| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | add a section about API changes. | Chris Lattner | 2007-05-17 | 1 | -10/+59 |
| | | | | | llvm-svn: 37181 | ||||
| * | More effective breakdown of memcpy into repeated load/store. These are now | Dale Johannesen | 2007-05-17 | 2 | -1/+77 |
| | | | | | | | | | in the order lod;lod;lod;sto;sto;sto which means the load-store optimizer has a better chance of producing ldm/stm. Ideally you would get cooperation from the RA as well but this is not there yet. llvm-svn: 37179 | ||||
| * | Correct a name in a comment. | Dan Gohman | 2007-05-17 | 1 | -3/+4 |
| | | | | | llvm-svn: 37178 | ||||
| * | silence some "comparison between signed and unsigned integer expressions" | Chris Lattner | 2007-05-17 | 1 | -3/+3 |
| | | | | | | | warnings llvm-svn: 37177 | ||||
| * | minor tweak | Chris Lattner | 2007-05-17 | 1 | -3/+4 |
| | | | | | llvm-svn: 37176 | ||||
| * | Get rid of leading zeros in the output of toString. | Reid Spencer | 2007-05-17 | 1 | -8/+27 |
| | | | | | llvm-svn: 37175 | ||||
| * | New test case. | Evan Cheng | 2007-05-17 | 1 | -0/+23 |
| | | | | | llvm-svn: 37174 | ||||
| * | Fix a bogus check that prevented folding VECTOR_SHUFFLE to UNDEF; add an ↵ | Evan Cheng | 2007-05-17 | 1 | -24/+61 |
| | | | | | | | optimization to fold VECTOR_SHUFFLE to a zero vector. llvm-svn: 37173 | ||||
| * | Added missing patterns for UNPCKH* and PUNPCKH*. | Evan Cheng | 2007-05-17 | 1 | -0/+20 |
| | | | | | llvm-svn: 37172 | ||||
| * | Fix some sporadic segfaults that are triggered when SmallVector's heap | Dan Gohman | 2007-05-17 | 1 | -3/+3 |
| | | | | | | | | | | storage lands near the end of the available address space. In the expression Begin+N > Capacity, the Begin+N was overflowing. Fix this by replacing it by with an expression that doesn't involve computation of an address beyond the end of allocated memory. llvm-svn: 37171 | ||||
| * | add testcase for 128-bit add/sub | Chris Lattner | 2007-05-17 | 1 | -0/+39 |
| | | | | | llvm-svn: 37170 | ||||
| * | disable MaskedValueIsZero, ComputeMaskedBits, and SimplifyDemandedBits for | Chris Lattner | 2007-05-17 | 1 | -0/+13 |
| | | | | | | | | i128 integers. The 64-bit masks are not wide enough to represent the results. These should be converted to APInt someday. llvm-svn: 37169 | ||||
| * | add expand support for ADDC/SUBC/ADDE/SUBE so we can codegen 128-bit add/sub ↵ | Chris Lattner | 2007-05-17 | 1 | -0/+42 |
| | | | | | | | on 32-bit (or less) targets llvm-svn: 37168 | ||||
| * | Regenerate. | Reid Spencer | 2007-05-17 | 1 | -24/+27 |
| | | | | | llvm-svn: 37166 | ||||
| * | Make Perl a required dependency and cause configure script to fail if it | Reid Spencer | 2007-05-17 | 1 | -0/+1 |
| | | | | | | | is not found. llvm-svn: 37164 | ||||
| * | This is the correct fix for PR1427. This fixes mmx-shuffle.ll and doesn't | Chris Lattner | 2007-05-17 | 1 | -2/+5 |
| | | | | | | | cause other regressions. llvm-svn: 37160 | ||||
| * | Revert patch for PR1427. It breaks almost all vector tests. | Anton Korobeynikov | 2007-05-17 | 1 | -10/+1 |
| | | | | | llvm-svn: 37159 | ||||
| * | add support for 128-bit add/sub on ppc64 | Chris Lattner | 2007-05-17 | 1 | -0/+34 |
| | | | | | llvm-svn: 37158 | ||||
| * | Print integer values as both decimal and hexadecimal for convenience | Reid Spencer | 2007-05-17 | 1 | -1/+1 |
| | | | | | | | of verifying result values when debugging. llvm-svn: 37156 | ||||
| * | add support for 128-bit integer add/sub | Chris Lattner | 2007-05-17 | 1 | -0/+20 |
| | | | | | llvm-svn: 37154 | ||||
| * | For lshr by 0 bits, just return *this as a short cut. This also prevents | Reid Spencer | 2007-05-17 | 1 | -0/+6 |
| | | | | | | | undefined behavior when the width > 64 bits. llvm-svn: 37153 | ||||
| * | New test. | Devang Patel | 2007-05-17 | 1 | -0/+24 |
| | | | | | llvm-svn: 37151 | ||||
| * | Fix PR1427 and test/CodeGen/X86/mmx-shuffle.ll | Chris Lattner | 2007-05-17 | 1 | -1/+10 |
| | | | | | llvm-svn: 37141 | ||||
