summaryrefslogtreecommitdiff
path: root/lib/Target
AgeCommit message (Collapse)AuthorFilesLines
2013-02-26bundling dot4scheduling2Vincent Lejeune4-1/+60
2013-02-26some work to get bottom up scheduling workingVincent Lejeune4-42/+76
2013-02-26R600: Recompute schedule graph non order dependencies.Vincent Lejeune2-2/+111
2013-02-26R600: initial scheduler codeVadim Girlin3-1/+620
This is a skeleton for a pre-RA MachineInstr scheduler strategy. Currently it only tries to expose more parallelism for ALU instructions (this also makes the distribution of GPR channels more uniform and increases the chances of ALU instructions to be packed together in a single VLIW group). Also it tries to reduce clause switching by grouping instruction of the same kind (ALU/FETCH/CF) together. Vincent Lejeune: - Support for VLIW4 Slot assignement - Recomputation of ScheduleDAG to get more parallelism opportunities Tom Stellard: - Fix assertion failure when trying to determine an instruction's slot based on its destination register's class - Fix some compiler warnings Vincent Lejeune: [v2] - Remove recomputation of ScheduleDAG (will be provided in a later patch) - Improve estimation of an ALU clause size so that heuristic does not emit cf instructions at the wrong position. - Make schedule heuristic smarter using SUnit Depth - Take constant read limitations into account
2013-02-26R600: Remove LowerConstCopyPass and lower CONST_COPY right after ISel.Vincent Lejeune5-228/+11
Maintaining CONST_COPY Instructions until Pre Emit may prevent some ifcvt case and taking them in account for scheduling is difficult for no real benefit.
2013-02-26R600: Turn BUILD_VECTOR into Reg_SequenceVincent Lejeune1-0/+29
2013-02-26R600: CONST_ADDRESS node is not marked as mayLoad anymoreVincent Lejeune1-1/+1
mayLoad complexify scheduling and does not bring any usefull info as the location is not writeable at all.
2013-02-26R600: Use MUL_IEEE for trig/fdiv intrinsicVincent Lejeune1-4/+4
2013-02-26R600: Do not predicate vector opVincent Lejeune1-0/+2
2013-02-26R600: Add support for indirect addressing of non default const bufferVincent Lejeune2-7/+8
NOTE: This is a candidate for the Mesa stable branch.
2013-02-26[mips] Use class RegDefsUses to track register defs and uses.Akira Hatanaka1-89/+82
No functionality change. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176070 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-26[fast-isel] Make sure the FastLowerArguments function checks to make sure theChad Rosier2-0/+2
arguments type is a simple type. rdar://13290455 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176066 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-25Refine fix to PR10499, no functionality changeMichael Liao1-1/+1
- Put expensive checking after simple one git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176060 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-25Fix PR10499Michael Liao1-1/+1
- Check whether SSE is available before lowering all 1s vector building with PCMPEQD, which is only available from SSE2 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176058 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-25[fast-isel] Add X86FastIsel::FastLowerArguments to handle functions with 6 orChad Rosier1-0/+73
fewer scalar integer (i32 or i64) arguments. It completely eliminates the need for SDISel for trivial functions. Also, add the new llc -fast-isel-abort-args option, which is similar to -fast-isel-abort option, but for formal argument lowering. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176052 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-25[ms-inline asm] Add support for the pushad/popad mnemonics.Chad Rosier1-4/+2
rdar://13254235 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176036 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-25Fix missing relocation for TLS addressing peephole optimization.Bill Schmidt1-0/+3
Report and fix due to Kai Nacke. Testcase update by me. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176029 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-25Make pseudos FEXT_CCRX16_ins and FEXT_CCRXI16_ins into custom emitters.Reed Kotler5-69/+70
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176007 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-24 Make psuedo FEXT_T8I816_ins into a custom emitter.Reed Kotler5-61/+39
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176002 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-24Fix PR14364.Bill Schmidt4-20/+27
This removes a const_cast hack from PPCRegisterInfo::hasReservedSpillSlot(). The proper place to save the frame index for the CR spill slot is in the PPCFunctionInfo object, not the PPCRegisterInfo object. No new test cases, as this just reimplements existing function. Existing tests such as test/CodeGen/PowerPC/crsave.ll are sufficient. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175998 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-24TypoFrancois Pichet1-1/+1
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175991 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-24Revert r169638 because it broke Mesa llvmpipe tests.Nadav Rotem1-6/+1
Fix PR15239. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175985 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-24Make psuedo FEXT_T8I816_ins a custom inserter. It should be expandedReed Kotler4-22/+34
as early as possible; which means during instruction selection. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175984 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-23Add new base instruction def for cmpi, cmp, slt and sltu so that def/usesReed Kotler1-5/+10
proper. Fixed this already a few days ago for slti. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175975 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-23X86: Disable cmov-memory patterns on subtargets without cmov.Benjamin Kramer1-6/+8
Fixes PR15115. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175962 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-23Expand pseudos/macros for Selt. This is the last of the complexReed Kotler3-0/+82
macros.The rest is some small misc. stuff. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175950 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-23ARM: Convenience aliases for 'srs*' instructions.Jim Grosbach3-0/+28
