Results (91 - 100 of 827)
- Quickjump to bpoulain@apple.com
- [199933]: [JSC] PredictionPropagation should not be in the top 5 heaviest phases ...
- ... org/show_bug.cgi?id=156891 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-22 Reviewed by Mark Lam. In DFG, PredictionPropagation is often way too high in profiles. It is a simple phase, it should not be that hot. Most of the time is spent accessing memory. This patch attempts to r ...
- By Apr 22, 2016 4:10:27 PM —
- [199894]: [JSC] Integer Multiply of a number by itself does not need negative ...
- ... org/show_bug.cgi?id=156895 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-22 Reviewed by Saam Barati. You cannot produce negative zero by squaring an integer. * dfg/DFGFixupPhase.cpp: (JSC::DFG::FixupPhase::fixupNode): * dfg/DFGSpeculativeJIT.cpp: (JSC::DFG::SpeculativeJIT::compil ...
- By Apr 22, 2016 12:27:57 PM —
- [199867]: [JSC] Add primitive String support to compare operators ...
- ... org/show_bug.cgi?id=156783 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-21 Reviewed by Geoffrey Garen. Just the basics. We should eventually inline some of the simplest cases. This is a 2% improvement on Longspider. It is unfortunately neutral for Sunspider on my machine because ...
- By Apr 21, 2016 10:08:28 PM —
- [199796]: [JSC] DFG should not generate two jumps when the target of ...
- ... org/show_bug.cgi?id=156815 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-20 Reviewed by Mark Lam. * dfg/DFGSpeculativeJIT.cpp: (JSC::DFG::SpeculativeJIT::compilePeepHoleDoubleBranch):
- By Apr 20, 2016 4:28:29 PM —
- [199792]: [JSC] Add register reuse for ArithAdd of an Int32 and constant in DFG ...
- ... org/show_bug.cgi?id=155164 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-20 Reviewed by Mark Lam. Every "inc" in loop was looking like this: move rX, rY inc rY jo 0x230f4a200580 This patch add register Reuse to that case to remove the extra "move". * dfg/DFGOSRExit.h ...
- By Apr 20, 2016 3:24:32 PM —
- [199710]: [JSC] Fix some overhead affecting small codegen ...
- ... org/show_bug.cgi?id=156728 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-18 Reviewed by Filip Pizlo. * assembler/AbstractMacroAssembler.h: (JSC::AbstractMacroAssembler::AbstractMacroAssembler): (JSC::AbstractMacroAssembler::random): cryptographicallyRandomNumber() is very costly. ...
- By Apr 18, 2016 11:54:25 PM —
- [199648]: [JSC] ReduceDoubleToFloat should work accross Phis ...
- ... //problem/25736205> Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-17 Reviewed by Saam Barati and Filip Pizlo. This patch extends B3's ReduceDoubleToFloat phase to work accross Upsilon-Phis. This is important to optimize loops and some crazy cases. In its simplest form, we ...
- By Apr 17, 2016 10:13:13 PM —
- [199638]: [JSC] FRound/Negate can produce an impure NaN out of a pure NaN ...
- ... org/show_bug.cgi?id=156528 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-16 Reviewed by Filip Pizlo. If you fround a double with the bits 0xfff7000000000000 you get 0xfffe000000000000. The first is a pure NaN, the second isn't. This is without test because I could not find a way ...
- By Apr 16, 2016 8:44:52 PM —
- [199481]: Merge r199025 - [JSC][x86] Fix an assertion in ...
- ... org/show_bug.cgi?id=156181 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-04-04 Reviewed by Geoffrey Garen. * assembler/MacroAssemblerX86Common.h: (JSC::MacroAssemblerX86Common::branch8): The test was wrong because valid negative numbers have ones in the top bits. I replaced the asse ...
- By Apr 13, 2016 7:51:36 AM —
- [199463]: Merge r198827 - [WTF] Removing a smart pointer from HashTable issues ...
- ... org/show_bug.cgi?id=155676 Patch by Benjamin Poulain <bpoulain@apple.com> on 2016-03-29 Reviewed by Darin Adler. Source/WTF: While working on the hot loop of r198376, I noticed something weird... Every time we removed a smart pointer from the hash table, the code generated was something like ...
- By Apr 13, 2016 5:16:17 AM —
Note: See TracSearch
for help on searching.