aboutsummaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86InstrInfo.cpp
AgeCommit message (Collapse)Author
2009-02-06Move getPointerRegClass from TargetInstrInfo to TargetRegisterInfo.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@63938 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-06Add TargetInstrInfo::isSafeToMoveRegisterClassDefs. It returns true if it's ↵Evan Cheng
safe to move an instruction which defines a value in the register class. Replace pre-splitting specific IgnoreRegisterClassBarriers with this new hook. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@63936 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-06Get rid of one more non-DebugLoc getNode andDale Johannesen
its corresponding getTargetNode. Lots of caller changes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@63904 91177308-0d34-0410-b5e6-96231b3b80d8
2009-02-03Create DebugLoc information in FastISel. Several temporary methods wereBill Wendling
created. Specifically, those BuildMIs which use "DebugLoc::getUnknownLoc()". I'll remove them soon. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@63584 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-20Change TargetInstrInfo::isMoveInstr to return source and destination ↵Evan Cheng
sub-register indices as well. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@62600 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-15Add load-folding table entries for BT*ri8 instructions.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@62267 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-09Add load-folding table entries for MOVDQA.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61972 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-07Add load-folding table entries for cmovno too.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61841 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-07Define instructions for cmovo and cmovno.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61836 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-07X86_COND_C and X86_COND_NC are alternate mnemonics forDan Gohman
X86_COND_B and X86_COND_AE, respectively. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61835 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-06Revert r42653 and forward-port the code that lets INC64_32r beDan Gohman
converted to LEA64_32r in x86's convertToThreeAddress. This replaces code like this: movl %esi, %edi inc %edi with this: lea 1(%rsi), %edi which appears to be beneficial. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61830 91177308-0d34-0410-b5e6-96231b3b80d8
2009-01-05Tidy up #includes, deleting a bunch of unnecessary #includes.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61715 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-23Make the fuse-failed debug output human-readable.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61356 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-18Fixed x86 code generation of multiple for v2i64. It was incorrect for SSE4.1.Mon P Wang
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61211 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-05Reason #3 from 60595 doesn't hold true. If we can fold a PIC load from ↵Evan Cheng
constpool into a use, the rewrite happens at time of spill (not in VirtRegMap). Later on, if the GlobalBaseReg is spilled, the spiller can see the use uses GlobalBaseReg and do the right thing. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60596 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-05Effectively undo 60461 in PIC mode which simply transform V_SET0 / ↵Evan Cheng
V_SETALLONES into a load from constpool in order to fold into restores. This is not safe to do when PIC base is being used for a number of reasons: 1. GlobalBaseReg may have been spilled. 2. It may not be live at the use. 3. Spiller doesn't know this is happening so it won't prevent GlobalBaseReg from being spilled later (That by itself is a nasty hack. It's needed because we don't insert the reload until later). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60595 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-03Split foldMemoryOperand into public non-virtual and protected virtualDan Gohman
parts, and add target-independent code to add/preserve MachineMemOperands. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60488 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-03Mark x86's V_SET0 and V_SETALLONES with isSimpleLoad, and teach X86'sDan Gohman
foldMemoryOperand how to "fold" them, by converting them into constant-pool loads. When they aren't folded, they use xorps/cmpeqd, but for example when register pressure is high, they may now be folded as memory operands, which reduces register pressure. Also, mark V_SET0 isAsCheapAsAMove so that two-address-elimination will remat it instead of copying zeros around (V_SETALLONES was already marked). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60461 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-02Reapply r60382. This time, don't mark "ADC" nodes with "implicit EFLAGS".Bill Wendling
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60385 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-01Temporarily revert r60382. It caused CodeGen/X86/i2k.ll and others to fail.Bill Wendling
