bmeurer e607e12ea0 [turbofan] Introduce Float64Pow and NumberPow operators. ... Introduce a new machine operator Float64Pow that for now is backed by the existing MathPowStub to start the unification of Math.pow, and at the same time address the main performance issue that TurboFan still has with the imaging-darkroom benchmark in Kraken. Also migrate the Math.pow builtin itself to a TurboFan builtin and remove a few hundred lines of hand-written platform code for special handling of the fullcodegen Math.pow version. BUG=v8:3599,v8:5086,v8:5157 Review-Url: https://codereview.chromium.org/2103733003 Cr-Commit-Position: refs/heads/master@{#37323}		2016-06-28 10:26:10 +00:00
..
arm	[arm] [arm64] Add optional operators Float32Neg and Float64Neg.	2016-05-27 11:22:07 +00:00
arm64	[arm64] Fix handling of CMN and ADD/SUB with overflow in VisitBinop.	2016-06-23 11:29:20 +00:00
ia32	[turbofan] Store nodes use only MachineRepresentation, not MachineType.	2015-12-11 15:34:16 +00:00
mips	MIPS: [turbofan] Optimize Float32 to Int32 rep. changes with Float32 round ops.	2015-12-18 16:12:51 +00:00
mips64	MIPS: [turbofan] Optimize Float32 to Int32 rep. changes with Float32 round ops.	2015-12-18 16:12:51 +00:00
ppc	Update PPC OWNERS	2015-07-27 21:37:55 +00:00
s390	S390: Initial test changes and files checkin.	2016-03-15 18:09:36 +00:00
x64	[turbofan] Store nodes use only MachineRepresentation, not MachineType.	2015-12-11 15:34:16 +00:00
branch-elimination-unittest.cc	[turbofan] Make MachineType a pair of enums.	2015-12-10 09:03:53 +00:00
checkpoint-elimination-unittest.cc	[turbofan] Rename {CheckPoint} to {Checkpoint} everywhere.	2016-06-01 09:07:19 +00:00
common-operator-reducer-unittest.cc	[turbofan] We never use Int64Constant for branch/select conditions.	2016-05-18 07:20:19 +00:00
common-operator-unittest.cc	[turbofan] Address the useless overflow bit materialization.	2016-06-21 15:46:40 +00:00
compiler-test-utils.h	[turbofan] Drop V8_TURBOFAN_BACKEND and V8_TURBOFAN_TARGET defines.	2015-08-10 07:17:34 +00:00
control-equivalence-unittest.cc	[tubofan] Remove .dot output of --trace-turbo	2015-12-11 16:58:31 +00:00
control-flow-optimizer-unittest.cc	[turbofan] Make MachineType a pair of enums.	2015-12-10 09:03:53 +00:00
dead-code-elimination-unittest.cc	[turbofan] Make MachineType a pair of enums.	2015-12-10 09:03:53 +00:00
diamond-unittest.cc	[turbofan] Make MachineType a pair of enums.	2015-12-10 09:03:53 +00:00
effect-control-linearizer-unittest.cc	[turbofan] Wire in floating control during effect linearization phase.	2016-04-25 04:29:23 +00:00
escape-analysis-unittest.cc	[turbofan] Introduce CheckTaggedSigned and CheckTaggedPointer operators.	2016-06-20 10:48:55 +00:00
graph-reducer-unittest.cc	[turbofan] Make Node::set_op safer via wrapper.	2015-09-24 14:46:37 +00:00
graph-reducer-unittest.h	[turbofan] Add AdvancedReducer::ReplaceWithValue() method and convert JSInlining to an AdvancedReducer.	2015-05-12 12:41:36 +00:00
graph-trimmer-unittest.cc	[turbofan] Proper dead code elimination as regular reducer.	2015-06-19 12:07:26 +00:00
graph-unittest.cc	[turbofan] Get rid of type lower bounds.	2015-09-16 11:55:43 +00:00
graph-unittest.h	[turbofan] Do strength reduction for ObjectIsSmi based on inputs.	2016-06-08 07:13:05 +00:00
instruction-selector-unittest.cc	[RegisterConfiguration] Streamline access to arch defaults, simplify Registers.	2016-06-27 15:31:31 +00:00
instruction-selector-unittest.h	[turbofan] Enforce that C calls do not use floating point params.	2016-02-15 13:25:23 +00:00
instruction-sequence-unittest.cc	[Turbofan] Allow compiler to elide complex aliasing code.	2016-06-27 11:57:51 +00:00
instruction-sequence-unittest.h	[turbofan] Create ExplicitOperands to specify operands without virtual registers	2015-10-27 13:27:00 +00:00
