aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Object file output from llc isn't experimental anymore.Benjamin Kramer2012-06-111-1/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158305 91177308-0d34-0410-b5e6-96231b3b80d8
* Re-enable the CMN instruction.Bill Wendling2012-06-116-69/+166
| | | | | | | | | | We turned off the CMN instruction because it had semantics which we weren't getting correct. If we are comparing with an immediate, then it's okay to use the CMN instruction. <rdar://problem/7569620> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158302 91177308-0d34-0410-b5e6-96231b3b80d8
* InstCombine: factor code better.Benjamin Kramer2012-06-111-14/+7
| | | | | | No functionality change. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158301 91177308-0d34-0410-b5e6-96231b3b80d8
* InstCombine: Turn (zext A) == (B & (1<<X)-1) into A == (trunc B), narrowing ↵Benjamin Kramer2012-06-102-1/+45
| | | | | | | | | | | | | | | | | | | | the compare. This saves a cast, and zext is more expensive on platforms with subreg support than trunc is. This occurs in the BSD implementation of memchr(3), see PR12750. On the synthetic benchmark from that bug stupid_memchr and bsd_memchr have the same performance now when not inlining either function. stupid_memchr: 323.0us bsd_memchr: 321.0us memchr: 479.0us where memchr is the llvm-gcc compiled bsd_memchr from osx lion's libc. When inlining is enabled bsd_memchr still regresses down to llvm-gcc memchr time, I haven't fully understood the issue yet, something is grossly mangling the loop after inlining. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158297 91177308-0d34-0410-b5e6-96231b3b80d8
* Enable ILP scheduling for all nodes by default on PPC.Hal Finkel2012-06-104-8/+10
| | | | | | | | | | | | | | | | | | | | | | | | Over the entire test-suite, this has an insignificantly negative average performance impact, but reduces some of the worst slowdowns from the anti-dep. change (r158294). Largest speedups: SingleSource/Benchmarks/Stanford/Quicksort - 28% SingleSource/Benchmarks/Stanford/Towers - 24% SingleSource/Benchmarks/Shootout-C++/matrix - 23% MultiSource/Benchmarks/SciMark2-C/scimark2 - 19% MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount - 15% (matrix and automotive-bitcount were both in the top-5 slowdown list from the anti-dep. change) Largest slowdowns: MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 28% MultiSource/Benchmarks/mediabench/gsm/toast/toast - 26% MultiSource/Benchmarks/MiBench/automotive-susan/automotive-susan - 21% SingleSource/Benchmarks/CoyoteBench/lpbench - 20% MultiSource/Applications/d/make_dparser - 16% git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158296 91177308-0d34-0410-b5e6-96231b3b80d8
* Add AutoUpgrade support for the SSE4 ptest intrinsics.Nadav Rotem2012-06-103-6/+103
| | | | | | | | Patch by Michael Kuperstein. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158295 91177308-0d34-0410-b5e6-96231b3b80d8
* Use critical anti-dep. breaking on all PPC targets, but also add other ↵Hal Finkel2012-06-101-4/+11
| | | | | | | | | | | | | | | | | | | | | | | | register classes. Using 'all' instead of 'critical' would be better because it would make it easier to satisfy the bundling constraints, but, as noted in the FIXME, that is currently not possible with the crs. This yields an average 1% speedup over the entire test suite (on Power 7). Largest speedups: SingleSource/Benchmarks/Shootout-C++/moments - 40% MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 28% SingleSource/Benchmarks/BenchmarkGame/nsieve-bits - 26% SingleSource/Benchmarks/McGill/misr - 23% MultiSource/Applications/JM/ldecod/ldecod - 22% Largest slowdowns: SingleSource/Benchmarks/Shootout-C++/matrix - -29% SingleSource/Benchmarks/Shootout-C++/ary3 - -22% MultiSource/Benchmarks/BitBench/uuencode/uuencode - -18% SingleSource/Benchmarks/Shootout-C++/ary - -17% MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount - -15% git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158294 91177308-0d34-0410-b5e6-96231b3b80d8
* Add intrinsics for immediate form of XOP vprot instructions. Use i128mem ↵Craig Topper2012-06-102-35/+55
| | | | | | instead of f128mem for integer XOP instructions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158291 91177308-0d34-0410-b5e6-96231b3b80d8
