromium.org/11818021

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13790 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-01 16:06:34 +00:00
rossberg@chromium.org
090d09d685 ES6 symbols: Implement Symbol intrinsic and basic functionality
- Add --harmony-symbols flag.
- Add Symbol constructor; allow symbols as (unreplaced) return value from constructors.
- Introduce %CreateSymbol and %_IsSymbol natives and respective instructions.
- Extend 'typeof' code generation to handle symbols.
- Extend CompareIC with a UNIQUE_NAMES state that (uniformly) handles internalized strings and symbols.
- Property lookup delegates to SymbolDelegate object for symbols, which only carries the toString method.
- Extend Object.prototype.toString to recognise symbols.

Per the current draft spec, symbols are actually pseudo objects that are frozen with a null prototype and only one property (toString). For simplicity, we do not treat them as proper objects for now, although typeof will return "object". Only property access works as if they were (frozen) objects (via the internal delegate object).

(Baseline CL: https://codereview.chromium.org/12223071/)

R=mstarzinger@chromium.org
BUG=v8:2158

Review URL: https://codereview.chromium.org/12296026

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13786 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-01 13:28:55 +00:00
mstarzinger@chromium.org
05f1be1bb3 Unify deoptimizer for accessor and arguments frames.
This unifies the translation of artificial accessor stub and arguments
adaptor frames. The frame layout is the same on all architectures and
the computation code can be shared.

R=svenpanne@chromium.org

Review URL: https://codereview.chromium.org/12374044

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13784 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-03-01 12:23:24 +00:00
rossberg@chromium.org
55f93b5532 Renamed "symbols" to "internalized strings" throughout the code base,
in preparation of the introduction of ES6 'symbols' (aka private/unique names).

The SymbolTable became the StringTable. I also made sure to adapt all comments. The only remaining use of the term "symbol" (other than unrelated uses in the parser and such) is now 'NewSymbol' in the API and the 'V8.KeyedLoadGenericSymbol' counter, changing which might break embedders.

The one functional change in this CL is that I removed the former 'empty_string' constant, since it is redundant given the 'empty_symbol' constant that we also had (and both were used inconsistently).

R=yangguo@chromium.org
BUG=

Review URL: https://codereview.chromium.org/12210083

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13781 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-28 17:03:34 +00:00
rossberg@chromium.org
8924d03e16 Minor cleanup of CompareIC state
Allow transitioning from KNOWN_OBJECT to KNONW_OBJECT or OBJECT.
Also, rename HEAP_NUMBER IC states to NUMBER, since they handle Smis, too.

R=jkummerow@chromium.org
BUG=

Review URL: https://codereview.chromium.org/12254036

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13775 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-28 14:43:57 +00:00
verwaest@chromium.org
3ab255f55d Currently this mostly just moves code around.
- Later the different parts will become individual code objects that tailcall into one another.
- The mapcheck/symbol check still needs to be separated from the overall prototype-chain check so that the ICs can reuse the handlers.

Review URL: https://chromiumcodereview.appspot.com/12209021

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13768 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-27 15:28:53 +00:00
svenpanne@chromium.org
bfaf38d2fd Miscellaneous profile-driven Isolate plumbing.
While doing this, it became clear that quite a few functions should not be
static and should better live in various classes as instance methods, but I'll
leave this for a later CL.

BUG=v8:2487

Review URL: https://codereview.chromium.org/12314152

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13765 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-27 14:45:59 +00:00
mstarzinger@chromium.org
ea5e9edac4 Fix materialization of arguments objects with unknown values.
This fixes the deoptimizer to materialize arguments objects of correct
length even in cases where the actual argument values are unknown and
were optimized away by Crankshaft. This can happen if only the length
property or the identity of an arguments object is used.

R=svenpanne@chromium.org
BUG=chromium:163530
TEST=mjsunit/regress/regress-crbug-163530

Review URL: https://codereview.chromium.org/12335132

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13763 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-27 14:37:51 +00:00
svenpanne@chromium.org
c26d100b10 Avoid TLS accesses in Object::Lookup and Object::GetPrototype.
Both methods were among the top causes for TLS accesses.