int64-lowering-unittest.cc	Fix int64 lowering on big-endian architectures.	2016-06-23 11:41:07 +00:00
js-builtin-reducer-unittest.cc	[turbofan] Introduce Float64Pow and NumberPow operators.	2016-06-28 10:26:10 +00:00
js-create-lowering-unittest.cc	[runtime] Fix number of literals for builtin functions.	2016-05-24 15:12:58 +00:00
js-intrinsic-lowering-unittest.cc	[builtins] Introduce proper Float64Tan operator.	2016-06-20 05:51:52 +00:00
js-operator-unittest.cc	Rip out most of our outdated modules implementation.	2016-06-28 07:25:38 +00:00
js-type-feedback-unittest.cc	Remove support for "loads and stores to global vars through property cell shortcuts installed into parent script context" from all compilers.	2015-10-22 09:17:24 +00:00
js-typed-lowering-unittest.cc	[turbofan] Type feedback for numeric comparisons.	2016-06-16 06:37:31 +00:00
linkage-tail-call-unittest.cc	[turbofan] Make MachineType a pair of enums.	2015-12-10 09:03:53 +00:00
live-range-builder.h	[turbofan] Make MachineType a pair of enums.	2015-12-10 09:03:53 +00:00
live-range-unittest.cc	[turbofan] Make MachineType a pair of enums.	2015-12-10 09:03:53 +00:00
liveness-analyzer-unittest.cc	[turbofan] Remove the JSContextRelaxation reducer.	2016-02-19 07:55:48 +00:00
load-elimination-unittest.cc	[turbofan] Turn common Guard operator into simplified TypeGuard.	2016-05-18 06:19:30 +00:00
loop-peeling-unittest.cc	Expose a lower bound of malloc'd memory via heap statistics	2016-04-01 10:01:56 +00:00
machine-operator-reducer-unittest.cc	[turbofan] Address the useless overflow bit materialization.	2016-06-21 15:46:40 +00:00
machine-operator-unittest.cc	[turbofan] Address the useless overflow bit materialization.	2016-06-21 15:46:40 +00:00
move-optimizer-unittest.cc	[RegisterConfiguration] Streamline access to arch defaults, simplify Registers.	2016-06-27 15:31:31 +00:00
node-cache-unittest.cc	[test] Turn compiler/test-node-cache into a unit test.	2015-04-29 14:40:05 +00:00
node-matchers-unittest.cc	[presubmit] Enable readability/namespace linter checking.	2015-09-30 13:47:11 +00:00
node-properties-unittest.cc	[turbofan] Proper dead code elimination as regular reducer.	2015-06-19 12:07:26 +00:00
node-test-utils.cc	[turbofan] Introduce Float64Pow and NumberPow operators.	2016-06-28 10:26:10 +00:00
node-test-utils.h	[turbofan] Introduce Float64Pow and NumberPow operators.	2016-06-28 10:26:10 +00:00
node-unittest.cc	Fix -Wsign-compare errors in TF tests under GCC 4.9.2	2015-06-15 12:03:45 +00:00
opcodes-unittest.cc	[turbofan] Strength reduction for inline comparisons.	2015-02-24 12:26:29 +00:00
register-allocator-unittest.cc	[turbofan] Retiring Greedy Allocator	2016-06-13 04:24:12 +00:00
schedule-unittest.cc	Model exceptional edges from call nodes in TurboFan.	2015-02-20 09:55:00 +00:00
scheduler-rpo-unittest.cc	Move RPO unittests into their own file.	2016-02-14 11:27:46 +00:00
scheduler-unittest.cc	[turbofan] Handle dead diamonds in scheduling and add a test.	2016-04-04 17:45:59 +00:00
simplified-operator-reducer-unittest.cc	[turbofan] Introduce simplified operator NumberAbs.	2016-06-28 04:37:02 +00:00
simplified-operator-unittest.cc	[turbofan] Introduce CheckTaggedSigned and CheckTaggedPointer operators.	2016-06-20 10:48:55 +00:00
state-values-utils-unittest.cc	[turbofan] Move SimplifiedOperatorBuilder into JSGraph.	2015-10-16 12:38:52 +00:00
tail-call-optimization-unittest.cc	[turbofan] Make MachineType a pair of enums.	2015-12-10 09:03:53 +00:00
typer-unittest.cc	[turbofan] Type feedback for numeric comparisons.	2016-06-16 06:37:31 +00:00
value-numbering-reducer-unittest.cc	[turbofan] Check node input/use consistency for changed operators and new nodes.	2015-09-25 08:43:11 +00:00
zone-pool-unittest.cc	Expose a lower bound of malloc'd memory via heap statistics	2016-04-01 10:01:56 +00:00