* Improve ext/trunc patterns on PPC64.Hal Finkel2012-06-092-11/+5
| | | | | | | | | | The PPC64 backend had patterns for i32 <-> i64 extensions and truncations that would leave self-moves in the final assembly. Replacing those patterns with ones based on the SUBREG builtins yields better-looking code. Thanks to Jakob and Owen for their suggestions in this matter. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158283 91177308-0d34-0410-b5e6-96231b3b80d8
* Use XOP vpcom intrinsics in patterns instead of a target specific SDNode ↵Craig Topper2012-06-094-60/+13
| | | | | | type. Remove the custom lowering code that selected the SDNode type. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158279 91177308-0d34-0410-b5e6-96231b3b80d8
* Replace XOP vpcom intrinsics with fewer intrinsics that take the immediate ↵Craig Topper2012-06-094-431/+149
| | | | | | as an argument. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158278 91177308-0d34-0410-b5e6-96231b3b80d8
* Hashing: Remove outdated comment. Support for reserved hash values was ↵Benjamin Kramer2012-06-091-4/+0
| | | | | | removed in r151865. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158276 91177308-0d34-0410-b5e6-96231b3b80d8
* Disabling a spurious deprecation warning about using PathV1 from within the ↵Aaron Ballman2012-06-091-0/+10
| | | | | | PathV1 implementation file. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158274 91177308-0d34-0410-b5e6-96231b3b80d8
* Fixing a typo in the comments.Aaron Ballman2012-06-091-1/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158273 91177308-0d34-0410-b5e6-96231b3b80d8
* Allocate the contents of DwarfDebug's StringMaps in a single big ↵Benjamin Kramer2012-06-092-5/+6
| | | | | | BumpPtrAllocator. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158265 91177308-0d34-0410-b5e6-96231b3b80d8
* Silence a gcc-4.6 warning: GCC fails to understand that secondReg and cmpOp2 areDuncan Sands2012-06-091-1/+1
| | | | | | | correlated, and thinks that cmpOp2 may be used uninitialized. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158263 91177308-0d34-0410-b5e6-96231b3b80d8
* Enable tail merging on PPC.Hal Finkel2012-06-092-12/+6
| | | | | | | | | | | | | | | | | | | | | | | | Tail merging had been disabled on PPC because it would disturb bundling decisions made during pre-RA scheduling on the 970 cores. Now, however, all bundling decisions are made during post-RA scheduling, and tail merging is generally beneficial (the average test-suite speedup is insignificantly positive). Largest test-suite speedups: MultiSource/Benchmarks/mediabench/gsm/toast/toast - 30% MultiSource/Benchmarks/BitBench/uuencode/uuencode - 23% SingleSource/Benchmarks/Shootout-C++/ary - 21% SingleSource/Benchmarks/Stanford/Queens - 17% Largest slowdowns: MultiSource/Benchmarks/MiBench/security-sha/security-sha - 24% MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 22% MultiSource/Applications/JM/ldecod/ldecod - 14% MultiSource/Benchmarks/mediabench/g721/g721encode/encode - 9% This is improved by using full (instead of just critical) anti-dependency breaking, but doing so still causes miscompiles and so cannot yet be enabled by default. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158259 91177308-0d34-0410-b5e6-96231b3b80d8
* Register pressure: added getPressureAfterInstr.Andrew Trick2012-06-092-33/+104
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158256 91177308-0d34-0410-b5e6-96231b3b80d8
* Sketch a LiveRegMatrix analysis pass.Jakob Stoklund Olesen2012-06-094-0/+297
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The LiveRegMatrix represents the live range of assigned virtual registers in a Live interval union per register unit. This is not fundamentally different from the interference tracking in RegAllocBase that both RABasic and RAGreedy use. The important differences are: - LiveRegMatrix tracks interference per register unit instead of per physical register. This makes interference checks cheaper and assignments slightly more expensive. For example, the ARM D7 reigster has 24 aliases, so we would check 24 physregs before assigning to one. With unit-based interference, we check 2 units before assigning to 2 units. - LiveRegMatrix caches regmask interference checks. That is currently duplicated functionality in RABasic and RAGreedy. - LiveRegMatrix is a pass which makes it possible to insert target-dependent passes between register allocation and rewriting. Such passes could tweak the register assignments with interference checking support from LiveRegMatrix. Eventually, RABasic and RAGreedy will be switched to LiveRegMatrix. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158255 91177308-0d34-0410-b5e6-96231b3b80d8
