Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Add a temporary command line option to verify machine code after each spill or | Jakob Stoklund Olesen | 2010-10-28 | 1 | -0/+6 |
| | | | | | | split. llvm-svn: 117597 | ||||
* | Revert r117582, which reverted r77396. Searching PATH for a string | Dan Gohman | 2010-10-28 | 1 | -1/+1 |
| | | | | | | | | | | | | which contains slashes is inconsistent with the meaning of PATH on Unix-type platforms, and pretty surprising. If the user has given a specific path to execute and we can't execute it, we should fail and say why. (Apparently the new posix_spawn code doesn't always say why, but that's a separate issue.) llvm-svn: 117596 | ||||
* | Add support for the .string directive. | Rafael Espindola | 2010-10-28 | 1 | -8/+10 |
| | | | | llvm-svn: 117592 | ||||
* | Do not work too hard to find type's file info. There is a special field to ↵ | Devang Patel | 2010-10-28 | 1 | -2/+2 |
| | | | | | | record file info. llvm-svn: 117588 | ||||
* | Defined weak symbols should have non-zero value. | Rafael Espindola | 2010-10-28 | 1 | -4/+3 |
| | | | | llvm-svn: 117585 | ||||
* | llvmc: Make ExecuteProgram() look in the driver directory first. | Mikhail Glushenkov | 2010-10-28 | 1 | -3/+6 |
| | | | | llvm-svn: 117584 | ||||
* | Remove an unnecessary check and an unnecessary temporary. | Mikhail Glushenkov | 2010-10-28 | 1 | -3/+2 |
| | | | | llvm-svn: 117583 | ||||
* | Revert r77396. | Mikhail Glushenkov | 2010-10-28 | 1 | -1/+1 |
| | | | | | | | | | | | | | | Original commit message: On "Unix", if Program::FindProgramByName is given a name containing slashes, just go with it, regardless of whether it looks like it will be executable. This follows the behavior of sh(1) more closely. It's better when behaviour is consistent between platforms. This change also makes FindExecutable() behave as expected on unix-likes (before this commit, it used to always succeed). llvm-svn: 117582 | ||||
* | Trailing whitespace. | Mikhail Glushenkov | 2010-10-28 | 1 | -4/+4 |
| | | | | llvm-svn: 117581 | ||||
* | Fix relocations with renamed symbols. | Rafael Espindola | 2010-10-28 | 1 | -5/+6 |
| | | | | llvm-svn: 117575 | ||||
* | Reduce malloc thrashing. | Benjamin Kramer | 2010-10-28 | 1 | -1/+1 |
| | | | | llvm-svn: 117572 | ||||
* | PLD, PLDW, PLI encodings, plus refactor their use of addrmode2. | Jim Grosbach | 2010-10-28 | 4 | -20/+44 |
| | | | | llvm-svn: 117571 | ||||
* | Aliases defined with .symver should copy the binding of the symbols they alias. | Rafael Espindola | 2010-10-28 | 1 | -6/+21 |
| | | | | | | | Move the existing patching for undefined symbols so that all the patching is done in the same function. llvm-svn: 117570 | ||||
* | Technically DIFile scope should also be handled here. | Devang Patel | 2010-10-28 | 1 | -0/+4 |
| | | | | llvm-svn: 117563 | ||||
* | rearrange ParseRegisterList. | Chris Lattner | 2010-10-28 | 1 | -16/+30 |
| | | | | llvm-svn: 117560 | ||||
* | refactor some code to simplify it, eliminating some owningptr's. | Chris Lattner | 2010-10-28 | 1 | -65/+60 |
| | | | | llvm-svn: 117559 | ||||
