summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/Hexagon/HexagonVLIWPacketizer.cpp
Commit message (Collapse)AuthorAgeFilesLines
* [Hexagon] Fix assert with packetizing IMPLICIT_DEF instructionsKrzysztof Parzyszek2018-04-061-1/+5
| | | | | | | | | | | | | | | | | | The compiler is generating packet with the following instructions, which causes an undefined register assert in the verifier. $r0 = IMPLICIT_DEF $r1 = IMPLICIT_DEF S2_storerd_io killed $r29, 0, killed %d0 The problem is that the packetizer is not saving the IMPLICIT_DEF instructions, which are needed when checking if it is legal to add the store instruction. The fix is to add the IMPLICIT_DEF instructions to the CurrentPacketMIs structure. Patch by Brendon Cahoon. llvm-svn: 329439
* [Hexagon] Prevent a stall across zero-latency instructions in a packetKrzysztof Parzyszek2018-04-061-15/+16
| | | | | | | | | | Packetizer keeps two zero-latency bound instrctions in the same packet ignoring the stalls on the later instruction. This should not be the case if there is no data dependence. Patch by Sumanth Gundapaneni. llvm-svn: 329437
* [Hexagon] Remove duplicated code, NFCKrzysztof Parzyszek2018-04-061-9/+0
| | | | llvm-svn: 329436
* [Hexagon] Avoid creating invalid offsets in packetizerKrzysztof Parzyszek2018-03-301-0/+3
| | | | | | | | | | Two memory instructions with a dependency only on the address register between the two (the first one of them being post-incrememnt) can be packetized together after the offset on the second was updated to the incremement value. Make sure that the new offset is valid for the instruction. llvm-svn: 328897
* [Hexagon] Subtarget feature to emit one instruction per packetKrzysztof Parzyszek2018-03-121-3/+4
| | | | | | | | | | | | | | | | | This adds two features: "packets", and "nvj". Enabling "packets" allows the compiler to generate instruction packets, while disabling it will prevent it and disable all optimizations that generate them. This feature is enabled by default on all subtargets. The feature "nvj" allows the compiler to generate new-value jumps and it implies "packets". It is enabled on all subtargets. The exception is made for packets with endloop instructions, since they require a certain minimum number of instructions in the packets to which they apply. Disabling "packets" will not prevent hardware loops from being generated. llvm-svn: 327302
* MachineFunction: Return reference from getFunction(); NFCMatthias Braun2017-12-151-1/+1
| | | | | | The Function can never be nullptr so we can return a reference. llvm-svn: 320884
* Rename LiveIntervalAnalysis.h to LiveIntervals.hMatthias Braun2017-12-131-0/+1
| | | | | | | | | | Headers/Implementation files should be named after the class they declare/define. Also eliminated an `#include "llvm/CodeGen/LiveIntervalAnalysis.h"` in favor of `class LiveIntarvals;` llvm-svn: 320546
* [Hexagon] Add support for Hexagon V65Krzysztof Parzyszek2017-12-111-16/+84
| | | | llvm-svn: 320404
* [CodeGen] Use MachineOperand::print in the MIRPrinter for MO_Register.Francis Visoiu Mistrih2017-12-071-12/+12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Work towards the unification of MIR and debug output by refactoring the interfaces. For MachineOperand::print, keep a simple version that can be easily called from `dump()`, and a more complex one which will be called from both the MIRPrinter and MachineInstr::print. Add extra checks inside MachineOperand for detached operands (operands with getParent() == nullptr). https://reviews.llvm.org/D40836 * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+)<def> ([^ ]+)/kill: \1 def \2 \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/kill: def ([^ ]+) ([^ ]+) ([^ ]+)<def>/kill: def \1 \2 def \3/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/<def>//g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<kill>/killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use,kill>/implicit killed \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<def[ ]*,[ ]*dead>/dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def[ ]*,[ ]*dead>/implicit-def dead \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-def>/implicit-def \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<imp-use>/implicit \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<internal>/internal \1/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" -o -name "*.s" \) -type f -print0 | xargs -0 sed -i '' -E 's/([^ ]+)<undef>/undef \1/g' llvm-svn: 320022
* [CodeGen] Print register names in lowercase in both MIR and debug outputFrancis Visoiu Mistrih2017-11-281-12/+12
