summaryrefslogtreecommitdiffstats
path: root/llvm/lib
Commit message (Collapse)AuthorAgeFilesLines
...
* Fix a compilation warning.Evan Cheng2007-12-081-1/+1
| | | | llvm-svn: 44691
* Initial commit of the machine code LICM pass. It successfully hoists this:Bill Wendling2007-12-073-10/+353
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | _foo: li r2, 0 LBB1_1: ; bb li r5, 0 stw r5, 0(r3) addi r2, r2, 1 addi r3, r3, 4 cmplw cr0, r2, r4 bne cr0, LBB1_1 ; bb LBB1_2: ; return blr to: _foo: li r2, 0 li r5, 0 LBB1_1: ; bb stw r5, 0(r3) addi r2, r2, 1 addi r3, r3, 4 cmplw cr0, r2, r4 bne cr0, LBB1_1 ; bb LBB1_2: ; return blr ZOMG!! :-) Moar to come... llvm-svn: 44687
* Add comment.Evan Cheng2007-12-071-0/+2
| | | | llvm-svn: 44686
* Much improved v8i16 shuffles. (Step 1).Evan Cheng2007-12-071-25/+126
| | | | llvm-svn: 44676
* Add an option to control this heuristic tweak so I can test it.Evan Cheng2007-12-071-1/+6
| | | | llvm-svn: 44671
* Remove a bogus optimization. It's not possible to do a move to low element ↵Evan Cheng2007-12-062-7/+1
| | | | | | to a <8 x i16> or <16 x i8> vector. llvm-svn: 44669
* Redo previous patch so optimization only done for i1.Dale Johannesen2007-12-061-16/+4
| | | | | | Simpler and safer. llvm-svn: 44663
* Turning simple splitting on. Start testing new coalescer heuristics as new ↵Evan Cheng2007-12-061-1/+1
| | | | | | llcbeta. llvm-svn: 44660
* third time around: instead of disabling this completely,Chris Lattner2007-12-061-6/+13
| | | | | | | only disable it if we don't know it will be obviously profitable. Still fixme, but less so. :) llvm-svn: 44658
* Actually, disable this code for now. More analysis and improvements toChris Lattner2007-12-061-0/+6
| | | | | | the X86 backend are needed before this should be enabled by default. llvm-svn: 44657
* implement a readme entry, compiling the code into:Chris Lattner2007-12-062-57/+65
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | _foo: movl $12, %eax andl 4(%esp), %eax movl _array(%eax), %eax ret instead of: _foo: movl 4(%esp), %eax shrl $2, %eax andl $3, %eax movl _array(,%eax,4), %eax ret As it turns out, this triggers all the time, in a wide variety of situations, for example, I see diffs like this in various programs: - movl 8(%eax), %eax - shll $2, %eax - andl $1020, %eax - movl (%esi,%eax), %eax + movzbl 8(%eax), %eax + movl (%esi,%eax,4), %eax - shll $2, %edx - andl $1020, %edx - movl (%edi,%edx), %edx + andl $255, %edx + movl (%edi,%edx,4), %edx Unfortunately, I also see stuff like this, which can be fixed in the X86 backend: - andl $85, %ebx - addl _bit_count(,%ebx,4), %ebp + shll $2, %ebx + andl $340, %ebx + addl _bit_count(%ebx), %ebp llvm-svn: 44656
* simplify some code.Chris Lattner2007-12-061-2/+1
| | | | llvm-svn: 44655
* implement the rest of the functionality from ↵Chris Lattner2007-12-061-10/+24
| | | | | | SelectionDAGLegalize::ScalarizeVectorOp llvm-svn: 44654
* Adjust VStudio files to add JITMemoryManager files + include <cassert> from ↵Chuck Rose III2007-12-061-0/+1
| | | | | | same. llvm-svn: 44651
* move some ashr-specific code out of commonShiftTransforms into visitAShr.Chris Lattner2007-12-061-15/+16
| | | | llvm-svn: 44650
* Fix PR1842.Dale Johannesen2007-12-061-4/+16
| | | | llvm-svn: 44649
* add a new ExecutionEngine::createJIT which can be used if you only want Chris Lattner2007-12-063-8/+33
| | | | | | | to create a JIT. This lets you specify JIT-specific configuration items like the JITMemoryManager to use. llvm-svn: 44647
* simplify creation of the interpreter, make ExecutionEngine ctor protected,Chris Lattner2007-12-066-25/+11
| | | | | | delete one ExecutionEngine ctor, minor cleanup. llvm-svn: 44646
* Fix for PR1831: if all defs of an interval are re-materializable, then it's ↵Evan Cheng2007-12-062-4/+48
| | | | | | a preferred spill candiate. llvm-svn: 44644
* If both result of the {s|z}xt and its source are live out, rewrite all uses ↵Evan Cheng2007-12-051-3/+71