* Test commitJack Carter2012-06-091-0/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158250 91177308-0d34-0410-b5e6-96231b3b80d8
* Also compute MBB live-in lists in the new rewriter pass.Jakob Stoklund Olesen2012-06-096-89/+32
| | | | | | | | | This deduplicates some code from the optimizing register allocators, and it means that it is now possible to change the register allocators' solutions simply by editing the VirtRegMap between the register allocator pass and the rewriter. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158249 91177308-0d34-0410-b5e6-96231b3b80d8
* Convert comments to proper Doxygen comments.Dmitri Gribenko2012-06-099-38/+38
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158248 91177308-0d34-0410-b5e6-96231b3b80d8
* Removing strange "using" declarations form TargetInstrInfo.Andrew Trick2012-06-081-4/+0
| | | | | | I can't imagine why these were added. Trial and error. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158247 91177308-0d34-0410-b5e6-96231b3b80d8
* Reintroduce VirtRegRewriter.Jakob Stoklund Olesen2012-06-089-78/+126
| | | | | | | | | | | | | | | | | | OK, not really. We don't want to reintroduce the old rewriter hacks. This patch extracts virtual register rewriting as a separate pass that runs after the register allocator. This is possible now that CodeGen/Passes.cpp can configure the full optimizing register allocator pipeline. The rewriter pass uses register assignments in VirtRegMap to rewrite virtual registers to physical registers, and it inserts kill flags based on live intervals. These finalization steps are the same for the optimizing register allocators: RABasic, RAGreedy, and PBQP. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158244 91177308-0d34-0410-b5e6-96231b3b80d8
* Don't run RAFast in the optimizing regalloc pipeline.Jakob Stoklund Olesen2012-06-0823-24/+24
| | | | | | | | | | | The fast register allocator is not supposed to work in the optimizing pipeline. It doesn't make sense to compute live intervals, run full copy coalescing, and then run RAFast. Fast register allocation in the optimizing pipeline is better done by RABasic. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158242 91177308-0d34-0410-b5e6-96231b3b80d8
* canonicalize:Nuno Lopes2012-06-082-4/+29
| | | | | | | | | | | | | | -%a + 42 into 42 - %a previously we were emitting: -(%a + 42) This fixes the infinite loop in PR12338. The generated code is still not perfect, though. Will work on that next git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158237 91177308-0d34-0410-b5e6-96231b3b80d8
* Start implementing pre-ra if-converter: using speculation and selects to ↵Evan Cheng2012-06-081-6/+15
| | | | | | eliminate branches. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158234 91177308-0d34-0410-b5e6-96231b3b80d8
* TargetInstrInfo hooks implemented in codegen should be declared pure virtual.Andrew Trick2012-06-082-19/+39
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158233 91177308-0d34-0410-b5e6-96231b3b80d8
* Reapply commit 158073 with a fix (the testcase was already committed). TheDuncan Sands2012-06-081-123/+120
| | | | | | | | | | | | | | | | | | | problem was that by moving instructions around inside the function, the pass could accidentally move the iterator being used to advance over the function too. Fix this by only processing the instruction equal to the iterator, and leaving processing of instructions that might not be equal to the iterator to later (later = after traversing the basic block; it could also wait until after traversing the entire function, but this might make the sets quite big). Original commit message: Grab-bag of reassociate tweaks. Unify handling of dead instructions and instructions to reoptimize. Exploit this to more systematically eliminate dead instructions (this isn't very useful in practice but is convenient for analysing some testcase I am working on). No need for WeakVH any more: use an AssertingVH instead. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158226 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove the TODO statement in the PPC README re: CTR loopsHal Finkel2012-06-081-1/+0