| | | | | | | | | | | As part of the unification of the debug format and the MIR format, always print registers as lowercase. * Only debug printing is affected. It now follows MIR. Differential Revision: https://reviews.llvm.org/D40417 llvm-svn: 319187
* Fix a bunch more layering of CodeGen headers that are in TargetDavid Blaikie2017-11-171-2/+2
| | | | | | | | All these headers already depend on CodeGen headers so moving them into CodeGen fixes the layering (since CodeGen depends on Target, not the other way around). llvm-svn: 318490
* [Packetizer] Add function to check for aliasing between instructionsKrzysztof Parzyszek2017-10-201-1/+1
| | | | llvm-svn: 316243
* [Hexagon] Make sure that new-value jump is packetized with producerKrzysztof Parzyszek2017-10-111-9/+15
| | | | llvm-svn: 315510
* [Pipeliner] Improve serialization order for post-incrementsKrzysztof Parzyszek2017-10-111-0/+52
| | | | | | | | | | | | | | | | | | | The pipeliner is generating a serial sequence that causes poor register allocation when a post-increment instruction appears prior to the use of the post-increment register. This occurs when there is a circular set of dependences involved with a sequence of instructions in the same cycle. In this case, there is no serialization of the parallel semantics that will not cause an additional register to be allocated. This patch fixes the problem by changing the instructions so that the post-increment instruction is used by the subsequent instruction, which enables the register allocator to make a better decision and not require another register. Patch by Brendon Cahoon. llvm-svn: 315466
* [Hexagon] Fix some Clang-tidy modernize and Include What You Use warnings; ↵Eugene Zelenko2017-09-281-25/+40
| | | | | | other minor fixes (NFC). llvm-svn: 314467
* [Hexagon] Switch to parameterized register classes for HVXKrzysztof Parzyszek2017-09-151-2/+2
| | | | | | | This removes the duplicate HVX instruction set for the 128-byte mode. Single instruction set now works for both modes (64- and 128-byte). llvm-svn: 313362
* [Hexagon] Check for potential bank conflicts in post-RA schedulingKrzysztof Parzyszek2017-08-281-0/+1
| | | | | | | Insert artificial edges between loads that could cause a cache bank conflict. llvm-svn: 311901
* [Hexagon] Break up DAG mutations into separate classes, move to subtargetKrzysztof Parzyszek2017-08-281-1/+2
| | | | llvm-svn: 311895
* [Hexagon] Fix check for HMOTF_ConstExtend operand flagKrzysztof Parzyszek2017-07-101-7/+5
| | | | | | This fixes https://llvm.org/PR33718. llvm-svn: 307566
* Sort the remaining #include lines in include/... and lib/....Chandler Carruth2017-06-061-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | I did this a long time ago with a janky python script, but now clang-format has built-in support for this. I fed clang-format every line with a #include and let it re-sort things according to the precise LLVM rules for include ordering baked into clang-format these days. I've reverted a number of files where the results of sorting includes isn't healthy. Either places where we have legacy code relying on particular include ordering (where possible, I'll fix these separately) or where we have particular formatting around #include lines that I didn't want to disturb in this patch. This patch is *entirely* mechanical. If you get merge conflicts or anything, just ignore the changes in this patch and run clang-format over your #include lines in the files. Sorry for any noise here, but it is important to keep these things stable. I was seeing an increasing number of patches with irrelevant re-ordering of #include lines because clang-format was used. This patch at least isolates that churn, makes it easy to skip when resolving conflicts, and gets us to a clean baseline (again). llvm-svn: 304787
* [Hexagon] Fix dependence check in the packetizerKrzysztof Parzyszek2017-06-011-26/+23
| | | | | | | An incorrect check in the packetizer lead to an attempt to convert an unconditional branch to a .new (conditional) form. llvm-svn: 304442
* [Hexagon] Fix comment in HexagonPacketizer::runOnMachineFunctionKrzysztof Parzyszek2017-05-241-2/+2
| | | | | | | | Patch by Wei-Ren Chen. Differential Revision: https://reviews.llvm.org/D33439 llvm-svn: 303745
* [Hexagon] Use automatically-generated scheduling information for HVXKrzysztof Parzyszek2017-05-031-68/+42
| | | | | | Patch by Jyotsna Verma. llvm-svn: 302073
* [Hexagon] Implement undoing .cur instructions in packetizerKrzysztof Parzyszek2017-05-031-2/+2
| | | | | | | | | | | | | The packetizer needs to convert .cur instruction to its regular form if the use is not in the same packet as the .cur. The code in the packetizer handles one type of .cur, which is the vector load case. This patch updates the packetizer so that it can undo all the .cur instructions. In the test case, the .cur is the 128B version, but there are also the post-increment versions. Patch by Brendon Cahoon. llvm-svn: 302032