BUG=v8:2487

Review URL: https://codereview.chromium.org/12319144

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13759 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-27 13:22:29 +00:00
svenpanne@chromium.org
6e829ed485 Added Isolate parameter to CodeStub::GetCode().
According to gprof, this was the #1 cause for TLS access during an Octane run.

BUG=v8:2487

Review URL: https://codereview.chromium.org/12317141

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13756 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-27 12:33:24 +00:00
ulan@chromium.org
d18e118f17 ARM: Fix disassembly of some VFP instructions with condition codes
Previously, we would disassemble some VFP instructions like this:

  vmla.f64eq d16, d17, d18

This patch moves the condition to the right place:

  vmlaeq.f64 d16, d17, d18

Spotted by Rodolph Perfetta!

BUG=none

Review URL: https://chromiumcodereview.appspot.com/12335129
Patch from Hans Wennborg <hans@chromium.org>.

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13752 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-27 11:52:45 +00:00
ulan@chromium.org
87265114c4 Emit VMLS for multiply-subtract on ARM.
BUG=none

Review URL: https://chromiumcodereview.appspot.com/12319113
Patch from Hans Wennborg <hans@chromium.org>.

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13748 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-27 10:24:40 +00:00
mstarzinger@chromium.org
7d681e014d Compile FastCloneShallowObjectStub using Crankshaft.
This changes FastCloneShallowObjectStub to be compiled independent of
the target architecture. It also adds tracing to the deoptimizer for
compiled stubs and contains some minor bugfixes.

R=danno@chromium.org

Review URL: https://codereview.chromium.org/12220074

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13732 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-26 13:08:08 +00:00
yangguo@chromium.org
72b802f27a Refactor RegExpStub to check lazily.
R=ulan@chromium.org
BUG=

Review URL: https://chromiumcodereview.appspot.com/12210143

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13727 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-26 09:53:07 +00:00
ulan@chromium.org
9ebcfb41e2 ARM: Make DoStoreKeyedFixedDoubleArray faster; don't allow conditional Vmov
This patch makes us generate faster code for DoStoreKeyedFixedDoubleArray,
by using a branch rather than a conditional Vmov instruction.

Conditional VFP instructions are not a great idea in general, and it was
especially bad in this case because Vmov expands to a bunch of instructions.
For this reason, the patch also removes the 'cond' parameter from Vmov.

Thanks to Rodolph for pointing me to this!

BUG=none

Review URL: https://chromiumcodereview.appspot.com/12316096
Patch from Hans Wennborg <hans@chromium.org>.

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13722 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-25 16:15:37 +00:00
svenpanne@chromium.org
fb6776e84a Made Isolate a mandatory parameter for everything Handle-related.
Unified parameter order of CreateHandle with the rest of v8 on the way. A few
Isolate::Current()s had to be introduced, which is not nice, and not every place
will win a beauty contest, but we can clean this up later easily in smaller steps.

Review URL: https://codereview.chromium.org/12300018

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13717 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-25 14:46:09 +00:00
mmassi@chromium.org
8ef28eb5ee Fixed numeric relations on HPhi instances.
Review URL: https://codereview.chromium.org/12301027

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13703 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-21 10:22:31 +00:00
yangguo@chromium.org
215ba8cfc9 Combine %_SubString and %_StringCharAt.
R=ulan@chromium.org
BUG=

Review URL: https://chromiumcodereview.appspot.com/12217071

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13700 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-20 14:29:40 +00:00
mstarzinger@chromium.org
b5a64451b1 Ensure deopt entries have no relocation information.
R=ulan@chromium.org
BUG=chromium:176943

Review URL: https://codereview.chromium.org/12314012

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13698 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-20 13:12:26 +00:00
ulan@chromium.org
3a1eca4242 Remove prototype checks for leaf maps in optimized code.
Review URL: https://chromiumcodereview.appspot.com/12225099

git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@13697 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2013-02-20 11:49:54 +00:00