| | | | | | | | As Chris points out, this can now be removed! TODO: check if the associated section on viterbi's inner loop can also be removed. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158224 91177308-0d34-0410-b5e6-96231b3b80d8
* Enable PPC CTR loop formation by default.Hal Finkel2012-06-084-13/+11
| | | | | | | | | | | | | | | | | | | | | | Thanks to Jakob's help, this now causes no new test suite failures! Over the entire test suite, this gives an average 1% speedup. The largest speedups are: SingleSource/Benchmarks/Misc/pi - 108% SingleSource/Benchmarks/CoyoteBench/lpbench - 54% MultiSource/Benchmarks/Prolangs-C/unix-smail/unix-smail - 50% SingleSource/Benchmarks/Shootout/ary3 - 32% SingleSource/Benchmarks/Shootout-C++/matrix - 30% The largest slowdowns are: MultiSource/Benchmarks/mediabench/gsm/toast/toast - -30% MultiSource/Benchmarks/Prolangs-C/bison/mybison - -25% MultiSource/Benchmarks/BitBench/uuencode/uuencode - -22% MultiSource/Applications/d/make_dparser - -14% SingleSource/Benchmarks/Shootout-C++/ary - -13% In light of these slowdowns, additional profiling work is obviously needed! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158223 91177308-0d34-0410-b5e6-96231b3b80d8
* Mark the PPC CTRRC and CTRRC8 register classes as non-allocatable.Hal Finkel2012-06-081-2/+10
| | | | | | | | | | | Marking these classes as non-alocatable allows CTR loop generation to work correctly with the block placement passes, etc. These register classes are currently used only by some unused TCRETURN patterns. In future cleanup, these will be removed. Thanks again to Jakob for suggesting this fix to the CTR loop problem! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158221 91177308-0d34-0410-b5e6-96231b3b80d8
* Enable optimization for integer ABS on X86 if Subtarget has CMOV.Manman Ren2012-06-081-3/+5
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158220 91177308-0d34-0410-b5e6-96231b3b80d8
* Test case for r158160Manman Ren2012-06-081-0/+42
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158218 91177308-0d34-0410-b5e6-96231b3b80d8
* Sched itinerary fix: Avoid static initializers.Andrew Trick2012-06-082-5/+14
| | | | | | | | This fixes an accidental dependence on static initialization order that I introduced yesterday. Thank you Lang!!! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158215 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix a crash in APInt::lshr when shiftAmt > BitWidth.Chad Rosier2012-06-082-1/+9
| | | | | | | Patch by James Benton <jbenton@vmware.com>. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158213 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix Target->Codegen dependence.Andrew Trick2012-06-082-195/+205
| | | | | | | | | | | | | | | | | Bulk move of TargetInstrInfo implementation into TargetInstrInfoImpl. This is dirty because the code isn't part of TargetInstrInfoImpl class, nor should it be, because the methods are not target hooks. However, it's the current mechanism for keeping libTarget useful outside the backend. You'll get a not-so-nice link error if you invoke a TargetInstrInfo method that depends on CodeGen. The TargetInstrInfoImpl class should probably be removed since it doesn't really solve this problem. To really fix this, we probably need separate interfaces for the CodeGen/nonCodeGen sides of TargetInstrInfo. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158212 91177308-0d34-0410-b5e6-96231b3b80d8
* BoundsChecking: add support for ConstantPointerNull. fixes a bunch of ↵Nuno Lopes2012-06-081-6/+7
| | | | | | instrumentation failures in loops with reallocs git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158210 91177308-0d34-0410-b5e6-96231b3b80d8
* test/CodeGen/Generic/APIntLoadStore.ll: Mark as XFAIL:ppc since r157911.NAKAMURA Takumi2012-06-081-0/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158209 91177308-0d34-0410-b5e6-96231b3b80d8
* Disable the PPC CTR-Loops pass by default.Hal Finkel2012-06-084-6/+19
