| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | Shrinkify some fields, fit to 80 columns | Chris Lattner | 2006-03-08 | 1 | -11/+11 | |
| | | | | | llvm-svn: 26611 | |||||
| * | revert the previous patch, didn't mean to check it in yet | Chris Lattner | 2006-03-08 | 1 | -25/+2 | |
| | | | | | llvm-svn: 26610 | |||||
| * | remove "Slot", it is dead | Chris Lattner | 2006-03-08 | 2 | -34/+56 | |
| | | | | | llvm-svn: 26609 | |||||
| * | Change the interface for getting a target HazardRecognizer to be more clean. | Chris Lattner | 2006-03-08 | 6 | -29/+23 | |
| | | | | | llvm-svn: 26608 | |||||
| * | libstdc++-v3 was failing to build. Needed to handle composite types with empty | Jim Laskey | 2006-03-08 | 1 | -5/+8 | |
| | | | | | | | members (running into a zero initializer.) llvm-svn: 26607 | |||||
| * | Fix a miscompilation of 188.ammp with the new CFE. 188.ammp is accessing | Chris Lattner | 2006-03-08 | 1 | -3/+19 | |
| | | | | | | | | arrays out of range in a horrible way, but we shouldn't break it anyway. Details in the comments. llvm-svn: 26606 | |||||
| * | add a note | Chris Lattner | 2006-03-08 | 1 | -0/+41 | |
| | | | | | llvm-svn: 26605 | |||||
| * | X86ISD::REP_STOS and X86ISD::REP_MOVS now produces a flag. | Evan Cheng | 2006-03-07 | 1 | -2/+2 | |
| | | | | | llvm-svn: 26604 | |||||
| * | Use rep/stosl; and Count 0x3; rep/stosb for memset with 4 byte aligned dest. | Evan Cheng | 2006-03-07 | 1 | -12/+72 | |
| | | | | | | | | and variable value. Similarly for memcpy. llvm-svn: 26603 | |||||
| * | Two things: | Chris Lattner | 2006-03-07 | 1 | -12/+89 | |
| | | | | | | | | | 1. Don't emit debug info, or other llvm.metadata to the .cbe.c file. 2. Mark static ctors/dtors as such, so that bugpoint works on C++ code compiled with the new CFE. llvm-svn: 26602 | |||||
| * | Use "llvm.metadata" section for debug globals. Filter out these globals in the | Jim Laskey | 2006-03-07 | 4 | -4/+11 | |
| | | | | | | | asm printer. llvm-svn: 26599 | |||||
| * | Switch to using a numeric id for anchors. | Jim Laskey | 2006-03-07 | 2 | -15/+32 | |
| | | | | | llvm-svn: 26598 | |||||
| * | Fix ConstantMerge/2006-03-07-DontMergeDiffSections.ll, a problem Jim | Chris Lattner | 2006-03-07 | 1 | -11/+14 | |
| | | | | | | | | hypotheticalized about, where we would incorrectly merge two globals in different sections. llvm-svn: 26597 | |||||
| * | add another missing store. | Chris Lattner | 2006-03-07 | 1 | -0/+2 | |
| | | | | | llvm-svn: 26595 | |||||
| * | add a couple more load/store instrs, add a newline to the end of file. | Chris Lattner | 2006-03-07 | 2 | -2/+17 | |
| | | | | | llvm-svn: 26594 | |||||
| * | Bitfield support. | Jim Laskey | 2006-03-07 | 1 | -2/+14 | |
| | | | | | llvm-svn: 26593 | |||||
| * | This kinda sorta implements "things that have to lead a dispatch group". | Nate Begeman | 2006-03-07 | 2 | -17/+42 | |
| | | | | | llvm-svn: 26591 | |||||
| * | add some new instructions to the classifier. With this, we correctly insert | Chris Lattner | 2006-03-07 | 1 | -0/+11 | |
| | | | | | | | a nop into Freebench/neural, which speeds it up from 136->129s (~5.4%). llvm-svn: 26590 | |||||
| * | add some comments that describe what we model | Chris Lattner | 2006-03-07 | 1 | -3/+18 | |
| | | | | | llvm-svn: 26588 | |||||
| * | Implement a very very simple hazard recognizer for LSU rejects and ctr set/read | Chris Lattner | 2006-03-07 | 3 | -2/+292 | |
| | | | | | | | flushes llvm-svn: 26587 | |||||
| * | Fix some formatting, when looking for hazards, prefer target nodes over | Chris Lattner | 2006-03-07 | 1 | -7/+15 | |
| | | | | | | | things like copyfromreg. llvm-svn: 26586 | |||||
| * | add a note | Chris Lattner | 2006-03-07 | 1 | -0/+14 | |
| | | | | | llvm-svn: 26585 | |||||
| * | add a note | Chris Lattner | 2006-03-07 | 1 | -0/+11 | |
| | | | | | llvm-svn: 26583 | |||||
| * | - Emit subsections_via_symbols for Darwin. | Evan Cheng | 2006-03-07 | 4 | -20/+41 | |
| | | | | | | | - Conditionalize Dwarf debugging output (Darwin only for now). llvm-svn: 26582 | |||||
| * | Enable Dwarf debugging info. | Evan Cheng | 2006-03-07 | 8 | -6/+83 | |
| | | | | | llvm-svn: 26581 | |||||
| * | Teach the alignment handling code to look through constant expr casts and GEPs | Chris Lattner | 2006-03-07 | 1 | -4/+12 | |
| | | | | | llvm-svn: 26580 | |||||
