| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | Generated files for previous patch. | Dale Johannesen | 2008-09-26 | 3 | -1823/+1800 | |
| | | | | | llvm-svn: 56679 | |||||
| * | Another file I forgot. | Dale Johannesen | 2008-09-26 | 1 | -1/+0 | |
| | | | | | llvm-svn: 56678 | |||||
| * | Add "inreg" field to CallSDNode (doesn't increase | Dale Johannesen | 2008-09-26 | 16 | -47/+37 | |
| | | | | | | | | | | its size). Adjust various lowering functions to pass this info through from CallInst. Use it to implement sseregparm returns on X86. Remove X86_ssecall calling convention. llvm-svn: 56677 | |||||
| * | Factor out the code for determining when symblic addresses | Dan Gohman | 2008-09-26 | 4 | -17/+50 | |
| | | | | | | | | | | require RIP-relative addressing and use it to fix a bug in X86FastISel in x86-64 PIC mode, where it was trying to use base/index registers with RIP-relative addresses. This fixes a bunch of x86-64 testsuite failures. llvm-svn: 56676 | |||||
| * | Avoid spilling EBP / RBP twice in the prologue. | Evan Cheng | 2008-09-26 | 1 | -8/+18 | |
| | | | | | llvm-svn: 56675 | |||||
| * | We don't need to insert copies for implicit_def's. | Owen Anderson | 2008-09-26 | 1 | -1/+5 | |
| | | | | | llvm-svn: 56674 | |||||
| * | X86 address displacement field must be interpreted as a 32-bit value. | Evan Cheng | 2008-09-26 | 1 | -3/+4 | |
| | | | | | llvm-svn: 56665 | |||||
| * | CMake: Builds all targets. | Oscar Fuentes | 2008-09-26 | 13 | -42/+226 | |
| | | | | | llvm-svn: 56641 | |||||
| * | Disable support for x86_f80 in X86FastISel. Supporting it would | Dan Gohman | 2008-09-26 | 1 | -9/+6 | |
| | | | | | | | require more work. llvm-svn: 56637 | |||||
| * | If we have a function with an unreachable statement such that the ending debug | Bill Wendling | 2008-09-26 | 4 | -10/+54 | |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | information is in an unreachable block, then it's possible that the high/low pc values won't be set for the dwarf information. E.g., this function: void abort(void) __attribute__((__noreturn__)); void dead_beef(void) __attribute__ ((noreturn)); int *b; void dead_beef(void) { *b=0xdeadbeef; abort(); } has a call to "@llvm.dbg.region.end" only in the unreachable block: define void @dead_beef() noreturn nounwind { entry: call void @llvm.dbg.func.start(...) call void @llvm.dbg.stoppoint(...) ... call void @abort( ) noreturn nounwind unreachable return: ; No predecessors! call void @llvm.dbg.stoppoint(...) call void @llvm.dbg.region.end(...) ret void } The dwarf information emitted is something like: 0x00000084: TAG_subprogram [5] AT_name( "dead_beef" ) AT_external( 0x01 ) AT_prototyped( 0x01 ) AT_decl_file( 0x01 ) AT_decl_line( 0x08 ) Note that this is *not* the best fix for this problem, but a band-aid for an gaping wound. This code needs to be changed when we revamp our debugging information. llvm-svn: 56628 | |||||
| * | Prefer movlhps over punpcklqdq, etc. in more cases. | Evan Cheng | 2008-09-25 | 1 | -5/+5 | |
| | | | | | llvm-svn: 56627 | |||||
| * | Fix a bug in which address displacements were being added to the | Dan Gohman | 2008-09-25 | 1 | -1/+9 | |
