| Commit message (Expand) | Author | Age |
* | Add disassembler support for VPERMIL2PD and VPERMIL2PS. | Craig Topper | 2011-12-30 |
* | Add FMA4 instructions to disassembler. | Craig Topper | 2011-12-30 |
* | Change FMA4 memory forms to use memopv* instead of alignedloadv*. No need to ... | Craig Topper | 2011-12-30 |
* | Fix load size for FMA4 SS/SD instructions. They need to use f32 and f64 size,... | Craig Topper | 2011-12-30 |
* | Cleanup stack/frame register define/kill states. This fixes two bugs: | Hal Finkel | 2011-12-30 |
* | Implement cfi_restore. Patch by Brian Anderson! | Rafael Espindola | 2011-12-29 |
* | Fix execution domains for PS/PD FMA3 instructions. Add SS/SD forms o FMA3 ins... | Craig Topper | 2011-12-29 |
* | Implement .cfi_escape. Patch by Brian Anderson! | Rafael Espindola | 2011-12-29 |
* | Expose FMA3 instructions to the disassembler. | Craig Topper | 2011-12-29 |
* | Change CaptureTracking to pass a Use* instead of a Value* when a value is | Nick Lewycky | 2011-12-28 |
* | Fix type-checking for load transformation which is not legal on floating-poin... | Eli Friedman | 2011-12-28 |
* | PR11662. | Nadav Rotem | 2011-12-28 |
* | Fixed a bug in LowerVECTOR_SHUFFLE and LowerBUILD_VECTOR. | Elena Demikhovsky | 2011-12-28 |
* | Turn cos(-x) into cos(x). Patch by Alexander Malyshev! | Nick Lewycky | 2011-12-27 |
* | Teach simplifycfg to recompute branch weights when merging some branches, and | Nick Lewycky | 2011-12-27 |
* | Make sure DAGCombiner doesn't introduce multiple loads from the same memory l... | Eli Friedman | 2011-12-26 |
* | Update the branch weight metadata when reversing the order of a branch. | Nick Lewycky | 2011-12-26 |
* | Add an explicit test that we now fold cttz.i32(..., true) >> 5 -> 0. | Chandler Carruth | 2011-12-24 |
* | InstCombine: Add a combine that turns (2^n)-1 ^ x back into (2^n)-1 - x iff x... | Benjamin Kramer | 2011-12-24 |
* | ComputeMaskedBits: Make knownzero computation more aggressive for ctlz with u... | Benjamin Kramer | 2011-12-24 |
* | InstCombine: Canonicalize (2^n)-1 - x into (2^n)-1 ^ x iff x is known to be s... | Benjamin Kramer | 2011-12-24 |
* | Use standard promotion for i8 CTTZ nodes and i8 CTLZ nodes when the | Chandler Carruth | 2011-12-24 |
* | Add systematic testing for cttz as well, and fix the bug I spotted by | Chandler Carruth | 2011-12-24 |
* | Add i8 and i64 testing for ctlz on x86. Also simplify the i16 test. | Chandler Carruth | 2011-12-24 |
* | Tidy up this rather crufty test. Put the declarations at the top to make | Chandler Carruth | 2011-12-24 |
* | Expand more when we have a nice 'tzcnt' instruction, to avoid generating | Chandler Carruth | 2011-12-24 |
* | Tidy up some of these tests. | Chandler Carruth | 2011-12-24 |
* | Switch the lowering of CTLZ_ZERO_UNDEF from a .td pattern back to the | Chandler Carruth | 2011-12-24 |
* | Cleanup this test a bit, sorting things and grouping them more clearly. | Chandler Carruth | 2011-12-24 |
* | Test case for r147232. | Akira Hatanaka | 2011-12-24 |
* | Move this test from date-name to feature-name, and port it to FileCheck. | Nick Lewycky | 2011-12-23 |
* | Experimental support for aligned NEON spills. | Jakob Stoklund Olesen | 2011-12-23 |
* | ARM VFP assembly parsing and encoding for VCVT(float <--> fixed point). | Jim Grosbach | 2011-12-22 |
* | Fix incorrect relocation generation. Patch by Kristof Beyls. | Rafael Espindola | 2011-12-22 |
* | Reinstate r146578; it doesn't appear to be the cause of some recent execution- | Chad Rosier | 2011-12-22 |
* | ARM assembler should accept shift-by-zero for any shifted-immediate operand. | Jim Grosbach | 2011-12-22 |
* | Give string constants generated by IRBuilder private linkage. | Benjamin Kramer | 2011-12-22 |
* | Make the unreachable probability much much heavier. The previous | Chandler Carruth | 2011-12-22 |
* | Speculatively revert r146578 to determine if it is the cause of a number of | Chad Rosier | 2011-12-22 |
* | Local dynamic TLS model for direct object output. Create the correct TLS MIPS | Akira Hatanaka | 2011-12-22 |
* | ARM VFP optional data type on VMOV GPR<-->SPR. | Jim Grosbach | 2011-12-21 |
* | Thumb2 assembly parsing of 'mov rd, rn, rrx'. | Jim Grosbach | 2011-12-21 |
* | Thumb2 assembly parsing of 'mov(register shifted register)' aliases. | Jim Grosbach | 2011-12-21 |
* | ARM NEON assmebly parsing for VLD2 to all lanes instructions. | Jim Grosbach | 2011-12-21 |
* | Fix a couple of copy-n-paste bugs. Noticed by George Russell! | Chad Rosier | 2011-12-21 |
* | Make some intrinsics safe to speculatively execute. | Nick Lewycky | 2011-12-21 |
* | Fix a couple of copy-n-paste bugs. Noticed by George Russell. | Evan Cheng | 2011-12-21 |
* | ARM NEON VLD2 assembly parsing for structure to all lanes, non-writeback. | Jim Grosbach | 2011-12-21 |
* | Fix bug in zero-store peephole pattern reported in pr11615. | Akira Hatanaka | 2011-12-21 |
* | Expand 64-bit CTLZ nodes if target architecture does not support it. Add test | Akira Hatanaka | 2011-12-21 |