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60383 91177308-0d34-0410-b5e6-96231b3b80d8
2008-12-01- Have "ADD" instructions return an implicit EFLAGS.Bill Wendling
- Add support for seto, setno, setc, and setnc instructions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60382 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-26Generate something sensible for an [SU]ADDO op when the overflow/carry flag isBill Wendling
the conditional for the BRCOND statement. For instance, it will generate: addl %eax, %ecx jo LOF instead of addl %eax, %ecx ; About 10 instructions to compare the signs of LHS, RHS, and sum. jl LOF git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60123 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-26Fish kill flag annotations in PUSH instructions.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60095 91177308-0d34-0410-b5e6-96231b3b80d8
2008-11-18Add more const qualifiers. This fixes build breakage from r59540.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@59542 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-27For now, don't split live intervals around x87 stack register barriers. ↵Evan Cheng
FpGET_ST0_80 must be right after a call instruction (and ADJCALLSTACKUP) so we need to find a way to prevent reload of x87 registers between them. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58230 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-25Generate code for TLS instructions.Nicolas Geoffray
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@58141 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-21Optimized FCMP_OEQ and FCMP_UNE for x86.Dan Gohman
Where previously LLVM might emit code like this: ucomisd %xmm1, %xmm0 setne %al setp %cl orb %al, %cl jne .LBB4_2 it now emits this: ucomisd %xmm1, %xmm0 jne .LBB4_2 jp .LBB4_2 It has fewer instructions and uses fewer registers, but it does have more branches. And in the case that this code is followed by a non-fallthrough edge, it may be followed by a jmp instruction, resulting in three branch instructions in sequence. Some effort is made to avoid this situation. To achieve this, X86ISelLowering.cpp now recognizes FCMP_OEQ and FCMP_UNE in lowered form, and replace them with code that emits two branches, except in the case where it would require converting a fall-through edge to an explicit branch. Also, X86InstrInfo.cpp's branch analysis and transform code now knows now to handle blocks with multiple conditional branches. It uses loops instead of having fixed checks for up to two instructions. It can now analyze and transform code generated from FCMP_OEQ and FCMP_UNE. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57873 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-21When the coalescer is doing rematerializing, have it removeDan Gohman
the copy instruction from the instruction list before asking the target to create the new instruction. This gets the old instruction out of the way so that it doesn't interfere with the target's rematerialization code. In the case of x86, this helps it find more cases where EFLAGS is not live. Also, in the X86InstrInfo.cpp, teach isSafeToClobberEFLAGS to check to see if it reached the end of the block after scanning each instruction, instead of just before. This lets it notice when the end of the block is only two instructions away, without doing any additional scanning. These changes allow rematerialization to clobber EFLAGS in more cases, for example using xor instead of mov to set the return value to zero in the included testcase. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57872 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-17Define patterns for shld and shrd that match immediateDan Gohman
shift counts, and patterns that match dynamic shift counts when the subtract is obscured by a truncate node. Add DAGCombiner support for recognizing rotate patterns when the shift counts are defined by truncate nodes. Fix and simplify the code for commuting shld and shrd instructions to work even when the given instruction doesn't have a parent, and when the caller needs a new instruction. These changes allow LLVM to use the shld, shrd, rol, and ror instructions on x86 to replace equivalent code using two shifts and an or in many more cases. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57662 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-16Const-ify several TargetInstrInfo methods.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57622 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-12Update size of inst correctly with segment override.Anton Korobeynikov
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57414 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-04Revert r56675 - it breaks unwinding runtime everywhere.Anton Korobeynikov
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57048 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-03Switch the MachineOperand accessors back to the short names likeDan Gohman
isReg, etc., from isRegister, etc. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57006 91177308-0d34-0410-b5e6-96231b3b80d8
2008-09-30Move the GlobalBaseReg field out of X86ISelDAGToDAG.cppDan Gohman