* | Teach the DAG combiner to fold a splat of a splat. Radar 8597790. | Bob Wilson | 2010-10-28 | 1 | -24/+28 |
| | | | | | | Also do some minor refactoring to reduce indentation. llvm-svn: 117558 | ||||
* | Use the IDVal directly as there's no need to convert to std::string. | Roman Divacky | 2010-10-28 | 1 | -2/+2 |
| | | | | | | Pointed out by Chris! llvm-svn: 117557 | ||||
* | Implement .equ directive as a synonym to .set. | Roman Divacky | 2010-10-28 | 1 | -6/+6 |
| | | | | llvm-svn: 117553 | ||||
* | Fix PR8494: when reading invalid bitcode, getTypeByID may return | Duncan Sands | 2010-10-28 | 1 | -2/+7 |
| | | | | | | a null pointer. llvm-svn: 117551 | ||||
* | Implement R_X86_64_DTPOFF32. | Rafael Espindola | 2010-10-28 | 1 | -0/+3 |
| | | | | llvm-svn: 117548 | ||||
* | Implement TLSLD. | Rafael Espindola | 2010-10-28 | 2 | -0/+6 |
| | | | | llvm-svn: 117547 | ||||
* | Implement DTPOFF. | Rafael Espindola | 2010-10-28 | 2 | -0/+6 |
| | | | | llvm-svn: 117546 | ||||
* | Implement TLSLDM. | Rafael Espindola | 2010-10-28 | 2 | -0/+6 |
| | | | | llvm-svn: 117544 | ||||
* | Implement VK_GOTNTPOFF and switch RelocNeedsGOT to use VariantKind. | Rafael Espindola | 2010-10-28 | 2 | -15/+18 |
| | | | | llvm-svn: 117543 | ||||
* | Reindent. | Mikhail Glushenkov | 2010-10-28 | 1 | -71/+71 |
| | | | | llvm-svn: 117538 | ||||
* | Re-commit 117518 and 117519 now that ARM MC test failures are out of the way. | Evan Cheng | 2010-10-28 | 5 | -23/+88 |
| | | | | llvm-svn: 117531 | ||||
* | Revert 117518 and 117519 for now. They changed scheduling and cause MC tests ↵ | Evan Cheng | 2010-10-28 | 5 | -88/+23 |
| | | | | | | to fail. Ugh. llvm-svn: 117520 | ||||
* | - Assign load / store with shifter op address modes the right itinerary classes. | Evan Cheng | 2010-10-28 | 4 | -23/+85 |
| | | | | | | | | | | - For now, loads of [r, r] addressing mode is the same as the [r, r lsl/lsr/asr #] variants. ARMBaseInstrInfo::getOperandLatency() should identify the former case and reduce the output latency by 1. - Also identify [r, r << 2] case. This special form of shifter addressing mode is "free". llvm-svn: 117519 | ||||
* | Fix a major bug in operand latency computation. The use index must be adjusted | Evan Cheng | 2010-10-28 | 1 | -0/+3 |
| | | | | | | by the number of defs first for it to match the instruction itinerary. llvm-svn: 117518 | ||||
* | Fix pastos in handling of AVX cvttsd2si, PR8491. | Dale Johannesen | 2010-10-28 | 1 | -4/+4 |
| | | | | | | | Bruno, please review, but I'm pretty sure this is right. Patch by Alex Mac! llvm-svn: 117514 | ||||
* | Add correct NEON encodings for vtbl and vtbx. | Owen Anderson | 2010-10-28 | 1 | -29/+29 |
| | | | | llvm-svn: 117513 | ||||
* | Add correct NEON encodings for vext, vtrn, vuzp, and vzip. | Owen Anderson | 2010-10-27 | 1 | -2/+8 |
| | | | | llvm-svn: 117512 | ||||
* | Fix compiler warnings about signed/unsigned comparisons. | Bob Wilson | 2010-10-27 | 1 | -2/+2 |
| | | | | llvm-svn: 117511 | ||||
* | Teach InstCombine not to use Add and Neg on FP. PR 8490. | Dale Johannesen | 2010-10-27 | 1 | -1/+8 |
| | | | | llvm-svn: 117510 | ||||