| * | testcase for PR1427 | Chris Lattner | 2007-05-17 | 1 | -0/+29 |
| | | | | | llvm-svn: 37140 | ||||
| * | Remove. Not needed. | Evan Cheng | 2007-05-17 | 2 | -9/+0 |
| | | | | | llvm-svn: 37139 | ||||
| * | Default implementation of TargetInstrInfo::getBlockSize(). | Evan Cheng | 2007-05-16 | 1 | -0/+4 |
| | | | | | llvm-svn: 37138 | ||||
| * | Add target hook to specify block size limit for if-conversion. | Evan Cheng | 2007-05-16 | 3 | -0/+22 |
| | | | | | llvm-svn: 37134 | ||||
| * | Merged in both release announcement guts. | Tanya Lattner | 2007-05-16 | 1 | -12/+241 |
| | | | | | llvm-svn: 37131 | ||||
| * | Don't fold bitconvert(load) for preinc/postdec loads. Likewise stores. | Dale Johannesen | 2007-05-16 | 1 | -1/+3 |
| | | | | | llvm-svn: 37130 | ||||
| * | isBlockPredicable() always ignore terminal instructions; add comments. | Evan Cheng | 2007-05-16 | 1 | -13/+23 |
| | | | | | llvm-svn: 37126 | ||||
| * | ARM::tB is also predicable. | Evan Cheng | 2007-05-16 | 1 | -2/+5 |
| | | | | | llvm-svn: 37125 | ||||
| * | PredicateInstruction returns true if the operation was successful. | Evan Cheng | 2007-05-16 | 4 | -20/+29 |
| | | | | | llvm-svn: 37124 | ||||
| * | Add default implementation of PredicateInstruction(). | Evan Cheng | 2007-05-16 | 1 | -0/+20 |
| | | | | | llvm-svn: 37123 | ||||
| * | Rename M_PREDICATED to M_PREDICABLE; Moved isPredicable() to MachineInstr. | Evan Cheng | 2007-05-16 | 2 | -14/+18 |
| | | | | | llvm-svn: 37121 | ||||
| * | Move if-conversion after all passes that may use register scavenger. | Evan Cheng | 2007-05-16 | 2 | -9/+3 |
| | | | | | llvm-svn: 37120 | ||||
| * | Removed isPredicable(). | Evan Cheng | 2007-05-16 | 2 | -10/+0 |
| | | | | | llvm-svn: 37119 | ||||
| * | Make ARM::B isPredicable; Make Bcc and MOVCC condition option a normal ↵ | Evan Cheng | 2007-05-16 | 1 | -5/+6 |
| | | | | | | | operand so they are not predicable. llvm-svn: 37118 | ||||
| * | Added isPredicable bit to class Instruction. | Evan Cheng | 2007-05-16 | 1 | -0/+1 |
| | | | | | llvm-svn: 37117 | ||||
| * | Rename M_PREDICATED to M_PREDICABLE; opcode can be specified isPredicable ↵ | Evan Cheng | 2007-05-16 | 3 | -4/+4 |
| | | | | | | | without having a PredicateOperand. llvm-svn: 37116 | ||||
| * | Rename M_PREDICATED to M_PREDICABLE; Move TargetInstrInfo::isPredicatable() ↵ | Evan Cheng | 2007-05-16 | 2 | -15/+10 |
| | | | | | | | to MachineInstr::isPredicable(). llvm-svn: 37115 | ||||
| * | Fix a bug in the "fromString" method where radix 2,8 and 16 values were | Reid Spencer | 2007-05-16 | 1 | -8/+13 |
| | | | | | | | | | not being generated correctly because the shl operator does not mutate its object but returns a new value. Also, make the distinction between radix 16 and the others more clear. llvm-svn: 37111 | ||||
| * | Update for arbitrary precision integer types. | Reid Spencer | 2007-05-16 | 1 | -8/+48 |
| | | | | | llvm-svn: 37109 | ||||
| * | Fix PR1355: Only compute the SUBPATH and TESTDIR once. | Reid Spencer | 2007-05-16 | 1 | -7/+9 |
| | | | | | llvm-svn: 37108 | ||||
| * | Fix PR number. | Devang Patel | 2007-05-16 | 1 | -1/+1 |
| | | | | | llvm-svn: 37107 | ||||
| * | New test for PR1417 | Devang Patel | 2007-05-16 | 1 | -0/+5 |
| | | | | | llvm-svn: 37106 | ||||
| * | Avoid a "loss of precision" error in gcc 4.1.3. | Reid Spencer | 2007-05-16 | 1 | -1/+1 |
| | | | | | llvm-svn: 37105 | ||||
| * | Output exception call-sites in address order, as required by the unwinding | Duncan Sands | 2007-05-16 | 1 | -10/+54 |
| | | | | | | | runtime. llvm-svn: 37104 | ||||
| * | Conditional branch is not a barrier. | Evan Cheng | 2007-05-16 | 1 | -4/+6 |
| | | | | | llvm-svn: 37103 | ||||
| * | Use a ptr set instead of a linear search to unique TokenFactor operands. | Chris Lattner | 2007-05-16 | 1 | -10/+13 |
| | | | | | | | This fixes PR1423 llvm-svn: 37102 | ||||
| * | testcase for maskmovq | Chris Lattner | 2007-05-16 | 1 | -0/+14 |
| | | | | | llvm-svn: 37101 | ||||