and X86FastISel.cpp into X86MachineFunction.h, so that it can be shared, instead of having each selector keep track of its own. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@56825 91177308-0d34-0410-b5e6-96231b3b80d8
2008-09-26Mark lea fi# as being really rematerializable.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@56698 91177308-0d34-0410-b5e6-96231b3b80d8
2008-09-26Avoid spilling EBP / RBP twice in the prologue.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@56675 91177308-0d34-0410-b5e6-96231b3b80d8
2008-09-23Move the code for initializing the global base reg out ofDan Gohman
X86ISelDAGToDAG.cpp and into X86InstrInfo.cpp. This will allow it to be reused by FastISel. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@56494 91177308-0d34-0410-b5e6-96231b3b80d8
2008-09-13Remove isImm(), isReg(), and friends, in favor of Dan Gohman
isImmediate(), isRegister(), and friends, to avoid confusion about having two different names with the same meaning. I'm not attached to the longer names, and would be ok with changing to the shorter names if others prefer it. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@56189 91177308-0d34-0410-b5e6-96231b3b80d8
2008-08-29Use static_cast instead of C style cast.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@55552 91177308-0d34-0410-b5e6-96231b3b80d8
2008-08-29Backing out 55521. Not safe.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@55548 91177308-0d34-0410-b5e6-96231b3b80d8
2008-08-28Swap fp comparison operands and change predicate to allow load folding.Evan Cheng
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@55521 91177308-0d34-0410-b5e6-96231b3b80d8
2008-08-26These assertions should be return false's instead, allowing the client to ↵Owen Anderson
detect the failure. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@55377 91177308-0d34-0410-b5e6-96231b3b80d8
2008-08-26Make TargetInstrInfo::copyRegToReg return a bool indicating whether the copy ↵Owen Anderson
requested was inserted or not. This allows bitcast in fast isel to properly handle the case where an appropriate reg-to-reg copy is not available. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@55375 91177308-0d34-0410-b5e6-96231b3b80d8
2008-08-14Convert uses of std::vector in TargetInstrInfo to SmallVector. This change ↵Owen Anderson
had to be propoagated down into all the targets and up into all clients of this API. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@54802 91177308-0d34-0410-b5e6-96231b3b80d8
2008-08-08Add an EXTRACTPSmr pattern to match the pattern thatDan Gohman
X86ISelLowering creates. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@54544 91177308-0d34-0410-b5e6-96231b3b80d8
2008-08-07Re-enable elimination of unnecessary SUBREG_TO_REG instructions inDan Gohman
LowerSubregs, and fix an x86-64 isel bug that this exposed. SUBREG_TO_REG for x86-64 implicit zero extension is only safe for isel to generate when the source is known to always have zeros in the high 32 bits. The EXTRACT_SUBREG instruction does not clear the high 32 bits. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@54444 91177308-0d34-0410-b5e6-96231b3b80d8
2008-07-27Rename SDOperand to SDValue.Dan Gohman
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@54128 91177308-0d34-0410-b5e6-96231b3b80d8
2008-07-21Use movaps instead of movups to spill 16-byte vector values when default ↵Evan Cheng
alignment is >= 16. This fixes some massive performance regressions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@53844 91177308-0d34-0410-b5e6-96231b3b80d8
2008-07-19Use aligned stack spills, where possible. This fixes PR2549.Anton Korobeynikov
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@53784 91177308-0d34-0410-b5e6-96231b3b80d8
2008-07-17Add a new function, ReplaceAllUsesOfValuesWith, which handles bulkDan Gohman
replacement of multiple values. This is slightly more efficient than doing multiple ReplaceAllUsesOfValueWith calls, and theoretically could be optimized even further. However, an important property of this new function is that it handles the case where the source value set and destination value set overlap. This makes it feasible for isel to use SelectNodeTo in many very common cases, which is advantageous because SelectNodeTo avoids a temporary node and it doesn't require CSEMap updates for users of values that don't change position. Revamp MorphNodeTo, which is what does all the work of SelectNodeTo, to handle operand lists more efficiently, and to correctly handle a number of corner cases to which its new wider use exposes it. This commit also includes a change to the encoding of post-isel opcodes in SDNodes; now instead of being sandwiched between the target-independent pre-isel opcodes and the target-dependent pre-isel opcodes, post-isel opcodes are now represented as negative values. This makes it possible to test if an opcode is pre-isel or post-isel without having to know the size of the current target's post-isel instruction set. These changes speed up llc overall by 3% and reduce memory usage by 10% on the InstructionCombining.cpp testcase with -fast and -regalloc=local. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@53728 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2025-08-18 15:29:58 +0000