* [Hexagon] Don't ignore mult-cycle latency informationKrzysztof Parzyszek2017-05-021-7/+22
| | | | | | | | | | | | | | | | | | | | | | | | The compiler was generating code that ends up ignoring a multiple latency dependence between two instructions by scheduling the intructions in back-to-back packets. The packetizer needs to end a packet if the latency of the current current insruction and the source in the previous packet is greater than 1 cycle. This case occurs when there is still room in the current packet, but scheduling the instruction causes a stall. Instead, the packetizer should start a new packet. Also, if the current packet already contains a stall, then it is okay to add another instruction to the packet that also causes a stall. This occurs when there are no instructions that can be scheduled in between the producer and consumer instructions. This patch changes the latency for loads to 2 cycles from 3 cycles. This change refects that a load only needs to be separated by one extra packet to eliminate the stall. Patch by Ikhlas Ajbar. llvm-svn: 301954
* [Hexagon] Pick a dot-old instruction that matches the architectureKrzysztof Parzyszek2017-03-061-1/+1
| | | | llvm-svn: 297031
* [Hexagon] Start using regmasks on callsKrzysztof Parzyszek2017-02-171-4/+53
| | | | | | Reapply r295371 with a fix for the Windows bot failures. llvm-svn: 295504
* Revert "[Hexagon] Start using regmasks on calls"Rafael Espindola2017-02-171-53/+4
| | | | | | | | | | This reverts commit r295371. It broke windows bots: http://bb.pgr.jp/builders/ninja-clang-i686-msc19-R/builds/11402/steps/test-llvm/logs/stdio llvm-svn: 295402
* [Hexagon] Start using regmasks on callsKrzysztof Parzyszek2017-02-161-4/+53
| | | | | | All the cool targets are doing it... llvm-svn: 295371
* [Hexagon] Update instruction typesKrzysztof Parzyszek2017-02-071-1/+3
| | | | | | | | | Remove TypeXTYPE, TypeALU32, TypeSYSTEM, TypeJR, and instead use their architecture counterparts. Patch by Colin LeMahieu. llvm-svn: 294321
* Use StringRef in Pass/PassManager APIs (NFC)Mehdi Amini2016-10-011-3/+1
| | | | llvm-svn: 283004
* MachineFunctionProperties/MIRParser: Rename AllVRegsAllocated->NoVRegs, ↵Matthias Braun2016-08-251-1/+1
| | | | | | | | | | | | | compute it Rename AllVRegsAllocated to NoVRegs. This avoids the connotation of running after register and simply describes that no vregs are used in a machine function. With that we can simply compute the property and do not need to dump/parse it in .mir files. Differential Revision: http://reviews.llvm.org/D23850 llvm-svn: 279698
* CodeGen: Remove MachineFunctionAnalysis => Enable (Machine)ModulePassesMatthias Braun2016-08-241-1/+0
| | | | | | | | | | | | | | | | | | | | | | Re-apply this patch, hopefully I will get away without any warnings in the constructor now. This patch removes the MachineFunctionAnalysis. Instead we keep a map from IR Function to MachineFunction in the MachineModuleInfo. This allows the insertion of ModulePasses into the codegen pipeline without breaking it because the MachineFunctionAnalysis gets dropped before a module pass. Peak memory should stay unchanged without a ModulePass in the codegen pipeline: Previously the MachineFunction was freed at the end of a codegen function pipeline because the MachineFunctionAnalysis was dropped; With this patch the MachineFunction is freed after the AsmPrinter has finished. Differential Revision: http://reviews.llvm.org/D23736 llvm-svn: 279602
* Revert r279564. It introduces undefined behavior (binding a reference to aRichard Smith2016-08-231-0/+1
| | | | | | | dereferenced null pointer) in MachineModuleInfo::MachineModuleInfo that causes -Werror builds (including several buildbots) to fail. llvm-svn: 279580
* CodeGen: Remove MachineFunctionAnalysis => Enable (Machine)ModulePassesMatthias Braun2016-08-231-1/+0
| | | | | | | | | | | | | | | | | | | | | | | Re-apply this commit with the deletion of a MachineFunction delegated to a separate pass to avoid use after free when doing this directly in AsmPrinter. This patch removes the MachineFunctionAnalysis. Instead we keep a map from IR Function to MachineFunction in the MachineModuleInfo. This allows the insertion of ModulePasses into the codegen pipeline without breaking it because the MachineFunctionAnalysis gets dropped before a module pass. Peak memory should stay unchanged without a ModulePass in the codegen pipeline: Previously the MachineFunction was freed at the end of a codegen function pipeline because the MachineFunctionAnalysis was dropped; With this patch the MachineFunction is freed after the AsmPrinter has finished. Differential Revision: http://reviews.llvm.org/D23736 llvm-svn: 279564