| | | | | | | | load from the stub, instead of the result of the load from the stub. llvm-svn: 56626 | |||||
| * | Make pointer parameter const for isUsedInBasicBlock. | Bill Wendling | 2008-09-25 | 1 | -1/+1 | |
| | | | | | llvm-svn: 56625 | |||||
| * | Large mechanical patch. | Devang Patel | 2008-09-25 | 44 | -1007/+1007 | |
| | | | | | | | | | | | | | | | | s/ParamAttr/Attribute/g s/PAList/AttrList/g s/FnAttributeWithIndex/AttributeWithIndex/g s/FnAttr/Attribute/g This sets the stage - to implement function notes as function attributes and - to distinguish between function attributes and return value attributes. This requires corresponding changes in llvm-gcc and clang. llvm-svn: 56622 | |||||
| * | Reapply 56585:56589 with proper fix for some gcc versions | Anton Korobeynikov | 2008-09-25 | 9 | -183/+221 | |
| | | | | | llvm-svn: 56621 | |||||
| * | With sse3 and when the source is a load or has multiple uses, favors movddup ↵ | Evan Cheng | 2008-09-25 | 3 | -17/+97 | |
| | | | | | | | over shuffp*, pshufd, etc. Without sse3 or when the source is from a register, make use of movlhps llvm-svn: 56620 | |||||
| * | Accept 'inreg' attribute on x86 functions as | Dale Johannesen | 2008-09-25 | 2 | -6/+15 | |
| | | | | | | | | | meaning sse_regparm (i.e. float/double values go in XMM0 instead of ST0). Update documentation to reflect reality. llvm-svn: 56619 | |||||
| * | Avoid a spurious extra space character when printing empty structs. | Dan Gohman | 2008-09-25 | 1 | -3/+4 | |
| | | | | | llvm-svn: 56616 | |||||
| * | Support for i1 XOR in FastISel. It is actually safe because | Dan Gohman | 2008-09-25 | 1 | -2/+3 | |
| | | | | | | | i1 operands are assumed to already by zero-extended. llvm-svn: 56615 | |||||
| * | Don't print fast-isel debug messages by default. Thanks Chris! | Dan Gohman | 2008-09-25 | 1 | -3/+6 | |
| | | | | | llvm-svn: 56614 | |||||
| * | Don't forget the newline in debug output. | Dan Gohman | 2008-09-25 | 1 | -1/+1 | |
| | | | | | llvm-svn: 56613 | |||||
| * | FastISel support for debug info. | Dan Gohman | 2008-09-25 | 3 | -3/+117 | |
| | | | | | llvm-svn: 56610 | |||||
| * | bug 2812: Segmentation fault on a big emdiam processor. | Richard Pennington | 2008-09-25 | 1 | -1/+1 | |
| | | | | | llvm-svn: 56609 | |||||
| * | PIC support in X86FastISel. | Dan Gohman | 2008-09-25 | 1 | -10/+57 | |
| | | | | | llvm-svn: 56608 | |||||
| * | Temporarily backing out 56585:56589 to unbreak the build. | Evan Cheng | 2008-09-25 | 9 | -210/+183 | |
| | | | | | llvm-svn: 56607 | |||||
| * | Fix a recent fast-isel coverage regression - don't bail out before | Dan Gohman | 2008-09-25 | 1 | -3/+4 | |
| | | | | | | | giving the target a chance to materialize constants. llvm-svn: 56605 | |||||
| * | Enable DeadMachineInstructionElim when Fast-ISel is enabled. | Dan Gohman | 2008-09-25 | 2 | -3/+13 | |
| | | | | | llvm-svn: 56604 | |||||
| * | Add debug output to this pass. | Dan Gohman | 2008-09-25 | 1 | -0/+2 | |
| | | | | | llvm-svn: 56602 | |||||
| * | pmovsxbq etc. requires sse4.1. | Evan Cheng | 2008-09-25 | 1 | -6/+6 | |
| | | | | | llvm-svn: 56600 | |||||