| | | | | | of the source with result of extension. llvm-svn: 44643
* split the JIT memory management code out from the main JIT logic into itsChris Lattner2007-12-052-411/+454
| | | | | | | own JITMemoryManager interface. There is no functionality change with this patch. llvm-svn: 44640
* add a noteChris Lattner2007-12-051-0/+37
| | | | llvm-svn: 44638
* add a noteChris Lattner2007-12-051-0/+20
| | | | llvm-svn: 44637
* Minor updates:Scott Michel2007-12-051-2/+1
| | | | | | | | - Fix typo in SPUCallingConv.td - Credit myself for CellSPU work - Add CellSPU to 'all' host target list llvm-svn: 44627
* Commit 44487 broke bootstrap of llvm-gcc-4.2. It isDuncan Sands2007-12-052-4/+15
| | | | | | | not yet clear why, but in the meantime work around the problem by making less use of readnone/readonly info. llvm-svn: 44626
* Added canFoldMemoryOperand for PPC.Evan Cheng2007-12-052-0/+23
| | | | llvm-svn: 44623
* Update foldMemoryOperand.Evan Cheng2007-12-052-4/+11
| | | | llvm-svn: 44621
* fix warningsChris Lattner2007-12-051-2/+2
| | | | llvm-svn: 44620
* allow this to buildChris Lattner2007-12-051-1/+1
| | | | llvm-svn: 44619
* Prior commit updated wrong if, apologies.Neil Booth2007-12-051-2/+2
| | | | llvm-svn: 44614
* Handle zero correctly.Neil Booth2007-12-051-3/+3
| | | | llvm-svn: 44613
* MachineInstr can change. Store indexes instead.Evan Cheng2007-12-053-14/+23
| | | | llvm-svn: 44612
* If a split live interval is spilled again, remove the kill marker on its ↵Evan Cheng2007-12-053-2/+25
| | | | | | last use. llvm-svn: 44611
* Clobber more bugs.Evan Cheng2007-12-051-2/+3
| | | | llvm-svn: 44610
* Fix kill info for split intervals.Evan Cheng2007-12-053-23/+37
| | | | llvm-svn: 44609
* more scalarizationChris Lattner2007-12-051-0/+30
| | | | llvm-svn: 44608
* scalarize vector binopsChris Lattner2007-12-051-1/+24
| | | | llvm-svn: 44607
* - Mark last use of a split interval as kill instead of letting spiller track it.Evan Cheng2007-12-052-28/+73
| | | | | | | | | This allows an important optimization to be re-enabled. - If all uses / defs of a split interval can be folded, give the interval a low spill weight so it would not be picked in case spilling is needed (avoid pushing other intervals in the same BB to be spilled). llvm-svn: 44601
* Add a argument to storeRegToStackSlot and storeRegToAddr to specify whetherEvan Cheng2007-12-0522-92/+147
| | | | | | the stored register is killed. llvm-svn: 44600
* More stuff for CellSPU -- this should be enough to get an error-freeScott Michel2007-12-051-0/+9
| | | | | | compilation (no files missing). Test cases remain to be checked in. llvm-svn: 44598
* Updated source file headers to llvm coding standard.Scott Michel2007-12-0532-85/+74
| | | | llvm-svn: 44597
* Two missing files.Scott Michel2007-12-052-0/+469
| | | | llvm-svn: 44596
* Main CellSPU backend files checked in. Intrinsics and autoconf filesScott Michel2007-12-0513-0/+2697
| | | | | | remain. llvm-svn: 44595
* Handle 0 correctly in string->APFloat conversion.Dale Johannesen2007-12-051-1/+1
| | | | llvm-svn: 44594
* Remove a unsafe optimization. This fixes 401.bzip2.Evan Cheng2007-12-041-8/+0
| | | | llvm-svn: 44587
* More files in the CellSPU drop...Scott Michel2007-12-043-0/+3383
| | | | llvm-svn: 44584
* More of the Cell SPU code drop from "Team Aerospace".Scott Michel2007-12-0411-0/+4792
| | | | llvm-svn: 44582
* Spiller unfold optimization bug: do not clobber a reusable stack slot value ↵Evan Cheng2007-12-041-10/+16
| | | | | | unless it can be modified. llvm-svn: 44575
* Implement framework for scalarizing node results. This is sufficient Chris Lattner2007-12-041-11/+80
| | | | | | | | | | | | to codegen this: define float @test_extract_elt(<1 x float> * %P) { %p = load <1 x float>* %P %R = extractelement <1 x float> %p, i32 0 ret float %R } llvm-svn: 44570
* start providing framework for scalarizing vectors.Chris Lattner2007-12-041-4/+106
| | | | llvm-svn: 44569
OpenPOWER on IntegriCloud