* [Hexagon] Packetize return value setup with the return instructionKrzysztof Parzyszek2016-08-231-3/+4
| | | | | | Commit r279241 unintentionally reverted that ability. llvm-svn: 279526
* Revert "(HEAD -> master, origin/master, origin/HEAD) CodeGen: Remove ↵Matthias Braun2016-08-231-0/+1
| | | | | | | | | | MachineFunctionAnalysis => Enable (Machine)ModulePasses" Reverting while tracking down a use after free. This reverts commit r279502. llvm-svn: 279503
* CodeGen: Remove MachineFunctionAnalysis => Enable (Machine)ModulePassesMatthias Braun2016-08-231-1/+0
| | | | | | | | | | | | | | | | | | | This patch removes the MachineFunctionAnalysis. Instead we keep a map from IR Function to MachineFunction in the MachineModuleInfo. This allows the insertion of ModulePasses into the codegen pipeline without breaking it because the MachineFunctionAnalysis gets dropped before a module pass. Peak memory should stay unchanged without a ModulePass in the codegen pipeline: Previously the MachineFunction was freed at the end of a codegen function pipeline because the MachineFunctionAnalysis was dropped; With this patch the MachineFunction is freed after the AsmPrinter has finished. Differential Revision: http://reviews.llvm.org/D23736 llvm-svn: 279502
* [Hexagon] Avoid register dependencies on indirect branches in packetizerKrzysztof Parzyszek2016-08-191-7/+8
| | | | | | | Do not packetize the instruction setting the branch address with the indirect branch itself. llvm-svn: 279324
* [Hexagon] Enforce LLSC packetization rulesKrzysztof Parzyszek2016-08-191-0/+18
| | | | | | | | | Ensure that load locked and store conditional instructions are only packetized with ALU32 instructions. Patch by Ben Craig. llvm-svn: 279272
* [Hexagon] Mark PS_jumpret as pseudo-instruction, expand it into J2_jumprKrzysztof Parzyszek2016-08-191-6/+3
| | | | llvm-svn: 279241
* Use the range variant of find instead of unpacking begin/endDavid Majnemer2016-08-111-1/+1
| | | | | | | | | If the result of the find is only used to compare against end(), just use is_contained instead. No functionality change is intended. llvm-svn: 278433
* Replace MachineInstr* with MachineInstr& in TargetInstrInfo, NFCKrzysztof Parzyszek2016-08-011-4/+4
| | | | | | There were a few cases introduced with the modulo scheduler. llvm-svn: 277358
* [Hexagon] Referencify MachineInstr in HexagonInstrInfo, NFCKrzysztof Parzyszek2016-07-291-177/+177
| | | | llvm-svn: 277220
* MachineFunction: Return reference for getFrameInfo(); NFCMatthias Braun2016-07-281-2/+2
| | | | | | | getFrameInfo() never returns nullptr so we should use a reference instead of a pointer. llvm-svn: 277017
* [Hexagon] Post-increment loads/stores enhancementsKrzysztof Parzyszek2016-07-261-2/+8
| | | | | | | - Generate vector post-increment stores more aggressively. - Predicate post-increment and vector stores in early if-conversion. llvm-svn: 276800
* [Hexagon] Update store offset when not packetizing it with allocframeKrzysztof Parzyszek2016-07-261-15/+49
| | | | | | | | | | When the packetizer wants to put a store to a stack slot in the same packet with an allocframe, it updates the store offset to reflect the value of SP before it is updated by allocframe. If the store cannot be packetized with the allocframe after all, the offset needs to be updated back to the previous value. llvm-svn: 276749
* [Hexagon] Add a scheduling DAG mutationKrzysztof Parzyszek2016-07-151-0/+2
| | | | | | | - Remove output dependencies on USR_OVF register. - Update chain edge latencies between v60 vector loads/stores. llvm-svn: 275586
* [Hexagon] Packetize function call arguments with tail call instructionsKrzysztof Parzyszek2016-07-141-1/+1
| | | | | | | | On Hexagon is it legal to packetize the instructions setting up call arguments with the call instruction itself. This was already done, except for tail calls. Make sure tail calls are handled as well. llvm-svn: 275458
* Hexagon: Avoid implicit iterator conversions, NFCDuncan P. N. Exon Smith2016-07-121-14/+18
| | | | | | | | | | | | | | Avoid implicit iterator conversions from MachineInstrBundleIterator to MachineInstr* in the Hexagon backend, mostly by preferring MachineInstr& over MachineInstr* and switching to range-based for loops. There's a long tail of API cleanup here, but I'm planning to leave the rest to the Hexagon maintainers. HexagonInstrInfo defines many of its own predicates, and most of them still take MachineInstr*. Some of those actually check for nullptr, so I didn't feel comfortable changing them to MachineInstr& en masse. llvm-svn: 275142
OpenPOWER on IntegriCloud