aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/ARM/ARMScheduleV6.td
Commit message (Collapse)AuthorAgeFilesLines
* Sorry, several patches in one.Evan Cheng2011-01-201-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | TargetInstrInfo: Change produceSameValue() to take MachineRegisterInfo as an optional argument. When in SSA form, targets can use it to make more aggressive equality analysis. Machine LICM: 1. Eliminate isLoadFromConstantMemory, use MI.isInvariantLoad instead. 2. Fix a bug which prevent CSE of instructions which are not re-materializable. 3. Use improved form of produceSameValue. ARM: 1. Teach ARM produceSameValue to look pass some PIC labels. 2. Look for operands from different loads of different constant pool entries which have same values. 3. Re-implement PIC GA materialization using movw + movt. Combine the pair with a "add pc" or "ldr [pc]" to form pseudo instructions. This makes it possible to re-materialize the instruction, allow machine LICM to hoist the set of instructions out of the loop and make it possible to CSE them. It's a bit hacky, but it significantly improve code quality. 4. Some minor bug fixes as well. With the fixes, using movw + movt to materialize GAs significantly outperform the load from constantpool method. 186.crafty and 255.vortex improved > 20%, 254.gap and 176.gcc ~10%. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123905 91177308-0d34-0410-b5e6-96231b3b80d8
* Conditional moves are slightly more expensive than moves.Evan Cheng2010-11-131-0/+2
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@118985 91177308-0d34-0410-b5e6-96231b3b80d8
* putback r116983 and fix simple-fp-encoding.ll testsAndrew Trick2010-10-211-0/+12
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116992 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert r116983, which is breaking all the buildbots.Owen Anderson2010-10-211-12/+0
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116987 91177308-0d34-0410-b5e6-96231b3b80d8
* Add missing scheduling itineraries for transfers between core registers and ↵Evan Cheng2010-10-211-0/+12
| | | | | | VFP registers. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116983 91177308-0d34-0410-b5e6-96231b3b80d8
* Model operand cycles of vldm / vstm; also fixes scheduling itineraries of ↵Evan Cheng2010-10-071-2/+8
| | | | | | vldr / vstr, etc. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115898 91177308-0d34-0410-b5e6-96231b3b80d8
* - Add TargetInstrInfo::getOperandLatency() to compute operand latencies. ThisEvan Cheng2010-10-061-6/+19
| | | | | | | | | | | | | | allow target to correctly compute latency for cases where static scheduling itineraries isn't sufficient. e.g. variable_ops instructions such as ARM::ldm. This also allows target without scheduling itineraries to compute operand latencies. e.g. X86 can return (approximated) latencies for high latency instructions such as division. - Compute operand latencies for those defined by load multiple instructions, e.g. ldm and those used by store multiple instructions, e.g. stm. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115755 91177308-0d34-0410-b5e6-96231b3b80d8
* ARM instruction itinerary fixes:Evan Cheng2010-09-301-13/+30
| | | | | | | | | 1. Cortex-a9 8-bit and 16-bit loads / stores AGU cycles are 1 cycle longer than 32-bit ones. 2. Cortex-a9 is out-of-order so model all read cycles as cycle 1. 3. Lots of other random fixes for A8 and A9. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115121 91177308-0d34-0410-b5e6-96231b3b80d8
* Separate itinerary classes for mvn from mov; for tst / teq from cmp / cmn.Evan Cheng2010-09-291-0/+12
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115010 91177308-0d34-0410-b5e6-96231b3b80d8
* Assign bitwise binary instructions different itinerary classes from ALU ↵Evan Cheng2010-09-291-0/+7
| | | | | | instructions such as add / sub. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115008 91177308-0d34-0410-b5e6-96231b3b80d8
* Add support to model pipeline bypass / forwarding.Evan Cheng2010-09-281-1/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115005 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove a unused instruction itinerary class.Evan Cheng2010-09-251-1/+0
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114782 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix zero and sign extension instructions scheduling itineraries.Evan Cheng2010-09-251-0/+4
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114780 91177308-0d34-0410-b5e6-96231b3b80d8
* More pseudo instruction scheduling itinerary fixes.Evan Cheng2010-09-241-0/+7
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114768 91177308-0d34-0410-b5e6-96231b3b80d8
* For each instruction itinerary class, specify the number of micro-ops eachEvan Cheng2010-09-091-0/+5
| | | | | | | | | | | instruction in the class would be decoded to. Or zero if the number of uOPs must be determined dynamically. This will be used to determine the cost-effectiveness of predicating a micro-coded instruction. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113513 91177308-0d34-0410-b5e6-96231b3b80d8
* Clean up 80 column violations. No functional change.Jim Grosbach2010-06-021-1/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@105350 91177308-0d34-0410-b5e6-96231b3b80d8
* Make processor FUs unique for given itinerary. This extends the limit of 32Anton Korobeynikov2010-04-181-69/+73
| | | | | | | FU per CPU arch to 32 per intinerary allowing precise modelling of quite complex pipelines in the future. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@101754 91177308-0d34-0410-b5e6-96231b3b80d8
* Add ARMv6 itineraries.David Goodwin2009-11-181-1/+187
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89218 91177308-0d34-0410-b5e6-96231b3b80d8
* Checkpoint NEON scheduling itineraries.David Goodwin2009-09-231-86/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82657 91177308-0d34-0410-b5e6-96231b3b80d8
* Add Cortex-A8 VFP model.David Goodwin2009-09-211-6/+35
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82483 91177308-0d34-0410-b5e6-96231b3b80d8
* Update Cortex-A8 instruction itineraries for integer instructions.David Goodwin2009-08-191-6/+46
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79436 91177308-0d34-0410-b5e6-96231b3b80d8
* Turn on if-conversion for thumb2.Evan Cheng2009-08-151-2/+4
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@79084 91177308-0d34-0410-b5e6-96231b3b80d8
* Finalize itineraries for cortex-a8 integer multiplyDavid Goodwin2009-08-131-1/+3
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78908 91177308-0d34-0410-b5e6-96231b3b80d8
* Allow a zero cycle stage to reserve/require a FU without advancing the cycle ↵David Goodwin2009-08-111-9/+7
| | | | | | counter. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78736 91177308-0d34-0410-b5e6-96231b3b80d8
* Checkpoint scheduling itinerary changes.David Goodwin2009-08-101-7/+13
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78564 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix comment.Evan Cheng2009-07-211-1/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@76693 91177308-0d34-0410-b5e6-96231b3b80d8
* Latency information for ARM v6. It's rough and not yet hooked up. Right now ↵Evan Cheng2009-06-191-0/+22
we are only using branch latency to determine if-conversion limits. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@73747 91177308-0d34-0410-b5e6-96231b3b80d8