| * | Refactor the code that adds standard LLVM codegen passes into | Dan Gohman | 2008-09-25 | 1 | -109/+44 | |
| | | | | | | | | a separate function, eliminating duplication between the add-passes-for-file and add-passes-for-machine-code code. llvm-svn: 56599 | |||||
| * | <rdar://problem/6234798> Assertion failed: ↵ | Evan Cheng | 2008-09-25 | 1 | -2/+5 | |
| | | | | | | | (!OpInfo.AssignedRegs.Regs.empty() && "Couldn't allocate input reg!") llvm-svn: 56597 | |||||
| * | Give LowerSubregs.cpp a top-level description. | Dan Gohman | 2008-09-24 | 1 | -0/+7 | |
| | | | | | llvm-svn: 56596 | |||||
| * | Fix patterns for SSE4.1 move and sign extend instructions. Also add ↵ | Evan Cheng | 2008-09-24 | 2 | -6/+86 | |
| | | | | | | | instructions which fold VZEXT_MOVL and VZEXT_LOAD. llvm-svn: 56594 | |||||
| * | X86ISD::VZEXT_LOAD should produce and fold a chain. | Evan Cheng | 2008-09-24 | 1 | -10/+14 | |
| | | | | | llvm-svn: 56593 | |||||
| * | Remove SelectionDag early allocation of registers | Dale Johannesen | 2008-09-24 | 3 | -41/+61 | |
| | | | | | | | | for earlyclobbers. Teach Local RA about earlyclobber, and add some tests for it. llvm-svn: 56592 | |||||
| * | Minor cleanup | Anton Korobeynikov | 2008-09-24 | 4 | -0/+10 | |
| | | | | | llvm-svn: 56588 | |||||
| * | Get rid of virtual inheritance for ARM TAI | Anton Korobeynikov | 2008-09-24 | 3 | -33/+40 | |
| | | | | | llvm-svn: 56587 | |||||
| * | Get rid of virtual inheritance for PPC TAI | Anton Korobeynikov | 2008-09-24 | 2 | -24/+23 | |
| | | | | | llvm-svn: 56586 | |||||
| * | Use crazy template-based inheritance instead of virtual one. | Anton Korobeynikov | 2008-09-24 | 4 | -127/+138 | |
| | | | | | llvm-svn: 56585 | |||||
| * | Use helper | Anton Korobeynikov | 2008-09-24 | 1 | -8/+2 | |
| | | | | | llvm-svn: 56584 | |||||
| * | SmallPtrSet will be better | Anton Korobeynikov | 2008-09-24 | 1 | -3/+2 | |
| | | | | | llvm-svn: 56583 | |||||
| * | Get rid of ReadOnlySection duplicate | Anton Korobeynikov | 2008-09-24 | 7 | -23/+15 | |
| | | | | | llvm-svn: 56582 | |||||
| * | Use named sections, where they should be | Anton Korobeynikov | 2008-09-24 | 1 | -7/+5 | |
| | | | | | llvm-svn: 56581 | |||||
| * | Get rid of now unused {Four,Eight,Sixteen}ByteConstantSection | Anton Korobeynikov | 2008-09-24 | 7 | -35/+11 | |
| | | | | | llvm-svn: 56580 | |||||
| * | Use generic section-handling stuff to emit constant pool entries | Anton Korobeynikov | 2008-09-24 | 1 | -45/+36 | |
| | | | | | llvm-svn: 56579 | |||||
| * | Cleanup | Anton Korobeynikov | 2008-09-24 | 2 | -2/+2 | |
| | | | | | llvm-svn: 56578 | |||||
| * | Get rid of duplicate char*/Section* stuff for TLS sections | Anton Korobeynikov | 2008-09-24 | 3 | -11/+7 | |
| | | | | | llvm-svn: 56577 | |||||
| * | Cleanup, no functionality change | Anton Korobeynikov | 2008-09-24 | 2 | -4/+4 | |
| | | | | | llvm-svn: 56576 | |||||
| * | Get rid of duplicate char*/Section* DataSection | Anton Korobeynikov | 2008-09-24 | 8 | -16/+14 | |
| | | | | | llvm-svn: 56575 | |||||
| * | Get rid of duplicate char*/Section* TextSection | Anton Korobeynikov | 2008-09-24 | 8 | -21/+21 | |
| | | | | | llvm-svn: 56574 | |||||

