Commit Graph

11 Commits

Author SHA1 Message Date
Jakob Stoklund Olesen
397fc4874e Add an MF argument to TRI::getPointerRegClass() and TII::getRegClass().
The getPointerRegClass() hook can return register classes that depend on
the calling convention of the current function (ptr_rc_tailcall).

So far, we have been able to infer the calling convention from the
subtarget alone, but as we add support for multiple calling conventions
per target, that no longer works.

Patch by Yiannis Tsiouris!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156328 91177308-0d34-0410-b5e6-96231b3b80d8
2012-05-07 22:10:26 +00:00
Jia Liu
31d157ae1a Emacs-tag and some comment fix for all ARM, CellSPU, Hexagon, MBlaze, MSP430, PPC, PTX, Sparc, X86, XCore.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@150878 91177308-0d34-0410-b5e6-96231b3b80d8
2012-02-18 12:03:15 +00:00
Evan Cheng
ddfd1377d2 - Add MachineInstrBundle.h and MachineInstrBundle.cpp. This includes a function
to finalize MI bundles (i.e. add BUNDLE instruction and computing register def
  and use lists of the BUNDLE instruction) and a pass to unpack bundles.
- Teach more of MachineBasic and MachineInstr methods to be bundle aware.
- Switch Thumb2 IT block to MI bundles and delete the hazard recognizer hack to
  prevent IT blocks from being broken apart.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146542 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-14 02:11:42 +00:00
Evan Cheng
5a96b3dad2 Add bundle aware API for querying instruction properties and switch the code
generator to it. For non-bundle instructions, these behave exactly the same
as the MC layer API.

For properties like mayLoad / mayStore, look into the bundle and if any of the
bundled instructions has the property it would return true.
For properties like isPredicable, only return true if *all* of the bundled
instructions have the property.
For properties like canFoldAsLoad, isCompare, conservatively return false for
bundles.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146026 91177308-0d34-0410-b5e6-96231b3b80d8
2011-12-07 07:15:52 +00:00
Evan Cheng
e837dead3c - Rename TargetInstrDesc, TargetOperandInfo to MCInstrDesc and MCOperandInfo and
sink them into MC layer.
- Added MCInstrInfo, which captures the tablegen generated static data. Chang
TargetInstrInfo so it's based off MCInstrInfo.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134021 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-28 19:10:37 +00:00
Evan Cheng
15993f83a4 More refactoring. Move getRegClass from TargetOperandInfo to TargetInstrInfo.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133944 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-27 21:26:13 +00:00
Bob Wilson
84c5eed15b This patch combines several changes from Evan Cheng for rdar://8659675.
Making use of VFP / NEON floating point multiply-accumulate / subtraction is
difficult on current ARM implementations for a few reasons.
1. Even though a single vmla has latency that is one cycle shorter than a pair
   of vmul + vadd, a RAW hazard during the first (4? on Cortex-a8) can cause
   additional pipeline stall. So it's frequently better to single codegen
   vmul + vadd.
2. A vmla folowed by a vmul, vmadd, or vsub causes the second fp instruction to
   stall for 4 cycles. We need to schedule them apart.
3. A vmla followed vmla is a special case. Obvious issuing back to back RAW
   vmla + vmla is very bad. But this isn't ideal either:
     vmul
     vadd
     vmla
   Instead, we want to expand the second vmla:
     vmla
     vmul
     vadd
   Even with the 4 cycle vmul stall, the second sequence is still 2 cycles
   faster.

Up to now, isel simply avoid codegen'ing fp vmla / vmls. This works well enough
but it isn't the optimial solution. This patch attempts to make it possible to
use vmla / vmls in cases where it is profitable.

A. Add missing isel predicates which cause vmla to be codegen'ed.
B. Make sure the fmul in (fadd (fmul)) has a single use. We don't want to
   compute a fmul and a fmla.
C. Add additional isel checks for vmla, avoid cases where vmla is feeding into
   fp instructions (except for the #3 exceptional case).
D. Add ARM hazard recognizer to model the vmla / vmls hazards.
E. Add a special pre-regalloc case to expand vmla / vmls when it's likely the
   vmla / vmls will trigger one of the special hazards.

Enable these fp vmlx codegen changes for Cortex-A9.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@129775 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-19 18:11:57 +00:00
Evan Cheng
6557bce3ec VFP single precision arith instructions can go down to NEON pipeline, but on Cortex-A8 only.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126238 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-22 19:53:14 +00:00
Evan Cheng
04e2b639c1 Eliminate unneeded #include's.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120971 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-05 23:41:43 +00:00
Evan Cheng
f79ed109ec Remove an unused variable.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120964 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-05 23:03:35 +00:00
Evan Cheng
48575f6ea7 Making use of VFP / NEON floating point multiply-accumulate / subtraction is
difficult on current ARM implementations for a few reasons.
1. Even though a single vmla has latency that is one cycle shorter than a pair
   of vmul + vadd, a RAW hazard during the first (4? on Cortex-a8) can cause
   additional pipeline stall. So it's frequently better to single codegen
   vmul + vadd.
2. A vmla folowed by a vmul, vmadd, or vsub causes the second fp instruction to
   stall for 4 cycles. We need to schedule them apart.
3. A vmla followed vmla is a special case. Obvious issuing back to back RAW
   vmla + vmla is very bad. But this isn't ideal either:
     vmul
     vadd
     vmla
   Instead, we want to expand the second vmla:
     vmla
     vmul
     vadd
   Even with the 4 cycle vmul stall, the second sequence is still 2 cycles
   faster.

Up to now, isel simply avoid codegen'ing fp vmla / vmls. This works well enough
but it isn't the optimial solution. This patch attempts to make it possible to
use vmla / vmls in cases where it is profitable.

A. Add missing isel predicates which cause vmla to be codegen'ed.
B. Make sure the fmul in (fadd (fmul)) has a single use. We don't want to
   compute a fmul and a fmla.
C. Add additional isel checks for vmla, avoid cases where vmla is feeding into
   fp instructions (except for the #3 exceptional case).
D. Add ARM hazard recognizer to model the vmla / vmls hazards.
E. Add a special pre-regalloc case to expand vmla / vmls when it's likely the
   vmla / vmls will trigger one of the special hazards.

Work in progress, only A+B are enabled.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120960 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-05 22:04:16 +00:00