| | | | | | | | | | The pass itself works well, but the something in the Machine* infrastructure does not understand terminators which define registers. Without the ability to use the block-placement pass, etc. this causes performance regressions (and so is turned off by default). Turning off the analysis turns off the problems with the Machine* infrastructure. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158206 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix a bug in the new PPC CTR-Loops pass.Hal Finkel2012-06-082-0/+88
| | | | | | | | | The code which tests for an induction operation cannot assume that any ADDI instruction will have a register operand because the operand could also be a frame index; for example: %vreg16<def> = ADDI8 <fi#0>, 0; G8RC:%vreg16 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158205 91177308-0d34-0410-b5e6-96231b3b80d8
* Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form ↵Hal Finkel2012-06-0810-18/+890
| | | | | | | | | | CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158204 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert commit 158073 while waiting for a fix. The issue is that reassociateDuncan Sands2012-06-082-111/+144
| | | | | | | | | | | | | | | | | | can move instructions within the instruction list. If the instruction just happens to be the one the basic block iterator is pointing to, and it is moved to a different basic block, then we get into an infinite loop due to the iterator running off the end of the basic block (for some reason this doesn't fire any assertions). Original commit message: Grab-bag of reassociate tweaks. Unify handling of dead instructions and instructions to reoptimize. Exploit this to more systematically eliminate dead instructions (this isn't very useful in practice but is convenient for analysing some testcase I am working on). No need for WeakVH any more: use an AssertingVH instead. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158199 91177308-0d34-0410-b5e6-96231b3b80d8
* cmake: Pass the -m32 flag to modules if LLVM_BUILD_32_BITS is enabledTobias Grosser2012-06-081-0/+1
| | | | | | | | | | | This was previously only done for executables and shared libraries, but not for modules. As modules are essentially shared libraries (that need to be dlopened explicitly), threating them the same as shared libraries seems reasonable. This fixes the LLVM_BUILD_32_BITS build of Polly. Contributed by: Ondra Hosek <ondra.hosek@gmail.com> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158195 91177308-0d34-0410-b5e6-96231b3b80d8
* Teach the AsmMatcherEmitter to allow InstAlias' where the suboperands of a ↵Owen Anderson2012-06-082-5/+27
| | | | | | complex operand are called out explicitly in the asm string. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158183 91177308-0d34-0410-b5e6-96231b3b80d8
* [CMake] Promote extension warnings to errors.Michael J. Spencer2012-06-071-1/+4
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158176 91177308-0d34-0410-b5e6-96231b3b80d8
* X86: optimize generated code for integer ABSManman Ren2012-06-072-8/+54
| | | | | | | | | | | | | | | | | | | | | This patch will generate the following for integer ABS: movl %edi, %eax negl %eax cmovll %edi, %eax INSTEAD OF movl %edi, %ecx sarl $31, %ecx leal (%rdi,%rcx), %eax xorl %ecx, %eax There exists a target-independent DAG combine for integer ABS, which converts integer ABS to sar+add+xor. For X86, we match this pattern back to neg+cmov. This is implemented in PerformXorCombine. rdar://10695237 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158175 91177308-0d34-0410-b5e6-96231b3b80d8
* [CMake] Order MSVC warnings numerically.Michael J. Spencer2012-06-071-2/+2
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158171 91177308-0d34-0410-b5e6-96231b3b80d8
* [CMake] Adjust MSVC warnings.Michael J. Spencer2012-06-071-2/+6
| | | | | | | Remove /Wall from LLVM_ENABLE_WARNINGS (it's useless) and promote 4239 to a level 1 warning. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158170 91177308-0d34-0410-b5e6-96231b3b80d8
* Do not optimize the used bits of the x86 vselect condition operand, when the ↵Nadav Rotem2012-06-071-4/+6
| | | | | | | | | | condition operand is a vector of 1-bit predicates. This may happen on MIC devices. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158168 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.1 at 2025-02-05 03:33:40 +0000