Handle an implied 'sp' operand. rdar://11466783 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175940 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22[mips] Emit call16 operator instead of got_disp. The former allows lazy binding.Akira Hatanaka1-3/+1
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175920 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22x86_64: designate most general purpose and SSE registers as callee save ↵Peter Collingbourne2-21/+28
under coldcc git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175911 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22R600/SI: Add pattern for sign extension of i1 to i32.Michel Danzer1-0/+5
16 more little piglits with radeonsi. NOTE: This is a candidate for the Mesa stable branch. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175887 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22R600/SI: Add pattern for logical or of i1 values.Michel Danzer1-0/+4
24 more little piglits with radeonsi. NOTE: This is a candidate for the Mesa stable branch. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175886 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22R600/SI: Add pattern for fceil.Michel Danzer1-1/+3
9 more little piglits with radeonsi. NOTE: This is a candidate for the Mesa stable branch. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175885 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22Make ARMAsmPrinter generate the correct alignment specifier syntax in ↵Kristof Beyls1-2/+1
instructions. The Printer will now print instructions with the correct alignment specifier syntax, like vld1.8 {d16}, [r0:64] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175884 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22Fix a nomenclature mistake. Slt->Slti in the functions. The "i" refersReed Kotler2-8/+8
to the immediate operand of sli or cmp function. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175865 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22Expand mips16 SelT form pseudso/macros.Reed Kotler3-0/+81
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175862 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-22Remove code copied from GenRegisterInfo.inc.Andrew Trick2-57/+0
There's no apparent reason this code was copied from generated source into a .cpp. It sets a bad example for those working on other targets and trying to understand the register info API. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175849 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21Move the eliminateCallFramePseudoInstr method from TargetRegisterInfoEli Bendersky53-569/+541
to TargetFrameLowering, where it belongs. Incidentally, this allows us to delete some duplicated (and slightly different!) code in TRI. There are potentially other layering problems that can be cleaned up as a result, or in a similar manner. The refactoring was OK'd by Anton Korobeynikov on llvmdev. Note: this touches the target interfaces, so out-of-tree targets may be affected. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175788 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21Hexagon: Expand cttz, ctlz, and ctpop for now.Anshuman Dasgupta1-0/+5
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175783 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21Radar numbers don't belong in source code.Evan Cheng3-4/+1
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175775 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21Trivial cleanupBill Schmidt1-2/+2
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175771 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21Large code model support for PowerPC.Bill Schmidt5-15/+20
Large code model is identical to medium code model except that the addis/addi sequence for "local" accesses is never used. All accesses use the addis/ld sequence. The coding changes are straightforward; most of the patch is taken up with creating variants of the medium model tests for large model. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175767 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21getX86SubSuperRegister has a special mode with High=true for i64 whichEli Bendersky1-17/+9
exists solely to enable it to call itself for i8 with some registers. The proposed patch simplifies the function somewhat to make the High bit only meaningful for the i8 mode, which makes sense. No functional difference (getX86SubSuperRegister is not getting called from anywhere outside with i64 and High=true). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175762 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21R600/SI: inline V_ADD|SUB_F32 patternsChristian Konig1-9/+5
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175758 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21R600/SI: replace IMPLICIT_DEF with SIOperand.ZEROChristian Konig1-1/+1
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175757 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21R600/SI: replace SI_V_CNDLT with a patternChristian Konig3-31/+5
It actually fixes quite a bunch of piglit tests. This is a candidate for the mesa-stable branch. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175756 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21R600/SI: use patterns for clamp, fabs, fnegChristian Konig2-40/+22
Instead of using custom inserters, it's simpler and should make DAG folding easier. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175755 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21R600/SI: add all the other missing asm operands v2Christian Konig2-22/+29
v2: put implicit parameters in [] Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175754 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21R600/SI: add the missing M*BUF|IMG asm operandsChristian Konig1-4/+8
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175753 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21R600/SI: add the missing S_* asm operandsChristian Konig1-18/+34
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175752 91177308-0d34-0410-b5e6-96231b3b80d8
2013-02-21R600/SI: rework VOP3 classesChristian Konig1-14/+14
Order the classes and add asm operands. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Tom Stellard <thomas.stellard@amd.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175751 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-19 09:34:29 +0000