| * | Teach instcombine to increase the alignment of memset/memcpy/memmove when | Chris Lattner | 2006-03-06 | 1 | -3/+74 | |
| | | | | | | | | | | | | | the pointer is known to come from either a global variable, alloca or malloc. This allows us to compile this: P = malloc(28); memset(P, 0, 28); into explicit stores on PPC instead of a memset call. llvm-svn: 26577 | |||||
| * | update file comment | Chris Lattner | 2006-03-06 | 1 | -3/+8 | |
| | | | | | llvm-svn: 26573 | |||||
| * | Remove some code that doesn't make sense | Evan Cheng | 2006-03-06 | 1 | -12/+5 | |
| | | | | | llvm-svn: 26572 | |||||
| * | Remove SUnit::Priority1: it is re-calculated on demand as number of live | Evan Cheng | 2006-03-06 | 1 | -35/+25 | |
| | | | | | | | range to be generated. llvm-svn: 26570 | |||||
| * | Hoist the HazardRecognizer out of the ScheduleDAGList.cpp file to where | Chris Lattner | 2006-03-06 | 2 | -112/+32 | |
| | | | | | | | | | targets can implement them. Make the top-down scheduler non-g5-specific. Remove the old testing hazard recognizer. llvm-svn: 26569 | |||||
| * | Comment fixes | Chris Lattner | 2006-03-05 | 1 | -2/+2 | |
| | | | | | llvm-svn: 26567 | |||||
| * | Don't depend on the C99 copysign function, implement it ourselves. | Chris Lattner | 2006-03-05 | 1 | -7/+17 | |
| | | | | | llvm-svn: 26566 | |||||
| * | When a hazard recognizer needs noops to be inserted, do so. This represents | Chris Lattner | 2006-03-05 | 2 | -10/+19 | |
| | | | | | | | noops as null pointers in the instruction sequence. llvm-svn: 26564 | |||||
| * | implement TII::insertNoop | Chris Lattner | 2006-03-05 | 3 | -1/+8 | |
| | | | | | llvm-svn: 26562 | |||||
| * | Implement G5HazardRecognizer as a trivial thing that wants 5 cycles between | Chris Lattner | 2006-03-05 | 1 | -2/+42 | |
| | | | | | | | copyfromreg nodes. Clearly useful! llvm-svn: 26559 | |||||
| * | Add basic hazard recognizer support. noop insertion isn't complete yet though. | Chris Lattner | 2006-03-05 | 1 | -15/+104 | |
| | | | | | llvm-svn: 26558 | |||||
| * | Fix VC++ compilation error. | Jeff Cohen | 2006-03-05 | 1 | -0/+5 | |
| | | | | | llvm-svn: 26554 | |||||
| * | Split the list scheduler into top-down and bottom-up pieces. The priority | Chris Lattner | 2006-03-05 | 2 | -43/+185 | |
| | | | | | | | | | function of the top-down scheduler are completely bogus currently, and having (future) PPC specific in this file is also wrong, but this is a small incremental step. llvm-svn: 26552 | |||||
| * | Move the available queue to being inside the ListSchedule method, since it | Chris Lattner | 2006-03-05 | 1 | -10/+15 | |
| | | | | | | | bounds its lifetime. llvm-svn: 26550 | |||||
| * | add a note | Chris Lattner | 2006-03-05 | 1 | -0/+4 | |
| | | | | | llvm-svn: 26549 | |||||
| * | Reinstate this now that the offending opposite xform has been removed. | Chris Lattner | 2006-03-05 | 1 | -0/+7 | |
| | | | | | llvm-svn: 26548 | |||||
| * | Do not fold (add (shl x, c1), (shl c2, c1)) -> (shl (add x, c2), c1), | Chris Lattner | 2006-03-05 | 1 | -18/+0 | |
| | | | | | | | we want to canonicalize the other way. llvm-svn: 26547 | |||||
| * | print arbitrary constant pool entries | Chris Lattner | 2006-03-05 | 1 | -0/+9 | |
| | | | | | llvm-svn: 26545 | |||||
| * | Back out fold (shl (add x, c1), c2) -> (add (shl x, c2), c1<<c2) for now. | Evan Cheng | 2006-03-05 | 1 | -7/+0 | |
| | | | | | | | It's causing an infinite loop compiling ldecod on x86 / Darwin. llvm-svn: 26544 | |||||
| * | Add some simple copysign folds | Chris Lattner | 2006-03-05 | 2 | -7/+61 | |
| | | | | | llvm-svn: 26543 | |||||
| * | Codegen copysign[f] into a FCOPYSIGN node | Chris Lattner | 2006-03-05 | 3 | -4/+63 | |
| | | | | | llvm-svn: 26542 | |||||
| * | Copysign needs to be expanded everywhere. Note that Alpha and IA64 should | Chris Lattner | 2006-03-05 | 5 | -0/+16 | |
| | | | | | | | implement copysign as a native op if they have it. llvm-svn: 26541 | |||||
| * | add a note for something evan noticed | Chris Lattner | 2006-03-05 | 1 | -0/+28 | |
| | | | | | llvm-svn: 26539 | |||||
| * | Make vector narrowing more effective, implementing | Chris Lattner | 2006-03-05 | 1 | -22/+62 | |
| | | | | | | | | Transforms/InstCombine/vec_narrow.ll. This add support for narrowing extract_element(insertelement) also. llvm-svn: 26538 | |||||