* | Shifter ops are not always free. Do not fold them (especially to form | Evan Cheng | 2010-10-27 | 2 | -16/+119 |
| | | | | | | | complex load / store addressing mode) when they have higher cost and when they have more than one use. llvm-svn: 117509 | ||||
* | Putting r117193 back except for the compile time cost. Rather than assuming ↵ | Evan Cheng | 2010-10-27 | 1 | -3/+10 |
| | | | | | | fallthroughs uses all registers, just gather the union of all successor liveins. llvm-svn: 117506 | ||||
* | Refactor ARM STR/STRB instruction patterns into STR{B}i12 and STR{B}rs, like | Jim Grosbach | 2010-10-27 | 9 | -101/+94 |
| | | | | | | | | the LDR instructions have. This makes the literal/register forms of the instructions explicit and allows us to assign scheduling itineraries appropriately. rdar://8477752 llvm-svn: 117505 | ||||
* | Provide correct encodings for NEON vcvt, which has its own special immediate ↵ | Owen Anderson | 2010-10-27 | 4 | -6/+16 |
| | | | | | | | | encoding for specifying fractional bits for fixed point conversions. llvm-svn: 117501 | ||||
* | Trailing whitespace | Jim Grosbach | 2010-10-27 | 1 | -17/+17 |
| | | | | llvm-svn: 117496 | ||||
* | Provide correct encodings for the get_lane and set_lane variants of vmov. | Owen Anderson | 2010-10-27 | 2 | -41/+64 |
| | | | | llvm-svn: 117495 | ||||
* | Add support for R_386_TLS_GD, R_386_TLS_LE_32, R_386_TLS_IE and R_386_TLS_LE. | Rafael Espindola | 2010-10-27 | 1 | -0/+17 |
| | | | | llvm-svn: 117494 | ||||
* | Added the x86 instruction ud2b (2nd official undefined instruction). | Kevin Enderby | 2010-10-27 | 1 | -1/+3 |
| | | | | llvm-svn: 117485 | ||||
* | JIT imm12 encoding for constant pool entry references. | Jim Grosbach | 2010-10-27 | 1 | -0/+4 |
| | | | | llvm-svn: 117483 | ||||
* | SelectionDAG shuffle nodes do not allow operands with different numbers of | Bob Wilson | 2010-10-27 | 1 | -0/+55 |
| | | | | | | | | | | | | | | | | | | | elements than the result vector type. So, when an instruction like: %8 = shufflevector <2 x float> %4, <2 x float> %7, <4 x i32> <i32 1, i32 0, i32 3, i32 2> is translated to a DAG, each operand is changed to a concat_vectors node that appends 2 undef elements. That is: shuffle [a,b], [c,d] is changed to: shuffle [a,b,u,u], [c,d,u,u] That's probably the right thing for x86 but for NEON, we'd much rather have: shuffle [a,b,c,d], undef Teach the DAG combiner how to do that transformation for ARM. Radar 8597007. llvm-svn: 117482 | ||||
* | Implement R_X86_64_GOTTPOFF, R_X86_64_TLSGD and R_X86_64_TPOFF32. | Rafael Espindola | 2010-10-27 | 1 | -0/+12 |
| | | | | llvm-svn: 117481 | ||||
* | ARM JIT fix for LDRi12 and company. | Jim Grosbach | 2010-10-27 | 2 | -4/+18 |
| | | | | llvm-svn: 117478 | ||||
* | Replace pointer arithmetic with StringRef::substr. | Benjamin Kramer | 2010-10-27 | 1 | -6/+5 |
| | | | | llvm-svn: 117477 | ||||
* | Provide correct NEON encodings for vdup. | Owen Anderson | 2010-10-27 | 2 | -8/+42 |
| | | | | llvm-svn: 117475 | ||||
* | x86-Win32: Switch ftol2 calling convention from stdcall to C. | Michael J. Spencer | 2010-10-27 | 1 | -2/+2 |
| | | | | llvm-svn: 117474 |